摘要
在多机器人系统的研究中,多移动机器人系统的协调合作始终是一个热点,也是该领域中一个基础性的研究方向。机器人足球系统是典型的多机器人协作系统,是研究多机器人协作问题的标准平台。本文以基于全局视觉的足球机器人系统为实验平台,对多机器人协作问题进行了研究。
首先,研究了足球机器人系统中的多机器人体系结构问题,在参考已有的决策推理模型基础上,提出了合作层、协调层、动作层三层体系结构。该结构将决策过程分解为策略及队形选择、角色分配和动作选择等具体问题。在动作层中,分析了足球机器人运动模型,设计并实现了动作层中的各类动作,为下面工作的开展作了准备。
其次,对足球机器人合作层进行了设计,包括信息预处理、态势分析、策略和队形的选择机制,建立了相应的Petri网模型,并运用理论和仿真工具分析了该模型的各种特性。由于本系统中采用固定守门员的方案,所以单独设计了守门员的防守策略,建立了守门员策略选择的Petri网模型,通过理论分析和仿真实验验证了其正确性和合理性。
最后,在足球机器人协调层中,提出了基于动态参考点的角色评估函数的角色分配方法,并运用优度评价方法解决同类角色间潜在的局部冲突,仿真实验证明该方法简单并且决策速度快,使任务分配更加明确。在此基础上以进攻队形为例建立了任务分配的Petri网模型,并分析了该模型的特性。在本章最后,给出了本系统的程序框架,并对实验效果进行了分析。
Multi-robot system is a new aspect of robotics development. In the research of multi-robot system, multiple mobile robots coordination is a well-attended and essential topic. One of the typical multi-robot cooperation systems is Robot soccer system, and it is a standard platform for researching in multi-robot cooperation problems. This paper did some research on multi-robot cooperation, and chose a Vision-Based Remote Brainless Soccer Robot system as the experiment platform.
Firstly, a three-layer structure of the collaborative, coordinate and behavior-control was proposed base on existing decision-making model and the research for the multi-robot control architecture under soccer environment, which involves some problems such as strategy and formation choice, role assignment and action selection. All kind of actions were designed and implemented in the action layer based on the analysis of the robot motion model, and this is the basis of the subsequent work.
Secondly, we designed the coordination layer, which included the information pretreatment、the situation analyses、the strategy and formation chosen mechanism, the corresponding Petri net model was built based on it and its characters were analyzed by theory and simulator. The defend strategy of goalkeeper was designed independently to make this system follow a fixed goalkeeper scheme. The Petri net model of goalkeeper's strategy choice was built and analyzed theoretically, and emulational experimentations were done to verify the model's correctness and rationality.
Finally, a role assignment method was presented in the coordination layer which was based on the role evaluating function of dynamic reference point, and the potential local conflict of the same kind of roles was solved by using the method of optimize estimate. The emulational experimentations approved that the method was simple and fast, and the task assignment was clearer. Taking the attack order for example, a Petri net model of task assignment was built based on this, and completed the analysis of this model. At last, a program framwork was given, and the effect of experimentations were analysed.
