Sandeep Chichali, 16 Oct 2019 - Revision history

Sdathath: /* Schedule */

2019-10-16T01:37:34Z

Schedule

← Older revision		Revision as of 01:37, 16 October 2019
Line 5:		Line 5:
	* 11 am: seminar		* 11 am: seminar
	* 12 pm: lunch with Richard (and Joel, if he is around)		* 12 pm: lunch with Richard (and Joel, if he is around)
	* 1 pm: ~~Open~~		* 1 pm: Sumanth (Ann Lounge, level 3)
	* 1:30 pm: Open		* 1:30 pm: Open
	* 2:00 pm: Open		* 2:00 pm: Open

Fbaldini: /* Schedule */

2019-10-15T15:12:29Z

Schedule

← Older revision		Revision as of 15:12, 15 October 2019
Line 8:		Line 8:
	* 1:30 pm: Open		* 1:30 pm: Open
	* 2:00 pm: Open		* 2:00 pm: Open
	* 2:30 pm: ~~Open~~		* 2:30 pm: Francesca
	* 3 pm: CDS tea (optional)		* 3 pm: CDS tea (optional)
	* 3:45 pm: RMM group meeting (you are welcome to come if you like)		* 3:45 pm: RMM group meeting (you are welcome to come if you like)

Murray: /* Seminar */

2019-10-14T15:25:18Z

Seminar

← Older revision		Revision as of 15:25, 14 October 2019
Line 16:		Line 16:
	Distributed Perception Between Robots and the Cloud: A Learning-Based Approach <br>		Distributed Perception Between Robots and the Cloud: A Learning-Based Approach <br>
	Sandeep Chinchali, PhD candidate, Stanford <br>		Sandeep Chinchali, PhD candidate, Stanford <br>
	16 Oct (Wed), 11a-12p, ~~room TBD~~		16 Oct (Wed), 11a-12p, 121 Annenberg

	Today’s robotic fleets are increasingly facing two coupled challenges. First, they are measuring growing volumes of high-bitrate video and LIDAR sensory streams, which, second, often leads them to use increasingly compute-intensive models, such as deep neural networks (DNNs), for downstream perception or control. To cope with these intertwined challenges, compute and storage-limited robots, such as low-power drones, can offload data to central servers (or “the cloud”), for more accurate real-time perception as well as offline model learning. However, cloud processing of large robotic sensory streams introduces acute systems bottlenecks ranging from network delay for real-time inference, to cloud storage, human annotation, and cloud-computing costs for offline model learning.		Today’s robotic fleets are increasingly facing two coupled challenges. First, they are measuring growing volumes of high-bitrate video and LIDAR sensory streams, which, second, often leads them to use increasingly compute-intensive models, such as deep neural networks (DNNs), for downstream perception or control. To cope with these intertwined challenges, compute and storage-limited robots, such as low-power drones, can offload data to central servers (or “the cloud”), for more accurate real-time perception as well as offline model learning. However, cloud processing of large robotic sensory streams introduces acute systems bottlenecks ranging from network delay for real-time inference, to cloud storage, human annotation, and cloud-computing costs for offline model learning.

Murray at 05:34, 13 October 2019

2019-10-13T05:34:56Z

← Older revision		Revision as of 05:34, 13 October 2019
Line 14:		Line 14:
	=== Seminar ===		=== Seminar ===

	~~Title~~ <br>		Distributed Perception Between Robots and the Cloud: A Learning-Based Approach <br>
	Sandeep Chinchali, PhD candidate, Stanford <br>		Sandeep Chinchali, PhD candidate, Stanford <br>
	16 Oct (Wed), 11a-12p, room TBD		16 Oct (Wed), 11a-12p, room TBD

	~~Abstract~~		Today’s robotic fleets are increasingly facing two coupled challenges. First, they are measuring growing volumes of high-bitrate video and LIDAR sensory streams, which, second, often leads them to use increasingly compute-intensive models, such as deep neural networks (DNNs), for downstream perception or control. To cope with these intertwined challenges, compute and storage-limited robots, such as low-power drones, can offload data to central servers (or “the cloud”), for more accurate real-time perception as well as offline model learning. However, cloud processing of large robotic sensory streams introduces acute systems bottlenecks ranging from network delay for real-time inference, to cloud storage, human annotation, and cloud-computing costs for offline model learning.

			In this talk, I will present learning-based approaches for robots to improve model performance with cloud computing, but with minimal systems cost. For real-time inference, I will present a deep reinforcement learning based offloader that decides when a robot should exploit low-latency, on-board computation, or, when highly uncertain, query a more accurate cloud model. Then, for continual learning, I will present an intelligent, on-robot sampler that mines real-time sensory streams for valuable training examples to send to the cloud for model re-training and specialization. Using insights from months of field data and experiments on state-of-the-art embedded deep learning hardware, I will show how simple learning algorithms can allow robots to significantly transcend their on-board sensing performance, but with limited cloud communication cost. Finally, I will conclude with future directions in data-driven networked control, informed by my industry collaborations.

			Bio:
			Sandeep Chinchali is a final-year Computer Science PhD candidate at Stanford, advised by Marco Pavone and Sachin Katti. Previously, he was an early engineer at Uhana, a Stanford startup working on data-driven optimization of cellular networks, now acquired by VMWare. His
			research on cloud robotics and data-driven control of wireless systems has led to successful proof-of-concept trials with major cellular network operators, and was a finalist for best student paper at Robotics: Science and Systems 2019. Prior to Stanford, he graduated from Caltech, where he worked on applications of formal methods in robotics.

Murray: Created page with "Sandeep Chinchali, a Caltech alum and PhD students at Stanford, will visit Caltech onn 16 Oct (Wed). If you would like to meet with him, sign up here. === Schedule === *..."

2019-10-12T21:04:47Z

Created page with "Sandeep Chinchali, a Caltech alum and PhD students at Stanford, will visit Caltech onn 16 Oct (Wed). If you would like to meet with him, sign up here. === Schedule === *..."

New page

Sandeep Chinchali, a Caltech alum and PhD students at Stanford, will visit Caltech onn 16 Oct (Wed). If you would like to meet with him, sign up here.

=== Schedule ===

* 11 am: seminar
* 12 pm: lunch with Richard (and Joel, if he is around)
* 1 pm: Open
* 1:30 pm: Open
* 2:00 pm: Open
* 2:30 pm: Open
* 3 pm: CDS tea (optional)
* 3:45 pm: RMM group meeting (you are welcome to come if you like)

=== Seminar ===

Title <br>
Sandeep Chinchali, PhD candidate, Stanford <br>
16 Oct (Wed), 11a-12p, room TBD

Abstract