整個機器人足球競賽系統為一視覺回授控制系統。藉由CCD 回授競賽場地上環境的動態資訊及機器人與球的相對狀況，再由中央控制電腦決定我方進攻及防守策略。本論文主要係探討五對五機器人足球競賽之行為策略之研究。首先提出機器人模糊控制及雙重方向漸近控制機構，藉此控制機構完成機器人的避障，射球，傳球，攔球和阻擋等行為動作設計。接著提出一個三個階層策略控制架構，第一階層為策略層負責進攻或防守方的策略；第二階層為角色層依據球在競賽場位置分派角色、編組及選定角色；第三階層係以模糊決策樹來決定每個足球機器人的動作行為。完成整個動態切換策略及賦予每個足球機器人所需扮演的角色。最後以FIRA 3D 模擬器實際進行五對五機器人模擬足球競賽說明所設計之機器人足球系統的效益與適用性。

　The robot soccer system can be considered as a visual feedback control system. According to the dynamic environment information grabbed by the CCD camera, the central control computer will determine the offensive and defensive strategy on the basis of relative positions among ball and the robots. This thesis is mainly to study the control strategy for five-on-five robot soccer competition. In this thesis, a fuzzy motion control and dual directional asymptotic motion control for wheeled robot is proposed firstly, where all the actions including obstacle avoidance, shoot ball, pass ball, intercept ball, and block ball are designed. Secondly, the tree levels control structure is proposed. The first level is the strategy level that decides offensive or defensive strategy; the second level is role level, which is determined on the basis of the ball location in which division of the field, the roles include goalie, primary ttacker, secondary attacker, helper, and defender, and the robot grouping scheme is also proposed in this level; the third level is fuzzy decision tree that determines the actionbehaviors of each soccer robot. Finally, the experiments and real five-on-five robot soccer competition based on the 3D simulator of the FIRA are performed to verify the benefit and the feasibility of the developed schemes.

[1] RoboCup, http://www.robocup.org/.
[2] FIRA, http://www.fira.net/.
[3] S. Hedberg, “Robots Playing Soccer? RoboCup Poses a New Set of AI ResearchChallenges, ” IEEE Expert [see also IEEE Intelligent Systems],Vol. 12,
pp. 5-9, 1997.
[4] I. F. Lin, “Design and Implementation of a One-on-One Robot Soccer
Game,”Master Thesis, Dept. of Electrical Engineering, National Cheng Kung Univ., Tainan, Taiwan, R.O.C., June 2001.
[5] C. Y. Chen, “Design and Implementation of a Role Assignment for the
Five-on-Five Robot Soccer Competition,” Master Thesis, Dept. of Electrical
Engineering, National Cheng Kung Univ., Tainan, Taiwan, R.O.C., June 2003.
[6] S. C. Lee, “Design and implementation of a Five-On-Five Robot Soccer Game
System” Master Thesis, Dept. of Electrical Engineering, National Cheng Kung
Univ., Tainan, Taiwan, R.O.C., June 2003.
[7] T. M. Hung, “Design and implementation of a Three-On-Three Robot Soccer
System” Master Thesis, Dept. of Electrical Engineering, National Cheng Kung
Univ., Tainan, Taiwan, R.O.C., June 2002.
[8] M. Bowling and M. Veloso, “Motion Control in Dynamic Multi-Robot
Environments,” Proc. of IEEE International Conf. on Robotics and Automation, pp. 168-173, 1999.
[9] B.L. Brumitt and A.Stentz., “Dynamic mission of Planning for multiple mobile robots,” in Proc. IEEE Int. Conf. Robot. Automat. pp. 40-45, April 1998.
[10] H. P. Huang, C. C. Liang, and C. W. Lin, “Construction and Soccer Dynamics
Analysis for an Integrated Multi-agent Soccer System,” Proc. Natl. Sci. Counc.
ROC(A), Vol. 25, pp. 84-93, 2001.
[11] Barraquand and J.C.Latombe, “Robot motion planning: a distributed representation approach,” International Journal Automation, Vol. 10, No. 6, 1991.
[12] C. J. Taylor and D. J. Kriegman, “Vision-based motion planning and exploration algorithms for mobile robots,” IEEE Transactions on Robotics and Automation, Vol. 14, No. 3, pp. 417-426, June 1995.
[13] Sng, H.L, G. Sen Gupta, and C.H. Messom, “Strategy for Collabration in Robot Soccer,” Proceedings. The First IEEE International Workshop on, pp.347-351, Jan. 2002
[14] C. F. Lin, “Design and implementation of Dynamic Switching Strategy for
Five-on-Five Robot Soccer Competition” Master Thesis, Dept. of Electrical
Engineering, National Cheng Kung Univ., Tainan, Taiwan, R.O.C., June 2004.
