Paper:
Language: English:

Adaptive Action Selection of Body Expansion Behavior in Multi-Robot System Using Communication

Tomohisa Fujiki^*, Kuniaki Kawabata^**, and Hajime Asama^*

^*RACE, The University of Tokyo, 5-1-5 Kashiwanoha, Kashiwa, Chiba 277-8568, Japan
^**Distributed Adaptive Robotics Research Unit, RIKEN, 2-1 Hirosawa, Wako, Saitama 351-0198, Japan

Received: October 21, 2005

Accepted: December 21, 2006

Keywords: Q-learning, multi-robot system, communication, cooperation, mobile robot

Journal ref: Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.11, No.2 pp. 142-148, 2007

Abstract

In a multi-robot system, cooperation within robots is essential in order to execute tasks efficiently. The purpose of this study is to investigate how robots cooperate with each other using interactive communication. A fundamental role of communication in a multi-robot system is to control other robots by an intension transmission. We believe that a multi-robot system can be more adaptive by treating communication as an action. In this paper, we implemented the action adjustment function to achieve cooperation between two mobile robots. Also we discuss the results of computer simulations of collision avoidance as an example of cooperative task.

Reference

[1] N. Hutin, C. Pegard, and E. Brassart, “A Communication Strategy for Cooperative Robots,” Proc. of IEEE/RSJ Intl. Conference on Intelligent Robots and Systems, pp. 114-119, 1998.

[2] Y. Ishida, H. Asama, K. Ozaki, A. Matsumoto, and I. Endo, “Design of Communication System and Development of a Simulator for an Autonomous and Decentralized Robot System,” Journal of Robotics Society of Japan, 10(4), pp. 544-551, 1992 (in Japanese).

[3] Y. Arai, S. Suzuki, S. Kotosaka, H. Asama, H. Kaetsu, and I. Endo, “Collision Avoidance among Multiple Autonomous Mobile Robots using LOCISS (LOcally Communicable Infrared Sensory System),” Proceedings of the IEEE International Conference on Robotics and Automation, pp. 2091-2096, 1996.

[4] H. Yanco and L. A. Stein, “An Adaptive Communication Protocol for Cooperating Mobile Robots,” From Animals to Animats 2, pp. 478-485, 1993.

[5] A. Billard and G. Hayes, “Learning to Communicate Through Imitation in Autonomous Robots,” Artificial Neural Networks – ICANN’97, pp. 763-768, 1997.

[6] W. Von Raffler-Engel (Ed.), “Aspects of Nonverbal Communication,” Loyola Pr, 1979.

[7] M. Hoshino, H. Asama, K. Kawabata, Y. Kunii, and I. Endo, “Communication Learning for Cooperation among Autonomous Robots,” Proceedings of the IEEE International Conference on Industrial Electronics, Control & Instrumentation, pp. 2111-2116, 2000.

[8] K. Kawabata, H. Asama, and M. Tanaka, “A Study of Communication Emergence among Mobile Robots: Simulations of Intention Transmission,” Distributed Autonomous Robotic Systems 5, Springer-Verlag, pp. 71-80, 2002.

[9] R. S. Sutton and A. G. Barto, “Reinforcement Learning: An Introduction (Adaptive Computation and Machine Learning),” The MIT Press, 1998.

[10] S. J. Bradtke and M. O. Duff, “Reinforcement Learning Methods for Continuous-Time Markov Decision Problems,” In G. Tesauro, D. Touretzky, and T. Leen (Eds.), Advances in Neural Information Processing Systems, Vol.7, pp. 393-400, 1995.

[11] S. P. Singh, T. Jaakkola, and M. I. Jordan, “Learning Without State-Estimation in Partially Observable Markovian Decision Processes,” International Conference on Machine Learning, pp. 284-292, 1994.