Disturbance Observer-Based Cooperative Learning Tracking Control for Multi-Manipulators

Abstract

This paper studies the disturbance observer-based cooperative learning tracking control for a homogenous multi-robot manipulator system. Firstly, in the ideal environment, adaptive neural network (NN) controllers are constructed based on distributed cooperative learning (DCL) to obtain the knowledge of unknown manipulator system dynamics. Then, for similar tasks in the practical environment full of disturbances, in order to avoid the re-adaption of NN weights, the knowledge learned in the ideal environment is used to construct the novel controllers based on disturbance observer, which effectively enhances the robustness of the proposed controllers. The boundedness of all signals in the closed-loop system is guaranteed by employing the proposed control scheme, and the tracking error of each manipulator eventually converge to a small neighborhood of the origin. Finally, a numerical example is given to verify the effectiveness of the proposed control strategy.