Skip to main content
Presentation
A Decentralized Reinforcement Learning Controller For Collaborative Driving
Proceeings of the First IFAC Workshop on Multi-Vehicle Systems
  • Luke Ng, University of Waterloo
  • Christopher M. Clark, University of Waterloo
  • Jan P. Huissoon, University of Waterloo
Publication Date
10-2-2006
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
Citation Information
Luke Ng, Christopher M. Clark and Jan P. Huissoon. "A Decentralized Reinforcement Learning Controller For Collaborative Driving" Proceeings of the First IFAC Workshop on Multi-Vehicle Systems (2006)
Available at: http://works.bepress.com/cmclark/22/