臺灣博碩士論文加值系統

　　本論文主要探討中型足球機器人之動態環境資訊共享及階層式策略之研究。首先，依據RoboCup聯盟的規範，架設於中型足球機器人上的全方位影像系統為主要的感測器，經由足球機器人的獨立影像處理系統，進行影像的識別與重要特徵物體之定位。藉由無線通訊架構，場上每個機器人傳遞其影像處理系統所偵測的場地資訊到守門員的階層式策略判斷，階層式策略由環境資訊分析與角色分派兩種機制構成，透過環境資訊分析機制可決定進攻或防守的策略，再經由角色分派機制判斷出每個機器人適合的角色，最後機器人利用其目前環境影像資訊與所接收的動態角色派任結果透過模糊控制器來實現動態行為。此機器人涵蓋了獨立的影像處理系統、機構、行為策略系統以及無線通訊，使其具有自主能力。最後，以實驗來驗證所設計之足球機器人系統的效益及適用性。

　　This thesis is mainly to confer the study of dynamic environmental information sharing and hierarchical strategies for middle-size soccer robot. According to the rules of RoboCup, the omnidirectional vision system mounted on the robot is the only sensor of middle-size soccer robot (MSR). Through the image processing system, The MSR can analyze the environmental information and identify the objects and positions of the important features in the field. By utilizing the wireless communication architecture, every MSR sends its image feature to the hierarchical strategy center of the goalkeeper to make decisions. The hierarchical strategy center is composed of the environmental information analysis unit and role-assignment mechanism. Where the environmental information analysis unit will choose offensive or defensive strategy and the role-assignment mechanism will decide proper role for each robot. Each robot combines the current image information and role assignment to perform dynamic behavior with fuzzy logic controller. The MSR possesses individual image processing system, wireless communication, and strategy decision system. Finally, the efficiency and feasibility of the proposed system are demonstrated by practical experiments.

Abstract Ⅰ
Acknowledgment III
Contents IV
List of Figures VII
List of Tables Ⅹ



Chapter 1. Introduction 1
1.1 Motivation 1
1.2 Thesis Organization 3
Chapter 2. Setup of Middle Size Robot Soccer System 4
2.1 Introduction 4
2.2 Overview of the Middle Size Robot Soccer Game 5
2.3 Middle Size Robot Soccer System 6
2.4 Hardware Specification of the Robot Soccer System 9
2.4.1 The omnidirectional mirror and the CCD 9
2.4.2 Image Grabbing Card 11
2.4.3 Wireless Communication System 13
2.4.4 The Driver and DC Motor 15
2.4.5 Battery Module and Voltage Regular Module 17
2.4.6 Notebook Computer 18
2.4.7 The TDCM3 Digital Compass Model 18
2.5 Hardware Configuration of the Soccer Robot 19
2.6 Summary 22
Chapter 3. Omnidirectional Vision System and Wireless Communication System 23
3.1 Introduction 23
3.2 Overview of the Vision System 26
3.2.1 The Important Colors and Markers 27
3.2.2 Overview Image Processing Procedures 28
3.2.3 The Objects-Identification Sub-system 30
3.2.4 The Information of Real World about the Robot Sub-system 33
3.2.5 Self-Localization of soccer robot 34
3.3 Overview of the Wireless Communication System 37
3.3.1 The Windows Sockets Application Programming Interface 39
3.3.2 The Client/Server organization of communication architecture 42
3.3.3 Multi-thread of Server 43
3.3.4 Three way handshake of communication 43
3.4 Summary 45
Chapter 4. Dynamic Strategy 46
4.1 Introduction 46
4.2 Strategy 47
4.2.1 Division of field 47
4.2.2 The Worthy Positions Computation 48
4.2.3 Information Sharing 52
4.2.4 Environmental Information Processing Unit 54
4.2.5 The Role-Assignment Mechanism 57
4.2.6 Dynamic Role Assignment 60
4.2.7 Basic Behavior of Different Role 63
4.2.8 Obstacle-Avoidance Using the Ring Univector Filed 67
4.3 Fuzzy Logic Controller of the Middle Size Soccer Robot 69
4.4 Summary 71
Chapter 5. Experimental Results 72
5.1 Introduction 72
5.2 Operative Interface 73
5.3 Pictures of the Experimental Results 75
Chapter 6. Conclusion and Future Works 78
6.1 Conclusion 78
6.2 Future Works 79
References 80
Biography 84

