Integral reinforcement learning-based event-triggered optimal tracking control for modular robot manipulators via non-zero-sum game

Abstract

Under the event-triggered mechanism, a non-zero-sum game optimal tracking control method for modular robot manipulators (MRMs) system with input constraints is proposed by using the adaptive dynamic programming (ADP) method based on integral reinforcement learning (IRL). First, the dynamic model of MRMs system, based on joint torque feedback (JTF) technology, consists of n joint subsystem which is related to interconnected dynamic coupling (IDC). Second, we design the robust compensation controller to handle the model known term and optimal compensation controller to deal with the uncertainty term caused by the IDC and friction, respectively. In addition, a nonlinear disturbance observer is established to dispose the negative effect caused by uncertain sensor output disturbance. Third, based on differential game theory, we transform the optimal tracking control problem of MRMs system into an n-player NZS game problem. Then, the IRL-based ADP method is adopted that relax the need for system partial unknown dynamic information and only critic neural network (NN) is used to solve the coupled Hamilton-Jacobi (HJ) equation, so as to obtain the optimal control policy. Then by Lyapunov theory, the tracking error of MRMs system is demonstrated to be uniformly ultimately bounded (UUB). Finally, the effectiveness and superiority of the proposed algorithm are verified through experiments.