基于动觉智能图式足球机器人运动控制
|
摘要
机器人足球是一个新兴的交叉学科,涉及机器人学、智能控制和人工生命等多个领域。机器人足球系统本身是一个多机器人协作自治系统,它为理论研究和模型测试提供了一个标准实验平台。
本文基于动觉智能图式的仿人智能控制理论,采用了两种机器人足球系统(RoboCup中型足球机器人系统和FIRA MiroSot小型足球机器人系统)对两轮轮式机器人的运动控制进行研究。针对足球机器人运动控制系统的设计实现,主要进行了如下研究工作:
①应用基于动觉智能图式的仿人智能控制理论(SMIS-HSIC理论),从建立感知-关联-运动图式的角度,完成了足球机器人运动控制系统分层递阶的总体设计。
②基于感知图式的理念,建立了足球机器人的全景、前向视觉系统和里程计系统的定性定量模型;特别针对单目视觉定位,提出了一种完整的坐标变换模型和一种新型的基于进化计算的模型参数辩识方法,解决了机器人感知系统模型的精确辨识问题。
③采用机理建模和仿人智能控制的“类等效”模型简化,建立了足球机器人运动执行系统的一种新型非线性状态空间模型,并以该模型为基础建立了用于机器人基本运动控制设计的仿真研究平台。
④提出了基于运动约束和几何约束的移动机器人基本运动构成方法,并对具有非完整性约束的两轮轮式机器人设计了一组基本运动控制的运动图式;特别对其中的点镇定控制提出了基于分段比例和基于轮速增量的SMIS-HSIC控制算法。
⑤从关联的基本形式出发,提出了多种具体关联结构,设计了足球机器人包括感知图式和运动图式间的各类关联,完成了对基本运动控制的选择和时空规划,解决了单个足球机器人运动控制决策问题。
⑥将多机器人协调视为更高阶的关联,提出了基于意图的多机器人协调机制,将意图作为基本的协调信息引入到单个足球机器人的运动控制决策中,实现了足球机器人的多机器人协调控制。
通过上述工作,本文针对足球机器人系统这一多传感器、多控制量、非线性、强干扰、协作对抗环境下的复杂系统运动控制问题,基于动觉智能图式的仿人智能控制理论,设计实现了实际系统的运动控制。通过对实际机器人的控制证实了本文运动控制的有效性。
The robot soccer is a new interdisciplinary research area, referring to diverse fields like robotics, intelligent control, artificial life, etc. The robot soccer system is a cooperation multi-robot autonomy system. It is a standard experimentation platform for theory research and model testing.
Based on SMIS-HSIC (Human Simulated Intelligence Control based on Sensory-Motor Intelligence Schema) theory, the motion control of two wheels robot is researched, using two kinds of robot soccer systems (RoboCup Middle Size Robot Soccer System and FIRA Mirosot System). For designing and realizing the motion contrl system of soccer robot, the main achievements of research work are done:
①Applying SMIS-HSIC theory, the summary design of hierarchical soccer robot motion control system is completed and is realized in order to get schema of perception-association-motion.
②Based on idea of perception schema, the soccer-robot sensor-models to determine the nature and to fix quantify are advanced in order to describe the panorama vision system, the ahead monocular vision system and the milemeter system. Especially, a new model to transform coordinate is advanced and a new method to confirm the model parameters is gotten based on evolutional calculation for the ahead monocular vision system. The precision models of perception system are gotten by these works.
③Adoptting the mechanism-modeling method and the thought of Quasi Equivalent Predigestion based on HSIC (Human Simulated Intelligence Control) modeling, a new non-linear state space model of soccer robot motion performing system is advanced. Using the model, a simulation system is founded in order to design the basic motion controller of robot.
④According to the restriction of kinematics and the restriction of geometry, the method to get mobile robot basic motion is adanced. A set of basic motion schemas is designed in order to control the two wheels mobile robot with nonholonomic restriction. Especially, The SMIS-HSIC control arithmetic based on Multi-Proportion and The SMIS-HSIC control arithmetic based on wheel speed increment are carried out for Point Stabilization.
⑤Basic modes of association is researched, some association structures are advanced. These soccer-robot association schemas including perception-motion association and perception-group-motion-group association are designed. According to choice and space-time-layout of basic motion control, the design solves the question of robot decision-making.
⑥The Multi-Robots Coordination Mechanism is advanced, Multi-Robots Coordination is regarded as higher association. Robot’s intention is put into decision-making system of single soccer robot as basic coordination information in order to carry out the Multi-Robots Coordination Control.
The control problem of soccer robot system is the control problem of one complex system with multi-sensor, multi-controll-variable and nonlinear characteristic on the strong interference, cooperation and antagonizing condition. Based on SMSI-HSIC theory, motion control system is designed and realized for fact system. The validity of motion control is proved by the actual robot control in this paper.
本文基于动觉智能图式的仿人智能控制理论,采用了两种机器人足球系统(RoboCup中型足球机器人系统和FIRA MiroSot小型足球机器人系统)对两轮轮式机器人的运动控制进行研究。针对足球机器人运动控制系统的设计实现,主要进行了如下研究工作:
①应用基于动觉智能图式的仿人智能控制理论(SMIS-HSIC理论),从建立感知-关联-运动图式的角度,完成了足球机器人运动控制系统分层递阶的总体设计。
②基于感知图式的理念,建立了足球机器人的全景、前向视觉系统和里程计系统的定性定量模型;特别针对单目视觉定位,提出了一种完整的坐标变换模型和一种新型的基于进化计算的模型参数辩识方法,解决了机器人感知系统模型的精确辨识问题。
③采用机理建模和仿人智能控制的“类等效”模型简化,建立了足球机器人运动执行系统的一种新型非线性状态空间模型,并以该模型为基础建立了用于机器人基本运动控制设计的仿真研究平台。
④提出了基于运动约束和几何约束的移动机器人基本运动构成方法,并对具有非完整性约束的两轮轮式机器人设计了一组基本运动控制的运动图式;特别对其中的点镇定控制提出了基于分段比例和基于轮速增量的SMIS-HSIC控制算法。
⑤从关联的基本形式出发,提出了多种具体关联结构,设计了足球机器人包括感知图式和运动图式间的各类关联,完成了对基本运动控制的选择和时空规划,解决了单个足球机器人运动控制决策问题。
⑥将多机器人协调视为更高阶的关联,提出了基于意图的多机器人协调机制,将意图作为基本的协调信息引入到单个足球机器人的运动控制决策中,实现了足球机器人的多机器人协调控制。
通过上述工作,本文针对足球机器人系统这一多传感器、多控制量、非线性、强干扰、协作对抗环境下的复杂系统运动控制问题,基于动觉智能图式的仿人智能控制理论,设计实现了实际系统的运动控制。通过对实际机器人的控制证实了本文运动控制的有效性。
The robot soccer is a new interdisciplinary research area, referring to diverse fields like robotics, intelligent control, artificial life, etc. The robot soccer system is a cooperation multi-robot autonomy system. It is a standard experimentation platform for theory research and model testing.
