Policy iteration-based integral reinforcement learning for online adaptive trajectory tracking of mobile robot

被引:0
作者
Ashida T. [1 ]
Ichihara H. [1 ]
机构
[1] Department of Mechanical Engineering Informatics, Meiji University, Chiyoda City, Tokyo
基金
日本学术振兴会;
关键词
adaptive dynamic programming; continuous-time system; Integral reinforcement learning; mobile robot; policy iteration; trajectory tracking;
D O I
10.1080/18824889.2021.1972266
中图分类号
学科分类号
摘要
This paper considers trajectory tracking control for a nonholonomic mobile robot using integral reinforcement learning (IRL) based on a value functional represented by integrating a local cost. The tracking error dynamics between the robot and reference trajectories takes the form of time-invariant input-affine continuous-time nonlinear systems if the reference trajectory counterpart of the translational and angular velocities are constant. This paper applies integral reinforcement learning to the tracking error dynamics by approximating the value functional from the data collected along the robot trajectory. The paper proposes a specific procedure to implement the IRL-based policy iteration online, including a batch least-squares minimization. The approximate value function updates the control policy to compensate for the translational and angular velocities that drive the robot. Numerical examples illustrate to demonstrate the tracking performance of integral reinforcement learning. © 2021 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.
引用
收藏
页码:233 / 241
页数:8
相关论文
共 50 条
  • [21] Trajectory tracking control for mobile robot based on the fuzzy sliding mode
    Xie Mu-jun
    Li Li-ting
    Wang Zhi-qian
    PROCEEDINGS OF THE 10TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA 2012), 2012, : 2706 - 2709
  • [22] Genetic Algorithms for Trajectory Tracking of Mobile Robot Based on PID Controller
    Alouache, Ali
    Wu, Qinghe
    2018 IEEE 14TH INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTER COMMUNICATION AND PROCESSING (ICCP), 2018, : 237 - 241
  • [23] Navigation and trajectory tracking of mobile robot based on kinematic PI controller
    Ben Halima Abid, Donia
    Yousfi Allagui, Najah
    Derbel, Nabil
    2017 18TH INTERNATIONAL CONFERENCE ON SCIENCES AND TECHNIQUES OF AUTOMATIC CONTROL AND COMPUTER ENGINEERING (STA), 2017, : 252 - 256
  • [24] Adaptive trajectory tracking control of a differential drive wheeled mobile robot
    Shojaei, Khoshnam
    Shahri, Alireza Mohammad
    Tarakameh, Ahmadreza
    Tabibian, Behzad
    ROBOTICA, 2011, 29 : 391 - 402
  • [25] Mobile Robot Trajectory Tracking on Adaptive Binocular Vision and Fuzzy Control
    Hong, Huang
    Ting, Zhang
    CCDC 2009: 21ST CHINESE CONTROL AND DECISION CONFERENCE, VOLS 1-6, PROCEEDINGS, 2009, : 632 - 635
  • [26] A Self-Adaptive Double Q-Backstepping Trajectory Tracking Control Approach Based on Reinforcement Learning for Mobile Robots
    He, Naifeng
    Yang, Zhong
    Fan, Xiaoliang
    Wu, Jiying
    Sui, Yaoyu
    Zhang, Qiuyan
    ACTUATORS, 2023, 12 (08)
  • [27] Reinforcement Learning-Based Tracking Control for a Three Mecanum Wheeled Mobile Robot
    Zhang, Dianfeng
    Wang, Guangcang
    Wu, Zhaojing
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (01) : 1445 - 1452
  • [28] A new framework for mobile robot trajectory tracking using depth data and learning algorithms
    Alamiyan-Harandi, Farinaz
    Derhami, Vali
    Jamshidi, Fatemeh
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2018, 34 (06) : 3969 - 3982
  • [29] Policy Iteration Based Online Adaptive Optimal Fault Compensation Control for Spacecraft
    Yanbin Du
    Bin Jiang
    Yajie Ma
    International Journal of Control, Automation and Systems, 2021, 19 : 1607 - 1617
  • [30] Policy Iteration Based Online Adaptive Optimal Fault Compensation Control for Spacecraft
    Du, Yanbin
    Jiang, Bin
    Ma, Yajie
    INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS, 2021, 19 (04) : 1607 - 1617