Vibration Control Based on Reinforcement Learning for a Single-link Flexible Robotic Manipulator

Abstract

In this paper, we focus on the reinforcement learning control of a single-link flexible manipulator and attempt to suppress the vibration due to its flexibility and lightweight structure. The assumed mode method (AMM) and the Lagrange’s equation are adopted in modeling to enhance the satisfaction of precision. Two radial basis function neural networks (RBFNNs) are employed in the designed control algorithm, actor neural network (NN) for generating a policy and critic NN for evaluating the cost-function. Rigorous stability of the system has been proven via Lyapunov’s direct method. According to the performance of simulation for the proposed control scheme, the superiority and feasibility of the proposed controller is verified.