Based on SMIS-HSIC (Human Simulated Intelligence Control based on Sensory-Motor Intelligence Schema) theory, the motion control of two wheels robot is researched, using two kinds of robot soccer systems (RoboCup Middle Size Robot Soccer System and FIRA Mirosot System). For designing and realizing the motion contrl system of soccer robot, the main achievements of research work are done:
①Applying SMIS-HSIC theory, the summary design of hierarchical soccer robot motion control system is completed and is realized in order to get schema of perception-association-motion.
②Based on idea of perception schema, the soccer-robot sensor-models to determine the nature and to fix quantify are advanced in order to describe the panorama vision system, the ahead monocular vision system and the milemeter system. Especially, a new model to transform coordinate is advanced and a new method to confirm the model parameters is gotten based on evolutional calculation for the ahead monocular vision system. The precision models of perception system are gotten by these works.
③Adoptting the mechanism-modeling method and the thought of Quasi Equivalent Predigestion based on HSIC (Human Simulated Intelligence Control) modeling, a new non-linear state space model of soccer robot motion performing system is advanced. Using the model, a simulation system is founded in order to design the basic motion controller of robot.
④According to the restriction of kinematics and the restriction of geometry, the method to get mobile robot basic motion is adanced. A set of basic motion schemas is designed in order to control the two wheels mobile robot with nonholonomic restriction. Especially, The SMIS-HSIC control arithmetic based on Multi-Proportion and The SMIS-HSIC control arithmetic based on wheel speed increment are carried out for Point Stabilization.
⑤Basic modes of association is researched, some association structures are advanced. These soccer-robot association schemas including perception-motion association and perception-group-motion-group association are designed. According to choice and space-time-layout of basic motion control, the design solves the question of robot decision-making.
⑥The Multi-Robots Coordination Mechanism is advanced, Multi-Robots Coordination is regarded as higher association. Robot’s intention is put into decision-making system of single soccer robot as basic coordination information in order to carry out the Multi-Robots Coordination Control.
The control problem of soccer robot system is the control problem of one complex system with multi-sensor, multi-controll-variable and nonlinear characteristic on the strong interference, cooperation and antagonizing condition. Based on SMSI-HSIC theory, motion control system is designed and realized for fact system. The validity of motion control is proved by the actual robot control in this paper.
引文
[1] Hiroaki Kitano, RoboCup as a Research Program[A], IEEE1997 IROS97 0-7803-4119-8/97[C].1997
[2] Chunhui Zhang, Chen Qu, Dazhi Gao. the Design and Development of Robot Soccer Player[C]. International Symposium on Artificial Life and Robotics,Japan,1999,2.
[3]战强,等.多机器人技术的研究现状[J].机器人.1998.2(增):439-443.
[4] Jong-Hwan Kim. Third Call for Participation[A]. Micro-robot World Cup Soccer Tournament 1996 (MiroSot'96)[C]. Taejon,Korea,11.1996.Accessible from http://vivaldi. kaist. ac.kr.
[5]李实,徐旭明,叶榛,孙增圻.国际机器人足球比赛及其相关技术[J].机器人. 2000,22(5):420-426.
[6]王文学,赵姝颖,孙萍,徐心和.多智能足球机器人系统的关键技术[J].东北大学学报(自然科学版). 2001,22(2):192-195.
[7] Hiroki Kitano, Minoru A sada, Yasuo Kuniyoshi, Itsuki Noda, EiichiO sawa. HitoshiM atsubara RoboCup: A Challenge Problem for AI and Robotics[C], RoboCup-97: Robot SoccerWorld Cup I, 1-19, Springer, 1998.
[8] ItsukiNoda et al. Soccer Server Manual. RoboCup Federation. http://www.robocup.org.
[9]李磊,叶涛,谭民,陈细军.移动机器人技术研究现状与未来[J].机器人.2002,24(5): 475-480.
[10]王越超,景兴建.轮式移动机器人控制[J].机器人, 2000,22(7):724-729.
[11] IIya Kolmanovsky, N Harris McClamroch. Developments in nonholonomic control problems[J]. IEEE Control System,1995,20-36.
[12] Brockett R W. Asymptotic stability and feedback stabilization[A]. Differential Geometric Control Theory[M]. Boston: Birkhauser, 1983, 181-208.
[13] Samson C. Control of chained systems-application to path following and time-varying point-stabilization of mobile robots[J]. IEEE Transactions Automation Control,1995,40: 64-77.
[14]董文杰,霍伟.链式系统的轨迹跟踪控制[J].自动化学报, 2000,26(3):310-316.
[15] O J Sordalen, O Egeland. Exponential Stabilization of Nonholonomic Chained Systems[J]. IEEE Transactions Automation Control,1995,40(1):35-49.
[16] KyuCheol Park, Hakyoung Chung, Jang Gyu Lee. Point stabilization of mobile robots via state-space exact feedback linearization[J]. Robotics and Computer Integrated Manufacturing,2000,16:353-363.
[17] Ranjan Mukherjee, Degang Chen, Gangbing Song. Feedback Control Strategies for a Nonholonomic Mobile Robot Using a Nonlinear Oscillator[J]. Journal of Robotic Systems, 1999,4(16):237-248.
[18]王越超,景兴建.非完整约束轮式移动机器人人工场导向控制研究[J].自动化学报, 2002,28(5):777-783.
