The Application of Game Theory in RoboCup Soccer Game

Abstract:

In response to characters of multi-robot systems in RoboCup soccer game and dependence between decisions of robots, multi-robot systems task allocation was analyzed by means of game theory in this paper. Formalized description based on game theory for multi-robot system task allocation was offered, and a game theory based task allocation algorithm for multi-robot systems (GT-MRTA) was proposed. Experiments show that GT-MRTA has low complexity, and less time-consumption, can obtain comparative schemes with centralized method, and shows good robustness to communication failure and robot failure.

• Periodical: Applied Mechanics and Materials (Volumes 530-531)
• Pages: 1053-1057
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.530-531.1053
• Online since: February 2014
• Authors: Ping Li*, Jun Yan Zhu
• Keywords: Game Theory, Multi-Robot System (MRS), RoboCup, Task Allocation

References

[1] H. Kitano, M. Asada, and Y. Kuniyoshi, et al. RoboCup: the robot world cup initiative Proceedings of the International Conference on Autonomous Agents Marina del Rey, CA, and USA: ACM, New York, NY, USA, 1997, 340-347.

DOI: 10.1145/267658.267738

[2] Lin Liu. Research on multi-robot system task allocation and formation control [D]. Changsha: National university of defense technology, 2006. 9. (in Chinese).

[3] Graham Romp, Translation of Game theory introduction and application [M], Translated by Ke Huaqing, Yan Jingyi in chinese, Beijing: China university of political science and law press, 2005. 11.

[4] C. Boutilier. Planning, learning and coordination in Multi-agent decision processes. In Proceedings of the Conference on Theoretical Aspects of Rationality and Knowledge, 1996: 195-210.

[5] M. Bowling, M. Veloso. Multi-agent learning using a variable learning rage. Artificial Intelligence, 2002, 136(8): 215-250.

DOI: 10.1016/s0004-3702(02)00121-2

[6] X. Wang, T. Sandholm. Reinforcement leaning to play an optimal Nash equilibrium in team Markov games. In advances in Neural Information Processing Systems (NIPS) 15, MIT Press, Cambridge, MA, (2003).

[7] Zhang Zhixing, Sun Chunzai, Eiji Mizutani. Neuro-Fuzzy and Soft Computing [M]. Translated by Zhang Pingan, Gao Chunhua in chinese. Xi'an: Xi'an Jiaotong University Press. 2000. 6.

[8] Ping Li. Research on Multi-robot System Task Allocation [D]. Guangdong: Guangdong University of Technology, 2009. (in Chinese).

[9] Jiwei. Wu. Study of Collaborative coordination method in multi-agent system [D], Shanghai: Tongji University, 2003. (in Chinese).

[10] M. Veloso, P. Stone. Individual and collaborative behaviors in a team of homogeneous robotic soccer agents in ICMAS, 1998, 309-316.

DOI: 10.1109/icmas.1998.699074

[11] M.B. Dias, A. Stentz. A market approach to multi-robot coordination technical report. CMU-RI-TR-01-26, Robotics Institute, Carnegie Mellon University, (2001).

[12] P. Stone. Layered Learning in Multi-Agent Systems [D]. Pittsburgh, PA 15213-3891, Carnegie Mellon University, (1998).