A combined reactive and reinforcement learning controller for an autonomous tracked vehicle

Authors:
Isabelle Vincent;Qiao Sun
Affiliations:
Defence R&D Canada-Suffield, PO Box 4000, Station Main, Medicine Hat, AB, Canada;Department of Mechanical and Manufacturing Engineering, University of Calgary, 2500 University Drive NW, Calgary, AB, Canada
Venue:
Robotics and Autonomous Systems
Year:
2012

Citing 6
Cited 0

Neural network design

Neural network design
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Learning to Control in Operational Space

International Journal of Robotics Research
Automated Design of Adaptive Controllers for Modular Robots using Reinforcement Learning

International Journal of Robotics Research
Learning to coordinate behaviors

AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 2
Automatic programming of behavior-based robots using reinforcement learning

AAAI'91 Proceedings of the ninth National conference on Artificial intelligence - Volume 2

Quantified Score

Hi-index	0.00

Visualization

Abstract

Unmanned ground vehicles currently exhibit simple autonomous behaviours. This paper presents a control algorithm developed for a tracked vehicle to autonomously climb obstacles by varying its front and back track orientations. A reactive controller computes a desired geometric configuration based on terrain information. A reinforcement learning algorithm enhances vehicle mobility by finding effective exit strategies in deadlock situations. It is capable of incorporating complex information including terrain and vehicle dynamics through learned experiences. Experiments illustrate the effectiveness of the proposed approach for climbing various obstacles.