[19]曹洋,方帅,徐心和.加速度约束条件下的非完整移动机器人运动控制[J].控制与决策, 2006,21(2):193-196.
[20]张春晖.机器人足球策略系统研究与实现[D].东北大学博士学位论文,2002, 50-51.
[21]杨欣欣,等.基于神经网络的室外移动机器人前轮转向模型[J].自动化学报, 2000,26(2):154-161.
[22]董文杰,霍伟.受非完整约束移动机器人的跟踪控制[J].自动化学报,2000,26(1);1-6.
[23] YJ.Kanayama, F.Fahroo.A new continuous-curvature line/path-tracking method for car-like vehicles [J]. Advanced Robotics 2000,13(7):663-689.
[24] Chun Yi. Robust motion/force control of mechanical systems with classical nonholonomic constraints[C]. IEEE Transactions Automatic Control, 1994,39(3):389-393.
[25] Sheng Lin, A. Goldenberg. Robust damping control of wheeled mobile robots[C]. Proc. of the 2000 IEEE International Conference on Robotics and Automation, San Francisco, CA, 2000,2919-2924.
[26] C.-S. Hong, et al. A vision-guided object tracking and prediction algorithm for soccer robots[C]. Proc. of the 1997 IEEE International Conference on Robotics&Automation, Albuquerque, 1997.4:346-351.
[27]谷东兵,胡豁生.移动机器人的运动预测控制[J].仪器仪表学报,2000, 21(2):155-158.
[28] Wei Kang, Ning Xi, Jindong Tan. Analysis and design of noontime based motion controller for mobile robots[A]. Proc of the 1999 IEEE International Conference on Robotics and Automation[C], Detroit, Michigan,1999,2645-2650.
[29]张春晖.机器人足球策略系统研究与实现[D].东北大学博士学位论文, 2002, 50-51.
[30] Omar Ait Aider, Philippe Hoppenot, Etienne Colle. A model-based method for indoor mobile robot localization using monocular vision and straight-line correspondences[J]. Robotics and Autonomous Systems, 2005,(52):229–246.
[31] Eric Royer, Maxime Lhuillier, etc. Monocular Vision for Mobile Robot Localization and Autonomous Navigation[J]. International Journal of Computer Vision,2007,74(3) 237-260.
[32]厉茂海,洪炳镕,罗荣华,蔡则苏.基于单目视觉的移动机器人全局定位[J].机器人. 2007,2(29):140-144.
[33] Jeon S H, Kim B K. Monocular-based position determination for indoor navigation of mobilerobots[C]. Proc. IASTED Intl.Conf. on Control and Applications, Banff:1999,408–413.
[34]王健,王孝通,徐晓刚.基于单目机器视觉的船舶测距定位原理研究[J].中国航海, 2005(3):8-10.
[35] Liu B R, Xie Y, Yang Y M, et al. A Self-location method with monocular vision for autonomous soccer robot [C]. Industrial Technology,2005. ICIT 2005. IEEE International Conference on ,2005,888-892.
[36]谢云,杨宜民.自主足球机器人的单目视觉自定位方法[J].微电子学与计算机, 2005,22(10):129-132.
[37]朱莹,洪炳镕,阮玉峰.全自主足球机器人快速目标识别与定位方法[J].哈尔滨工业大学学报, 2003,35(9):1060-1063.
[38]姜延,高庆吉,张利辉,等.全自主足球机器人目标识别与定位方法研究[J].东北电力学院学报, 2002,22(3):12-16.
[39]王景川,陈卫东,曹其新.基于全景视觉与里程计的移动机器人自定位方法研究[J].机器人. 2007.27(1):41-45.
[40] Motomura A , Matsuoka T , Hasegawa T. Self-localization method using two landmarks and dead reckoning for autonomous mobile soccer robots[A]. Proc. of the RoboCup 2003 Symposium[C]. Padova , Italy :2003,526-533.
[41] HallD L, Llinas J. An Introduction to Multisensor Data Fusion[J]. Proc. IEEE,2004,85(1): 6-23
[42] Halld L. Mathematical technique in multi-sensor data fusion[M]. London: Artech House, 2000.15-21.
[43] Richard T. Princip les of effective multisensor data fusion[J]. Military Technology,2003, 27(5):29-37.
[44] Gao J B, Harris C J. Some remarks on Kalman filters for the multi-sensor fusion[J]. Information Fusion, 2002,3 (3):191-201.
[45] Gao J B. Some remark on Kalman filters for the multi-sensor fusion[J]. Information Fusion, 2002,3(3):191– 201.
[46] HF Durrant-Whyte. Sensor models and multi-sensor integration[J]. The International Journal of Robotics Research, 2001,7(6):87-92.
[47] Megalooikonomou V, Yesha Y. Space efficient quantization for distributed estimation by a multi2sensor fusion system[J]. Information Fusion,2004,5(5):299-308.
[48] Arkin R. Behavior-Based Robotics[M]. MIT Press. 1998.
[49] Marr D. Behavior-Based Control:Main Properties and Implications[C]. Proc.1992 IEEE International Conference on robotics and Automation, Nice, France, May, 1992:830-835.
[50] Dean T, Wellman M. Planning and Control[M]. Morgan Kaufmann Publishers. San Mateo, CA, 1991.
[51] Saridis G. Toward the Realization of Intelligent Controls[C]. Proc.of the IEEE.1979, 67(8):1115-1133.
[52] Albus J S, Mcain H G, Lumia R. NASA/NBS standard reference model for tele-robot control system architecture (NASREM). NIST Technical Note 1235,1989.
[53] Brooks R. A robust layered control system for a mobile robot[J]. IEEE Transactions on Robotics and Automation. 1986,2(1):14-23.
[54] Conell J. Minimalist mobile robotics: a colony-style architecture for an artificial creature[M]. Academic Press, 1990.
[55]李佳宁,易建强.移动机器人体系结构研究进展[J].机器人, 2003,25(7):756-760.
[56] The FIRA Executive Committee. FIRA small league MiroSot game rules[S]. http://www.fira.net.
[57] Camacho, David, Fernandez, Fernando. An architecture for coordinating robot soccer agents[J]. Engineering Applications of Artificial Intelligence. 2006,19:179-188.