引文
[1]Yamauchi,B.Schultz,A.Adams.Mobile Robot Exploration and Map-building with Continuous Localization Robotics and Automation,Proc-IEEE International Conference on Volume 4,1998:3715 - 3720
[2]陈忠泽,林良明,颜国正.基于MAS的多机器人系统.机器人,2001,23(4):368-373
[3]CAO Y U.Cooprerative Mobile Robotics:Antecedents and Directions.Autonomous Robotics,1997,4:7-27
[4]王越超,谈大龙.协作机器人学的研究现状与发展.机器人,1998,20(1):69-75
[5]SHIM H S,KIM H S,JUNG M J et al.Designing Distributed Control Architecture for Cooperative Multi-agent System and it's Real-time Application to Soccer Robot.Robotics Auto Syst.1997,21(2):149-165
[6]洪炳熔,刘新宇.基于视觉的足球机器人系统.计算机应用研究,2001(1):1-3
[7]Zanichelli Francescon.A Multi-agent Framework and Programming Environment for Autonomous Robotics.Proc-IEEE ConfRobotics and Automation,1994:3501-3507
[8]Asama H.Design of an Autonomous and Distributed Robot System:ACTRESS[C].Proc IEEE/RSJ IROS'89,Tsukubs,1989:283
[9]李俊华.多机器人的协调合作技术与群组控制策略研究[D].西安电子科技大学.2006:16
[10]李实,徐旭明等.国际机器人足球比赛及其相关技术[J].机器人,2000,22(5):420-426
[11]席裕庚,陈卫东.机器人向智能化的发展和多移动机器人协作系统[J].自动化博览,2003(1):149-154
[12]钟碧良.机器人足球系统的研究与实现[D].广东工业大学博士论文,2003
[13]续欣莹.MiroSot足球机器人决策子系统的研究与设计[D].太原理工大学硕士论文,2005
[14]Cai.A.H,Fukuda.T,Arai F,Ueyama.T,Sakai.Hierachical Control Architecture for Cellular Robotic System.Proceeding of the 1995 IEEE International Conference on Robotice and Automation.1995:1196-1196
[15]Parker L E.ALLIANCE:An Architecture for Fault Tolerant Cooperative Control of Heterogeneous Mobile Robots.IEEE/RSJ IROS,1994,2:776-783
[16]M.J.Mararic,M.Nilsson and K.T.Simsarian.Cooperative Multi-robot Box-Pushing.Proceedings of IROS-95,Pittsburgh,PA,1995,3:556-561
[17]C.Ronald Kube,Hong Zhang.Collective Robotics:From Social Insects to Robots[J]. Adaptive Behavior,1993,2(2):189-219
[18]Lynne E Parker.The Effect of Action Recognition and Robot Awareness in Cooperative Robotic Teams.Journals of the IEEE/RSJ Intelligent Robots and Systems.1995,2(5):212-219
[19]Lynne E Parker,Brad Emmons.Cooperative Multi-Robot Observation of Multiple Moving Targets[C].Journal of International Conference on Robotics and Automation,1997,3(2):2082-2089
[20]J.Wang.Deadlock Detection and Resolution in Distributed Robotic Systems.Proc.of the Japan/USA Symp.On Flxible Automation,1992:673-677
[21]Rosenchen,J.S.Rational Interaction:Cooperation Among Intelligent Agent PHD.Dissertation:Stanfort University,1986
[22]高志军,颜国正,颜德田,陈忠泽.多机器人协调与合作系统的研究现状和发展.光学精密土程,2001,9(2):99-103
[23]W.A.Rausch,p.Levi.Types of cooperation in the Distributed Robot System CoMRoS.Intelligent Robotics:sensing,Modelling and Planning,1997(2):340-355
[24]P Cohen,H Levesque.Intention is Choice with Commitment.Artificial Intelligence,1990,42(3):213-261
[25]R.Alami,S.Fleury,m.Herrd,et al.Multi - Robot Cooperation in TheMARTHA Project.IEEE Robotics and Automation,1998,15(1):36-47
[26]高红霞.基于MAS的多移动机器人的协作问题研究.南京理工大.硕士学位论文.2003:18-19
[27]吴旭华.基于MAS的多机器人系统及其机制研.西北工业大学.硕士学位论文.2004:29-31
[28]张维明.智能协作信息技术.第1版.北京:电子工业出版社.2001:63-64
[29]R G Smith,R Davis.Frameworks for Cooperation in Distributed Problem Solving.IEEE Transactions on Systems,Man and Cybernetics,1981,11:61-70
[30]Wolfgang Reisig.Petri Nets-An Introduction.Springer Verlag,1982
[31]吴哲辉.Petir网导论.第1版.北京:机械工业出版社.2006.4
[32]袁崇义.Petri网原理与应用.第1版.北京:电子工业出版社.2005:3
[33]江志斌.Petri网及其在制造系统建模与控制中的应用.第1版.北京:机械工业出版社.2004
[34]薛宏涛,叶媛媛等.多智能体系统体系结构及协调机制研究综述.机器人,2001,23(1):85-90
[35]RodneyA.Brooks.ARobust Layered Control System for a Mobile Robot IEEE Journal of Roboties and Automation,RA-2(1):14-23
[36]薛方正,徐心和,冯挺.集控式足球机器人决策与控制系统设计与开发.机器人,2005,27(5):432
[37]陈鑫,吴敏,车迅.足球机器人决策子系统设计与分析.计算机与自动化,2001,9,第20卷第3期:48-52
[38]霍迎辉.机器人足球比赛系统中三个子系统的研究与设计[D].广东工业大学硕士学位论文.2004:22-26
[39]Campion G,Bastin G,D'Andrea-Novol B.Structural properties and classification of kinematic and dynamic models of wheeled mobile robots.IEEE Trans.On Robotics and Automation,1996,12(1):47-61.
