Murray Wiki - User contributions [en]

CDS 101/110a, Fall 2006 - Course Project

2006-12-01T04:58:09Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==

'''Wednesday, November 28'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1500-1630</td><td>klimka</td></tr>
<tr><td> 1630-1800</td><td>christine</td></tr>
</table>

'''Sunday, December 3'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1000-1100</td><td>ghyrn</td></tr>
<tr><td> 1100-1200</td><td>ghfaria</td></tr>
<tr><td> 1200-1400</td><td>ikeda</td></tr>
<tr><td> 1400-1500</td><td></td></tr>
<tr><td> 1500-1600</td><td></td></tr>
<tr><td> 1600-1700</td><td></td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-30T05:16:59Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==

'''Wednesday, November 28'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1500-1630</td><td>klimka</td></tr>
<tr><td> 1630-1800</td><td>christine</td></tr>
</table>

'''Sunday, December 3'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1100-1200</td><td>ghfaria</td></tr>
<tr><td> 1200-1400</td><td>ikeda</td></tr>
<tr><td> 1400-1500</td><td></td></tr>
<tr><td> 1500-1600</td><td></td></tr>
<tr><td> 1600-1700</td><td></td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-29T16:04:15Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==

'''Wednesday, November 28'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1500-1630</td><td>klimka</td></tr>
<tr><td> 1630-1800</td><td>christine</td></tr>
</table>

'''Sunday, December 3'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1100-1200</td><td>ghfaria</td></tr>
<tr><td> 1200-1300</td><td></td></tr>
<tr><td> 1300-1400</td><td></td></tr>
<tr><td> 1400-1500</td><td></td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-29T06:09:28Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==

'''Wednesday, November 28'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1500-1630</td><td>klimka</td></tr>
<tr><td> 1630-1800</td><td></td></tr>
</table>

'''Sunday, December 3'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1100-1200</td><td>ghfaria</td></tr>
<tr><td> 1200-1300</td><td></td></tr>
<tr><td> 1300-1400</td><td></td></tr>
<tr><td> 1400-1500</td><td></td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-29T05:08:42Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==

'''Wednesday, November 28'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1500-1600</td><td></td></tr>
<tr><td> 1600-1700</td><td></td></tr>
<tr><td> 1700-1800</td><td></td></tr>
</table>

'''Sunday, December 3'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1100-1200</td><td>ghfaria</td></tr>
<tr><td> 1200-1300</td><td></td></tr>
<tr><td> 1300-1400</td><td></td></tr>
<tr><td> 1400-1500</td><td></td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-29T01:39:33Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==

'''Sunday, December 3'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1100-1200</td><td>ghfaria</td></tr>
<tr><td> 1200-1300</td><td></td></tr>
<tr><td> 1300-1400</td><td></td></tr>
<tr><td> 1400-1500</td><td></td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-28T07:01:52Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==

'''Tuesday, November 28'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1100-1300</td><td>Ghyrn</td></tr>
<tr><td> 1300-1400</td><td>ghfaria</td></tr>
</table>

'''Sunday, December 3'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1100-1200</td><td></td></tr>
<tr><td> 1200-1300</td><td></td></tr>
<tr><td> 1300-1400</td><td></td></tr>
<tr><td> 1400-1500</td><td></td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-28T06:53:11Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==

'''Tuesday, November 28'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1100-1300</td><td>Ghyrn</td></tr>
<tr><td> 1300-1400</td><td>ghfaria</td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-28T01:21:07Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==

'''Thursday, November 30'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1100-1230</td><td>Kenny</td></tr>
<tr><td> 1200-1300</td><td></td></tr>
<tr><td> 1300-1400</td><td></td></tr>
<tr><td> 1400-1500</td><td></td></tr>
</table>

'''Tuesday, November 28'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1100-1300</td><td>Ghyrn</td></tr>
<tr><td> 1300-1400</td><td></td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-28T00:10:15Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==

'''Thursday, November 30'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1100-1230</td><td>Kenny</td></tr>
<tr><td> 1200-1300</td><td></td></tr>
<tr><td> 1300-1400</td><td></td></tr>
<tr><td> 1400-1500</td><td></td></tr>
</table>

'''Tuesday, November 28'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1100-1200</td><td></td></tr>
<tr><td> 1200-1300</td><td></td></tr>
<tr><td> 1300-1400</td><td></td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-27T07:03:19Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==

'''Thursday, November 30'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1100-1200</td><td></td></tr>
<tr><td> 1200-1300</td><td></td></tr>
<tr><td> 1300-1400</td><td></td></tr>
<tr><td> 1400-1500</td><td></td></tr>
</table>

'''Tuesday, November 28'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td></tr>
<tr><td> 1100-1200</td><td></td></tr>
<tr><td> 1200-1300</td><td></td></tr>
<tr><td> 1300-1400</td><td></td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-22T05:13:01Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==