[58] Pan, Quan; Zhang, Hong-Cai. Multi-agent coordination method based on Markov game and application to robot soccer[J]. Robot, 2005,27:46-51.
[59] Zhou, Tong; Hong, Bing-Rong; Shi, Chao-Xia; Zhou, Hong-Yu. Cooperative behavior acquisition based modular Q learning in multi-agent system[C].2005 International Conference on Machine Learning and Cybernetics. Guangzhou: Institute of Electrical and Electronics Engineers Computer Society, 2005:205-210.
[60] Crawford, Elisabeth; Veloso, Manuela, Learning to select negotiation strategies in multi-agent meeting scheduling[C]. Pittsburgh, PA, United States: AAAI Workshop - Technical Report,2005,Vol WS-05-09:27-33.
[61]王文学,孙萍,徐心和.足球机器人系统结构与关键技术研究[J].控制与决策. 2001.16: 234.
[62]李实,陈江,孙增圻.清华机器人足球队的结构设计与实现[J].清华大学学报(自然科学版).2001,41:7.
[63]姜成志,叶明凤,顾泽元.基于决策树学习的智能机器人控制方法[J].计算机工程与设计.2002,23:10.
[64]吴丽娟,张春晖,徐心和.足球机器人决策系统推理模型[J].东北大学学报(自然科学版).2001,22:6.
[65]王牛,李祖枢,潘娅.基于预测的足球机器人抢点射门动作实现研究[J].华中科技大学学报(自然科学版) . 2004,32:143.
[66]宋健. 21世纪的控制智能控制——超越世纪的目标[J].中国工程科学. 1999,l(1):1-5.
[67]张钹,郑应平.从现代信息科技发展看自动化学科的使命和发展趋势[J].自动化学报. 2002,28(Suppl):19-22.
[68]孙增圻.智能控制理论与技术[M].北京:清华大学出版社,1997:1-344.
[69] K. S. Fu, M. Walts. A Heuristic Approach to Reinforcement Learning Control System[C]. IEEE Trans. Automatic Control, 1965, 10(4), 390-398.
[70] Leondes C. T, Mendel J M. Artificial Intelligence Control. Tech. Rept.[C], 4336, McDonnel-Douglas Astronoutics Co, 1967.
[71] ?str?m, K. J, Adaptive control around 1960[J], IEEE Control Systems, June 1996:44-49.
[72]蔡自兴.智能控制(第2版)[M].北京:电子工业出版社. 2004:103-330.
[73]蔡自兴.人工智能控制[M].北京:化学工业出版社. 2005:22-142.
[74]王耀南.智能控制系统[M].长沙:湖南大学出版社. 1996:11-306.
[75]吴宏鑫,王迎春,邢淡.基于智能特征模型的智能控制及应用[J].中国科学(E辑).2002,12(32). 805-816.
[76]蔡自兴.智能控制及移动机器人研究进展[J].中南大学学报(自然科学版),2005,36(l5):721-725.
[77]郑南宁,贾新春,袁泽剑.控制科学与技术的发展及其思考[J].自动化学报, 2002, 28(Suppl):7-17.
[78]李祖枢,涂亚庆.仿人智能控制[M].北京:国防工业出版, 2003:4-95, 96-197, 96-376, 40, 105-121, 121-134, 224-245.
[79] Zhou Qijian, Bai Jianguo. An Intelligent Controller of Novel Design[C]. Proc. of a多National Instrumentation Conference, Part 1.Shanghai, China.1983:137-149.
[80] Q. J. Zhou, J. G. Bai. An Intelligent Controller of Novel Design[C]. Proc. of a National Instrumentation Conference, Part 1, Shanghai. China. 1983: 137-149.
[81]李祖枢.仿人智能控制研究20年[A].重庆:1999年中国智能自动化学术会议论文集(上册)[C].北京:清华大学出版社, 1999:20-23.
[82]皮亚杰著.王宪钿等译.发生认识论原理[M].北京:商务印书馆,1981.
[83] N.维纳.郝季仁译.控制论(第二版) [M].北京:科学出版社,1985.
[84]李敏强,寇纪淞,林丹,李书全.遗传算法的基本理论与应用[M].北京:科学出版社,2002:17-348.
[85]涂序彦.人工智能:回顾与展望[M].北京:科学出版社, 2006.7.
[86]廉师友.人工智能技术导论[M].西安:西安电子科技大学出版社, 2000.
[87]王文杰,叶世伟.人工智能原理与应用[M].北京:人民邮电出版社, 2004.
[88]蔡自兴.徐光佑,人工智能及其应用[M].北京:清华大学出版社, 2004.
[89]李德毅,杜鹢.不确定性人工智能[M].北京:国防工业出版社.2005.29-54.
[90]张华,李祖枢,古建功.一种通用仿人智能控制器的参数整定方法及应用研究[A].第六届全球智能控制与自动化大会论文集[C],中国大连,2006,6: 9089-9093.
[91] Yuanhong Dan, Zushu Li, YongLing Wen. Structural Design and Discussion of Key Parameters in Swing-Up and Handstand Control of a Cart-Double Pendulum System[A], Proc. of SICE Annual Conference, Okayama, Japan ,2005:2483-2488 .
[92] Zushu Li, YuanHong Dan, Yongling Wen, Hua Zhang, Xiaochuan Zhang,Swing-up and Handstand Control of Cart-Triple-Pendulum System Based on HSIC[A], Proc. of the Eighth IASTED International Conference Intelligent Systems And Control, October 31-November 2,2005,Cambrige USA:1-6.
[93]李祖枢.仿人智能控制理论和多级倒立摆的摆起控制[A].人工智能:回顾与展望[M].北京:科学出版社, 2006.7:174-207.
[94] Li Zushu, Guifang Shao. An Behavior Selection Model of Artificial Life With Dodge Action Based on Priority Degree[C]. Proc. of the Third International Conference on Machine Learning and Cybernetics,2005,8.
[95] Guifang Shao, Zushu Li. An Evaluation Method for Fusion Image Quality Based on HVS[C]. The 3rd international conference on mechanics and information technology,2005,12.
[96] Guifang Shao, Zushu Li. The Action-Selection and Evolution Structure of Artificial Life based on Schema Theory[C]. 2006 International Symposium on Artificial Intelligence (ISAI’06),2006,8.
[97] http://www.fira.net/.
[98] http://www.robocup.org/.
[99]曹其新,陈卫东等. RoboCup中型组机器人比赛规则(MSLR). 2007年中国RoboCup国际公开赛比赛规则.济南,2007.10.
[100]洪炳熔.机器人足球的最终目标机器实现途径[J].华中科技大学学报(自然科学版).2004,32.
[101]皮亚杰著.倪连生,王琳译.结构主义[M].北京:商务印书馆,1984.
[102]雷永生,王至元,杜丽燕等.皮亚杰发生认识论评述[M].北京:人民出版社,1987.
[103]皮亚杰著.儿童智力理论[M] .北京:人民出版社,1987.
[104] Michael A Arbib, E Jeffrey Conklin, Jane C. Hill. From Schema Theory to Language[C], Oxford University Press, 1987.
[105] Sandra P. Marshall, Schemas in problem solving[C], New York: Cambridge University Press, 1995.
[106] Ronald C. Arkin, Motor Schema-Based Mobile Robot Navigation[J], International Journal ofRobotics Research, 1989,18(4).
[107] Tucker Balch, Ronald C. Arkin, Motor Schema-based Formation Control for Robot Teams[C], Proceedings of the First International Conference on Robot Teams Systems (ICMAS'95).
[108] George Maistros and Gillian Hayes, An imitation mechanism inspired from neurophysiology[C]. Proc. of EmerNet: Third International Workshop on Current Computational Architectures Integrating Neural Networks and Neuroscience, Durham, August 2000.
[109] R. Poli and W. B. Langdon, An Experimental Analysis on Schema Creation, Propagation and Disruption in Genetic Programming[C], In E Goodman, Ed. Proc. of Seventh International Conference on Genetic Algorithms, Michigan State University, East Lansing, USA, July 1997. Morgan Kaufmann.
[110]王桂平.图式理论在复杂系统控制中的应用研究[D].重庆大学硕士学位论文,2003.
[111] Li Zushu,Wang, GuiPing, Schema Theory and Human Simulated Intelligent Control[C], IEEE International Conference on Robotics, Intelligent Systems and Signal Processing, RISSP 2003, 2003.10.8, Chang Sha,China:524-530.
[112]王育新.小车-二级摆系统摆起倒立控制——基于动觉智能图式的仿人智能控制在复杂系统控制中应用研究[D].重庆大学硕士学位论文,2004
[113] Motomura A , Matsuoka T , Hasegawa T. Self-localization method using two landmarks and dead reckoning for autonomous mobile soccer robots [A] . Proceedings of the RoboCup 2003 Symposium[C]. Padova , Italy :2003.526-533.
[114]凌云峰.移动机器人全景视觉应用研究[D].哈尔滨工程大学硕士研究论文,2007
[115] L Huang. Speed Control of Differentially Driven Wheeled Mobile Robots—Model-Based Adaptive Approach[J]. Journal of Robotic Systems(S0741-2223), 2005, (22):323-332.
[116] Weiguo Wu, Huitang Chen, Peng-Yung Woo. Time Optimal Path Planning for a Wheeled Mobile Robot[J]. Journal of Robotic Systems(S0741-2223), 2000, (11):585-591.
[117] Wang Xiaoyu, Zhao Jie, Cai Hegao. Dynamic and control system analysis of two wheeled robot for welding application[J]. China Welding, 2004,(13):147-150.
[118]朱咏杰,付宜利,王树国,常疆.一种改进的移动机器人运动控制算法[J].哈尔滨工业大学学报. 2004(36):4-6.
[119] Zhou Ru xun, Zhang Zelong, Qi Yingchuan. Direct Identification of DC Electromotor Model Parameter[J]. Computer Simulation, 2006,23(6):113-115.
[120]陈伯时.电力拖动自动控制系统[M].北京:机械工业出版社, 1997:48-55.
[121] Wang Xiaoyu, Zhao Jie, Cai Hegao. Dynamic and control system analysis of two wheeledrobot for welding application[J]. China Welding, 2004,(13):147-150 .
[122]曹艳,王典洪.足球机器人定点行走模型的研究[J].武汉理工大学学报. 2005(29):595-598.
[123]张华.基于动觉智能图式的多级摆系统仿人智能运动控制[D].重庆大学博士学位论文, 2005.
[124]邵桂芳.基于动觉智能图式的人工生命体行为及其选择与进化研究[D].重庆大学博士学位论文, 2006.
[125] Llinas J, HallD L. An Introduction to Multi-Sensor Data Fusion[C]. Proc. of the 1998 IEEE International Symposium on, 1998, 6:537-540.
[126] Robin R Murphy著.杜军平,吴立成,胡金春.人工智能机器人学导论[M].北京:电子工业出版社, 2004.
[2] Chunhui Zhang, Chen Qu, Dazhi Gao. the Design and Development of Robot Soccer Player[C]. International Symposium on Artificial Life and Robotics,Japan,1999,2.
[3]战强,等.多机器人技术的研究现状[J].机器人.1998.2(增):439-443.
[4] Jong-Hwan Kim. Third Call for Participation[A]. Micro-robot World Cup Soccer Tournament 1996 (MiroSot'96)[C]. Taejon,Korea,11.1996.Accessible from http://vivaldi. kaist. ac.kr.
[5]李实,徐旭明,叶榛,孙增圻.国际机器人足球比赛及其相关技术[J].机器人. 2000,22(5):420-426.
[6]王文学,赵姝颖,孙萍,徐心和.多智能足球机器人系统的关键技术[J].东北大学学报(自然科学版). 2001,22(2):192-195.
[7] Hiroki Kitano, Minoru A sada, Yasuo Kuniyoshi, Itsuki Noda, EiichiO sawa. HitoshiM atsubara RoboCup: A Challenge Problem for AI and Robotics[C], RoboCup-97: Robot SoccerWorld Cup I, 1-19, Springer, 1998.
[8] ItsukiNoda et al. Soccer Server Manual. RoboCup Federation. http://www.robocup.org.
[9]李磊,叶涛,谭民,陈细军.移动机器人技术研究现状与未来[J].机器人.2002,24(5): 475-480.
[10]王越超,景兴建.轮式移动机器人控制[J].机器人, 2000,22(7):724-729.
