PMBC及其在Robocup中的应用  

A Plan Model Based on Cooperation(PMBC) and Its Application in Robocup

作　　者：谢雅[1] 彭军[1] 吴敏[1] 

机构地区：[1]中南大学信息科学与工程学院,湖南长沙410075

出　　处：《计算机仿真》2006年第3期120-122,176,共4页Computer Simulation

基　　金：国家863计划项目(2001AA422200)

摘　　要：智能体间的协作能够提高多智能体系统的智能度,而规划作为一种重要的问题求解技术,能够有效地实现多智能体间的协作。该文介绍了一种基于协作的规划模型及此模型的前提、动作和终止条件三要素,通过对特定状态和局部协作的提前规划,有效地实现了多智能体系统中智能体间的协作。通过把此规划模型运用到典型的多智能体系统—机器人足球比赛中,证明了在多智能体系统中应用此规划模型不仅能够提高单个智能体的反应速度,还可以提高整个系统的运行效率。Cooperation can enhance the intelligence of Multi -Agent System （MAS）, and plan as an .important question solution technique can realize Multi - Agent cooperation effectively. A Plan Model Based on Cooperation （PMBC） and its three elements including precondition, action and ending condition are introduced in this paper, Multi- Agent cooperation is implemented by preplanning the specifical state and local cooperation. This model is used in Robocup which is the typical MAS. Simulation results indicate that with PMBC the reaction velocity of single Agent is enhanced, at the same time it can improve the efficiency of MAS.

关 键 词：基于协作的规划模型 足球机器人比赛 多智能体系统 多智能体的协作 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]