'''Sunday, November 26'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td> <td> Team2 </td></tr>
<tr><td> 1100-1200</td><td></td><td></td></tr>
<tr><td> 1200-1300</td><td></td><td></td></tr>
<tr><td> 1300-1400</td><td></td><td></td></tr>
<tr><td> 1400-1500</td><td></td><td></td></tr>
<tr><td> 1500-1600</td><td></td><td></td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-19T00:31:45Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==

'''Sunday, November 19'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td> <td> Team2 </td></tr>
<tr><td> 1500-1600</td><td>Steven Gray</td><td></td></tr>
<tr><td> 1600-1700</td><td>Mike Ikeda</td><td></td></tr>
<tr><td> 1700-1800</td><td>Craig Montuori</td><td></td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-17T09:15:57Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==
*If you need to test this week, emailed me your schedule, and none of these times work for you, let me know (sooner rather than later) and I can try to work something out -Laura

'''Sunday, November 19'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td> <td> Team2 </td></tr>
<tr><td> 1400-1500</td><td>Mike Ikeda</td><td></td></tr>
<tr><td> 1500-1600</td><td>Craig Montuori</td><td></td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-17T09:05:08Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==
*If you need to test this week, emailed me your schedule, and none of these times work for you, let me know (sooner rather than later) and I can try to work something out -Laura

'''Sunday, November 19'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td> <td> Team2 </td></tr>
<tr><td> 1400-1500</td><td>Mike Ikeda</td><td></td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-16T08:49:24Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==
*If you need to test this week, emailed me your schedule, and none of these times work for you, let me know (sooner rather than later) and I can try to work something out -Laura

'''Sunday, November 19'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td> <td> Team2 </td></tr>
<tr><td> tbd</td><td></td></td></td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-13T13:14:18Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==
*If you need to test this week, emailed me your schedule, and none of these times work for you, let me know (sooner rather than later) and I can try to work something out -Laura

'''Thursday, November 16'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td> <td> Team2 </td></tr>
<tr><td> 1200-1300</td><td></td></td></td></tr>
<tr><td> 1300-1400</td><td></td></td></td></tr>
<tr><td> 1400-1500</td><td></td></td></td></tr>
</table>

'''Wednesday, November 15'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td> <td> Team2 </td></tr>
<tr><td> 0900-1000</td><td></td></td></td></tr>
<tr><td> 1000-1100</td><td></td></td></td></tr>
<tr><td> 1100-1200</td><td></td></td></td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-12T12:09:36Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==
*If you need to test this week, emailed me your schedule, and none of these times work for you, let me know (sooner rather than later) and I can try to work something out -Laura

'''Thursday, November 16'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td> <td> Team2 </td></tr>
<tr><td> 1200-1300</td><td></td></td></td></tr>
<tr><td> 1300-1400</td><td></td></td></td></tr>
<tr><td> 1400-1500</td><td></td></td></td></tr>
</table>

'''Friday, November 17'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td> <td> Team2 </td></tr>
<tr><td> 0900-1000</td><td></td></td></td></tr>
<tr><td> 1000-1100</td><td></td></td></td></tr>
<tr><td> 1100-1200</td><td></td></td></td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-09T05:17:25Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==
'''Thursday, November 9'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td> <td> Team2 </td></tr>
<tr><td> 1130-1230</td><td>Steve</td><td></td></tr>
<tr><td> 1200-1300</td><td></td></td></td></tr>
<tr><td> 1300-1400</td><td></td></td></td></tr>
<tr><td> 1400-1500</td><td></td></td></td></tr>

</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-02T08:23:58Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==
'''Thursday, November 2'''
<table border=1>
<tr><td> Time </td> <td> TAs/Implementation team</td> <td> Team1 </td> <td> Team2 </td></tr>
<tr><td> 1100-1200</td><td>Nok, Dom, Laura, Richard (?)</td><td> Kenny, Christine, Majipal</td><td>...</td></tr>
<tr><td> 1200-1300</td><td>Nok, Dom, Laura, Richard (?)<td>Chris, Johnny, Steve</td><td>Jessica, Russell, Francisco</td></tr>
<tr><td> 1300-1400</td><td>...</td><td>...</td><td>...</td></tr>
<tr><td> 1400-1500</td><td>...</td><td>...</td><td>...</td></tr>
<tr><td> 1500-1600</td><td>Pete, Richard,Laura</td><td>Sanjeeb, Mike, Harrison</td><td>Ghyrn, Klimka, Chris</td></tr>
<tr><td> 1600-1700</td><td>Pete, Richard, Laura</td><td>ghfaria</td><td>Craig, Andrew</td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-02T07:54:56Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==
'''Thursday, November 2'''
<table border=1>
<tr><td> Time </td> <td> TAs/Implementation team</td> <td> Team1 </td> <td> Team2 </td></tr>
<tr><td> 1100-1200</td><td>Nok, Dom, Laura, Richard (?)</td><td> Kenny, Christine, Majipal</td><td>...</td></tr>
<tr><td> 1200-1300</td><td>Nok, Dom, Laura, Richard (?)<td>Chris, Johnny, Steve</td><td>Jessica, Russell, Francisco</td></tr>
<tr><td> 1300-1400</td><td>...</td><td>...</td><td>...</td></tr>
<tr><td> 1400-1500</td><td>...</td><td>...</td><td>...</td></tr>
<tr><td> 1500-1600</td><td>Pete, Richard,Laura</td><td>Sanjeeb, Mike, Harrison</td><td>Ghyrn, Klimka, Chris</td></tr>
<tr><td> 1600-1700</td><td>Pete, Richard, Laura</td><td>ghfaria</td><td>...</td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-11-01T11:15:35Z

