Timezone: »

 
Oral
Visual Memory for Robust Path Following
Ashish Kumar · Saurabh Gupta · David Fouhey · Sergey Levine · Jitendra Malik

Wed Dec 05 07:05 AM -- 07:20 AM (PST) @ Room 220 E

Humans routinely retrace a path in a novel environment both forwards and backwards despite uncertainty in their motion. In this paper, we present an approach for doing so. Given a demonstration of a path, a first network generates an abstraction of the path. Equipped with this abstraction, a second network then observes the world and decides how to act in order to retrace the path under noisy actuation and a changing environment. The two networks are optimized end-to-end at training time. We evaluate the method in two realistic simulators, performing path following both forwards and backwards. Our experiments show that our approach outperforms both a classical approach to solving this task as well as a number of other baselines.

Author Information

Ashish Kumar (UC Berkeley)
Saurabh Gupta (UC Berkeley / FAIR / UIUC)
David Fouhey (UC Berkeley)
Sergey Levine (UC Berkeley)
Sergey Levine

Sergey Levine received a BS and MS in Computer Science from Stanford University in 2009, and a Ph.D. in Computer Science from Stanford University in 2014. He joined the faculty of the Department of Electrical Engineering and Computer Sciences at UC Berkeley in fall 2016. His work focuses on machine learning for decision making and control, with an emphasis on deep learning and reinforcement learning algorithms. Applications of his work include autonomous robots and vehicles, as well as applications in other decision-making domains. His research includes developing algorithms for end-to-end training of deep neural network policies that combine perception and control, scalable algorithms for inverse reinforcement learning, deep reinforcement learning algorithms, and more

Jitendra Malik (University of California at Berkley)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors