四足机器人仿生控制方法及行为进化研究
|
摘要
足式机器人是近年来机器人研究一个比较活跃的领域,其涉及机器人学、生物学、控制理论、传感器技术、信息处理技术等,因其不同于传统的轮式、履带式机器人的运动特点,得到了各国科学家的大力关注,其中又以四足机器人以其结构和控制方法的相对简单成为足式机器人的一个理想研究对象。四足机器人不但可以应用在军事、行星探测、救灾等领域,而且在家庭娱乐、仿生学等领域大显身手。
在国家自然科学重点基金及中国科学院创新基金的资助下,本文对四足机器人的仿生控制和行为进化进行了研究。研究内容包括:
1、对四足动物的运动器官结构和运动机理研究,在此基础上对四足机器人的进行运动学和动力学建模,并成功研制出了四足机器人实验样机。
2、设计了一种具有本体感觉的中枢模式振荡器;早期的基于仿生学的控制方法只是简单的模仿生物的一些基本行为和功能,这在执行一些相对固定、简单的任务时没有问题,但是对于复杂的任务和环境时就显得有些力不从心了;随着生物学和神经学研究的不断发展,为四足机器人的仿生控制带来了新的概念和方法;本文采用基于仿生学的运动控制原理,从工程应用角度出发,设计了一种具有本体感觉的中枢模式振荡器(CPG,Central Pattern Generator),并在其基础上实现四足机器人的运动控制。
3、引入生物学中的反射概念和神经学中的动态连接机理,并与中枢模式振荡器相结合,实现四足机器人复杂环境中的运动控制。反射行为是生物行为的一个基本要素,是生物对外界环境情况的反应,是生物环境适应能力的一种反映;引入生物的反射行为提高了机器人的环境适应能力,拓展了仿生控制方法的内容。
4、根据哺乳动物的行为进化特点,进行四足机器人的行为进化研究。采用强化学习方法,利用CMAC神经网络实现了强化学习系统,完成了基于CMAC神经网络的Q学习算法,综合考虑了四足机器人的运动特点,即可以越过一定高度的障碍来实现避障,进行了四足机器人在未知环境中的自主导航行为进化研究;运用进化算法,利用计算机模拟的方法,模拟一个刚出生的四足动物学习行走的过程,通过这一技术,可以使机器人自行获得运动能力,这对于四足机器人的发展具有重要意义,将来可以将这一能力扩展到其它方面,从而使四足机器人真正具有生物的学习能力,这有利于提高四足机器人在陌生环境中应对突发事件的能力,这一点对于执行星球探测任务的四足机器人尤为重要。
本论文的创新点有:采用基于仿生学的运动控制原理,借鉴生物学、神经学的最新进展,从工程应用角度出发,设计了一种具有本体感觉的中枢模式振荡器;引入神经学中的动态连接机理和生物学的反射概念,结合中枢模式振荡器,研究四足机器人复杂环境中的运动控制;根据哺乳动物的行为进化特点,采用强化学习和进化算法,研究四足机器人行为进化,使其在无先验知识的情况下自行获得在未知环境中的运动能力。
Legged robot is an active field in the study of robot in recent years. It is a high integration of robotics, biology, control theory, sensor technology, signal processing, etc. Because of its trait which is different from the wheeled robot or derailed robot, scientists from many countries pay much attention to it. Among the legged robots, the quadruped robot is an ideal research object because of the much more simple control method and structure. The quadruped robot can be used not only in military, planet exploration, catastrophic reaction but also in bionics and home entertainment.
Sponsored by the National Nature Science Foundation of China and the Innovation Fund projects of the Chinese Academy of Sciences, this thesis focused on the research and development of a quadruped robot system. The whole thesis involves many research fields manifested in following several aspects:
1. Made the kinematics and dynamics model based on the study of motion organ and motion philosophy of the quadruped, and developed the quadruped robot successfully.
2. Designed a CPG with proprioception. The earlier control method based on the bionics only imitated the basic behavior and function of the creature, and it is effective when it is executing simple and regular tasks. But it is less useful when it comes to a complicated task and environment. With the development of biology and neurology, the new method and concept were brought into the biomimetic control field. We designed a novel CPG with proprioception from the practical engineering facet, and controlled the quadruped robot with it.
3. Reflex and dynamic regulation used in neurology are brought into the CPG, with which the quadruped robot was controlled in complicated environments. Reflex is a basic element of the creature behavior. It is the creature's reaction for the outward environment and a mirror to its adaptation ability. The adaptive ability of the robots was improved by bringing reflex into the CPG, so it widens the content of the biomimetic Control method.
4. This thesis focuses on the behavior evolution based on the characteristic of the mammal behavior evolution. The reinforcement learning was used and CMAC neural network constructed the reinforcement learning system,implemented the Q-learning. Study the self-navigation in the unknownenvironment considering the characteristic of quadruped robot motion, itcan stride some lower obstacle; Applying the evolutionary learning, weimitated the progress of learning walking of a quadruped. With it,quadruped robot can learn to motion itself. It is important for thedevelopment of the quadruped robot. The ability can be used in otheraspects and it will make the quadruped robot have the learning ability that acreature has. This will improve the emergency action of a quadruped robotand it is more important for a quadruped robot exploring the planet.
The original contributions of this thesis: The thesis designed a novel CPG withproprioception from the engineering point based on the development of biology andneurology; The reflex and the dynamic linkage are brought into the CPG and controlthe quadruped robot in complicated environment; Study the behavior evolution ofquadruped robot with reinforcement learning and evolutionary learning based on thecharacteristic of the mammal behavior evolution. It improves the environmentadaptation ability and can get the motion ability itself without any other earlierinformation.
