Clustering and planning for rescue agent simulation

Abstract

The paper describes the contribution of the GUC-ArtSapience team to the Rescue Agent Simulation competition in RoboCup in terms of the current research approach. The approach is divided into two parts: clustering and planning. Clustering is done through task allocation to divide the map among the agents. Planning is done after assigning the agents to parts of the map to determine how they should cooperate and coordinate together and how they should prioritize their tasks [2]. The agents can coordinate together using centers and communication if available or dynamically without the use of communication. © 2014 Springer-Verlag Berlin Heidelberg.