A partitioning-based task allocation strategy for Police Multi-Agents

RCRSS (RoboCup Rescue Simulation System, RCRSS) is a typical multi-agent system. In order to solve the task allocation problem for police multi-agents of this system, this paper presents a novel partitioning-based task allocation strategy. It is carried out through the use of clustering, namely the K-means clustering algorithm, to divide the map into several regions. Then the dynamic adjustment system with static assignment was adopted synthetically for the implementation. The experimental results show that the new task allocation strategy for the police can adapt to a variety of disaster environments and improve the efficiency of multi-agent collaboration.