[11] IIya Kolmanovsky, N Harris McClamroch. Developments in nonholonomic control problems[J]. IEEE Control System,1995,20-36.
[12] Brockett R W. Asymptotic stability and feedback stabilization[A]. Differential Geometric Control Theory[M]. Boston: Birkhauser, 1983, 181-208.
[13] Samson C. Control of chained systems-application to path following and time-varying point-stabilization of mobile robots[J]. IEEE Transactions Automation Control,1995,40: 64-77.
[14]董文杰,霍伟.链式系统的轨迹跟踪控制[J].自动化学报, 2000,26(3):310-316.
[15] O J Sordalen, O Egeland. Exponential Stabilization of Nonholonomic Chained Systems[J]. IEEE Transactions Automation Control,1995,40(1):35-49.
[16] KyuCheol Park, Hakyoung Chung, Jang Gyu Lee. Point stabilization of mobile robots via state-space exact feedback linearization[J]. Robotics and Computer Integrated Manufacturing,2000,16:353-363.
[17] Ranjan Mukherjee, Degang Chen, Gangbing Song. Feedback Control Strategies for a Nonholonomic Mobile Robot Using a Nonlinear Oscillator[J]. Journal of Robotic Systems, 1999,4(16):237-248.
[18]王越超,景兴建.非完整约束轮式移动机器人人工场导向控制研究[J].自动化学报, 2002,28(5):777-783.
[19]曹洋,方帅,徐心和.加速度约束条件下的非完整移动机器人运动控制[J].控制与决策, 2006,21(2):193-196.
[20]张春晖.机器人足球策略系统研究与实现[D].东北大学博士学位论文,2002, 50-51.
[21]杨欣欣,等.基于神经网络的室外移动机器人前轮转向模型[J].自动化学报, 2000,26(2):154-161.
[22]董文杰,霍伟.受非完整约束移动机器人的跟踪控制[J].自动化学报,2000,26(1);1-6.
[23] YJ.Kanayama, F.Fahroo.A new continuous-curvature line/path-tracking method for car-like vehicles [J]. Advanced Robotics 2000,13(7):663-689.
[24] Chun Yi. Robust motion/force control of mechanical systems with classical nonholonomic constraints[C]. IEEE Transactions Automatic Control, 1994,39(3):389-393.
[25] Sheng Lin, A. Goldenberg. Robust damping control of wheeled mobile robots[C]. Proc. of the 2000 IEEE International Conference on Robotics and Automation, San Francisco, CA, 2000,2919-2924.
[26] C.-S. Hong, et al. A vision-guided object tracking and prediction algorithm for soccer robots[C]. Proc. of the 1997 IEEE International Conference on Robotics&Automation, Albuquerque, 1997.4:346-351.
[27]谷东兵,胡豁生.移动机器人的运动预测控制[J].仪器仪表学报,2000, 21(2):155-158.
[28] Wei Kang, Ning Xi, Jindong Tan. Analysis and design of noontime based motion controller for mobile robots[A]. Proc of the 1999 IEEE International Conference on Robotics and Automation[C], Detroit, Michigan,1999,2645-2650.
[29]张春晖.机器人足球策略系统研究与实现[D].东北大学博士学位论文, 2002, 50-51.
[30] Omar Ait Aider, Philippe Hoppenot, Etienne Colle. A model-based method for indoor mobile robot localization using monocular vision and straight-line correspondences[J]. Robotics and Autonomous Systems, 2005,(52):229–246.
[31] Eric Royer, Maxime Lhuillier, etc. Monocular Vision for Mobile Robot Localization and Autonomous Navigation[J]. International Journal of Computer Vision,2007,74(3) 237-260.
[32]厉茂海,洪炳镕,罗荣华,蔡则苏.基于单目视觉的移动机器人全局定位[J].机器人. 2007,2(29):140-144.
[33] Jeon S H, Kim B K. Monocular-based position determination for indoor navigation of mobilerobots[C]. Proc. IASTED Intl.Conf. on Control and Applications, Banff:1999,408–413.
[34]王健,王孝通,徐晓刚.基于单目机器视觉的船舶测距定位原理研究[J].中国航海, 2005(3):8-10.
[35] Liu B R, Xie Y, Yang Y M, et al. A Self-location method with monocular vision for autonomous soccer robot [C]. Industrial Technology,2005. ICIT 2005. IEEE International Conference on ,2005,888-892.
[36]谢云,杨宜民.自主足球机器人的单目视觉自定位方法[J].微电子学与计算机, 2005,22(10):129-132.
[37]朱莹,洪炳镕,阮玉峰.全自主足球机器人快速目标识别与定位方法[J].哈尔滨工业大学学报, 2003,35(9):1060-1063.
[38]姜延,高庆吉,张利辉,等.全自主足球机器人目标识别与定位方法研究[J].东北电力学院学报, 2002,22(3):12-16.
[39]王景川,陈卫东,曹其新.基于全景视觉与里程计的移动机器人自定位方法研究[J].机器人. 2007.27(1):41-45.
[40] Motomura A , Matsuoka T , Hasegawa T. Self-localization method using two landmarks and dead reckoning for autonomous mobile soccer robots[A]. Proc. of the RoboCup 2003 Symposium[C]. Padova , Italy :2003,526-533.
[41] HallD L, Llinas J. An Introduction to Multisensor Data Fusion[J]. Proc. IEEE,2004,85(1): 6-23
[42] Halld L. Mathematical technique in multi-sensor data fusion[M]. London: Artech House, 2000.15-21.
[43] Richard T. Princip les of effective multisensor data fusion[J]. Military Technology,2003, 27(5):29-37.
[44] Gao J B, Harris C J. Some remarks on Kalman filters for the multi-sensor fusion[J]. Information Fusion, 2002,3 (3):191-201.
[45] Gao J B. Some remark on Kalman filters for the multi-sensor fusion[J]. Information Fusion, 2002,3(3):191– 201.
[46] HF Durrant-Whyte. Sensor models and multi-sensor integration[J]. The International Journal of Robotics Research, 2001,7(6):87-92.
[47] Megalooikonomou V, Yesha Y. Space efficient quantization for distributed estimation by a multi2sensor fusion system[J]. Information Fusion,2004,5(5):299-308.
