An Evolutionary Fuzzy Behaviour Controller Using Genetic Algorithm in RoboCup Soccer Game

The problem of an effective behavior learning of autonomous robots is one of the most important tasks of the modern robotics. In fact, it is well known that the learning to optimize actions of autonomous agents in a dynamic environment is one of the most complex challenges of the intelligent system design. In this paper, we propose a hybrid approach integrating fuzzy logic system with genetic algorithm for high-level skills learning of robots within the RoboCup simulation soccer domain. Through the experiments, we found that the proposed method has good property of computation efficiency and also has a good advantage applied to the environment of RoboCup.