[1]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.
[2]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.
[3]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.
[4]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.
[5]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.
[6]M. Bowling and M. Veloso, “Motion Control in Dynamic Multi-Robot Environments,” Proc. of IEEE Int. Conf. on Robotics and Automation, pp. 168-173, 1999.
[7]B.L. Brumitt and A.Stentz., “Dynamic mission of Planning for multiple mobile robots,” Proc. Of IEEE Int. Conf. Robot. Automat. pp. 40-45, April 1998.
[8]Ali U. K¨uc¨ukemre. “Using Echo State Networks as Robust Ball Trackers”. Technical report, FH Bonn-Rhein-Sieg, 2005.
[9]Thomas Wisspeintner, Walter Nowak, and Ansgar Bredenfeld. Volksbot,” a flexible component-based mobile robot system”. In Robocup 2005: Robot Soccer World Cup IX, Lecture Notes in Computer Science. Springer.
[10]Paul G. Pl¨oger, Ardiana Arghir, Tobias G¨unther, and Ramin Hosseiny.,” Echo State,Networks for Mobile Robot Modeling and Control”. In D. Polani, B. Browning, A.Bonarini, and K. Yoshida, editors, RoboCup 2003: Robot Soccer World Cup VII volume 3020 of Lecture Notes in Computer Science, pages 157–168. Springer, 2004
[11]Y. Yagi, S. Kawato and S. Tsuji, “Collision avoidance using omnidirectional image sensor (COPIS),” Proc. of the IEEE Int. Conf. on Robotics and Automation, pp. 910-915, April 1991.
[12]Y. Sun, Q. Cao and W. Chen, “An object tracking and global localization method using omnidirectional vision system,” Proc. of the 5th World Congress on Intelligent Control and Automation, pp. 4730-4735, June 2004.
[13]M. Jamzad, A. Foroughnassiraei, E. Chiniforooshan, R. Ghorbani, M. Kazemi, H. Chitsaz, F. Mobasser and S.B. Sadjad, “Middle sized soccer robots: ARVAND,” RoboCup-99: Robot Soccer World Cup III, Springer, pp. 61-73, 2000.
[14]Barraquand and J.C.Latombe, “Robot motion planning: a distributed representation approach,” International Journal Automation, Vol. 10, No. 6, 1991.
[15]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.
[16]Sng, H.L, G. Sen Gupta, and C.H. Messom, “Strategy for Collabration in Robot Soccer,” Proc. of The First IEEE International Workshop, pp.347-351, Jan. 2002.
[17]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..
[18]RoboCup, http://www.robocup.org/.
[19]FIRA, http://www.fira.net/.
[20]The rules of RoboCup 2004 Middle Size League, http://www.er.ams.eng.osaka-u.ac.jp/rc2004msl/msl-rules-2004.pdf.
[21]Instruction Manual, WATEC CCD, http://apisc.com/camera_watec.htm, APISC corp.
[22]Instruction Manual, USB 2.0 Video Grabber, S-960, http://www.vcam.com.tw/sitemap_cc.htm, AME Optimedia Technology Co. Ltd.
[23]Instruction Manual, Intel's Wireless PRO B/G card, http://www.intel.com/network/connectivity/products/wireless/prowireless_mobile.htm, ©2006 Intel Corporation.
[24]Instruction Manual, Series MCDC 2805, Motion Controller for DC-Micromotors, Faulhaber Co.
[25]Instruction Manual, RE-36 and HEDL 5540, http://www.maxonmotor.com/, Maxon Motor Ag.
