Visual Memory for Robust Path Following
Ashish Kumar, Saurabh Gupta, David Fouhey, Sergey Levine, Jitendra Malik
Abstract
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.
BibTeX
@inproceedings{NEURIPS2018_66368270,
author = {Kumar, Ashish and Gupta, Saurabh and Fouhey, David and Levine, Sergey and Malik, Jitendra},
booktitle = {Advances in Neural Information Processing Systems},
editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Visual Memory for Robust Path Following},
url = {https://proceedings.neurips.cc/paper_files/paper/2018/file/66368270ffd51418ec58bd793f2d9b1b-Paper.pdf},
volume = {31},
year = {2018}
}