在国家自然科学重点基金及中国科学院创新基金的资助下,本文对四足机器人的仿生控制和行为进化进行了研究。研究内容包括:
1、对四足动物的运动器官结构和运动机理研究,在此基础上对四足机器人的进行运动学和动力学建模,并成功研制出了四足机器人实验样机。
2、设计了一种具有本体感觉的中枢模式振荡器;早期的基于仿生学的控制方法只是简单的模仿生物的一些基本行为和功能,这在执行一些相对固定、简单的任务时没有问题,但是对于复杂的任务和环境时就显得有些力不从心了;随着生物学和神经学研究的不断发展,为四足机器人的仿生控制带来了新的概念和方法;本文采用基于仿生学的运动控制原理,从工程应用角度出发,设计了一种具有本体感觉的中枢模式振荡器(CPG,Central Pattern Generator),并在其基础上实现四足机器人的运动控制。
3、引入生物学中的反射概念和神经学中的动态连接机理,并与中枢模式振荡器相结合,实现四足机器人复杂环境中的运动控制。反射行为是生物行为的一个基本要素,是生物对外界环境情况的反应,是生物环境适应能力的一种反映;引入生物的反射行为提高了机器人的环境适应能力,拓展了仿生控制方法的内容。
4、根据哺乳动物的行为进化特点,进行四足机器人的行为进化研究。采用强化学习方法,利用CMAC神经网络实现了强化学习系统,完成了基于CMAC神经网络的Q学习算法,综合考虑了四足机器人的运动特点,即可以越过一定高度的障碍来实现避障,进行了四足机器人在未知环境中的自主导航行为进化研究;运用进化算法,利用计算机模拟的方法,模拟一个刚出生的四足动物学习行走的过程,通过这一技术,可以使机器人自行获得运动能力,这对于四足机器人的发展具有重要意义,将来可以将这一能力扩展到其它方面,从而使四足机器人真正具有生物的学习能力,这有利于提高四足机器人在陌生环境中应对突发事件的能力,这一点对于执行星球探测任务的四足机器人尤为重要。
本论文的创新点有:采用基于仿生学的运动控制原理,借鉴生物学、神经学的最新进展,从工程应用角度出发,设计了一种具有本体感觉的中枢模式振荡器;引入神经学中的动态连接机理和生物学的反射概念,结合中枢模式振荡器,研究四足机器人复杂环境中的运动控制;根据哺乳动物的行为进化特点,采用强化学习和进化算法,研究四足机器人行为进化,使其在无先验知识的情况下自行获得在未知环境中的运动能力。
Legged robot is an active field in the study of robot in recent years. It is a high integration of robotics, biology, control theory, sensor technology, signal processing, etc. Because of its trait which is different from the wheeled robot or derailed robot, scientists from many countries pay much attention to it. Among the legged robots, the quadruped robot is an ideal research object because of the much more simple control method and structure. The quadruped robot can be used not only in military, planet exploration, catastrophic reaction but also in bionics and home entertainment.
Sponsored by the National Nature Science Foundation of China and the Innovation Fund projects of the Chinese Academy of Sciences, this thesis focused on the research and development of a quadruped robot system. The whole thesis involves many research fields manifested in following several aspects:
1. Made the kinematics and dynamics model based on the study of motion organ and motion philosophy of the quadruped, and developed the quadruped robot successfully.
2. Designed a CPG with proprioception. The earlier control method based on the bionics only imitated the basic behavior and function of the creature, and it is effective when it is executing simple and regular tasks. But it is less useful when it comes to a complicated task and environment. With the development of biology and neurology, the new method and concept were brought into the biomimetic control field. We designed a novel CPG with proprioception from the practical engineering facet, and controlled the quadruped robot with it.
3. Reflex and dynamic regulation used in neurology are brought into the CPG, with which the quadruped robot was controlled in complicated environments. Reflex is a basic element of the creature behavior. It is the creature's reaction for the outward environment and a mirror to its adaptation ability. The adaptive ability of the robots was improved by bringing reflex into the CPG, so it widens the content of the biomimetic Control method.
4. This thesis focuses on the behavior evolution based on the characteristic of the mammal behavior evolution. The reinforcement learning was used and CMAC neural network constructed the reinforcement learning system,implemented the Q-learning. Study the self-navigation in the unknownenvironment considering the characteristic of quadruped robot motion, itcan stride some lower obstacle; Applying the evolutionary learning, weimitated the progress of learning walking of a quadruped. With it,quadruped robot can learn to motion itself. It is important for thedevelopment of the quadruped robot. The ability can be used in otheraspects and it will make the quadruped robot have the learning ability that acreature has. This will improve the emergency action of a quadruped robotand it is more important for a quadruped robot exploring the planet.
The original contributions of this thesis: The thesis designed a novel CPG withproprioception from the engineering point based on the development of biology andneurology; The reflex and the dynamic linkage are brought into the CPG and controlthe quadruped robot in complicated environment; Study the behavior evolution ofquadruped robot with reinforcement learning and evolutionary learning based on thecharacteristic of the mammal behavior evolution. It improves the environmentadaptation ability and can get the motion ability itself without any other earlierinformation.
引文
Miller D P . Multi p le behavior controlled micro robots for p lanetary surface missions.Proceedings of the IEEE International Conference on Systems, Man and Cybernetics [C].USA: IEEE, 1990.289-292.
Delcomyn F, NelsonM E. Architectures for a biomimetic hexapod robot [J]. Robotics and Autonomous Systems, 2000,30 (1), pp. 5-15.
Bares J E, WhittakerW L. Walking robot with a circulating gait. Proceedings of the 1990 IEEE/RSJ International Conference on Intelligent Robots and Systems. [C]. USA: SPIE, 1991.pp.809-816.
A. Ijspeert, A. Crespi, D. Ryczko, and J.-M. Cabelguen. From swimming to walking with a salamander robot driven by a spinal cord model. Science, 315(5817): 1416-1420, 2007。
R.S. Mosher, Test and Evaluation of a Versatile Walking Truck, in: Procs. Off-Road Mobility Research Symp.,1968, pp. 359-379 。
Shigeo Hirose, Yoji Umetani: Some Consideration on a Feasible Walking Mechanism as a Terrain Vehicle, Proc. 3rd RoManSy Symp., Udine, Italy, pp.357-375,1978.
Shigeo Hirose, Matsuo Nose, Hidekazu Kikuchi, Yoji Umetani: Adaptive Gait Control of a Quadruped Walking Vehicle, Robotics Research (1st Int. Symp.),The MIT Press,pp.253-277,1984。
Shigeo Hirose, Tomoyuki Masui, Hidekazu Kikuchi: TITAN 111: A Quadruped Walking Vehicle -Its Structure and Basic Char- acteristics, Robotic Research (2nd Int. Symp.), The MIT Press, pp.325-331, 1985.
Shigeo Hirose, Kan Yoneda, Kazuhiro Arai, Tomoyoshi Ibe: Design of Prismatic Quadruped Walking Vehicle TITAN VI, Proc. 5th Int. Conf. Advanced Robotics, Pisa, Italy, pp.723-728,1991.
Kan Yoneda, Shigeo Hirose: Dynamic and Static Fusion Gait of Quadruped Walking Vehicle on Winding Path, Proc. IEEE Int. Conf. on Robotics and Automation, pp.143-148, 1992.