Lindzey: /* Field Test Signup */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==
'''Thursday, November 2'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td> <td> Team2 </td></tr>
<tr><td> 1100-1200</td><td> Kenny, Christine, Majipal</td><td>...</td></tr>
<tr><td> 1200-1300</td><td>Chris, Johnny, Steve</td><td>Jessica, Russell, Francisco</td></tr>
<tr><td> 1300-1400</td><td>...</td><td>...</td></tr>
<tr><td> 1400-1500</td><td>...</td><td>...</td></tr>
<tr><td> 1500-1600</td><td>Sanjeeb, Mike, Harrison</td><td>Ghyrn, Klimka, Chris</td></tr>
<tr><td> 1600-1700</td><td>ghfaria</td><td>...</td></tr>
</table>

== Preliminary Timeline ==
'''Week 4'''
* [[media:cds110a-fa06_projectintro.pdf|Course project introduction]] (pdf)

'''Week 5'''
* Recitation Section: [[media:cds110a-fa06_follow.pdf|How follow works]] (pdf)
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-10-31T06:12:04Z

Lindzey: /* Overview */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

<b>note:</b> I'd prefer to receive questions by email or during the recitation sections. I will answer any emails w/in 24 hours (usually much faster, but sometimes I am swamped with other classes) -Laura

==Field Test Signup==
'''Thursday, November 2'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td> <td> Team2 </td><td> Team3 </td> </tr>
<tr><td> 1100-1300</td><td>...</td><td>...</td><td>... </td></tr>
<tr><td> 1300-1500</td><td>...</td><td>...</td><td>... </td></tr>
<tr><td> 1500-1700</td><td>...</td><td>...</td><td>... </td></tr>

</table>
== Preliminary Timeline ==
'''Week 5'''
* Recitation Section: How follow works
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-10-28T22:31:40Z

Lindzey:

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be choosing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

==Field Test Signup==
'''Thursday, November 2'''
<table border=1>
<tr><td> Time </td> <td> Team1 </td> <td> Team2 </td><td> Team3 </td> </tr>
<tr><td> 1100-1300</td><td>...</td><td>...</td><td>... </td></tr>
<tr><td> 1300-1500</td><td>...</td><td>...</td><td>... </td></tr>
<tr><td> 1500-1700</td><td>...</td><td>...</td><td>... </td></tr>

</table>
== Preliminary Timeline ==
'''Week 5'''
* Recitation Section: How follow works
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
* Dominic Rizzo
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS110a before a Field Test

2006-10-28T21:33:28Z

Lindzey:

===Requirements===

Before any field test, you should have several sets of gains that you plan to test (chances are, many of them won't work, so you want to be prepared). For each set, you should have run it in simulation, and shown me plots of the following: (<b> warning: </b> these requirements may change - check back before Thursday)
# control signal vs. time
# lateral error vs. time

===How to run the simulation? ===
You will do this either on Alice or on one of the shop machines.
Log in, using the username/password that you should have gotten from Prof. Murray

These steps are a bit different then those on the follow page, because each of you will have your own copy of the code, and we're ignoring everything that has to do with the observers.

