【作者】 吴杰； 许映秋； 钮伟； 谈英姿；

【Author】 WU Jie;XU Ying-qiu;NIU Wei;TAN Ying-zi;Mechanical College of Southeast University;Automation College of Southeast University;

【机构】 东南大学机械工程学院； 东南大学自动化学院；

【摘要】 在Robo Cup救援仿真中,警察智能体清理阻塞道路、搜索地图环境信息对整个灾难救援有着至关重要的作用。分区策略是警察任务分配的重要策略,同时有助于对地图的搜索遍历。提出一种基于K-means算法的警察分区方法,根据距离将所有建筑物进行聚类分析形成建筑簇并分开成为不同的区域,然后分配给对应的警察智能体。通过仿真实验和实战比赛验证了该方法的有效性。更多还原

【Abstract】 In the Robo Cup rescue simulation, the effects of policeforce agent clearing blockades in roads and searching the map environment has a vital role in the whole disaster. Partitioning strategy is an important method for policeforce’s task allocation. It is also helpful to search and ergodic the whole map at the same time. This paper proposed a partitioning strategy based on K-means algorithm of policeforce agent. In this method, all the buildings were clustered and separated into different regions according to distance. And then, the regions were assigned to the corresponding policeforce agents. Finally, the validity of this method has been confirmed through simulation test and competition.更多还原