An Intelligent Non-Integer PID Controller-Based Deep Reinforcement Learning: Implementation and Experimental Results

被引:57
|
作者
Gheisarnejad, Meysam [1 ]
Khooban, Mohammad Hassan [2 ]
机构
[1] Islamic Azad Univ, Dept Elect Engn, Najafabad Branch, Esfahan 1477893855, Iran
[2] Aarhus Univ, Dept Engn, DIGIT, DK-8200 Aarhus, Denmark
关键词
Mobile robots; Vehicle dynamics; Kinematics; Wheels; Mathematical model; Heuristic algorithms; Deep deterministic policy gradient (DDPG); dynamic controller; noninteger proportional integral derivative (PID) controller; wheeled mobile robot (WMR); SLIDING-MODE CONTROL; MOBILE ROBOT; DYNAMIC CONTROLLER; DESIGN; TRACKING; STABILIZATION; MANIPULATOR;
D O I
10.1109/TIE.2020.2979561
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In this article, a noninteger proportional integral derivative (PID)-type controller based on the deep deterministic policy gradient algorithm is developed for the tracking problem of a mobile robot. This robot system is a typical case of nonholonomic plants and is exposed to the measurement noises and external disturbances. To accomplish the control methodology, two control mechanisms are established independently: a kinematic controller (which is designed based on the kinematic model of the vehicle), and a dynamic controller (which is realized according to the physical specifications of the vehicle dynamics). In particular, an optimal noninteger PID controller is initially designed as the primary dynamic controller for the tracking problem of a nonholonomic wheeled mobile robot. Then, a DDPG algorithm with the actor-critic framework is established for the supplementary dynamic controller, which is beneficial to the tracking stabilization by adapting to the uncertainties and disturbances. This strategy implements the supplementary based control to compensate for what the original controller is unable to handle. A prototype of the WMR was also adopted to investigate the applicability of the suggested controller from a real-time platform perspective. The outcomes in experimental environments are presented to affirm the effectiveness of the suggested control methodology.
引用
收藏
页码:3609 / 3618
页数:10
相关论文
共 50 条
  • [1] Intelligent PID Controller Based on Deep Reinforcement Learning
    Zhai, Yinhe
    Zhao, Qiang
    Han, Yinghua
    Wang, Jinkuan
    Zeng, Wenying
    [J]. 2024 8TH INTERNATIONAL CONFERENCE ON ROBOTICS, CONTROL AND AUTOMATION, ICRCA 2024, 2024, : 343 - 348
  • [2] Non-Integer Order Approximation of a PID-Type Controller for Boost Converters
    Sanchez, Allan G. S.
    Perez-Pinal, Francisco J.
    Rodriguez-Licea, Martin A.
    Posadas-Castillo, Cornelio
    [J]. ENERGIES, 2021, 14 (11)
  • [3] An approximation method and PID controller tuning for systems having integer order and non-integer order delay
    Ozyetkin, Munevver Mine
    [J]. ALEXANDRIA ENGINEERING JOURNAL, 2022, 61 (12) : 11365 - 11375
  • [4] PID Controller-Based Stochastic Optimization Acceleration for Deep Neural Networks
    Wang, Haoqian
    Luo, Yi
    An, Wangpeng
    Sun, Qingyun
    Xu, Jun
    Zhang, Lei
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2020, 31 (12) : 5079 - 5091
  • [5] PID controller-based adaptive gradient optimizer for deep neural networks
    Dai, Mingjun
    Zhang, Zelong
    Lai, Xiong
    Lin, Xiaohui
    Wang, Hui
    [J]. IET CONTROL THEORY AND APPLICATIONS, 2023, 17 (15): : 2032 - 2037
  • [6] Frequency Deviation Control Incorporating Fuzzy Plus Non-Integer PID Controller in EV Based Unified System
    Tripathy, Sabita
    Debnath, Manoj Kumar
    Kar, Sanjeeb Kumar
    [J]. INTERNATIONAL JOURNAL OF RENEWABLE ENERGY RESEARCH, 2023, 13 (02): : 879 - 887
  • [7] Optimization and Implementation of Intelligent PID Controller Based on FPGA
    Wang, Kaiyu
    Tang, Zhenan
    Zhang, Yongrui
    Song, Zhiming
    Li, Zhiheng
    Xi, Mengmeng
    [J]. PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON ELECTRIC AND ELECTRONICS, 2013, : 232 - 235
  • [8] Design and Implementation of Intelligent PID Controller Based on FPGA
    Qu, Liguo
    Huang, Yourui
    Ling, Liuyi
    [J]. ICNC 2008: FOURTH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, VOL 7, PROCEEDINGS, 2008, : 511 - 515
  • [9] Parameter tuning and hardware implementation of a non integer order PID controller
    Brunno, F.
    Caponetto, R.
    Fortuna, L.
    Porto, D.
    [J]. PROCEEDINGS OF 2006 MEDITERRANEAN CONFERENCE ON CONTROL AND AUTOMATION, VOLS 1 AND 2, 2006, : 990 - +
  • [10] Fault-Tolerant Control of Programmable Logic Controller-Based Production Systems With Deep Reinforcement Learning
    Zinn, Jonas
    Vogel-Heuser, Birgit
    Gruber, Marius
    [J]. JOURNAL OF MECHANICAL DESIGN, 2021, 143 (07)