期刊文献+

一种基于操作条件反射原理的学习模型 被引量:4

A learning model based on operant conditioning principles
原文传递
导出
摘要 针对认知机器人的自主学习问题,提出一种基于操作条件反射原理的学习模型(OCLM).该模型采用状态空间、操作行为空间、概率分布函数、仿生学习机制、系统熵等进行描述,给出状态的"负理想度"的概念,定义了取向函数的计算方法.运用模型对机器人避障导航问题进行仿真实验,并对参数设置进行了讨论.实验结果表明,基于OCLM模型的机器人能通过与环境的交互获得认知,成功避障到达目的地,具有一定的自学习能力,从而表明了模型的有效性. Inspired by Skinner’s operant conditioning theory, an operant conditioning learning model is presented to deal with the autonomous learning problem in cognitive robotics. The model is described by nine elements, including the space set, the action set, the bionic learning function and the system entropy etc. A notion "negative ideal rate" is defined to compute the orientation function. The OCLM is applied to solve obstacle avoidance and navigation problems for mobile robots. The experiment results show that the robot based on the model can autonomously learn how to arrive at the goal in a collision-free way through interaction with the environment, and show the effectiveness of the proposed model.
出处 《控制与决策》 EI CSCD 北大核心 2014年第6期1016-1020,共5页 Control and Decision
基金 国家自然科学基金项目(61075110) 北京市自然科学基金项目(KZ201210005001) 国家973计划项目(2012CB720000) 高等学校博士学科点专项科研基金项目(20101103110007)
关键词 学习模型 操作条件反射 自学习 仿生 避障 learning model operant conditioning autonomous learning bionics obstacle avoidance
  • 相关文献

参考文献10

  • 1Skinner B F.The behavior of organisms: An experimental analysis[M].New York: Appleton-Century Company, 1938: 110-150.
  • 2Zalama E, Gaudiano P, Coronado J L.Obstacle avoidance by means of an operant conditioning model[M].Berlin: Springer, 1995: 471-477.
  • 3Gaudiano P, Chang C.Adaptive obstacle avoidance with a neural network for operant conditioning: experiments with real robots[C].IEEE Int Symposium on Computational Intelligence in Robotics and Automation.Monterey: IEEE Press, 1997: 13-18.
  • 4Gaudiano P, Zalama E, Chang C, et al.A model of operant conditioning for adaptive obstacle avoidance[C].From Animals to Animats.Cambridge: MIT Press, 1996: 373-381.
  • 5Ishii H, Nakasuji M, Ogura M, et al.Accelerating rat’s learning speed using a robot: The robot autonomously shows rats its functions[C].Proc of the 2004 IEEE Int Workshop on Robot and Human Interactive Communication.Roman: IEEE Press, 2004: 229-234.
  • 6Itoh K, Miwa H, Matsumoto M, et al.Behavior model of humanoid robots based on operant conditioning[C].The 5th IEEE-RAS Int Conf on Humanoid Robots.Tsukuba: IEEE Press, 2005: 220-225.
  • 7Taniguchi T, Sawaragi T.Incremental acquisition of behaviors and signs based on a reinforcement learning schemata model and a spike timing-dependent plasticity network[J].Advanced Robotics, 2007, 21(10): 1177-1199.
  • 8Salotti J M, Lepretre F.Classical and operant conditioning as roots of interaction for robots[C].Proc of the Workshop From Motor to Interaction Learning in Robots Conf on Intelligent Robotics Systems.Nice: Springer, 2008: 124-133.
  • 9阮晓钢,蔡建羡,戴丽珍.基于概率自动机的操作条件反射计算模型[J].北京工业大学学报,2010,36(8):1025-1030. 被引量:3
  • 10蔡建羡,阮晓钢.OCPA仿生自主学习系统及在机器人姿态平衡控制上的应用[J].模式识别与人工智能,2011,24(1):138-146. 被引量:5

