Stochastic Optimal Control for Robot Manipulation Skill Learning Under Time-Varying Uncertain Environment

• Published in: IEEE transactions on cybernetics Vol. 54; no. 4; pp. 2015 - 2025
• Main Authors: Liu, Xing, Liu, Zhengxiong, Huang, Panfeng
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.04.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Control methods; Environment models; Feedforward control; Gaussian process; Gaussian processes; Impedance; iterative linear quadratic Gaussian with learned external dynamic (ILQG-LED) method; Iterative methods; Manipulator dynamics; model-based reinforcement learning; Nonlinear systems; Optimal control; Parameters; Robot arms; Robot control; robot manipulation skill; robot-environment interaction; Robots; stochastic optimal manipulation control; Stochastic processes; System dynamics; Task complexity; Time-varying systems; time-varying uncertain environment; Trajectory; Unknown environments

In this article, a novel stochastic optimal control method is developed for robot manipulator interacting with a time-varying uncertain environment. The unknown environment model is described as a nonlinear system with time-varying parameters as well as stochastic information, which is learned via t...