Cooperative architecture for multi-agent systems in robotic soccer (CAMASS)

Abstract

In order to create a cooperative architecture for multi-agent systems in robotic soccer, it is necessary to model and understand the human soccer concepts to use and express them computationally. This work presents the main features for a multi-agent cooperative architecture based on human soccer concepts. The architecture can be applied to different categories of RoboCup. To test its performance, an initial development was accomplished for the RoboCup 2D simulation category, obtaining a system able to execute synchronized simple tactics.