[48] Arkin R. Behavior-Based Robotics[M]. MIT Press. 1998.
[49] Marr D. Behavior-Based Control:Main Properties and Implications[C]. Proc.1992 IEEE International Conference on robotics and Automation, Nice, France, May, 1992:830-835.
[50] Dean T, Wellman M. Planning and Control[M]. Morgan Kaufmann Publishers. San Mateo, CA, 1991.
[51] Saridis G. Toward the Realization of Intelligent Controls[C]. Proc.of the IEEE.1979, 67(8):1115-1133.
[52] Albus J S, Mcain H G, Lumia R. NASA/NBS standard reference model for tele-robot control system architecture (NASREM). NIST Technical Note 1235,1989.
[53] Brooks R. A robust layered control system for a mobile robot[J]. IEEE Transactions on Robotics and Automation. 1986,2(1):14-23.
[54] Conell J. Minimalist mobile robotics: a colony-style architecture for an artificial creature[M]. Academic Press, 1990.
[55]李佳宁,易建强.移动机器人体系结构研究进展[J].机器人, 2003,25(7):756-760.
[56] The FIRA Executive Committee. FIRA small league MiroSot game rules[S]. http://www.fira.net.
[57] Camacho, David, Fernandez, Fernando. An architecture for coordinating robot soccer agents[J]. Engineering Applications of Artificial Intelligence. 2006,19:179-188.
[58] Pan, Quan; Zhang, Hong-Cai. Multi-agent coordination method based on Markov game and application to robot soccer[J]. Robot, 2005,27:46-51.
[59] Zhou, Tong; Hong, Bing-Rong; Shi, Chao-Xia; Zhou, Hong-Yu. Cooperative behavior acquisition based modular Q learning in multi-agent system[C].2005 International Conference on Machine Learning and Cybernetics. Guangzhou: Institute of Electrical and Electronics Engineers Computer Society, 2005:205-210.
[60] Crawford, Elisabeth; Veloso, Manuela, Learning to select negotiation strategies in multi-agent meeting scheduling[C]. Pittsburgh, PA, United States: AAAI Workshop - Technical Report,2005,Vol WS-05-09:27-33.
[61]王文学,孙萍,徐心和.足球机器人系统结构与关键技术研究[J].控制与决策. 2001.16: 234.
[62]李实,陈江,孙增圻.清华机器人足球队的结构设计与实现[J].清华大学学报(自然科学版).2001,41:7.
[63]姜成志,叶明凤,顾泽元.基于决策树学习的智能机器人控制方法[J].计算机工程与设计.2002,23:10.
[64]吴丽娟,张春晖,徐心和.足球机器人决策系统推理模型[J].东北大学学报(自然科学版).2001,22:6.
[65]王牛,李祖枢,潘娅.基于预测的足球机器人抢点射门动作实现研究[J].华中科技大学学报(自然科学版) . 2004,32:143.
[66]宋健. 21世纪的控制智能控制——超越世纪的目标[J].中国工程科学. 1999,l(1):1-5.
[67]张钹,郑应平.从现代信息科技发展看自动化学科的使命和发展趋势[J].自动化学报. 2002,28(Suppl):19-22.
[68]孙增圻.智能控制理论与技术[M].北京:清华大学出版社,1997:1-344.
[69] K. S. Fu, M. Walts. A Heuristic Approach to Reinforcement Learning Control System[C]. IEEE Trans. Automatic Control, 1965, 10(4), 390-398.
[70] Leondes C. T, Mendel J M. Artificial Intelligence Control. Tech. Rept.[C], 4336, McDonnel-Douglas Astronoutics Co, 1967.
[71] ?str?m, K. J, Adaptive control around 1960[J], IEEE Control Systems, June 1996:44-49.
[72]蔡自兴.智能控制(第2版)[M].北京:电子工业出版社. 2004:103-330.
[73]蔡自兴.人工智能控制[M].北京:化学工业出版社. 2005:22-142.
[74]王耀南.智能控制系统[M].长沙:湖南大学出版社. 1996:11-306.
[75]吴宏鑫,王迎春,邢淡.基于智能特征模型的智能控制及应用[J].中国科学(E辑).2002,12(32). 805-816.
[76]蔡自兴.智能控制及移动机器人研究进展[J].中南大学学报(自然科学版),2005,36(l5):721-725.
[77]郑南宁,贾新春,袁泽剑.控制科学与技术的发展及其思考[J].自动化学报, 2002, 28(Suppl):7-17.
[78]李祖枢,涂亚庆.仿人智能控制[M].北京:国防工业出版, 2003:4-95, 96-197, 96-376, 40, 105-121, 121-134, 224-245.
[79] Zhou Qijian, Bai Jianguo. An Intelligent Controller of Novel Design[C]. Proc. of a多National Instrumentation Conference, Part 1.Shanghai, China.1983:137-149.
[80] Q. J. Zhou, J. G. Bai. An Intelligent Controller of Novel Design[C]. Proc. of a National Instrumentation Conference, Part 1, Shanghai. China. 1983: 137-149.
[81]李祖枢.仿人智能控制研究20年[A].重庆:1999年中国智能自动化学术会议论文集(上册)[C].北京:清华大学出版社, 1999:20-23.
[82]皮亚杰著.王宪钿等译.发生认识论原理[M].北京:商务印书馆,1981.
[83] N.维纳.郝季仁译.控制论(第二版) [M].北京:科学出版社,1985.
[84]李敏强,寇纪淞,林丹,李书全.遗传算法的基本理论与应用[M].北京:科学出版社,2002:17-348.
[85]涂序彦.人工智能:回顾与展望[M].北京:科学出版社, 2006.7.
[86]廉师友.人工智能技术导论[M].西安:西安电子科技大学出版社, 2000.
[87]王文杰,叶世伟.人工智能原理与应用[M].北京:人民邮电出版社, 2004.
[88]蔡自兴.徐光佑,人工智能及其应用[M].北京:清华大学出版社, 2004.
[89]李德毅,杜鹢.不确定性人工智能[M].北京:国防工业出版社.2005.29-54.
[90]张华,李祖枢,古建功.一种通用仿人智能控制器的参数整定方法及应用研究[A].第六届全球智能控制与自动化大会论文集[C],中国大连,2006,6: 9089-9093.
