Dynamic coordination in RoboCup soccer simulation

Abstract

The RoboCup Soccer Simulation is considered as a good application of the Multi-Agent Systems. By using the multi-agent approach, each team in this simulation is considered as a multiagent system, which is coordinated each other and by a coach agent. Different strategies have been proposed in order to improve the efficiency of this agent. In this paper, we investigate firstly the coordination in several modern teams by identifying all of their disadvantages. We present then our approach related the dynamic coordination in order to improve the performance of our team. The experimentation and evaluation to validate this approach will be concluded in this paper.