Loughborough University
Browse
Trans on Neural Networks and Learning Systems.pdf (4.31 MB)

Reinforcement learning-based fixed-time trajectory tracking control for uncertain robotic manipulators with input saturation

Download (4.31 MB)
journal contribution
posted on 2021-10-26, 10:49 authored by Shengjie Cao, Liang Sun, Jingjing JiangJingjing Jiang, Zongyu Zuo
A fixed-time trajectory tracking control method for uncertain robotic manipulators with input saturation based on reinforcement learning (RL) is studied. The designed reinforcement learning control algorithm is implemented by radial basis function (RBF) neural network, in which the actor neural network is used to generate the control strategy and the critic neural network is used to evaluate the execution cost. A new non-singular fast terminal sliding mode technique is used to ensure the convergence of tracking error in fixed time, and the upper bound of convergence time is estimated. To solve the saturation problem of an actuator, a nonlinear anti-windup compensator is designed to compensate for the saturation effect of the joint torque actuator in real time. Finally, the stability of the closed-loop system based on Lyapunov candidate is analyzed, and the timing convergence of the closed-loop system is proved. Simulation and experimental results show the effectiveness and superiority of the proposed control law.

Funding

National Natural Science Foundation of China (Nos. 61903025, 62073019)

China Scholarship Council (No. 201906465028)

Fundamental Research Funds for the Central Universities (No. FRF-BD-19-002A)

History

School

  • Aeronautical, Automotive, Chemical and Materials Engineering

Department

  • Aeronautical and Automotive Engineering

Published in

IEEE Transactions on Neural Networks and Learning Systems

Volume

34

Issue

8

Pages

4584 - 4595

Publisher

Institute of Electrical and Electronics Engineers

Version

  • AM (Accepted Manuscript)

Rights holder

© IEEE

Publisher statement

© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Acceptance date

2021-09-26

Publication date

2021-10-15

Copyright date

2021

ISSN

2162-237X

eISSN

2162-2388

Language

  • en

Depositor

Dr Jingjing Jiang. Deposit date: 28 September 2021

Usage metrics

    Loughborough Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC