@COMMENT This file was generated by bib2html.pl <http://www.cs.cmu.edu/~pfr/misc_software/index.html#bib2html> version 0.90
@COMMENT written by Patrick Riley <http://www.cs.cmu.edu/~pfr>
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@InProceedings{ICRA2023-ZIFAN,
  author = {Zifan Xu and Bo Liu and Xuesu Xiao and Anirudh Nair and Peter Stone},
  title = {Benchmarking Reinforcement Learning Techniques for Autonomous Navigation},
  booktitle = {Proceedings of the 2023 IEEE International Conference on Robotics and Automation (ICRA 2023)},
  location = {London, England},
  month = {May},
  year = {2023},
  abstract = {
Deep reinforcement learning (RL) has brought
many successes for autonomous robot navigation. However,
there still exists important limitations that prevent real-world
use of RL-based navigation systems. For example, most learning
approaches lack safety guarantees; and learned navigation
systems may not generalize well to unseen environments.
Despite a variety of recent learning techniques to tackle these
challenges in general, a lack of an open-source benchmark
and reproducible learning methods specifically for autonomous
navigation makes it difficult for roboticists to choose what
learning methods to use for their mobile robots and for learning
researchers to identify current shortcomings of general learning
methods for autonomous navigation. In this paper, we identify
four major desiderata of applying deep RL approaches for
autonomous navigation: (D1) reasoning under uncertainty, (D2)
safety, (D3) learning from limited trial-and-error data, and (D4)
generalization to diverse and novel environments. Then, we
explore four major classes of learning techniques with the
purpose of achieving one or more of the four desiderata:
memory-based neural network architectures (D1), safe RL (D2),
model-based RL (D2, D3), and domain randomization (D4). By
deploying these learning techniques in a new open-source large-
scale navigation benchmark and real-world environments, we
perform a comprehensive study aimed at establishing to what
extent can these techniques achieve these desiderata for RL-
based navigation systems
  },
}