Fuzzy reinforcement learning prescribed-time algorithm for the rigid–flexible coupled robotic mechanisms with input deadzone

Abstract

In the horizontal plane, the dynamic model for rigid–flexible coupled robotic mechanisms under large beam-deformations are determined through the utilization of a comprehensive modeling approach based on the virtual work concept. To track the desired angular positions of such robotic mechanisms with input nonsymmetric deadzone, the fuzzy nonsymmetric deadzone compensation based prescribed time adaptive reinforcement learning control strategy, incorporated with virtual robust linear quadratic state feedback input is proposed. To handle the unknown nonsymmetric input deadzone and uncertain system dynamics, an actor prescribed time fuzzy law is adopted. For further reduce the large vibration modes and tracking errors simultaneously, a virtual input and the proposition of a robust linear quadratic state feedback controller are developed. With the Lyapunov direct strategy, the angular position tracking errors and the flexible vibration of robotic mechanisms are demonstrated to converge to a tiny confined compact set. In numerical scenarios, the proposed fuzzy nonsymmetric deadzone compensation-based prescribed time adaptive reinforcement learning strategy simultaneously reduced mean angular tracking errors in a preset time and flexible vibration when compared respectively to virtual robust state feedback-free and backstepping mode control baselines.