Abstract: A method to improve the adaptability of robot is presented, which can overcome the limitation of traditional robot design method. Obstacle avoidance, target approach and their combination behavior learning of evolutionary robot are realized by the use of artificial neural network in this paper. First, a robot learning environment and a robot model are presented and the implementation of evolutionary learning system is discussed. Then, the simulation experiments are carried out for basic and combined behavior learning system of intelligent robot that adopted evolutionary learning mechanism. Finally, the simulation results are analyzed and the future research direction is given.