[26]Instruction Manual, TDCM3 Digital Compass Model, Parallax, Inc.
[27]W. M. Shen, J. Adibi, R. Adobbati, B. Cho, A. Erdem, H. Moradi, B. Salemi and S. Tejada “Autonomous soccer robots,” RoboCup-97: Robot Soccer World Cup I, Springer, pp. 295-304, 1998.
[28]G. Klancar, M. Kristan and R. Karba, “Wide-angle camera distortions and non-uniform illumination in mobile robot tracking,” Robotics and Autonomous Systems, Vol. 46, pp. 125-133, February 2004.
[29]S.W. Bang and M.J. Chung, “Sensor fusion for omnidirectional sensor-based local homming navigation using fuzzy arithmetic,” Intelligent Automation and Soft Computing, pp.718-724 1998.
[30]D.Y. Kim, Y.J Lee., and M.J. Chung, “Feature matching for omnidirectional image based on singular value decomposition,” Proc. of International Conference on Control, Automation and Systems, pp. 395-412, 2002.
[31]Y.J. Lee, D.Y. Kim and M.J. Chung, “Feature matching in omnidirectional images with a large sensor motion for map generation of a mobile robot,” Pattern Recognition Letters, Vol. 24, pp. 413-427, 2004.
[32]C. Marques and P. Lima, “A localization method for a soccer robot using a vision-based omni-directional sensor,” Proc. of RoboCup Workshop, Melbourne, Australia, 2000.
[33]R. Jain, R. Kasturi, and B. G. Schunk, Machine Vision, McGraw-Hill Book Co., 1995.
[34]E. Ardizzone, A. Chella, and R. Pirrone, “A Neural Based Approach to Image Segmentation,” Proc. of the International Conference on Artificial Neural Networks, pp. 1152-1156, London, 1994.
[35]I.D. Scalbe, “Natural representations for straight lines and the Hough transform on discrete arrays,” IEEE Transactions on pattern analysis and machine intelligence, Vol. 11, No.9, pp. 941-950, Sept 1989.
[36]R. Braden. Requirements for internet hosts – communication layers. RFC 1122, Internet Engineering Task Force, October 1989.
[37]D. D. Clark. Window and acknowledgement strategy in TCP. RFC 813, Internet Engineering Task Force, July 1982.
[38]黃俊堯, Key to winSock network programming, 資訊人文化事業出版, 1996.
[39]The GCC Team. The GNU compiler collection. Web page. 2002-10-14. URL: http://gcc.gnu.org/.
[40]S. Floyd and K. Fall. Promoting the use of end-to-end congestion control in the internet. IEEE/ACM Transactions on Networking, pp. 602-630, August 1999.
[41]C. Marques and P. Lima, “Multi-sensor navigation for soccer robots,” in RoboCup-2001: Robot Soccer World Cup V, pp. 144-153, 2002.
[42]E. Rimon, “Exact robot navigation using artificial potential functions,” IEEE Trans. on Robotics and Automation, Vol. 8, No. 5, pp. 501-518, Oct. 1992.
[43]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., Tainan, Taiwan, R.O.C., June 2001.
[44]T.H. S. Li, C.Y. Chen, S. Lee, and Y.Z. Guo, ”Design of fuzzy ring univector field and its application to robot soccer game”, Pro. of the IEEE International Symposium on Computational Intelligence in Robotics and Automation, pp. 85-90, 2003.
[45]Jin-Oh Kim, Pradeep K. Khosla, H. Kitano “Real-Time Obstacle Avoidance Using Harmonic Potential Function,” IEEE Transactions on Robotics and Automaation., Vol. 8, No.3, pp. 338-349, June 1992.