Abstract:Behavior selection mechanism is one of the key issues in behavior based robotics.This paper presents a detailed review of the existing behavior selection mechanisms and the state of the art of current research,and then discusses the research trend in this area.Especially,biologically inspired robot behavior selection mechanisms and its future are introduced in detail.Finally,difficulties in robot behavior selection mechanism research are analyzed and the future research directions are forecasted.
[1] Arbib M A,Liaw J S.Sensorimotor transformations in the worlds of frogs and robots[J].Artificial Intelligence,1995,72(1-2):53-79.
[2] Brooks R A.A robust layered control system for a mobile roboc[J].IEEE Journal of Robotics and Automation,1986,2(1):14-23.
[3] Brooks R A.Intelligence without reason[C]//Proceedings of the International Joint Conference on Artificial Intelligence.San Mateo,CA,USA:Morgan Kaufmann,1991:569-595.
[4] Brooks R A.Intelligence without representation[J].Artificial Intelligence,1991,47(1/2/3):139-159.
[5] 李磊,曹志强,候增广,等.基于行为的轮式移动机器人导航控制[J].控制与决策,2004,19(6):707-710.Li Lei,Cao Zhiqiang,Hou Zengguang,et al.Behavior-based navigation control of wheeled mobile robot[J].Control and Decision,2004,19(6):707-710.
[6] Zhu A,Yang S X.Neurofuzzy-based approach tO mobile robot navigation in unknown environments[J].IEEE Transactions on Systems,Man,and Cybernetics,Part C:Applications and Reviews,2007,37(4):610-621.
[7] 张磊,秦元庆,孙德宝,等.基十行为的多机器人任意队形的控制[J].挖制工程,2005,12(2):174-176.Zhang Lei,Qin Yuanqing,Sun Debao,et al.Behavior-based control for arbitrary formation of multiple robots[J].Control Engineering of China,2005,12(2):174-176.
[8] 雷艳敏,冯志彬,宋继红.基于行为的多机器人编队控制的仿真研究[J].长春大学学报,2008,18(4):40-44.Lei Yanmin,Feng Zhibin,Song Jihong.The simulation study on formation control of multi-robot system based on behaviors[J].Journal of Changchun University,2008,18(4):40-44.
[9] 叶剑,乔俊飞,李明爱,等.一种基于行为控制的两自由度机械臂智能控制器[J].控制理论与应用,2007,24(3):440-444,448.Ye Jian,Qiao Junfei,Li Mingai,et al.A behavior-based intelligent controller for a 2-dof manipulator[J].Control Theory & Applications,2007,24(3):440-444,448.
[10] Mitsunaga N,Smith C,Kanda T,et al.Adapting robot behavior for human-robot interaction[J].IEEE Transactions on Robotics,2008,24(4):911-916.
[11] 吴敏,曹卫华,桂卫华,等.一种新的多智能体系统结构及其在RoboCup中的应用[J].自动化学报,2006,32(5):686-694.Wu Min,Cao Weihua,Gui Weihua.et al.A new multi-agent system architecture and its application in RoboCup[J].Acta Automatica Sinica,2006,32(5):686-694.
[12] Jung D,Zelinsky A.An architecture for distributed cooperative planning in a behaviour-based multi-robot system[J].Robotics and Autonomous Systems,1999,26(2/3):149-174.
[13] Murphy R R.Introduction to AI robotics[M].Cambridge,MA,USA:MIT Press,2000.
[14] Arkin R C.Behavior-based robotics[M].Cambridge,MA,USA:MIT Press,1998.
[15] Maes P.How to do the right thing[J].Connection Science,1989,1(3):291-323.
[16] Singleton D.An evolvable approach to the Maes action selection mechanism[D].Sussex,USA:University of Sussex,2002.
[17] Thrun S.Probabilistic algorithms in robotics[J].AI Magazine,2000,21(4):93-109.
[18] Kristensen S.Sensor planning with Bayesian decision theory[J].Robotics and Autonomous Systems,1997,19(3/4):273-286.
