A neuro-optimal control method of modular robot manipulators based on nonzero-sum game strategy

This paper presents a nonzero-sum strategy-based neuro-optimal control method for modular robot manipulators (MRMs). Based on joint torque feedback (JTF) technique, the dynamic model of the manipulator systems is described as an integration of joint subsystems. A local dynamic information-based robust compensator is designed to engage the model uncertainty compensation, and then, the optimal tracking control problem of an MRM system is transformed into an n-player nonzero-sum game issue of multiple joint subsystems. By taking advantage of the adaptive dynamic programming (ADP) algorithm, a cost function approximator is developed for solving the Hamilton- Jacobi (HJ) equation, thus facilitating the feasible derivation of the neuro-optimal control policy. Finally, experiment results illustrated the effectiveness of the developed control method.