Cooperative transportation system for humanoid robots using simulation-based learning

Authors:
Yutaka Inoue;Takahiro Tohge;Hitoshi Iba
Affiliations:
Department of Frontier Informatics, Graduate School of Frontier Sciences, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan;Department of Frontier Informatics, Graduate School of Frontier Sciences, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan;Department of Frontier Informatics, Graduate School of Frontier Sciences, The University of Tokyo, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8656, Japan
Venue:
Applied Soft Computing
Year:
2007

Citing 3
Cited 1

Technical Note: \cal Q-Learning

Machine Learning
Reinforcement Learning

Reinforcement Learning
Cooperative transportation by humanoid robots: learning to correct positioning

Design and application of hybrid intelligent systems

Indoor Positioning System Using Beacon Devices for Practical Pedestrian Navigation on Mobile Phone

UIC '09 Proceedings of the 6th International Conference on Ubiquitous Intelligence and Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, an approach to the behavior acquisition required for humanoid robots to carry out a cooperative transportation task is proposed. In the case of object transportation involving two humanoid robots, mutual position shifts may occur due to the body swinging of the robots. Therefore, it is necessary to correct the position in real-time. Developing the position shift correction system requires a great deal of effort. Solution to the problem of learning the required behaviors is obtained by using the Classifier System and Q-Learning. The successful cooperation of two HOAP-1 humanoid robots in the transportation task has been confirmed by several experimental results.