ME/CS 132b, Spring 2012
Advanced Robotics: Navigation and Vision
Teaching Assistants (firstname.lastname@example.org)
Course Mailing List: email@example.com (sign up)
There are no formal prerequisites for the course. ME 115 ab (Introduction to Kinematics and Robotics) is recommended but not necessary. Students are expected to have basic understanding of linear algebra, probability and statistics. We will review some of the required background materials during the first week of lectures. Besides these, students should have some prior programming experience and know at least one of the following languages: C, Python, or MATLAB. Depending on the background of the class, we will hold tutorials for some of the programming languages to help students get started.
There are no midterm/final exams for this course. The grade will be based on (1) homework assignments (40%), (2) a week-long lab (20%), and (3) a course project 40%). Late homework will not be accepted without a letter from the health center or the Dean. However, you are granted a grace period of three late days throughout the entire term for weekly homework. Please email the TAs and indicate the number of late days you have used on the homework. No grace period is allowed for the week-long lab or the course project.
- Homework: Homework is usually due in one week after it is assigned. You can choose to
- turn in a hard copy in class,
- or, upload an electronic copy to the course server and send the TAs a note.
- If you are unable attend the lecture, contact the TAs to find an alternative way to turn in your homework.
- Course Project: Grading for the term project will be a weighted combination of navigation task success, focus task results, and presentation. Each member in the group will receive the same grade. All group members are expected to participate equally throughout all facets of the term project.
- On the back of the first page of your homework, write down the number of hours you have spent, including reading. This will help us keep track of the amount of homework and adjust future assignments if necessary.
- Justify your answers. This will help us assign partial credits to your assignment even if the results are incorrect. On the other hand, we will deduct points if only results are shown without the necessary derivations.
- You are encouraged to use professional libraries (such as OpenCV) for reading/writing ﬁles and analogous tasks. However, you cannot use functions which the homework implies you have to write yourself.
- You will be given code examples in a few languages (MATLAB, C++, Python), but you are free to use any language with which you are comfortable.
- You are responsible for the parameters you choose. If we give you a “reasonable” value for a parameter that does not appear to work, you should try other values.
For electronic submissions (including your code):
- Package code, data, and answers in a single .zip or .tgz ﬁle.
- Email the writeup as a single file to the TAs. Do not upload multiple files for different parts of the writeup. The file must not be in proprietary formats (e.g. MS Word, Mathematica notebook). We recommend using PDF format to guarantee portability.
- Separate code & commentary: do not write your discussion/derivation in the source ﬁles, but in a separate report ﬁle, clearly labeled as such.
- Include instructions/scripts that allow reproducing your experiments with relatively little eﬀort. For example, include a script “main.m” that calls the other ﬁles.
Students are encouraged to discuss and collaborate with others on the homework. You are free to discuss general ideas about the problem. However, you should write your own solution to show your own understanding of the material. You cannot copy other people's solution as part of your solution. You cannot share code for homework or look at other people’s code. Reading aloud your code does not count as discussion. You are allowed to consult the instructors, the TAs, and/or other students. Outside reference materials can be used except for solutions from prior years or similar courses taught at other universities. Outside materials must be cited if used.
The required textbook is (also freely available online):
- Steven M. LaValle, Planning Algorithms, Cambridge University Press, 2006.
|1||3 Apr (Tu)||Overview, Kinematic and Dynamic Models (part 1, part 2)||Tom Howard|
|5 Apr (Th)||Motion Simulation||Yoshi Kuwata|
|2||10 Apr (Tu)||Search Spaces I||Tom Howard|
|12 Apr (Th)||Search Spaces II||Tom Howard|
|3||17 Apr (Tu)||Search Algorithms I||Yoshi Kuwata|
|19 Apr (Th)||Search Algorithms II||Tom Howard|
|4||24 Apr (Tu)||Sensor-Based Planning I||Yoshi Kuwata|
|26 Apr (Th)||Sensor-Based Planning II||Yoshi Kuwata|
|5||1 May (Tu)||Week-long lab|
|3 May (Th)||Week-long lab|
|6||8 May (Tu)||Term Project Overview and Kickoff|
|10 May (Th)||Case Studies||TBD|
|7||15 May (Tu)||Term Project Mentor Meetings|
|17 May (Th)||Term Project Mentor Meetings|
|8||22 May (Tu)||Term Project Progress Presentations|
|24 May (Th)||Term Project Progress Presentations (cont.)|
|9||29 May (Tu)||Term Project Mentor Meetings|
|31 May (Th)||Term Project Mentor Meetings|
|9||5 June (Tu)||Term Project Final Presentations|
|7 June (Th)||Term Project Final Presentations (cont.)|