Adaptive learning of teleoperating robotic motion

摘要

In this paper, we propose a method of adaptive learning control applicable to the bilaterally controlled teleoperating system. The control scheme learns the desired inverse dynamics of the system to predict and compensate for the nonlinear dynamics which is the source of poor trajectory tracking and force regulation. In addition, the uncertain system parameters and input disturbances are continuously learned and the time-variance of which is also taken into account by the feedforward learning controller. The proposed control scheme is shown to be stable and the effectiveness of which is experimentally verified with a teleoperating system composed of master-slave SCARA robots.