|Ashish Kumar||UC Berkeley|
|Saurabh Gupta||UC Berkeley / FAIR / UIUC|
|David Fouhey||UC Berkeley|
|Sergey Levine||UC Berkeley|
|Jitendra Malik||University of California at Berkley|
Humans routinely retrace a path in a novel environment both forwards and backwards despite uncertainty in their motion.In this paper, the authors present an approach for doing so.
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.