Robot Action Acquisition by Self-Learning Fuzzy Controller

A kind of stable self-learning fuzzy neural networks control system based on genetic algorithm is proposed in this paper, and it is used to acquire soccer robot shooting action. The system is composed of two parts. A fuzzy neural networks controller which uses genetic algorithm to search optimal fuzzy rules and membership function. A supervisor which uses gradient learning algorithm to train the network weights. The results of simulation and real experiments show the effectiveness of the proposed controller.