1) open up a terminal, and check out the code:
<pre>
svn co svn+ssh://gc.caltech.edu/dgc/subversion/dgc/trunk dgc
</pre>
this will create a directory called dgc, with all of team caltech's code in it

2) you will need 3 open terminals for this: in each one, you need to set your skynet key
<pre> export SKYNET_KEY=xxxx</pre>
where xxxx is a unique number (a good choice is your student ID #)

3) In terminal #1,
<pre>
cd dgc
make simulator
cd bin
./simulator
</pre>
This will start the simulator: when you're ready to actually run, type 'U' to unpause (for information about how to configure the simulator, see follow page)

4) In terminal #2,
<pre>
cd dgc
make gui
cd bin
./gui
</pre>
This will start the gui (not necessary, but useful to check that everything's working like it should)

5) In terminal #3,
<pre>
cd dgc/projects/cds110b
make
./follow -t TRAJ_FILENAME -c CONTROLLER_FILENAME --projerr
</pre>
CONTROLLER_FILENAME needs to be the .mat file where you've saved your ABCD matrices (see the follow page for more details)

TRAJ_FILENAME is the trajectory that your controller is trying to follow. For now, use stluke_sine_wave.traj (may add more later)

This starts follow: when you're ready to start the logs, type 'L'. To enable the controller, type 'R'. To quit, type 'Q'

CDS110a Requirements before running on Alice

2006-10-28T21:07:25Z

Lindzey: CDS110a Requirements before running on Alice moved to CDS110a before a Field Test

#redirect [[CDS110a before a Field Test]]

CDS110a before a Field Test

2006-10-28T21:07:25Z

Lindzey: CDS110a Requirements before running on Alice moved to CDS110a before a Field Test

Before any field test, you should have several sets of gains that you plan to test (chances are, many of them won't work, so you want to be prepared). For each set, you should have run it in simulation, and shown me plots of the following:
# control signal vs. time
# error vs. time

CDS110a before a Field Test

2006-10-28T21:06:54Z

Lindzey:

CDS 101/110a, Fall 2006 - Course Project

2006-10-26T04:33:08Z

Lindzey: /* Active Projects */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be designing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

== Preliminary Timeline ==
'''Week 5'''
* Recitation Section: How follow works
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Russell Newman
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-10-26T03:00:18Z

Lindzey: /* Preliminary Timeline */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be designing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

== Preliminary Timeline ==
'''Week 5'''
* Recitation Section: How follow works
* What needs to be done for this week: GOTChA charts
* First cut simulation

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Dominic Rizzo
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-10-26T02:42:22Z

Lindzey: /* Preliminary Timeline */

{{righttoc}}
== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be designing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

== Preliminary Timeline ==
'''Week 5'''
* Recitation Section: How follow works
* What needs to be done for this week: GOTChA charts

'''Week 6'''
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
* Start working on first cut simulation for project; if you've tested controller in simulation, you will be allowed to test on Alice @ the demo.

'''Week 7'''
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

'''Week 8'''
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

'''Week 9'''
* Recitation Section: Discussion about everybody's current status

'''Week 10'''
* Recitation Section: Group presentations

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Dominic Rizzo
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-10-25T21:12:20Z

Lindzey:

== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be designing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See [http://gc.caltech.edu/wiki/index.php/Follow here] for more information on follow, and [[CDS110a_Requirements_before_running_on_Alice|here]] for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. More information about this will be posted later, and you should feel free to ask Laura for more details.

== Preliminary Timeline ==
===Week 5===
* Recitation Section: How follow works
* What needs to be done for this week: GOTChA charts
===Week 6===
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
===Week 7===
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

===Week 8===
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

===Week 9===
* Recitation Section: Discussion about everybody's current status

===Week 10===
* Recitation Section: Group presentations

The following projects can be done as a course project for CDS 101/110. Projects marked as "DGC" are appropriate for use as a project in CS/EE/ME 75.

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Dominic Rizzo
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

CDS 101/110a, Fall 2006 - Course Project

2006-10-25T20:57:07Z

Lindzey:

== Overview ==
For the project track of CDS110, each group will be working with two controllers.

First, you will be designing appropriate gains for a pre-existing controller called follow. The idea of this is for everybody to learn how to run code on Alice and collect data. See (follow documentation) for more information on follow, and (before testing) for the steps you need to complete before you will be allowed to try your gains out on Alice.

The second half of the project will be designing your own controllers, based on the project you chose. For these, you can assume that the sensor data will be made available to you -- However, you will need to think about what data/format you need. I'll post more information about this later, and you should feel free to ask Laura for more details.

== Preliminary Timeline ==
===Week 5===
* Recitation Section: How follow works
* What needs to be done for this week: GOTChA charts
===Week 6===
* Recitation Section: Prep for Alice demo
* At some point this week (times TBA) each group will need to schedule time in Alice to learn how she works and to test out their gains in follow.
===Week 7===
* Recitation Section: Presentations of each group's state-space implementation
* It is possible that the first attempt at designing a stable controller with acceptable performance won't work. There may be an oppportunity for a second test.
* Each group should prepare a short presentation describing the controller they designed. This should include charts of: controller design, pole placement, data, etc.

