Reinforcement Learning-Based Adaptive Vibration Control of Flexible Two-Link Manipulator Systems With Input Saturation

This article focuses on the vibration issue of flexible two-link manipulators (FTLMs) with input saturation. An efficient system model is represented by a set of ordinary differential equations (ODEs) based on the assumed mode method (AMM). Subsequently, a reinforcement learning (RL)-based adaptive vibration control strategy, which is a model-free control approach, is proposed by employing the actor–critic algorithm structure. Additionally, an auxiliary system is constructed to tackle the influence of input saturation, ensuring trajectory tracking while achieving vibration suppression. Furthermore, the stability of the closed-loop system under RL control is examined using the Lyapunov direct method, which demonstrates the semi-global uniform ultimate boundedness (SGUUB) of tracking and vibration errors. Finally, to verify the effectiveness and superiority of the proposed RL strategy, the comparative simulations and experimental studies are conducted on the Quanser experimental platform. The experimental results demonstrate that RL control reduces steady-state errors by 40% and 96.6% against PSF control and by 50% and 97.2% against neural network (NN) control, respectively.