Neural network-based adaptive sliding mode control for multi-joint manipulator

Considering the problems of slow convergence speed and low tracking accuracy in the trajectory tracking control system of the multi-DOF manipulator, it is of great significance to design an effective control method to quickly track the target trajectories. In this paper, the dynamic modeling of the manipulator is conducted, followed by the development of a control strategy and an analysis of its stability. Firstly, the Lagrange method is applied to establish dynamic modeling of the manipulator. Secondly, a controller based on neural network adaptive sliding mode control is proposed to realize the trajectory tracking of the manipulator, which realizes the suppression of external disturbance and overcomes the influence of friction. Then, the Lyapunov direct method was applied to prove the stability of the designed system to guarantee the convergence of the tracking error. Finally, the experimental results based on Simulink under software Matlab indicate that the designed control strategy absolutely solve the problems of slow convergence speed and low tracking accuracy. It can adaptively compensate the uncertainties of the system and has good robustness against external interference.