Shigeo Hirose, Akihiko Nagakubo, Ryosei Toyama: Machine that can Walk and Climb on Floors,Walls and Ceilings, Proc. 5th Int. Cof. Advanced Robotics, Pisa, Italy, pp.753-758, 1991。
Keisuke Arikawa, Shigeo Hirose: Development of Quadruped Walking Robot TITAN-VIII, Proc.IROS96, pp.208-214, 1996。
R.D.Shraft, J.Dahlkemper, W.Baum and H.Gehringer: Smart Sensor Modules for Operator Assistance of Teleoperated Mobile Robots, Proc. Workshop on Anti-personnel Mine Detection and Removal, pp.21-25,1995。
Kimura, H., Fukuoka, Y., Hada, Y., and Takase, K. Adaptive Dynamic Walking of a Quadruped Robot on Irregular Terrain Using a Neural System Model. Robotics Research,Springer-Verlag, Berlin Heidelberg, 147-160.2003。
Matsuoka K. Sustained oscillations generated by mutually inhibiting neurons with adaptation [J].Biological Cybernetics, 1985, 52: 367-376。
Matsuoka K. Mechanism of frequency and pattern control in the neural rhythm generators [J].Biological Cybernetics, 1987, 56: 345-353。
Taga, G. A model of the neuro-musculo-skeletal system for human locomotion [J]. Biological Cybernetics, 73,2004.113-121.
Fukuoka. Y, Kimura, H., and Cohen, A. H., Adaptive Dynamic Walking of a Quadruped Robot on Irregular Terrain based on Biological Concepts. Int. Journal of Robotics Research,22(3-4), 2003.187-202.
Kimura H, Fukuoka Y, Minura T. Dynamics based integration of motion adaptation for a quadruped robot 'Tekken' [C]. Proc. of the 2~(nd) International Symposium on Adaptive Motion of Animals and Machines [C].Kyoto. 2003。
H.Miura, I. Shimoyama, etc. Dynamical walk of the quadruped robot(Collie-I), Robotics Research 2( the MIT Press),pp.317-324,1984.
H.Miura, I. Shimoyama, etc. Dynamics in the dynamic walk of a quadruped robot,RSJ.Advanced Robotics, vol.4, no.3, pp.283-301,1990.
Tsujita K, Tsuchiya K, Onat A. Adaptive gait pattern control of a quadruped locomotion robot. Proc of the IEEE Conf on Intelligent Robots and System[C]. Maui, Hawaii, 2001.2318-2325.
Takashi Emura and Akira. Arakawa, Attitude control of a quadruped robot during two leg supporting, Proc'91 Int.Conf. ofAdvanced Robotics,pp.711-716,1991.
Shiqi Peng. 2006. A Biologically Inspired Four Legged Walking Robot.[D]. Murdoch, Australia,Murdoch University.
Furusho, J., Sano, A., Sakaguchi, M., and Koizumi, E. Realization of bounce Gait in a Quadruped Robot with Articular-Joint-Type Legs, IEEE Int. Conf. Robotics and Automation, 1995. pp. 697-702
Raibert, M. H. 1985. Four-legged running with one-legged algorithms. In Second International Symposium on Robotics Research, H. Hanafusa, H. Inoue (eds.), (MIT Press, Cambridge),311-315
Raibert, M. H., Chepponis, M., Brown, H. B. Jr. 1986. Running on four legs as though they were one.IEEE J.Robotics and Automation,2:70-82.
Raibert,M.H.Trotting,pacing,and bounding by a quadruped robot.Jounal of Biomechanics.1990.Vol.1 pp.79-98.
D.J.Pack,A.C.Kak.A simplified forward gait control for a quadruped walking robot.Proceedings of the 1994 IEEE/RSJ International Conference on Intelligent Robots and Systems[C].USA:IEEE,1994.1011-1018.
Pack,D.J.,Perception-based control for a quadruped walking robot,1996 IEEE International Conference on Robotics and Automation,Volume 4,pp:2994- 3001.
Bostondynamics.com,http://www.bostondynamics.com/content/sec.php?section=BigDog
Johan Friede and Kim Kylstr(o|¨)m.Determination of mechanical parameters for the warpl robot using experimental methods,simulations and real-time control.Master's thesis,Dept.of Machine Design,Royal Institute of Technology,S-100 44 Stockholm,Sweden,1998.
Freyr Hardarson.Stability analysis and synthesis of statically balanced walking for quadruped robots.PhD thesis,The Royal Inst.of Technology,100 44 Stockholm,Sweden,June 2002.
llg,W.,Albiez,J.,and Jedele,H.(1998a) A biologically inspired adaptive control architecture based on neural net-works for a four-legged walking machine.In Proc.8th Int.Conf.on Artificial Neural Networks,Skoevde,Sweden,.455-460.
Ilg,W.,and Scholl,K.-U.(1998).Cqran:Continuous Q-learning resource allocation network towards reinforcement learning with multi-dimensional continuous action spaces.In Proc.8th Int.Conf.on Artificial Neural Networks,Sko-evde,Sweden,pp.455-460.
Ilg W,Albiez J,jedele H,et al.Adaptive periodic movement control for the four legged walking machine BISAM.IEEE Robotics &Automation[C].Detroit Michigan,1999.2354-2359.
Ilg W,Albiez J,Witte H,et al.Adaptive posture control of a four-legged walking machine using some principles of mammalian locomotion.Adaptive Motion of Animals and Machines[C].Montreal Canada,2000.
张秀丽,2004,四足机器人节律运动及环境适应性的生物控制研究境适应性的生物控制研究[D]:[博士].北京:清华大学,26-35。
汪劲松,易昕,QW-1型全方位四足步行机器人的设计及实验研究[J],机械工程学报,1991年27卷5期。
陈佳品,2001,四足机器人动态步行控制和学习辅助[D].上海交通大学博士论文。
孙迪生,王炎,机器人控制技术[M],北京:机械工业出版社,1997。
蔡自兴,机器人学[M],北京:清华大学出版社,2000.9。
NewtonC.D.,NunamakerD.M.,Textbook of Small Animal Orthopaedics,International Veterinary Information Service,1985;B0094.0685。
张锦荣,2007,基于虚拟样机技术的四足机器人仿真研究[D]:[硕士]。西安:西北工业大学,15-17。
Manocha D,Canny J.Real Time Inverse Kinematics for General 6R Manipulators[C],Proceedings of IEEE International Conference on Robotics and Automation.Raleign,North Carolina,USA:IEEE,1992:383-389.
Manseur R,Doty K L.Structural kinematics of 6-revolute-axis robot manipulators[J].Mechanism and Machine Theory(S0094-114X),1996,31(5):647-657.
周友行,何清华,邓伯禄.一种改进的爬山法优化求解冗余机械手运动学逆解[J].机器人,2003,25(1):35-38.
吴爱国,郝润生.一种改进BP算法在机械手逆运动学中的应用[J].中国工程科学,2005,7(7):34-38.
Lu B L,Ito K.Regularization of inverse kinematics for redundant manipulators using neural network inversions[C].Proceedings of IEEE International Conference on Neural Networks.Perth:IEEE,1995:2726-2731.
王常武,韩佩富,孔令富,黄真,赵立强,一并联机器人逆运动模型高效算法及其并行处理,计算机工程与设计,Vol.21,No.3,2000.6。
杭鲁滨,金琼,杨廷力,基于线性变换的一般串联机器人逆运动学分析[J],机械工程学报,Vol.37,No.5,2001.5。
Lei Sun,Max Q.-H.Meng,Wanming Chen,Huawei Liang,Tao Mei,Design of Quadruped Robot Based CPG and Fuzzy Neural Network,Proceedings of the IEEE International Conference on Automation and Logistics August 18-21,2007,Jinan,China.
王洪斌,宋佐时,王洪瑞,基于模糊神经网络的机器人逆运动学问题[J],系统仿真学报,Vol.1 4,No.7,2002.7。
钟金明,徐刚,张海波,模糊逆运动学控制方法在机器人视觉伺服中的应用[J],组合机床与自动化加工技术,2005.5。
熊有伦,机器人学[M],北京机械工业出版社,1993.10。
王新杰,2006,多足步行机器人运动及力规划研究,[D]:[博士].武汉:华中科技大学,11-19。
陈学东等,多足步行机顺人运动规划与控制[M],华中科技大学出版社,2006.6。
殷际英,何广平,关节型机器人[M],北京:化学工业出版社,2003.7。
龚振邦等,机器人机械设计[M],北京:电子工业出版社,1995.11。
张劲夫,秦卫阳,高等动力学[M],北京:科学出版社,2004.10。。
王太一,实验动物解剖图谱[M],辽宁美术出版社,2000.9。
金龙洙,食用动物解剖学[M],1984.8。
孙迪生,王炎,机器人控制技术[M],北京:机械工业出版社,1997。
何发昌,邵远,多功能机器人原理及应用[M],北京:高等教育出版社,1996。
姚春东,液压传动实用技术[M],北京:石油工业出版社,2001,7。
张利平,液压控制系统及设计[M],北京:化学工业出版社,2006.6。
袁子荣,液气压传动与控制[M],重庆:重庆大学出版,2003。
杨大智,智能材料与智能系统[M],天津:天津大学出版社,2000。
姚康德,智能材料[M],北京:化学工业出版社,2002.1。
Foruya Y,Shimads.Engineering aspects of shape memory alloys.Butterworth-Heinemann Ltd.1990.pp:228-355.
李东明,奚汉达,储金荻等,一种形状记忆合金丝驱动的微小型六足机器[J],上海交通大学学报,2002.10(34),pp:1426-1429。
瞿晓荣,2003,仿生机器蟹控制系统及驱动技术研究[D]:[硕士],哈尔滨:哈尔滨工程大学。
汤蕴璆,史乃,电机学[M],北京:机械工业出版社,2001.4。
谢明琛 张广溢,电机学[M],重庆:重庆大学出版社,1995.6
Christian Ridderstr(o|¨)m,Legged locomotion-balance,control and tools-from equation to action[D].PhD,Royal Institute of Technology,Sweden.2003。
zmp.co.jp,http://www.zmp.co.jp/html/products_pino.html。
沈炳余,顾荫双,机械原理[M],北京:机械工业出版社,1987.10。
张玲,2006,仿生机器蟹机构模型及控制系统研究[D]:[硕士],哈尔滨:哈尔滨工程大学。
Manfred Huber,Willard S.etc.A control Basis for Multilegged Walking.IEEE Conference on Robotics and Automation,Minneapolis,April 1996,Vol.4.pp:2988-2993.
Saridis G.1979,Toward the realization of intelligent controls[J],Proceedings of the IEEE,67(8):1115-1133.
袁鹏,2003,仿生机器蟹步行机理分析及控制系统研究[D]:[博士],哈尔滨:哈尔滨工程大学。
周立功单片机公司,DN-PCI-5110 DeviceNet主站卡数据手册。
Liang H,Mei T,Meng M,Design and Implementation of a digital inclinometer[C].Proceeding of the International Conference on Mechatronics&Automation,2005:489-492.
O.Michel,Webots:Professional mobile robot simulation.International Journal of Advanced Robotic Systems,vol.1,no.1,pp:39-42,2004。
李卓,萧德云,何世忠。基于神经网络的模糊自适应PID控制方法[J].控制与决策,1996,1 0(3):340-345.
高俊山,牟晓光,杨嘉祥,一种基于遗传算法和神经网络的PID控制[J],电机与控制学报,2004,8(2):108-111。
Srinivas M,Patnaik L.M.Adaptive Probabilities of Crossover and Mutations in Gas.IEEE Trans.on SMC,1994,24(4):656-667.
刘金琨.,先进PID控制及MATLAB仿真[M].北京:电子工业出版社.2003.
Z.米凯利维茨,演化程序-遗传算法和数据编码的结合[M].北京:科学出版社,2000.
吴志远,邵惠鹤,吴新余,一种新的自适应遗传算法及其在多峰值函数优化中的应用[J].控制理论与应用,1999,16(1):127-129。
牛建军,吴伟,陈国定,基于神经网络自整定PID控制策略及其仿真[J],系统仿真学报,2005,17(6),PP:1425-1427。
NIU Jian-jun,Wu Wei and CHEN Guo-ding.PID Controller with Neural Nets Optimizing Parameters and Its Stimulation[J].Journal of System Simulation,2005,17(6):1425-1427.
Lei Sun,Tao Mei,Yansheng Yao.etc,PID Controller based adaptive GA and Neural Networks,Proceedings of the 6~(th) World Congress on intelligent Control and Automation,June 21-23,2006,Dalian,China,pp:6564-6568.
Takashi.EMURA and Akira ARAKAWA."Attitude control of a quadruped robot during two legs supporting".Proceeding of 5th International.Conference.on Advanced Robotics.1991,pp:711-716。
杨保忠,1998,带弹性步行机构四足步行机器的动力学分析及实验研究[D]:[硕士],上海:上海交通大学。
Raibert,M.H.1985.Four-legged running with one-legged algorithms.In Second International Symposium on Robotics Research,H.Hanafusa,H.Inoue(eds.),(MIT Press,Cambridge),311-315.
