Abstract:A control system based on neural network sliding mode controller is designed for the trajectory tracking of parallel robot with strong coupling and high nonlinearity. On the basis of traditional sliding mode control, the neural network algorithm was used to correct the function of nonlinear and uncertain parameters of system, which could effectively suppress the chattering phenomenon of Sliding Mode Control (SMC) system. Firstly, the structure diagram and Matlab model of 3RRR planar parallel robot were established, and the inverse kinematics solution of the robot was obtained by the closed loop vector method, which was the reference input for control system. Then, based on the simplified dynamic equation of robot, a Radial Basis Function (RBF) neural network SMC was designed, and a Lyapunov function was constructed to prove the stability of the controller. Finally, the traditional SMC and neural network SMC were used to simulate the trajectory of robot. The simulation results show that the neural network sliding mode controller has better trajectory tracking accuracy and small steadystate error, and verifies the effectiveness of neural network SMC controller.