Micro-robots playing soccer games: A real implementation based on a multi-agent decision-making structure

Multi-Agent decision-making structures are expected to be extensively appli ed in complex industrial systems. Multi-robotic soccer competitions are a f orum where rales and constraints are good to develop for MIROSOT, and test them. This paper describes an implementation of such a robotic team consist ing of three micro-robots. It shows an agent-based decision-making method t hat takes into account an index of difficulty to execute collision-free pat h obtained by a path-planning method specially devised for this domain. Som e real situations are used to explain how robots behave, and which are thei r movements through the playground. Then, some agents persistence problems are analyzed, and simulation results are shown.