Decentralized Robust Optimal Control for Modular Robot Manipulators Based on Zero-Sum Game with ADP

In this paper, a decentralized robust zero-sum optimal control method is proposed for modular robot manipulators (MRMs) based on the adaptive dynamic programming (ADP) approach. The dynamic model of MRMs is formulated via joint torque feedback (JTF) technique that is deployed for each joint module, in which the local dynamic information is used to design the model compensation controller. An uncertainty decomposition-based robust control is developed to compensate the model uncertainties, and then the robust optimal control problem of MRMs with uncertain environments can be transformed into a two-player zero-sum optimal control one. According to the ADP algorithm, the Hamilton-Jacobi-Isaacs (HJI) equation is solved by constructing action-critic neural networks (NNs) and then the approximate optimal control policy derivation is possible. Experiments are conducted to verify the effectiveness of the proposed method.