Raibert,M.H.,Chepponis,M.,Brown,H.B.Jr.Running on four legs as though they were one [J].IEEE J.Robotics and Automation,1986,2:70-82。
Brooks R A.A robust layered control system for a mobile robot[J],IEEE.Journal of Robotics and Automation,1986,2(1):14-23。
Brooks R,A Robot that Walks:Emergent Behavior from a Carefully Evolved Net-work,Neural Computation 1:2,1989。
Huber M.,MacDonald W.S.,Grupen R.A.(1996),A Control Basis for Multilegged Walk-ing,Proceedings of ICRA'96。
寿天德,神经生物学,北京:高等教育出版社,2001.6。
Lewis M A,Simo L S.A model of visually triggered gait adaptation[A].Adaptive Motion of Animals and Machines[C].Montreal Canada,2000。
Hooper S L.Central pattern generators[J].Current Biology,2000,10(5):R176-177。
Mark James Randall.Stable Adaptive Neural control of Systems with Closed Kinematics Chains Applied to Biologically-Inspired Walking Robots.[D]:[Doctor].Thesis for University of the West of the England,Bristol,Dec.1999.
Kunichika Tsumoto,Tetsuya Yoshinaga,Kazuyuki Aihara,Bifurcatioon in Morris-lecar.Neuron Model[C].Proc.Of the international symposium on Nonlinear Theory and Its Applications.Xi An,PRC.2002.
Matsuoka K.Sustained oscillations generated by mutually inhibiting neurons with adaptation [J].Biological Cybernetics,1985,52:367-376。
Matsuoka K.Mechanism of frequency and pattern control in the neural rhythm generators[J].Biological Cybernetics,1987,56:345-353
Hiroshi Kimura,Yasuhiro Fukuoka,3D Adaptive Dynamic Walking of a Quadruped Robot by Using Neural System Model[C],Proc.Of 4~(th),Int.Conf.on Climbing and Walking Robots,Karlsruhe,2001.9.pp:97-104.
A.J.Ijspeert,J.Nakanishi,and S.Schaal.Learning rhythmic movements by demonstration using nonlinear oscillators[C].In Proceedings of the IEEE/RSJ Int.Conference on Intelligent Robots and Systems(IROS2002),pages 958-963,2002.
Hirofumi Nagashino,Generation and Transitions of Phase-locked Oscillations in coupled Neural Oscillators.Proceeding of World Multiconference on Systemics,cybernetics and informatics.Vol.8.,2001.
姜山,程君实,陈佳品等,基于多目标遗传算法的仿人机器人中枢神经运动控制器的设计[J].机器人,2001,23(1):58-62,67。
Shik M L,Severin F V,Orlovskii G N.Control of walking and running by means of electrical stimulation of the Mid-brain.Biofizyka[Biophysics].1966.7(04).pp:756-765。
S.Frigon and S.Rossignol,Experiments and models of sensorimotor interactions during locomotion.Biological Cybernetics,vol.95,no.2,pp.607-627,2006.
J.J.Collins,S.A.Richmond.Hard-wired central pattern generators for quadrupedal locomotion.Biologically Cybernetics,1994,71(1),pp:375-385.
奥托森D.神经系统生理学[M].吕国蔚译.北京:人民卫生出版社,1987.129-214。
万选才,现代神经生物学[M],北京:北京医科大学/中国协和医科大学联合出版社,1999.1。
Armen C Arevian,Vikrant Kapoor & Nathaniel N Urban,Activity-dependent gating of lateral inhibition in the mouse olfactory bulb,Nat Neurosci.2008 Jan;7(1),pp:80-87.Epub.2007Dec 12.
刘豹,现代控制理论[M],北京:机械工业出版社,1983.11。
王高雄,常微分方程[M],北京:高等教育出版社,1983。
Zhang Xiuli,Haojun Zheng,Walking up and down hill with a biologically-inspired postural reflex in a quadrupedal robot[J],Autonomous Robo,Volume 25,Issue 1-2,2008,pp:15-24
陈秉聪,步行车辆理论与脚踝设计[M].北京:机械丁业出版社,1991.10-98。
J.Buchli,L.Righetti,and A.J.Ijspeert.Engineering entrainment and adaptation in limit cycle systems-from biological inspiration to applications in robotics.Biological Cybernetics,95(6):645-664,2006.
蔡自兴,周翔,李枚毅,等.基于功能/行为集成的自主式移动机器人进化控制体系结构[J].机器人,2000,22(3):169-175。
潘俊民,赵玉芳.神经元在四足机器人伺服控制中的应用[J].上海交通大学学报,1997,31(3):20-23。
王巍,强文义,梁斌.月球探测机器人运动控制算法研究[J].航天控制,2000,4:47-52,59。
李难,行为的进化[M],上海:上海科技教育出版社,1990。
Beer R D,Chiel H J.The Neural Basis of Behavioral Choice in an Artificial Insect.In:Proc of the lst International Conference on Simulation of Adaptive Behavior.MIT Press,I991。
C.Watkins.Q-Learning[J],Machine Learning,1992,(8):279-292。
A.Schwartz.A Reinforcement Learning method for maximizing undiscounted rewards[J],In:Proceedings of the Tenth International Conference on Machine Learning,1993,298-305。
张汝波,杨广铭等,Q学习及其在智能机器人局部路径规划中的应用研究[J],计算机研究与发展,Vol.36,NO.12,1999,pp:1430-1436.
张汝波,强化学习理论及应用[M],哈尔滨:哈尔滨工程大学出版社,200l。
徐莉,Q-learning研究及其在AUV局部路径规划中的应用[D]:硕士,哈尔滨:哈尔滨:工程大学,2003。
靳小龙,张世武,吴建兵,多智能体模型与实验[M],北京:清华大学出版社,2003。
黄炳强,2007,强化学习算法及其应用研究[D]:博士,上海:上海交通大学。
Delcomyn F, NelsonM E. Architectures for a biomimetic hexapod robot [J]. Robotics and Autonomous Systems, 2000,30 (1), pp. 5-15.
Bares J E, WhittakerW L. Walking robot with a circulating gait. Proceedings of the 1990 IEEE/RSJ International Conference on Intelligent Robots and Systems. [C]. USA: SPIE, 1991.pp.809-816.
A. Ijspeert, A. Crespi, D. Ryczko, and J.-M. Cabelguen. From swimming to walking with a salamander robot driven by a spinal cord model. Science, 315(5817): 1416-1420, 2007。
R.S. Mosher, Test and Evaluation of a Versatile Walking Truck, in: Procs. Off-Road Mobility Research Symp.,1968, pp. 359-379 。
Shigeo Hirose, Yoji Umetani: Some Consideration on a Feasible Walking Mechanism as a Terrain Vehicle, Proc. 3rd RoManSy Symp., Udine, Italy, pp.357-375,1978.
