一种结合内在动机理论的移动机器人环境认知模型  

An environment cognition model combined with intrinsic motivation for mobile robots

作　　者：阮晓钢 张家辉[1,2] 黄静 柴洁 武悦[1,2] RUAN Xiao-gang;ZHANG Jia-hui;HUANG Jing;CHAI Jie;WU Yue(Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China;Beijing Key Laboratory of Computational Intelligence and Intelligent System,Beijing University of Technology,Beijing 100124,China)

机构地区：[1]北京工业大学信息学部,北京100124 [2]北京工业大学计算智能与智能系统北京市重点实验室,北京100124

出　　处：《控制与决策》2021年第9期2211-2217,共7页Control and Decision

基　　金：国家自然科学基金项目(61773027);工信部2018年工业互联网创新发展工程项目(Z135060009002)。

摘　　要：为了探讨动机在环境认知中所起作用,模仿生物环境认知行为,以学习自动机为框架,提出一种结合内在动机理论的移动机器人环境认知模型(CM-LA).该模型以访问次数及访问时间间隔共同定义内在动机,并以操作条件反射原理描述外在动机的影响.同时,所设计的动作选择机制可以使机器人根据已有的环境认知对新增障碍物进行有效避让.实验结果表明,所提出模型能够在两种动机的驱使下对环境进行有效的自主认知,并提高机器人在未知环境中的探索效率,搜索到的路径长度较短,且具有一定的环境自适应能力.In order to explore the role of motivation in environmental cognition and imatate the environment cognitive behavior of creatures,this paper proposes a mobile robot environment cognitive model(CM-LA)combining the theory of intrinsic motivation with the framework of learning automata.The number of visits and the time interval between visits define the intrinsic motivation,and describe the impact of extrinsic motivation based on the principle of operant conditioning.At the same time,the designed action selection mechanism enables the robot to effectively avoid new obstacles based on existing environmental awareness.The experimental results show that the model can effectively and autonomously recognize the environment driven by two motivations,and improve the exploration efficiency of the robot in an unknown environment.The path length searched using this method is shorter with the ability of self-adaptation to the environment.

关 键 词：内在动机 操作条件反射 环境认知 认知计算 移动机器人 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]