Context-Based Coordination for a Multi-Robot Soccer Team

Abstract

The key issue investigated in the field of Multi-Robot Systems (MRS) is the problem of coordinating multiple robots in a common environment. In tackling this issue, problems concerning the capabilities of multiple heterogeneous robots and their environmental constraints need to be faced. In this paper, we introduce a novel approach for coordinating a team of robots. The key contribution of the proposed method consists in exploiting the rules governing the scenario by identifying and using “contexts”. The robots actions and perceptions are specialized to the current context to enhance both single and collective behaviors. The presented approach has been largely validated in a RoboCup scenario. In particular, we adopt a soccer environment as a testing ground for our algorithm. We evaluate our method in several testing sessions on a simulator representing a virtual model of a soccer field. The obtained results show a substantial improvement of the team adopting our algorithm.