Shigeo Hirose, Matsuo Nose, Hidekazu Kikuchi, Yoji Umetani: Adaptive Gait Control of a Quadruped Walking Vehicle, Robotics Research (1st Int. Symp.),The MIT Press,pp.253-277,1984。
Shigeo Hirose, Tomoyuki Masui, Hidekazu Kikuchi: TITAN 111: A Quadruped Walking Vehicle -Its Structure and Basic Char- acteristics, Robotic Research (2nd Int. Symp.), The MIT Press, pp.325-331, 1985.
Shigeo Hirose, Kan Yoneda, Kazuhiro Arai, Tomoyoshi Ibe: Design of Prismatic Quadruped Walking Vehicle TITAN VI, Proc. 5th Int. Conf. Advanced Robotics, Pisa, Italy, pp.723-728,1991.
Kan Yoneda, Shigeo Hirose: Dynamic and Static Fusion Gait of Quadruped Walking Vehicle on Winding Path, Proc. IEEE Int. Conf. on Robotics and Automation, pp.143-148, 1992.
Shigeo Hirose, Akihiko Nagakubo, Ryosei Toyama: Machine that can Walk and Climb on Floors,Walls and Ceilings, Proc. 5th Int. Cof. Advanced Robotics, Pisa, Italy, pp.753-758, 1991。
Keisuke Arikawa, Shigeo Hirose: Development of Quadruped Walking Robot TITAN-VIII, Proc.IROS96, pp.208-214, 1996。
R.D.Shraft, J.Dahlkemper, W.Baum and H.Gehringer: Smart Sensor Modules for Operator Assistance of Teleoperated Mobile Robots, Proc. Workshop on Anti-personnel Mine Detection and Removal, pp.21-25,1995。
Kimura, H., Fukuoka, Y., Hada, Y., and Takase, K. Adaptive Dynamic Walking of a Quadruped Robot on Irregular Terrain Using a Neural System Model. Robotics Research,Springer-Verlag, Berlin Heidelberg, 147-160.2003。
Matsuoka K. Sustained oscillations generated by mutually inhibiting neurons with adaptation [J].Biological Cybernetics, 1985, 52: 367-376。
Matsuoka K. Mechanism of frequency and pattern control in the neural rhythm generators [J].Biological Cybernetics, 1987, 56: 345-353。
Taga, G. A model of the neuro-musculo-skeletal system for human locomotion [J]. Biological Cybernetics, 73,2004.113-121.
Fukuoka. Y, Kimura, H., and Cohen, A. H., Adaptive Dynamic Walking of a Quadruped Robot on Irregular Terrain based on Biological Concepts. Int. Journal of Robotics Research,22(3-4), 2003.187-202.
Kimura H, Fukuoka Y, Minura T. Dynamics based integration of motion adaptation for a quadruped robot 'Tekken' [C]. Proc. of the 2~(nd) International Symposium on Adaptive Motion of Animals and Machines [C].Kyoto. 2003。
H.Miura, I. Shimoyama, etc. Dynamical walk of the quadruped robot(Collie-I), Robotics Research 2( the MIT Press),pp.317-324,1984.
H.Miura, I. Shimoyama, etc. Dynamics in the dynamic walk of a quadruped robot,RSJ.Advanced Robotics, vol.4, no.3, pp.283-301,1990.
Tsujita K, Tsuchiya K, Onat A. Adaptive gait pattern control of a quadruped locomotion robot. Proc of the IEEE Conf on Intelligent Robots and System[C]. Maui, Hawaii, 2001.2318-2325.
Takashi Emura and Akira. Arakawa, Attitude control of a quadruped robot during two leg supporting, Proc'91 Int.Conf. ofAdvanced Robotics,pp.711-716,1991.
Shiqi Peng. 2006. A Biologically Inspired Four Legged Walking Robot.[D]. Murdoch, Australia,Murdoch University.
Furusho, J., Sano, A., Sakaguchi, M., and Koizumi, E. Realization of bounce Gait in a Quadruped Robot with Articular-Joint-Type Legs, IEEE Int. Conf. Robotics and Automation, 1995. pp. 697-702
Raibert, M. H. 1985. Four-legged running with one-legged algorithms. In Second International Symposium on Robotics Research, H. Hanafusa, H. Inoue (eds.), (MIT Press, Cambridge),311-315
Raibert, M. H., Chepponis, M., Brown, H. B. Jr. 1986. Running on four legs as though they were one.IEEE J.Robotics and Automation,2:70-82.
Raibert,M.H.Trotting,pacing,and bounding by a quadruped robot.Jounal of Biomechanics.1990.Vol.1 pp.79-98.
D.J.Pack,A.C.Kak.A simplified forward gait control for a quadruped walking robot.Proceedings of the 1994 IEEE/RSJ International Conference on Intelligent Robots and Systems[C].USA:IEEE,1994.1011-1018.
Pack,D.J.,Perception-based control for a quadruped walking robot,1996 IEEE International Conference on Robotics and Automation,Volume 4,pp:2994- 3001.
Bostondynamics.com,http://www.bostondynamics.com/content/sec.php?section=BigDog
Johan Friede and Kim Kylstr(o|¨)m.Determination of mechanical parameters for the warpl robot using experimental methods,simulations and real-time control.Master's thesis,Dept.of Machine Design,Royal Institute of Technology,S-100 44 Stockholm,Sweden,1998.
Freyr Hardarson.Stability analysis and synthesis of statically balanced walking for quadruped robots.PhD thesis,The Royal Inst.of Technology,100 44 Stockholm,Sweden,June 2002.
llg,W.,Albiez,J.,and Jedele,H.(1998a) A biologically inspired adaptive control architecture based on neural net-works for a four-legged walking machine.In Proc.8th Int.Conf.on Artificial Neural Networks,Skoevde,Sweden,.455-460.
Ilg,W.,and Scholl,K.-U.(1998).Cqran:Continuous Q-learning resource allocation network towards reinforcement learning with multi-dimensional continuous action spaces.In Proc.8th Int.Conf.on Artificial Neural Networks,Sko-evde,Sweden,pp.455-460.
Ilg W,Albiez J,jedele H,et al.Adaptive periodic movement control for the four legged walking machine BISAM.IEEE Robotics &Automation[C].Detroit Michigan,1999.2354-2359.
Ilg W,Albiez J,Witte H,et al.Adaptive posture control of a four-legged walking machine using some principles of mammalian locomotion.Adaptive Motion of Animals and Machines[C].Montreal Canada,2000.
