Gaskett, Chris, Fletcher, Luke, and Zelinsky, Alexander (2000) Reinforcement learning for a vision based mobile robot. In: Proceedings of IEEE/RSJ international conference on intelligent robots and systems. pp. 403-409. From: Proceedings of IEEE/RSJ international conference on intelligent robots and systems (IROS2000), 2000, Takamatsu, Japan.

Preview

PDF (Accepted Version) - Accepted Version Download (429kB)

Abstract

Reinforcement learning systems improve behaviour based on scalar rewards from a critic. In this work vision based behaviours, servoing and wandering, are learned through a Q-learning method which handles continuous states and actions. There is no requirement for camera calibration, an actuator model, or a knowledgeable teacher. Learning through observing the actions of other behaviours improves learning speed. Experiments were performed on a mobile robot using a real-time vision system.

Item ID:	629
Item Type:	Conference Item (Research - E1)
ISBN:	978-0-7803-6348-9
Keywords:	robotics, reinforcement learning, neural networks, wirefitting
Date Deposited:	04 Oct 2006
FoR Codes:	08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080108 Neural, Evolutionary and Fuzzy Computation @ 0% 08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080101 Adaptive Agents and Intelligent Robotics @ 0%
Downloads:	Total: 821 Last 12 Months: 7
	More Statistics