Reinforcement learning-based output feedback control of nonlinear systems with input constraints

被引：91
|
作者：
He, P [1 ]
Jagannathan, S [1 ]
机构：
[1] Univ Missouri, Dept Elect & Comp Engn, Rolla, MO 65409 USA
来源：
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS | 2005年 / 35卷 / 01期
关键词：
neural networks (NNs); output feedback control; reinforcement learning;
D O I：
10.1109/TSMCB.2004.840124
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
A novel neural network (NN)-based output feedback controller with magnitude constraints is designed to deliver a desired tracking performance for a class of multi-input and multi-output (MIMO) strict feedback nonlinear discrete-time systems. Reinforcement learning is proposed for the output feedback controller, which uses three NNs: 1) an NN observer to estimate the system states with the input-output data, 2) a critic NN to approximate certain strategic utility function, and 3) an action NN to minimize both the strategic utility function and the unknown dynamics estimation errors. Using the Lyapunov approach, the uniformly ultimate boundedness (UUB) of the state estimation errors, the tracking errors and weight estimates is shown.
引用
收藏
页码：150 / 154
页数：5
相关论文
共 50 条
  • [1] Reinforcement learning-based output feedback control of nonlinear systems with input constraints
    He, P
    Jagannathan, S
    [J]. PROCEEDINGS OF THE 2004 AMERICAN CONTROL CONFERENCE, VOLS 1-6, 2004, : 2563 - 2568
  • [2] Reinforcement learning-based optimized output feedback control of nonlinear strict-feedback systems with event sampled states
    Xin, Chun
    Li, Yuan-Xin
    [J]. INTERNATIONAL JOURNAL OF ADAPTIVE CONTROL AND SIGNAL PROCESSING, 2023, 37 (01) : 38 - 58
  • [3] Optimal control for a class of nonlinear systems with input constraints based on reinforcement learning
    Luo A.
    Xiao W.-B.
    Zhou Q.
    Lu R.-Q.
    [J]. Kongzhi Lilun Yu Yingyong/Control Theory and Applications, 2022, 39 (01): : 154 - 164
  • [4] Reinforcement-Learning-Based Adaptive Optimal Flight Control with Output Feedback and Input Constraints
    Sun, Bo
    van Kampen, Erik-Jan
    [J]. JOURNAL OF GUIDANCE CONTROL AND DYNAMICS, 2021, 44 (09) : 1685 - 1691
  • [5] Integral reinforcement learning-based guaranteed cost control for unknown nonlinear systems subject to input constraints and uncertainties
    Liang, Yuling
    Zhang, Huaguang
    Zhang, Juan
    Luo, Yanhong
    [J]. APPLIED MATHEMATICS AND COMPUTATION, 2021, 408
  • [6] Learning-Based Adaptive Fuzzy Output Feedback Control for MIMO Nonlinear Systems With Deception Attacks and Input Saturation
    Zhao, Ning
    Tian, Yongjie
    Zhang, Huiyan
    Herrera-Viedma, Enrique
    [J]. IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2024, 32 (05) : 2850 - 2862
  • [7] Integral reinforcement learning-based optimal output feedback control for linear continuous-time systems with input delay
    Wang, Gao
    Luo, Biao
    Xue, Shan
    [J]. NEUROCOMPUTING, 2021, 460 : 31 - 38
  • [8] Adaptive neural output feedback control for uncertain nonlinear systems with input quantization and output constraints
    Wang, Min
    Zhang, Tianping
    Yang, Yuequan
    [J]. INTERNATIONAL JOURNAL OF ADAPTIVE CONTROL AND SIGNAL PROCESSING, 2020, 34 (02) : 228 - 247
  • [9] Integral reinforcement learning-based optimal tracking control for uncertain nonlinear systems under input constraint and specified performance constraints
    Chang, Ru
    Liu, Zhi-Meng
    Li, Xiao-Bin
    Sun, Chang-Yin
    [J]. INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL, 2024, 34 (13) : 8802 - 8824
  • [10] Reinforcement Learning-Based Control for Nonlinear Discrete-Time Systems with Unknown Control Directions and Control Constraints
    Huang, Miao
    Liu, Cong
    He, Xiaoqi
    Ma, Longhua
    Lu, Zheming
    Su, Hongye
    [J]. NEUROCOMPUTING, 2020, 402 : 50 - 65
12345