张秀丽,2004,四足机器人节律运动及环境适应性的生物控制研究境适应性的生物控制研究[D]:[博士].北京:清华大学,26-35。
汪劲松,易昕,QW-1型全方位四足步行机器人的设计及实验研究[J],机械工程学报,1991年27卷5期。
陈佳品,2001,四足机器人动态步行控制和学习辅助[D].上海交通大学博士论文。
孙迪生,王炎,机器人控制技术[M],北京:机械工业出版社,1997。
蔡自兴,机器人学[M],北京:清华大学出版社,2000.9。
NewtonC.D.,NunamakerD.M.,Textbook of Small Animal Orthopaedics,International Veterinary Information Service,1985;B0094.0685。
张锦荣,2007,基于虚拟样机技术的四足机器人仿真研究[D]:[硕士]。西安:西北工业大学,15-17。
Manocha D,Canny J.Real Time Inverse Kinematics for General 6R Manipulators[C],Proceedings of IEEE International Conference on Robotics and Automation.Raleign,North Carolina,USA:IEEE,1992:383-389.
Manseur R,Doty K L.Structural kinematics of 6-revolute-axis robot manipulators[J].Mechanism and Machine Theory(S0094-114X),1996,31(5):647-657.
周友行,何清华,邓伯禄.一种改进的爬山法优化求解冗余机械手运动学逆解[J].机器人,2003,25(1):35-38.
吴爱国,郝润生.一种改进BP算法在机械手逆运动学中的应用[J].中国工程科学,2005,7(7):34-38.
Lu B L,Ito K.Regularization of inverse kinematics for redundant manipulators using neural network inversions[C].Proceedings of IEEE International Conference on Neural Networks.Perth:IEEE,1995:2726-2731.
王常武,韩佩富,孔令富,黄真,赵立强,一并联机器人逆运动模型高效算法及其并行处理,计算机工程与设计,Vol.21,No.3,2000.6。
杭鲁滨,金琼,杨廷力,基于线性变换的一般串联机器人逆运动学分析[J],机械工程学报,Vol.37,No.5,2001.5。
Lei Sun,Max Q.-H.Meng,Wanming Chen,Huawei Liang,Tao Mei,Design of Quadruped Robot Based CPG and Fuzzy Neural Network,Proceedings of the IEEE International Conference on Automation and Logistics August 18-21,2007,Jinan,China.
王洪斌,宋佐时,王洪瑞,基于模糊神经网络的机器人逆运动学问题[J],系统仿真学报,Vol.1 4,No.7,2002.7。
钟金明,徐刚,张海波,模糊逆运动学控制方法在机器人视觉伺服中的应用[J],组合机床与自动化加工技术,2005.5。
熊有伦,机器人学[M],北京机械工业出版社,1993.10。
王新杰,2006,多足步行机器人运动及力规划研究,[D]:[博士].武汉:华中科技大学,11-19。
陈学东等,多足步行机顺人运动规划与控制[M],华中科技大学出版社,2006.6。
殷际英,何广平,关节型机器人[M],北京:化学工业出版社,2003.7。
龚振邦等,机器人机械设计[M],北京:电子工业出版社,1995.11。
张劲夫,秦卫阳,高等动力学[M],北京:科学出版社,2004.10。。
王太一,实验动物解剖图谱[M],辽宁美术出版社,2000.9。
金龙洙,食用动物解剖学[M],1984.8。
孙迪生,王炎,机器人控制技术[M],北京:机械工业出版社,1997。
何发昌,邵远,多功能机器人原理及应用[M],北京:高等教育出版社,1996。
姚春东,液压传动实用技术[M],北京:石油工业出版社,2001,7。
张利平,液压控制系统及设计[M],北京:化学工业出版社,2006.6。
袁子荣,液气压传动与控制[M],重庆:重庆大学出版,2003。
杨大智,智能材料与智能系统[M],天津:天津大学出版社,2000。
姚康德,智能材料[M],北京:化学工业出版社,2002.1。
Foruya Y,Shimads.Engineering aspects of shape memory alloys.Butterworth-Heinemann Ltd.1990.pp:228-355.
李东明,奚汉达,储金荻等,一种形状记忆合金丝驱动的微小型六足机器[J],上海交通大学学报,2002.10(34),pp:1426-1429。
瞿晓荣,2003,仿生机器蟹控制系统及驱动技术研究[D]:[硕士],哈尔滨:哈尔滨工程大学。
汤蕴璆,史乃,电机学[M],北京:机械工业出版社,2001.4。
谢明琛 张广溢,电机学[M],重庆:重庆大学出版社,1995.6
Christian Ridderstr(o|¨)m,Legged locomotion-balance,control and tools-from equation to action[D].PhD,Royal Institute of Technology,Sweden.2003。
zmp.co.jp,http://www.zmp.co.jp/html/products_pino.html。
沈炳余,顾荫双,机械原理[M],北京:机械工业出版社,1987.10。
张玲,2006,仿生机器蟹机构模型及控制系统研究[D]:[硕士],哈尔滨:哈尔滨工程大学。
Manfred Huber,Willard S.etc.A control Basis for Multilegged Walking.IEEE Conference on Robotics and Automation,Minneapolis,April 1996,Vol.4.pp:2988-2993.
Saridis G.1979,Toward the realization of intelligent controls[J],Proceedings of the IEEE,67(8):1115-1133.
袁鹏,2003,仿生机器蟹步行机理分析及控制系统研究[D]:[博士],哈尔滨:哈尔滨工程大学。
周立功单片机公司,DN-PCI-5110 DeviceNet主站卡数据手册。
Liang H,Mei T,Meng M,Design and Implementation of a digital inclinometer[C].Proceeding of the International Conference on Mechatronics&Automation,2005:489-492.
O.Michel,Webots:Professional mobile robot simulation.International Journal of Advanced Robotic Systems,vol.1,no.1,pp:39-42,2004。
李卓,萧德云,何世忠。基于神经网络的模糊自适应PID控制方法[J].控制与决策,1996,1 0(3):340-345.
高俊山,牟晓光,杨嘉祥,一种基于遗传算法和神经网络的PID控制[J],电机与控制学报,2004,8(2):108-111。
Srinivas M,Patnaik L.M.Adaptive Probabilities of Crossover and Mutations in Gas.IEEE Trans.on SMC,1994,24(4):656-667.
刘金琨.,先进PID控制及MATLAB仿真[M].北京:电子工业出版社.2003.
Z.米凯利维茨,演化程序-遗传算法和数据编码的结合[M].北京:科学出版社,2000.
吴志远,邵惠鹤,吴新余,一种新的自适应遗传算法及其在多峰值函数优化中的应用[J].控制理论与应用,1999,16(1):127-129。
牛建军,吴伟,陈国定,基于神经网络自整定PID控制策略及其仿真[J],系统仿真学报,2005,17(6),PP:1425-1427。
NIU Jian-jun,Wu Wei and CHEN Guo-ding.PID Controller with Neural Nets Optimizing Parameters and Its Stimulation[J].Journal of System Simulation,2005,17(6):1425-1427.