[91] Yuanhong Dan, Zushu Li, YongLing Wen. Structural Design and Discussion of Key Parameters in Swing-Up and Handstand Control of a Cart-Double Pendulum System[A], Proc. of SICE Annual Conference, Okayama, Japan ,2005:2483-2488 .
[92] Zushu Li, YuanHong Dan, Yongling Wen, Hua Zhang, Xiaochuan Zhang,Swing-up and Handstand Control of Cart-Triple-Pendulum System Based on HSIC[A], Proc. of the Eighth IASTED International Conference Intelligent Systems And Control, October 31-November 2,2005,Cambrige USA:1-6.
[93]李祖枢.仿人智能控制理论和多级倒立摆的摆起控制[A].人工智能:回顾与展望[M].北京:科学出版社, 2006.7:174-207.
[94] Li Zushu, Guifang Shao. An Behavior Selection Model of Artificial Life With Dodge Action Based on Priority Degree[C]. Proc. of the Third International Conference on Machine Learning and Cybernetics,2005,8.
[95] Guifang Shao, Zushu Li. An Evaluation Method for Fusion Image Quality Based on HVS[C]. The 3rd international conference on mechanics and information technology,2005,12.
[96] Guifang Shao, Zushu Li. The Action-Selection and Evolution Structure of Artificial Life based on Schema Theory[C]. 2006 International Symposium on Artificial Intelligence (ISAI’06),2006,8.
[97] http://www.fira.net/.
[98] http://www.robocup.org/.
[99]曹其新,陈卫东等. RoboCup中型组机器人比赛规则(MSLR). 2007年中国RoboCup国际公开赛比赛规则.济南,2007.10.
[100]洪炳熔.机器人足球的最终目标机器实现途径[J].华中科技大学学报(自然科学版).2004,32.
[101]皮亚杰著.倪连生,王琳译.结构主义[M].北京:商务印书馆,1984.
[102]雷永生,王至元,杜丽燕等.皮亚杰发生认识论评述[M].北京:人民出版社,1987.
[103]皮亚杰著.儿童智力理论[M] .北京:人民出版社,1987.
[104] Michael A Arbib, E Jeffrey Conklin, Jane C. Hill. From Schema Theory to Language[C], Oxford University Press, 1987.
[105] Sandra P. Marshall, Schemas in problem solving[C], New York: Cambridge University Press, 1995.
[106] Ronald C. Arkin, Motor Schema-Based Mobile Robot Navigation[J], International Journal ofRobotics Research, 1989,18(4).
[107] Tucker Balch, Ronald C. Arkin, Motor Schema-based Formation Control for Robot Teams[C], Proceedings of the First International Conference on Robot Teams Systems (ICMAS'95).
[108] George Maistros and Gillian Hayes, An imitation mechanism inspired from neurophysiology[C]. Proc. of EmerNet: Third International Workshop on Current Computational Architectures Integrating Neural Networks and Neuroscience, Durham, August 2000.
[109] R. Poli and W. B. Langdon, An Experimental Analysis on Schema Creation, Propagation and Disruption in Genetic Programming[C], In E Goodman, Ed. Proc. of Seventh International Conference on Genetic Algorithms, Michigan State University, East Lansing, USA, July 1997. Morgan Kaufmann.
[110]王桂平.图式理论在复杂系统控制中的应用研究[D].重庆大学硕士学位论文,2003.
[111] Li Zushu,Wang, GuiPing, Schema Theory and Human Simulated Intelligent Control[C], IEEE International Conference on Robotics, Intelligent Systems and Signal Processing, RISSP 2003, 2003.10.8, Chang Sha,China:524-530.
[112]王育新.小车-二级摆系统摆起倒立控制——基于动觉智能图式的仿人智能控制在复杂系统控制中应用研究[D].重庆大学硕士学位论文,2004
[113] Motomura A , Matsuoka T , Hasegawa T. Self-localization method using two landmarks and dead reckoning for autonomous mobile soccer robots [A] . Proceedings of the RoboCup 2003 Symposium[C]. Padova , Italy :2003.526-533.
[114]凌云峰.移动机器人全景视觉应用研究[D].哈尔滨工程大学硕士研究论文,2007
[115] L Huang. Speed Control of Differentially Driven Wheeled Mobile Robots—Model-Based Adaptive Approach[J]. Journal of Robotic Systems(S0741-2223), 2005, (22):323-332.
[116] Weiguo Wu, Huitang Chen, Peng-Yung Woo. Time Optimal Path Planning for a Wheeled Mobile Robot[J]. Journal of Robotic Systems(S0741-2223), 2000, (11):585-591.
[117] Wang Xiaoyu, Zhao Jie, Cai Hegao. Dynamic and control system analysis of two wheeled robot for welding application[J]. China Welding, 2004,(13):147-150.
[118]朱咏杰,付宜利,王树国,常疆.一种改进的移动机器人运动控制算法[J].哈尔滨工业大学学报. 2004(36):4-6.
[119] Zhou Ru xun, Zhang Zelong, Qi Yingchuan. Direct Identification of DC Electromotor Model Parameter[J]. Computer Simulation, 2006,23(6):113-115.
[120]陈伯时.电力拖动自动控制系统[M].北京:机械工业出版社, 1997:48-55.
[121] Wang Xiaoyu, Zhao Jie, Cai Hegao. Dynamic and control system analysis of two wheeledrobot for welding application[J]. China Welding, 2004,(13):147-150 .
[122]曹艳,王典洪.足球机器人定点行走模型的研究[J].武汉理工大学学报. 2005(29):595-598.
[123]张华.基于动觉智能图式的多级摆系统仿人智能运动控制[D].重庆大学博士学位论文, 2005.
[124]邵桂芳.基于动觉智能图式的人工生命体行为及其选择与进化研究[D].重庆大学博士学位论文, 2006.
[125] Llinas J, HallD L. An Introduction to Multi-Sensor Data Fusion[C]. Proc. of the 1998 IEEE International Symposium on, 1998, 6:537-540.
[126] Robin R Murphy著.杜军平,吴立成,胡金春.人工智能机器人学导论[M].北京:电子工业出版社, 2004.