Martinez-Marin, Tomas and Duckett, Tom (2008) Learning visual docking for non-holonomic autonomous vehicles. In: The Intelligent Vehicles 2008 Symposium (IV08), June 4-6, 2008 , Eindhoven, Netherlands.

Preview

PDF tmtd_iv08ver5.8.pdf Download (1310Kb)

Abstract

This paper presents a new method of learning visual docking skills for non-holonomic vehicles by direct interaction with the environment. The method is based on a reinforcement algorithm, which speeds up Q-learning by applying memorybased sweeping and enforcing the “adjoining property”, a filtering mechanism to only allow transitions between states that satisfy a fixed distance. The method overcomes some limitations of reinforcement learning techniques when they are employed in applications with continuous non-linear systems, such as car-like vehicles. In particular, a good approximation to the optimal behaviour is obtained by a small look-up table. The algorithm is tested within an image-based visual servoing framework on a docking task. The training time was less than 1 hour on the real vehicle. In experiments, we show the satisfactory performance of the algorithm.

Item Type:	Conference or Workshop Item (Paper)
Additional Information:	This paper presents a new method of learning visual docking skills for non-holonomic vehicles by direct interaction with the environment. The method is based on a reinforcement algorithm, which speeds up Q-learning by applying memorybased sweeping and enforcing the “adjoining property”, a filtering mechanism to only allow transitions between states that satisfy a fixed distance. The method overcomes some limitations of reinforcement learning techniques when they are employed in applications with continuous non-linear systems, such as car-like vehicles. In particular, a good approximation to the optimal behaviour is obtained by a small look-up table. The algorithm is tested within an image-based visual servoing framework on a docking task. The training time was less than 1 hour on the real vehicle. In experiments, we show the satisfactory performance of the algorithm.
Keywords:	mobile robot, vision-based control, reinforcement learning
Subjects:	G Mathematical and Computer Sciences > G700 Artificial Intelligence G Mathematical and Computer Sciences > G760 Machine Learning G Mathematical and Computer Sciences > G400 Computer Science G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:	College of Sciences > Faculty of Science > Lincoln School of Computer Science
Depositing User:	Tom Duckett
Date Deposited:	20 Nov 2008 16:33
Last Modified:	13 Mar 2013 08:30
URI:	http://eprints.lincoln.ac.uk/id/eprint/1683

Actions (login required)

View Item