[15] T.-H. S. Li, “Fuzzy Logic Control,” lecture material, Dept. of Electrical
Engineering, National Cheng Kung Univ., Taiwan, R.O.C., 2003.
[16] Xianhua Jiang, Yuichi Motai, and Xingquan Zhu, “Predictive Fuzzy Logic
Controller for trajectory Tracking of a Mobil Robot,” IEEE Mid-Summer Workshop
on Soft Computing in Industrial Applications, Jun,2005.
[17] Hyun Sik Shim and Yoon Gyeoung Sung, “Asymptotic Control for Wheeled
Mobile Robots with Driftless Constraints,” SDOS Robotics and Autonomous
Systems, Vol. 43, pp. 29-37, April 30, 2003.
[18] T. C. Liang and J. S. Liu, “Motion Controller Realizing Cycle Ball Passing Strategy among Multiple Mobile Robots in Robot Soccer games,” Proc. of the 2002 IEEE International Conference on Robotics and Automation, n Electronic Design, Test and Applications, pp. 2587-2592, 2002.
[19] C. C. Hung, “Development of A Multiple-Soccer-Robot System” Doctor degree
Dissertation, Dept. of Mechanical Engineering, National Taiwang Univ., Taipei,
Taiwan, R.O.C., June 2000
[20] C. A. Lai, “Design of Fuzzy Field Control for a One-on-One Robot Soccer
System,” Master Thesis, Dept. of Electrical Engineering, National Cheng Kung
Univ., Taiwan, R.O.C., June, 2001.
[21] Y. Z. Guo, “Design and Implement Ring Potential Field Method for a
Three-on-Three Robot Soccer Game,” Master Thesis, Dept. of Electrical
Engineering, National Cheng Kung Univ., Tainan, Taiwan, R.O.C., June 2002.
[22] Min Gyu Park, Jae Hyun Jeon, and Min Cheol Lee, “Obstacle avoidance for mobile robots using artificial potential field approach with simulated annealing,” IEEE Conf. On IEEE International Symposium, Vol. 3, pp. 1530-1535, 2001.
[23] L. Wu, S. Zhao and X. Xu, “Design of An Obstacle-Avoidance Strategy Based on Robot Soccer Competition,” Proceeding of ICSP 2000 IEEE.
[24] S. Soundar and Z. Shiller, “Optimal Obstacle Avoidance Based on the
Hamiton-Jacobi-Bellman Equation,” IEEE Trans. On Robotics and Automaion, Vol.
13, No.2, pp. 305-310, Apr. 1997.
[25] Jin-Oh Kim, Pradeep K. Khosla, and H. Kitano “Real-Time Obstacle Avoidance
Using Harmonic Potential Function,” IEEE Trans. Robotics Automat., Vol. 8, No.3, pp. 338-349, June 1992.
[26] H. R. Kim, J. H. Hwang, and D. S. Kwon, “Human Robot Cooperation Strategy for Interactive Robot Soccer by Fuzzy Q-Learning,” Proc. of the 2003 IEEE/RSJ Intl Conference on Intelligent Robots and Systems, pp.3642-3647, 2003.
[27] J. H. Kim, H. S. Shim, H. S. Kim, M. J. Jung, I. H. Choi, and J. O. Kim, “A cooperative multi-agent system and its real time application to robot soccer,” IEEE International Conference on Volume 1,pp. 20-25 April 1997
[28] K. H. Park, Y. J. Kim, and J. H. Kim, “Modular Q-learning based multi-agent cooperation for robot soccer,” Elsevier Science Robotics and Autonomous Systems, Vol. 35, pp. 109-122, 2001.
[29] http://www.fira.net/soccer/simurosot/rules_mls.html
[30] H. P. Huang and C. C. Liang, “Strategy-based decision making of a soccer robot system using a real-time self-organizing decision tree,” Elsevier Science Fuzzy Sets and Systems, Vol. 127, pp. 49-64, 2002.
[31] Prahlad Vadakkepat, Ooi Chia Miin, Xiao Peng, and Ting Heng Lee, “Fuzzy
Behavior-Based Control of Mobile Robots,”IEEE Transactions on Fuzzy Systems,
Vol. 12,No. 4,Aug/2004
[32] Cang Ye, N. H. C. Yung, and Danwei Wang “A Fuzzy Controller with Supervised Learning Assisted Reinforcement Learning Algorithm for Obstacle Avoidance,” Systems, Man and Cybernetics, Part B, IEEE Transactions on
Volume 33, Issue 1, Feb. 2003 Page(s):17 - 27
[33] Roger L. King, Samuel H. Russ, Aric B. Lambert, and Donna S. Reeese, “An
artificial immune system model for intelligent agents,” Future Generation
Computer System, Vol. 17, pp. 335-343, 2001.
[34] I. K. Jeong and J. J. Lee, “Evolving cooperative mobile robots using a modified genetic algorithm,” Robotics and Autonomous System, Vol. 21, pp. 197-205,