Title

A Decentralized Reinforcement Learning Controller For Collaborative Driving

Author Info

Luke Ng, University of Waterloo
Christopher M. Clark, University of WaterlooFollow
Jan P. Huissoon, University of Waterloo

Recommended Citation

Postprint version. Published in Proceeings of the First IFAC Workshop on Multi-Vehicle Systems, October 2, 2006.

NOTE: At the time of publication, the author Christopher Clark was not yet affiliated with Cal Poly.

Abstract

Research in the collaborative driving domain strives to create control systems that coordinate the motion of multiple vehicles in order to navigate traffic both efficiently and safely. In this paper a novel individual vehicle controller based on reinforcement learning is introduced. This controller is capable of both lateral and longitudinal control while driving in a multi-vehicle platoon. The design and development of this controller is discussed in detail and simulation results showing learning progress and performance are presented.

Disciplines

Computer Sciences

Copyright

2006 IFAC. The definitive version is available at http://www.ifac-papersonline.net/Detailed/29815.html.