===Week 8===
* Recitation Section: How trajFollower worked (the controller that we used for the 2005 race)
* At this point, everybody should be working exclusively on the separate projects. Questions that you should be thinking about include:
# What inputs do we need? What format? How can we get them? (Talk to Laura - she will help with interfaces/spoofed data)
# Preliminary control law design?
# How can we test our controller in simulation/real life w/out putting Alice in danger?

===Week 9===
* Recitation Section: Discussion about everybody's current status

===Week 10===
* Recitation Section: Group presentations

The following projects can be done as a course project for CDS 101/110. Projects marked as "DGC" are appropriate for use as a project in CS/EE/ME 75.

== Active Projects ==

* '''Lateral control in forward and reverse, with gain scheduling''' (DGC) - Design a controller that matains the lateral position of the vehicle when it is moving either forwards or backwards and schedules the gains based on speed. This requires a rederivation of the dynamics of the vehicle that model the motion when moving backwards and determining how to switch between forward and reverse motion. The specifications for the controller will be based on the needs of the 2007 Urban Challenge.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Kenny Oslund (75)
* Christine Parry
* Mahipal Raythattha
| Team 2
* Andrew Krause
* Craig Montuori
|}
</blockquote>

* '''Lane following''' (DGC) - Design a controller that uses information about the right and left lane boundaries to remain centered in the middle of the lane. The location of the left and right lane boundaries will eventually be given by a vision system, but for the course project simulated lane boundaries will be used.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Chris Schantz (75)
* Johnny Zhang (75)
* Steve Gray (75)
| Team 2
* Mohamed Ali
* Gustavo Costa
* Tom Duong (75 only)
|}
</blockquote>

* '''Stopping at a line''' (DGC) - Design a controller that brings the vehicle to a stop within 1 meter of a stop line painted on the ground. The location of the stop line will be a combination of GPS data (when far from the stop line) and vision-based data (when near the stop line).
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Jessica Gonzalez (75)
* Francisco Zabala (75)
* Dominic Rizzo
| Team 2
* Sanjeeb Bose
* MIke Ikeda
* Harrison Stein
|}
</blockquote>

* '''Reactive obstacle avoidance''' (DGC) - Design a controller that uses direct information from a laser range finder (LADAR) to bring the vehicle to a stop and/or swerve to avoid a "pop-up" obstacle. For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.
<blockquote>
{| width=100%
|- valign=top
| width=50% | Team 1
* Ghyrn Loveness
* Klimka Szwaykowska
* Chris Yu
| Team 2
|}
</blockquote>

== Open Projects ==
* '''Looking down a road''' (DGC) - Design a pointing system that can point a camera down a road to the left or right of a vehicle. The location of the road must be determined based on visual data (could be combined with a EE/CNS 148 project). For CS/EE/ME 75 students, this could be a good project for someone on the sensing team.

Problem 4 (c) -- Errata

2006-10-18T22:28:49Z

Lindzey: Problem 4 (c) -- Errata moved to Problem 3 (c) -- Errata

#redirect [[Problem 3 (c) -- Errata]]

Problem 3 (c) -- Errata

2006-10-18T22:28:49Z

Lindzey: Problem 4 (c) -- Errata moved to Problem 3 (c) -- Errata

In part (c) of this problem you will have to use as input <math>u(k)=sin(\omega k)</math>, and find the steady state system response. The correct general formula which you should prove is as follows:

<math>M e^{j\theta}=C(e^{j\omega}I-A)^{-1}B + D</math>

Hint: assume that <math>u(k)=sin(\omega k)=\mathcal{I}m(e^{j\omega k})</math>.

You can therefore find the solution in the required form by using the Euler formulas: use <math>u(k)=e^{j\omega k}</math> and express the general solution of the difference equation as <math>x(k)= G e^{j ...}</math> (you need to figure out this exponent!).

--[[User:Franco|Elisa]]
[[Category:CDS 101/110 FAQ - Homework 4]]

TA Schedule

2006-10-17T17:55:51Z

Lindzey:

'''TAs for Office Hours'''

*Sept 29 (F): Laura
*Oct 1 (Su): Melvin, Elisa
*Oct 6 (F): Mary
*Oct 8 (Su): Ling, Laura
*Oct 13 (F): John
*Oct 15 (Su): Laura, Mary
*Oct 20 (F): Ling
*Oct 22 (Su): Elisa, Ling
*Oct 27 (F): ''Midterms'' - Elisa
*Oct 29 (Su): ''Midterms'' - Ling, Mary
*Nov 3 (F): Mary
*Nov 5 (Su): Ling, Elisa
*Nov 10 (F): Laura
*Nov 12 (Su): John, Laura
*Nov 17 (F): John
*Nov 19 (Su): Mary, Elisa
*Nov 24 (F): ''Thanksgiving holiday'' - no office hour
*Nov 26 (Su): John, Mary
*Dec 1 (F): ''Finals'' - Elisa
*Dec 3 (Su): ''Finals'' - John, Laura

Problem 3: How to deal with the saturation?