Lei Sun,Tao Mei,Yansheng Yao.etc,PID Controller based adaptive GA and Neural Networks,Proceedings of the 6~(th) World Congress on intelligent Control and Automation,June 21-23,2006,Dalian,China,pp:6564-6568.
Takashi.EMURA and Akira ARAKAWA."Attitude control of a quadruped robot during two legs supporting".Proceeding of 5th International.Conference.on Advanced Robotics.1991,pp:711-716。
杨保忠,1998,带弹性步行机构四足步行机器的动力学分析及实验研究[D]:[硕士],上海:上海交通大学。
Raibert,M.H.1985.Four-legged running with one-legged algorithms.In Second International Symposium on Robotics Research,H.Hanafusa,H.Inoue(eds.),(MIT Press,Cambridge),311-315.
Raibert,M.H.,Chepponis,M.,Brown,H.B.Jr.Running on four legs as though they were one [J].IEEE J.Robotics and Automation,1986,2:70-82。
Brooks R A.A robust layered control system for a mobile robot[J],IEEE.Journal of Robotics and Automation,1986,2(1):14-23。
Brooks R,A Robot that Walks:Emergent Behavior from a Carefully Evolved Net-work,Neural Computation 1:2,1989。
Huber M.,MacDonald W.S.,Grupen R.A.(1996),A Control Basis for Multilegged Walk-ing,Proceedings of ICRA'96。
寿天德,神经生物学,北京:高等教育出版社,2001.6。
Lewis M A,Simo L S.A model of visually triggered gait adaptation[A].Adaptive Motion of Animals and Machines[C].Montreal Canada,2000。
Hooper S L.Central pattern generators[J].Current Biology,2000,10(5):R176-177。
Mark James Randall.Stable Adaptive Neural control of Systems with Closed Kinematics Chains Applied to Biologically-Inspired Walking Robots.[D]:[Doctor].Thesis for University of the West of the England,Bristol,Dec.1999.
Kunichika Tsumoto,Tetsuya Yoshinaga,Kazuyuki Aihara,Bifurcatioon in Morris-lecar.Neuron Model[C].Proc.Of the international symposium on Nonlinear Theory and Its Applications.Xi An,PRC.2002.
Matsuoka K.Sustained oscillations generated by mutually inhibiting neurons with adaptation [J].Biological Cybernetics,1985,52:367-376。
Matsuoka K.Mechanism of frequency and pattern control in the neural rhythm generators[J].Biological Cybernetics,1987,56:345-353
Hiroshi Kimura,Yasuhiro Fukuoka,3D Adaptive Dynamic Walking of a Quadruped Robot by Using Neural System Model[C],Proc.Of 4~(th),Int.Conf.on Climbing and Walking Robots,Karlsruhe,2001.9.pp:97-104.
A.J.Ijspeert,J.Nakanishi,and S.Schaal.Learning rhythmic movements by demonstration using nonlinear oscillators[C].In Proceedings of the IEEE/RSJ Int.Conference on Intelligent Robots and Systems(IROS2002),pages 958-963,2002.
Hirofumi Nagashino,Generation and Transitions of Phase-locked Oscillations in coupled Neural Oscillators.Proceeding of World Multiconference on Systemics,cybernetics and informatics.Vol.8.,2001.
姜山,程君实,陈佳品等,基于多目标遗传算法的仿人机器人中枢神经运动控制器的设计[J].机器人,2001,23(1):58-62,67。
Shik M L,Severin F V,Orlovskii G N.Control of walking and running by means of electrical stimulation of the Mid-brain.Biofizyka[Biophysics].1966.7(04).pp:756-765。
S.Frigon and S.Rossignol,Experiments and models of sensorimotor interactions during locomotion.Biological Cybernetics,vol.95,no.2,pp.607-627,2006.
J.J.Collins,S.A.Richmond.Hard-wired central pattern generators for quadrupedal locomotion.Biologically Cybernetics,1994,71(1),pp:375-385.
奥托森D.神经系统生理学[M].吕国蔚译.北京:人民卫生出版社,1987.129-214。
万选才,现代神经生物学[M],北京:北京医科大学/中国协和医科大学联合出版社,1999.1。
Armen C Arevian,Vikrant Kapoor & Nathaniel N Urban,Activity-dependent gating of lateral inhibition in the mouse olfactory bulb,Nat Neurosci.2008 Jan;7(1),pp:80-87.Epub.2007Dec 12.
刘豹,现代控制理论[M],北京:机械工业出版社,1983.11。
王高雄,常微分方程[M],北京:高等教育出版社,1983。
Zhang Xiuli,Haojun Zheng,Walking up and down hill with a biologically-inspired postural reflex in a quadrupedal robot[J],Autonomous Robo,Volume 25,Issue 1-2,2008,pp:15-24
陈秉聪,步行车辆理论与脚踝设计[M].北京:机械丁业出版社,1991.10-98。
J.Buchli,L.Righetti,and A.J.Ijspeert.Engineering entrainment and adaptation in limit cycle systems-from biological inspiration to applications in robotics.Biological Cybernetics,95(6):645-664,2006.
蔡自兴,周翔,李枚毅,等.基于功能/行为集成的自主式移动机器人进化控制体系结构[J].机器人,2000,22(3):169-175。
潘俊民,赵玉芳.神经元在四足机器人伺服控制中的应用[J].上海交通大学学报,1997,31(3):20-23。
王巍,强文义,梁斌.月球探测机器人运动控制算法研究[J].航天控制,2000,4:47-52,59。
李难,行为的进化[M],上海:上海科技教育出版社,1990。
Beer R D,Chiel H J.The Neural Basis of Behavioral Choice in an Artificial Insect.In:Proc of the lst International Conference on Simulation of Adaptive Behavior.MIT Press,I991。
C.Watkins.Q-Learning[J],Machine Learning,1992,(8):279-292。
A.Schwartz.A Reinforcement Learning method for maximizing undiscounted rewards[J],In:Proceedings of the Tenth International Conference on Machine Learning,1993,298-305。
张汝波,杨广铭等,Q学习及其在智能机器人局部路径规划中的应用研究[J],计算机研究与发展,Vol.36,NO.12,1999,pp:1430-1436.
张汝波,强化学习理论及应用[M],哈尔滨:哈尔滨工程大学出版社,200l。
徐莉,Q-learning研究及其在AUV局部路径规划中的应用[D]:硕士,哈尔滨:哈尔滨:工程大学,2003。
靳小龙,张世武,吴建兵,多智能体模型与实验[M],北京:清华大学出版社,2003。
黄炳强,2007,强化学习算法及其应用研究[D]:博士,上海:上海交通大学。