신경회로망을 이용한 이륜 역진자형 이동로봇의 제어기 설계

Abstract

In this paper, a controller for two wheeled inverted pendulum type robot is designed to have more stable balancing capability than conventional controllers. Traditional PID control structure is chosen for the two wheeled inverted pendulum type robot, and proper gains for the controller are obtained for specified user`s weights using trial-and-error methods. Next a neural network is employed to generate PID controller gains for more stable control performance when the user`s weight is arbitrarily selected. Through simulation studies we find that the designed controller using the neural network is superior to the conventional PID controller.