[40]蒋仙华,熊蓉,周科,吴明光.基于模糊控制的足球机器人底层动作优化.工程设计学报,2003,10(3):140-143.
[41]刘金馄,王树青.多智能体控制系统的设计与实现.控制理论与应用,1999,16(4):580-582
[42]程福,马英庆,赵臣.基于非完整约束的轮式足球机器人运动控制.电子机械工程,2007,23(5):56-58
[43]刘宏志.一种改进的射门算法.哈尔滨工业大学学报,2004,36(7):975-977.
[44]张小川,李祖枢,张品红等.基于行为的足球机器人动作规划.哈尔滨工业大学学报,2003,35(9):1071-1073.
[45]刘丽.机器人足球比赛中的实时智能技术研究.西北工业大学.硕士学位论文.2004:38-41
[46]徐灵敏,曹长修,王牛.基于预测的足球机器人截球动作实现研究.2004年中国机器人足球比赛暨学术研讨会论文集:中国广州,2004:188-191
[47]施麟书,楼东武.足球机器人智能控制决策系统的优化.电子测量与仪器学报,2004:840-843
[48]PeterStone,David MeAllester.An Achitecture for Action Selectioning.Robotic Soeeer.In Proeeedings of the Fifth hitemational Conferenee on Autonomous Agents,2001
[49]燕必成.基于Petri网的足球机器人决策子系统的研究.西安电子科技大学.硕士学位论文.2007:35-40
[50]Christopher,Messom,Determining offensive and Defensive Possessior in Multi-agent Team Based Competitive Games,Proc.Of MiroSot'97,Taejon Korea,Jun.1997:71-75
[51]D-M.Tsai and Y-H,Cherts.A Fast Histogram-Clustering Approach for Multi-level Thresholding,Pattern Reeongition left,1992,Vol.13:245-252
[52]Sun-Gi Hong,Designing Soccer-playing robot Team Based on the Centraliaed Approach, 'Proc.Of MiroSot'97,Taejon Korea.1997(9):119-123
[53]John Harvey,High-level design of a Mirosot Simulator,Proc.Of Mirosot'96,Teajon Korean,1996(9),53-66
[54]J.H.Johnson and M.J.Booth,Robot football:emergen behavior in nonlinear discrete systems,Proc.ofMirosot'97.Teajon Korea,Jun 1997:87-99
[55]Daraselia N,Yuryev A,Egorov A,et al.Extracting protein interactions from MEDLINE using a full-sentence parser.Bioinformatics,2004,20(5):604-611
[56]Andrew Howard,MuCows,RoboCup 2000:Robot Soccer World Cup Ⅳ,LNAIU2019,Spring-Verlag,2001:535-538
[57]Stone P.,Veloso M.Task Decomposition,Dynamic Role Assignment and Low-Bandwidth Communication for Real-Time Strategic Teamwork.Atificial Intelligence,1999,110(2):241-273,
[58]吴丽娟,翟玉人,徐心和。足球机器人系统中角色分配策略的设计。基础自动化,2000,7(1):4-6
[59]Seong-Woo Hong,Shang-Woo Shin,Doo-Sung Ahn.Development of a Control System for the Multi-agent in the Dynamic Environment.2002 FIFA Robot World Congress,Seoul,Korea.2002:227-231
[60]H.S.Shim,M.J.Jung.Role Level Design in a Hybrid Control Structure for a Vision-Based Soccer Robot.Pro.of the Fourth Int,Symp.On Artificial Life and Robotics,1999:1406-1411
[61]蔡文,杨春燕,王光华.一门新的交叉学科--可拓学.中国科学基金,2004:268-272
[62]何卓华.基于Agent的机器人足球产生式决策子系统的研究.广东:广东工业大学.硕士学位论文,2003
[63]符东海,王中伟.实用的机器人足球角色分配算法设计.计算机工程与设计,2006,27(8):1343-1345
[64]蔡文,杨春燕,林伟初.可拓工程文法.北京:科学出版社,1997