Abstract
In this research, we propose the method to acquire operation characteristics in the control strategy by an expert operator. In this paper, we use CMAC learning algorithm which is one method of the neural network. The ordinary CMAC learning algorithm is able to learn a control parameter, but the control output to learn is generally plural in case of human operator's control characteristics. Therefore, in this method, we propose the modified CMAC learning algorithm to learn two operation characteristics when a human operator controls a mobile robot.Furthermore, in order to confirm the efficiency of the proposed method, we performed the learning experiment of the velocity and the steering angle velocity of operation characteristics of a human using a joystick to control the ball chasing and dribbling by a soccer robot for the Middle-Size League of RoboCup.
