RBF neural network compensation based trajectory tracking control for rehabilitation training robot

For rehabilitation robot, how to effectively control the movement of training, which depends on the performance of the robot control system, is very important to improve the quality of rehabilitation. Lower limb rehabilitation robot system is a nonlinear time-varying system, so the real-time calculation and compensation for the nonlinear coupling term is always neccessary, and linear control method can be used to achieve trajectory tracking with a high precision. For this target, a radial basis function (RBF) neural network compensation control method based on computed-torque is put forward. First, the controlled object and movement features of the rehabilitation robot system are briefly introduced. Then, computed torque control method is analyzed, and for the uncertainty part of computed torque as well as the environment disturbance, the RBF neural network compensator is designed. Finally, the simulation for the proposed algorithm is conducted and analyzed. The results show that the computed torque controller with RBF neural network compensator has smaller tracking error than the PD feedback controller based on computed torque.