二级参考文献23

  • 1吴克河,李为,柳长安,李国栋.双轮驱动式移动机器人动力学控制[J].宇航学报,2006,27(2):272-275. 被引量:12
  • 2SKINNER B F. The behavior of organisms[M]. New York: Appleton-Century-Crofts, 1938: 110-150.
  • 3SKINNER B F. Two types of conditioned reflex and a pseudo type[ J ]. Journal of General Psychology, 1935, 12 (1) : 66-77.
  • 4TOURETZKY D S, SAKSIDA L M. Skinnerbots[ C]//The Fourth International Conferenee on Simulation of Adaptive Behavior. Cape Cod, USA: MIT.Press, 1996: 285-294.
  • 5SAKSIDA L M, TOURETZKY D S. Application Of a model of instrumental conditioning to mobile robot control[ C ]//Sensor Fusion and Decentralized Control in Autonomous Robotic Systems. Pittsburgh, USA: SPIE, 1997: 55-66.
  • 6SAKSIDA L M, RAYMOND S M, TOURETZKY D S. Shaping robot behavior using principles from instrumental conditioning [ J ]. Robotics and Autonomous Systems, 1998, 22 (4) : 231-249.
  • 7TOURETZKY D S, DAWN D, TIRA-THOMPSON E J. Combining configural and TD learning on a robot[ C]//2nd Intemational Conference on Development and Learning. Cambridge, England: IEEE Computer Society , 2002: 47-52.
  • 8TOURETZKY D S, TIRA-THOMPSON E J. Tekkotsu: a framework for AIBO cognitive robotics[ C]//The National Conference on Artificial Intelligence. Pittsburgh, USA: American Association for Artificial Intelligence, 2005: 1741-1742.
  • 9VELOSO M M. CMRoboBits: creating an intelligent AIBO robot[J]. AI Magazine, 2006, 27 ( 1 ) : 67-82.
  • 10ITOH K, MIWA H. Behavior model of humanoid robot based on operant conditioning[C]//Proceedings of 2005 5th IEEE- RAS International Conference on Humanoid Robots. Tsukuba, Japan: IEEE, 2005: 220-225.

共引文献6

同被引文献26

  • 1沈晶,顾国昌,刘海波.分层强化学习研究综述[J].模式识别与人工智能,2005,18(5):574-581. 被引量:7
  • 2BROOKS R A. From earwigs to humans [J]. Robotics and Au- tonomous Systems, 1997, 20(2): 291- 304.
  • 3BROOKS R A, BREAZEAL C, MARJANOVIC M, et al. The Cog Project: Building a Humanoid Robot [M]. Berlin: Springer-Verlag, 1999:52 - 87.
  • 4NATALE L, ORABONA E BERTON F, et al. From sensorimotor development to object perception [C] //Humanoid Robots, 2005 5th IEEE-RAS International Conference on. Piscataway, NJ: IEEE Press, 2005:226 - 231.
  • 5KUNIYOSHI Y, SANGAWA S. Early motor development from par- tially ordered neural-body dynamics: experiments with a cortico- spinal-musculo-skeletal model [J]. Biological Cybernetics, 2006, 95(6): 589 - 605.
  • 6KIMURA H, FUKUOKA , COHEN A H. Adaptive dynamic walk- ing of a quadruped robot on natural ground based on biological concepts [J]. The International Journal of Robotics Research, 2007, 26(5): 475 - 490.
  • 7CHAO F, LEE M H. An autonomous developmental learning ap- proach for robotic eye-hand coordination [C] //Proceedings of the lASTED International Conference. Calgary: ACTA Press, 2009:13 -18.
  • 8MATHEWS Z, VERSCHURE P F M J. PASAR: an integrated model of prediction, anticipation, sensation, attention and response for arti- ficial sensorimotor systems [J]. Information Sciences, 2012, 186(1): 1-19.
  • 9SKINNER B E The Behavior of Organisms: an Experimental Anal- ysis [M]. New York: D. Appleton-Century Company, 1938:110 - 150.
  • 10ZALAMA E, GAUDIANO P, CORONADO J L. Obstacle Avoidance by Neans of an Operant Conditioning Model [M]. Berlin: Springer, 1995:471 - 477.

引证文献4

二级引证文献4

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部