OPTIMAL TRACKING CONTROL FOR ROBOT MANIPULATORS WITH INPUT CONSTRAINT BASED REINFORCEMENT LEARNING

This paper introduces an optimal tracking controller for robot manipulators with saturation torques. The model is presented as a strict-feedback nonlinear system. Firstly, the position control problem transformed into problem. Subsequently, saturated law designed. determined through solution of Hamilton-Jacobi-Bellman (HJB) equation. We use reinforcement learning algorithm only one neural network (NN) to approximate equation HJB. technique experience replay used relax persistent citation condition. By Lyapunov analysis, and approximation errors are uniformly ultimately bounded (UUB). Finally, simulation on manipulator torques performed verify efficiency proposed controller.