Trajectory Tracking Control Based on RBF Neural Network of The Lower Limb Rehabilitation Robot

The lower limb rehabilitation robot has been widely applied to the recovery of the patient's limb. For patients without autonomous movement ability, the robot will drive their limbs the planned trajectory to carry out rehabilitation training, and the accuracy of the trajectory tracking effect should be guaranteed. PID control is a conventional method for trajectory tracking. Due to the dynamic model uncertainties and lack of good adjustment ability of PID control method, this paper proposes a control method combining neural network and PID. In this study, Magnetorheological (MR) damper and motor are combined to provide actuation for the robot. The control is simulated in Simulink. By comparing the trajectory tracking errors under PID control and RBF-PID control, it is verified that the RBF-PID control has better anti-interference performance. In the process of rehabilitation robot work, the flexibility of movement and the real-time and stability of track tracking are improved.