Improved Robustness and Safety for Autonomous Vehicle Control with Adversarial Reinforcement Learning

Xiaobai Ma, Katherine Driggs-Campbell, Mykel J. Kochenderfer

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

To improve efficiency and reduce failures in autonomous vehicles, research has focused on developing robust and safe learning methods that take into account disturbances in the environment. Existing literature in robust reinforcement learning poses the learning problem as a two player game between the autonomous system and disturbances. This paper examines two different algorithms to solve the game, Robust Adversarial Reinforcement Learning and Neural Fictitious Self Play, and compares performance on an autonomous driving scenario. We extend the game formulation to a semi-competitive setting and demonstrate that the resulting adversary better captures meaningful disturbances that lead to better overall performance. The resulting robust policy exhibits improved driving efficiency while effectively reducing collision rates compared to baseline control policies produced by traditional reinforcement learning methods.

Original languageEnglish (US)
Title of host publication2018 IEEE Intelligent Vehicles Symposium, IV 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1665-1671
Number of pages7
ISBN (Electronic)9781538644522
DOIs
StatePublished - Oct 18 2018
Event2018 IEEE Intelligent Vehicles Symposium, IV 2018 - Changshu, Suzhou, China
Duration: Sep 26 2018Sep 30 2018

Publication series

NameIEEE Intelligent Vehicles Symposium, Proceedings
Volume2018-June

Conference

Conference2018 IEEE Intelligent Vehicles Symposium, IV 2018
CountryChina
CityChangshu, Suzhou
Period9/26/189/30/18

    Fingerprint

ASJC Scopus subject areas

  • Computer Science Applications
  • Automotive Engineering
  • Modeling and Simulation

Cite this

Ma, X., Driggs-Campbell, K., & Kochenderfer, M. J. (2018). Improved Robustness and Safety for Autonomous Vehicle Control with Adversarial Reinforcement Learning. In 2018 IEEE Intelligent Vehicles Symposium, IV 2018 (pp. 1665-1671). [8500450] (IEEE Intelligent Vehicles Symposium, Proceedings; Vol. 2018-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IVS.2018.8500450