Emergent Cooperative Strategies for Robot Team Sports

Abstract

ABSTRACTAutomatic development of cooperative strategies for teams of distributed autonomous robots, or software agents, is presented in this paper. It is shown that a team of robotic agents that initially plays a random game of simulated soccer, can acquire winning strategies through successive generations, utilizing techniques of evolutionary computation. The concept of Tropism-based Control Architecture is introduced that not only allows for the evolution of cooperative strategies, but also obtains the acquired knowledge in a format that is easily comprehensible by humans. The advantage of this approach is that the cooperative strategies can then be transported onto a variety of platforms for testing and deployment. It is discussed as to why the game of robot soccer provides a good environment for this type of investigation, and how the presented concepts can have applications in multi-robot system design. The proposed cognitive architecture has been inspired by biological systems, and the paper include...