2006-10-15T14:55:21Z

Lindzey:

<b> Q: </b>
For modeling this system, is the saturation of the control input a
fundamental nonlinearity that we just toss out by assuming a local
domain, or can this saturation be modeled formally?

<b> A: </b>
In this problem, you're trying to prove stability about an equilibruim point --
thus, you can deal with the saturation of the control input by proving
that it is linear in a region sufficiently close to the equilibrium
point.

--[[User:Lindzey|Lindzey]] 07:55, 15 October 2006 (PDT)

[[Category:CDS 101/110 FAQ - Homework 3]]

Problem 2 -- What's the second element in the state of the system?

2006-10-15T04:54:09Z

Lindzey:

<b>Q: </b>
This problem requires a phase portrait of the model. I was wondering
what two variables would be plotted in the portrait? One is easy to
figure out, but I'm not really sure what the other one would be...

<b>A: </b>

You're right that a one-dimesional phase portrait would be rather boring (and in this case, incorrect).
In this problem, you are modeling the <b>closed-loop</b> behavior of
the controller built in simulink last week. Keep in mind that when modeling feedback control,
additional states can arise that do not appear in the original dynamics.

This model is going to take the same form as the finger&flame problem had last
set -- it needs to return the derivative as a function of time and
current state (but in in this case, state is a vector).

Let the state X = [x1;x2]; you need to calculate to calculate dX/dt as a function of X and t.
If you know x1, go ahead and try to write dx1/dt for the
closed-loop system as a function of time and x1. In doing this, I think you'll
figure out what the other state needs to be. It may also help to remember
the formal definition for state of a system, and to <b>re-read section 3.1</b>, where the cruise-control example is described in detail.

--[[User:Lindzey|Lindzey]] 19:33, 10 October 2006 (PDT)

[[Category:CDS 101/110 FAQ - Homework 3]]

Problem 2 -- What's the second element in the state of the system?

2006-10-11T02:33:06Z

Lindzey:

<b>Q: </b>
This problem requires a phase portrait of the model. I was wondering
what two variables would be plotted in the portrait? One is easy to
figure out, but I'm not really sure what the other one would be...

<b>A: </b>

You're right that a one-dimesional phase portrait would be rather boring (and in this case, incorrect).
In this problem, you are modeling the <b>closed-loop</b> behavior of
the controller built in simulink last week. Keep in mind that when modeling feedback control,
additional states can arise that do not appear in the original dynamics.

This model is going to take the same form as the finger&flame problem had last
set -- it needs to return the derivative as a function of time and
current state (but in in this case, state is a vector).

Let the state X = [x1;x2]; you need to calculate to calculate dX/dt as a function of X and t.
If you know x1, go ahead and try to write dx1/dt for the
closed-loop system as a function of time and x1. In doing this, I think you'll
figure out what the other state needs to be. It may also help to remember
the formal definition for state of a system.

--[[User:Lindzey|Lindzey]] 19:33, 10 October 2006 (PDT)

[[Category:CDS 101/110 FAQ - Homework 3]]

How do equations given for dynamics on slide 10 relate to the state-space setup we used before?

2006-10-10T04:43:38Z

Lindzey:

A state space model attempts to model the states of a system, and provide a description for how they will evolve over time. Thus, the equations given for dynamics on slide 10 are a state-space system. The other type of system we will study is frequency domain.

Before, we used the setup dX/dt = A*X + B*u, where X was our state vector and u was the control. This requires the dynamics to be linear with respect to X. On slide 10, the dynamics are not linear, so we can't directly write it in the form used before (later we will learn about linearizing non-linear systems)

I'm not entirely sure what you wanted to know, so if the above doesn't clarify it for you, please email me and I'll try to better explain.

--[[User:Lindzey|Lindzey]] 21:43, 9 October 2006 (PDT)

[[Category:CDS 101/110 FAQ - Lecture 3-1]]

Who/What is Lyapunov?

2006-10-09T23:43:07Z

Lindzey:

Lyapunov was a Russian mathematician who worked on proving stability of systems (among many other things), and in this class we will use Lyapunov functions to prove the stability of non-linear systems.

If you want more info on the man, see http://en.wikipedia.org/wiki/Aleksandr_Lyapunov
For more info on the theory of Lyapunov functions, come to class Wed/Fri.