[19] Arkin R C.Motor schema based navigation for a mobile robot:An approach to programming by behavior[C]//Proceedings of the IEEE International Conference on Robotics and Automation.Piscataway,NJ,USA:IEEE,1987:264-271.
[20] 曹志强,王硕,张斌,等.基于MotorSchema的多移动机器人队形优化控制[J].控制与决策,2001,16(S1):763-765,769.Cao Zhiqiang,Wang Shoo,Zhang Bin,et al.Optimized formation control for motor schema-based multiple mobile robots[J].Control and Decision,2001,16(S1):763-765,769.
[21] Rusu P,Petriu E M,Whalen T E,et al.Behavior-based neurofuzzy controller for mobile robot navigation[J].IEEE Transactions on Instrumentation and Measurement,2003,52(4):1335-1340.
[22] Aguirre E,Gonzádez A.Fuzzy behaviors for mobile robot navigation:Design,coordination and fusion[J].International Journal of Approximate Reasoning,2000,25(3):255-289.
[23] Bonarini A,Invernizzi G,Halva Labella T,et al.An architectare to coordinate fuzzy behaviors to control an autonomous robot[J].Fuzzy Sets and Systems,2003,134(1):101-115.
[24] 杨品东,洪炳熔,朴松昊.基于模糊行为融合的移动机器人避障算法[J].华中科技人学学报,2008,36(S1):310-313.Yang lingdong,Hong Bingrong,Piao Songhao,The algorithm of obstacle avoidance based on fuzzy behavior fusion for mobile robot[J].Journal of Huazhong University of Science and Technology,2008,36(S1):310-313.
[25] Calleras M,Batlle J,Ridao R Hybrid Coordination of Reinforcement Learning-based Behaviors for AUV control[C]//Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.Piscataway,NJ,USA:IEEE,2001:1410-1415.
[26] Pirjanian P.Multiple objective behavior.based control[J].Robotics and Autonomous Systems,2000,31(1):53-60.
[27] Rosenblatt J K.DAMN:A distributed architecture for mobile navigation[J].Journal of Experimental and Theoretical Artificial Intelligence,1997,9(2/3):339-360.
[28] 贾建强,陈卫东,席裕庚.基于有限状态机的足球机器人行为设计与综合[J].高技术通讯,2004,14(4):61-65.Jia Jianqiang,Chen Weidong,Xi Yugeng.Behavior design and synthesis of autonomous soccer robot based on FSM[J].High Technology Letters,2004,14(4):61-65.
[29] 景兴建,王越超,谈人龙.基于仿生行为决策规则的协调运动行为[J].控制理论与应用,2003,20(3):407-410.ing Xingjian,Wang Yuechao,Tan Dalong.Cooperative motion behaviors using biology-modeling behavior decision-making rules[J].Control Theory & Applications,2003,20(3):407-410.
[30] Arkin R C,Riseman E,Hanson A.AuRA:An architecture for vision-based robot navigation[C]//Proceedings of DARPA Image Understanding Workshop.USA:DARPA,1987:417-413.
[31] Goerke N,Henne T.Learning hierarchical action selection for an autonomous robot[C]//Proceedings of the IEEE International Joint Conference on Neural Networks.Piscataway,NJ,USA:IEEE,2006:4958-4965.
[32] Liu X Y,Hong B R.Robot soccer action selection based on Q learning[J].Journal of Harbin Institute of Technology,2001,8(3):212-214.
[33] 段勇,杨淮清,崔宝侠,等.强化学习在足球机器人基本动作学习中的应用[J].机器人,2008,30(5):453-459.Dean Yong,Yang Huaiqing,Cui Baoxia,et al.Application of reinforcement learning to basic action learning of Soccer robot[J].Robot,2008,30(5):453-459.
[34] Moussa M A.Combining expert neural networks using reinforcement feedback for learning primitive grasping behavior[J].IEEE Transactions on Neural Networks,2004,15(3):629-638.
