Predefined-Time Trajectory Tracking Control for n-DOF Manipulator Based on Actor-Critic Algorithm

This paper addresses the predefined-time trajectory tracking problem of the n degree-of-freedom (DOF) manipulator system based on the actor-critic algorithm. First, a cost function is selected to design the critic network. Second, the actor network is designed by selecting appropriate predefined-time sliding surface and combining with the radial basis function neural network, which solves model uncertainty existing in the manipulator system. Finally, several experimental simulations are performed on a 2-DOF manipulator to prove the effectiveness of the proposed control method.