基于π演算的足球机器人协作Q学习方法  

Cooperative Q learning method based on π calculus in robot soccer

作　　者：柯文德[1,2] 朴松昊[2] 彭志平[1] 蔡则苏[2] 苑全德[2] 

机构地区：[1]广东石油化工学院计算机科学与技术系,广东茂名525000 [2]哈尔滨工业大学计算机科学与技术学院,哈尔滨150001

出　　处：《计算机应用》2011年第3期654-656,669,共4页journal of Computer Applications

基　　金：广东高校优秀青年创新人才培育项目(201180);国家863计划项目(2007AA041603;2006AA040202);国家自然科学基金资助项目(60905047;61075076;61075077);国家重点实验室项目(SKLRS200902C);广东省自然科学基金资助项目(8152500002000003)

摘　　要：针对多机器人协作学习时出现的学习速度慢、学习效率低等问题,提出了一种基于π演算心智模型的足球机器人协作Q学习方法,描述了机器人的运动模型,定义了球场现状、目标、意图、行为、协作、请求、扩展知识、能力判断和联合意图等机器人心智状态,构造了联合奖励函数。最后通过实验验证了方法的有效性。Concerning the low speed and low efficiency of learning in robot soccer when cooperating between muhirobots, a cooperative Q learning method based on the mental model of π calculus was proposed, in which the mental states were defined as the field state, goal, intention, action, cooperation, request, expanding knowledge, capability judging and connected intention, etc, and the combinational reward function was constructed. The validity of method was verified through experiments.

关 键 词：多机器人 协作 Q学习 心智状态 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]