[35] Gu D B,Hu H S.Integration of coordination architecture and behavior fuzzy learning in quadruped walking robots[J].IEEE Transactions on Systems,Man,and Cybernetics,Part C:Applications and Reviews,2007,37(4):670-681.
[36] Zalama E,Gomez J,Paul M,et al.Adaptive behavior navigation of a mobile robot system[J].IEEE Transactions on Systems,Man,and Cybernetics,Part A:Systems and Humans,2002,32(1):160-169.
[37] 李冬梅,陈卫东,席裕庚.基于强化学习的多机器人合作行为获取[J].上海交通大学学报,2005,39(8):1331-1335.Li Dongmei,Chen Weidong,Xi Yugeng.Multi-robot cooperative behavior generation based on reinforcement learning[J].Journal of Shanghai Jiaotong University,2005,39(8):1331-1335.
[38] Abul O,Polat E Alhajj R.Multiagent reinforcement learning using function approximation[J].IEEE Transactions on Systems,Man,and Cybernetics,Part C:Applications and Reviews,2000,30(4):485-497.
[39] Andronache V.APOC and ADE:Theory and practice in the design of architectures for behavior-based agents[D].Indiana,USA:University of Notre Dame,2004.
[40] Parker L E.ALLIANCE:An architecture for fault tolerant multirobot cooperation[J].IEEE Transactions on Robotics and Automation,1998,14(2):220-240.
[41] Parker L E.L-ALLIANCE:Task-oriented multi-robot leaming in behavior-based systems[C]//proceedings of the IEEE/RSJ Intemational Conference on Intelligent Robots and Systems.Piscataway,NJ,USA:IEEE,1997:305-322.
[42] Scheutz M.Affective action selection and behavior arbitration for autonomous robots[C]//International Conference on Artificial Intelligence.Las Vegas,USA:CSREA Press,2002:334-340.
[43] de Sevin E.Thalmann D.A motivational model of action selection for virtual humans[C]//Computer Graphics International 2005.Piscataway,NJ,USA:IEEE,2005:213-220.
[44] Garforth J,McHale S L,Meehan A.Executive attention.task selection and attention-based learning in a neumlly controlled simulated robot[J].Neurocomputing,2006,69(16/17/18):1923-1945.
[45] Dalgalarrondo A,Luzeaux D.Introducing attention in a behavior-based robot control architecture[C]//European Control Conference(ECC'99).Italy:EUCA,1999:378-385.
[46] 张惠娣,刘十荣,俞金寿.基于情感认知的学习与决策算法在移动机器人行为协调中的应用[J].华东理工大学学报:自然科学版,2008,34(3):399-404.Zhang Huidi,Liu Shirong,Yu Jinshou.Affective cognitive learning and decision making and application in behavior coordination for mobile robots[J].Journal of East China University of Science and Technology,2008,34(3):399-404.
[47] Albin R L,Young A B,Penney J B.The functional-anatomy of disorders of the basal ganglia[J].Trends in Neurosciences,1995,18(2):63-64.
[48] Gurney K,Prescott T J,Redgrave p.A computational model of action selection in the basal ganglia.I.A nov functional anatomy[J].Biological Cybernetics,2001,84(6):401-410.
[49] Humphries M D.The basal ganglia and action selection:A computational study at multiple levels of description[D].Sheffield,UK:University of Sheffield,2002.
[50] Prescott T J,Gonzhlez F M M,Gurney K,et al.A robot model of the basal ganglia:Behavior and intrinsic processing[J].Neural Networks,2006,19(1):31-61.
[51] Girard B,Cuzin V,Guillot A,et al.A basal ganglia inspired model of action selection evaluated in a robotic survival task[J].Journal of Integrative Neuroscience,2003,2(2):179-200.
[52] 谭民,工硕,曹志强.多机器人系统[M].北京:清华大学出版社,2005.Tan Ming,Wang Shuo,Can Zhiqiang.Multi-robot systems[M].Beijing:Tsinghua University Press,2005.
[53] Harper C J,Winfield A F T.A methodology for provably stable behaviour-based intelligent control[J].Robotics and Autonomous Systems,2006,54(1):52-73.