--[[User:Lindzey|Lindzey]] 16:43, 9 October 2006 (PDT)

[[Category:CDS 101/110 FAQ - Lecture 3-1]]

CS/EE/ME 75, 2006-07 - Team overviews

2006-10-09T05:58:24Z

Lindzey:

* [[Media:2006-10-09_sensing.ppt|Sensing Team]] (Laura Lindzey, Pete Trautman)
* Navigation Team (Jessica Gonzalez, Noel duToit)
* [[Media:2006-10-09_mission.pdf|Mission Team (Josh Feingold, Nok Wongpiromsarn)]]
* [[Media:2006-10-09_operations.pdf|Operations Team]] (Ken Fisher, Richard Murray)

File:2006-10-09 sensing.ppt

2006-10-09T05:56:26Z

Lindzey:

What does the at symbol mean in front of a function in matlab?

2006-10-03T01:48:30Z

Lindzey:

<b> Q: </b>
What does the @ sign mean when it is in front of the f function in the
Matlab simulation (pg. 6 of the lecture notes)?

<b> A: </b>
(Quoting the matlab help-files)
A function handle is a MATLAB value and data type that provides a
means of calling a function indirectly. You can pass function handles
in calls to other functions.

You construct a handle for a specific function by preceding the
function name with an @ sign. Use only the function name (with no path information) after the @ sign.
example:
fhandle = @myfunction

For more information, open matlab's help browser and search for 'function', 'ode45', or 'function handle'

--[[User:Lindzey|Lindzey]] 18:47, 2 October 2006 (PDT)

[[Category:CDS 101/110 FAQ - Lecture 2-1]]

What does the at symbol mean in front of a function in matlab?

2006-10-03T01:47:54Z

Lindzey:

Is q1 a function of time

2006-10-03T01:19:21Z

Lindzey:

<b> Q: </b>
Are the q_1 and q_2 functions of time or some kind of absolute position?

<b> A: </b>
I'm assuming that this question referred to the spring mass system found on p. 5 of the lecture notes.

In this case, q1 and q2 give the positions of the masses, and as such are going to be functions of time.

The state of this system, X, is represented by the positions and velocities of the two masses [q1, q2, q1_dot, q2_dot],
and we are trying to set up the equation that will give dX/dt in terms of elements of X. If we were to solve this system of equations, we'd then get q1 and q2 as functions of time and the initial conditions.

--[[User:Lindzey|Lindzey]] 18:19, 2 October 2006 (PDT)

[[Category:CDS 101/110 FAQ - Lecture 2-1]]

Problem 2b -- Does this mean exactly or at least fifty percent?

2006-09-27T18:48:33Z

Lindzey:

<b> Question: </b> In question 2b it says “design a controller that settles 50% percent faster than the default controller”. Does this mean exactly 50% or at least 50%? For example, if my settling time for 2a was, say, 30 seconds, would you want us to design a new controller that settles in exactly 15 seconds or could it settle anywhere from 0 to 15 seconds?

<b> Answer: </b> you can find any controller that allows a settling time at least 50% faster than the default. Finding the controller that gives you precisely the 50% faster settling would require mathematical manipulations that you do not know yet. Moreover, keep in mind that in the real world one always has to deal with uncertainty. Therefore as far as settling times and performances you will be more likely to encounter requirements specified by inequalities rather than exact equalities.

[[Category:CDS 101/110 FAQ - Homework 1]]

Problem 2b -- Does this mean exactly or at least fifty percent?

2006-09-27T18:14:57Z

Lindzey:

CS/EE/ME 75, 2006-07

2006-09-21T18:17:43Z

Lindzey: /* Fall Courses */

{{dgc75-fa06}}
<table width=80%>
<tr valign=top>
<td>
'''Instructors'''
* [[Main Page|Richard Murray]], murray@cds.caltech.edu
* Joel Burdick, jwb@robotics.caltech.edu
* Lectures: TDB
* [http://www.cds.caltech.edu/~murray/courses/dgc75 2004-05 homepage]
<td>
'''Teaching Assistants'''
* Noel duToit
* Pete Trautman
* Nok Wongpiromsarn
</table> __NOTOC__

== Announcements ==
<table align=right border=0><tr><td>[[#Old Announcements|Archive]]</table>
* 14 Sep 06: The organizational meeting for CS/EE/ME 75 will be on 25 Sep (Mon) at 4:30 pm in 102 Steele

== Course Syllabus ==

=== Course Description ===
[[Image:Alice-gce.jpg|right]]
CS/EE/ME 75 presents the fundamentals of modern multi-disciplinary systems engineering in the context of a substantial design project. Students from a variety of disciplines will conceive, design, implement, and operate a system involving electrical, information, and mechanical engineering components. Specific tools will be provided for setting project goals and objectives, managing interfaces between component subsystems, working in design teams, and tracking progress against tasks. Students will be expected to apply knowledge from other courses at Caltech in designing and implementing specific subsystems. During the first two terms of the course, students will attend project meetings and learn some basic tools for project design, while taking courses in CS, EE, and ME that are related to the course project. During the third term, the entire team will build, document, and demonstrate the course design project, which will differ from year to year.

The third term of the course may be used to satisfy specific graduation requirements in the CS, EE, and ME options and may be taken for up to 18 units of total credit, with permission of the instructors. Freshman must receive permission from the instructor to enroll.

==== Course structure ====
CS/EE/ME 75 is designed to be integrated with the curriculum in the individual engineering disciplines. This is accomplished by linking the activities in the first two terms with regular classes in CS, EE and ME. These courses are used to design subsystems for the overall project, with the system integration occuring in the third term and the final implementation and operation occuring over the summer.

<table width=100% border=0 cellpadding=0 cellspacing=0>
<tr valign=top><td>
[[Image:cem75_structure.gif|400px|left]]
<td>
===== Fall Courses =====
* CDS 110 - Control Systems
* CS 11 - C/C++ Programming
* [http://vision.caltech.edu/wikis/EE148-Fall06/index.php/EE/CNS_148_-_Fall_2006 EE/CS/CNS 148 - Machine Vision]
* Independent project courses

===== Winter Courses =====
* CDS 110 - Control Systems
* CS 11 - Multi-Threaded Programming
* ME/CS 131 - Path Planning
* Independent project courses
</table>

==== Grading ====
In the first two terms, the course grade will be equally weighted between course homework sets (one each for the first three weeks), course participation in project and team meetings, and the final project presentation. For the third term, the course grade will be based on the following factors:
* Homework (20%): Homework sets will be handed out weekly for the first four weeks of the class. Most sets will consist of some work that is done by the student's team, as well as a (short) individual portion
* Team presentations (20%): Each team will be required to make a presentation to the class summarizing their design studies.
* Project documentation (40%): All work performed as part of the class should be documented in an appropriate format (to be decided by the teams). Each individual will turn in the documentation for the items they are responsible by the end of the term.
* Participation (20%): Students are expected to attend project and team meetings and to participate in a constructive manner toward the over goals of the team. Team coordinators and instructors will provide assessments for each student based on the level and quality of participation in project activities.

=== 2006-07 Project ===

This year's project is the development of an autonomous vehicle capable of participating in the 2007 Urban Challenge, scheduled for 3 November 2007. The Urban Challenge is an autonomous vehicle competition involving up to 60 miles of autonomous driving in urban-like environments, including moving traffic, intersections, parking lots and traffic circles. The vehicle that completes the route in the shortest time under 6 hours wins the $2M grand prize.

For 2007, students in CS/EE/ME 75 will design, build, and document an autonomous vehicle capable of winning the urban challenge. The vehicle must be capable of operating in dynamic environments for 6 hours, at speeds of up to 30 miles per hour. This will require a level of sophistication in planning algorithms, sensor fusion and driving software substantially beyond current capabilities for autonomous vehicles.

==== First term ====

The course activities in the first term are designed to get students up to speed on the processes that will be used in the project. Students will generally fall into one of the three following groups, which will all have slightly different approaches to the course:

* ''No prior DGC experience, taking linked course'' - This is the nominal track for students in the course. In addition to CS/EE/ME 75, you should be taking one of the "linked courses" (listed above), where you will do a project aimed at the grand challenge. Students pursuing this option will be expected to bring their projects to [[GC:TRL|TRL]] 4 (prototype implementation) or higher in the first term, using the tools from CS/EE/ME 75.

* ''No prior DGC experience, ''not'' taking linked course'' - If you are not taking one of the courses that is linked to CS/EE/ME 75, you can still participate in the class by taking on a smaller [[CS/EE/ME 75 2006-07 - Course Projects|course project]]. These projects should be advanced to [[GC:TRL|TRL]] 4 (prototyle implementation) or higher in the first term, using the tools from CS/EE/ME 75.

* ''Prior DGC experience'' - If you have had prior experience in the DGC, for example through the 2006 Autonomous Vehicles SURF, you can use that work as the basis for your project. In this case, you are probably already at [[GC:TRL|TRL]] 5 and the goal is to get the project to [[GC:TRL|TRL 7]] (baselined code). Students pursuing this option will generally have to take a project course (eg, CDS 190 or equivalent) in order to account for the time required to implement their project.

==== Second term ====

In the second term, students with no prior DGC experience will focus on bringing their projects to [[GC:TRL|TRL]] 7 (baselined code). This may be done in conjunction with other courses, if applicable.

Students with prior DGC experience can either continue their projects, working toward [[GC:TRL|TRL 8]] (integrated module) and adding new features or start a new project (either through a class project, an independent project class or CS/EE/ME 75 credit).

==== Third term ====

All students taking CS/EE/ME 75c will work in small teams to implement technology on Alice and bring it to [[GC:TRL]] 8 (integrated module).

== Old Announcements ==