The docking control system of an autonomous underwater vehicle combining intelligent object recognition and deep reinforcement learning

被引:0
作者
Yu, Chao-Ming [1 ]
Lin, Yu-Hsien [1 ]
机构
[1] Natl Cheng Kung Univ, Dept Syst & Naval Mechatron Engn, Tainan 70101, Taiwan
关键词
Autonomous underwater vehicle; Docking; Visual navigation; Intelligent object recognition; Deep reinforcement learning; AUV NAVIGATION; FUZZY CONTROL; SEA; LOGIC;
D O I
10.1016/j.engappai.2024.109565
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This study develops a visual-based docking system (VDS) for an autonomous underwater vehicle (AUV), significantly enhancing docking performance by integrating intelligent object recognition and deep reinforcement learning (DRL). The system overcomes traditional navigation limitations in complex and unpredictable environments by using a variable information dock (VID) for precise multi-sensor docking recognition in the AUV. Employing image-based visual servoing (IBVS) technology, the VDS efficiently converts 2D visual data into accurate 3D motion control commands. It integrates the YOLO (short for You Only Look Once) algorithm for object recognition and the deep deterministic policy gradient (DDPG) algorithm, improving continuous motion control, docking accuracy, and adaptability. Experimental validation at the National Cheng Kung University towing tank demonstrates that the VDS enhances control stability and operational reliability, reducing the mean absolute error (MAE) in depth control by 42.03% and pitch control by 98.02% compared to the previous method. These results confirm the VDS's reliability and its potential for transforming AUV docking.
引用
收藏
页数:29
相关论文
共 86 条
  • [1] Pipeline following by visual servoing for Autonomous Underwater Vehicles
    Allibert, Guillaume
    Minh-Duc Hua
    Krupinski, Szymon
    Hamel, Tarek
    [J]. CONTROL ENGINEERING PRACTICE, 2019, 82 : 151 - 160
  • [2] Arnold S, 2018, IEEE INT CONF ROBOT, P4889
  • [3] Reinforcement learning for control: Performance, stability, and deep approximators
    Busoniu, Lucian
    de Bruin, Tim
    Tolic, Domagoj
    Kober, Jens
    Palunko, Ivana
    [J]. ANNUAL REVIEWS IN CONTROL, 2018, 46 : 8 - 28
  • [5] Chao Wang, 2021, ICDSP 2021: 2021 5th International Conference on Digital Signal Processing, P225, DOI 10.1145/3458380.3459041
  • [6] Viosual servo control - Part I: Basic approaches
    Chaumette, Francois
    Hutchinson, Seth
    [J]. IEEE ROBOTICS & AUTOMATION MAGAZINE, 2006, 13 (04) : 82 - 90
  • [7] Cong Wang, 2019, 2019 IEEE International Conference on Robotics and Biomimetics (ROBIO), P2571, DOI 10.1109/ROBIO49542.2019.8961491
  • [8] Sparus Docking Station: A current aware docking station system for a non-holonomic AUV
    Esteba, Joan
    Cieslak, Patryk
    Palomeras, Narcis
    Ridao, Pere
    [J]. JOURNAL OF FIELD ROBOTICS, 2024, 41 (06) : 1765 - 1779
  • [9] Eysenbach B, 2019, ADV NEUR IN, V32
  • [10] Multi-Agent Distributed Deep Deterministic Policy Gradient for Partially Observable Tracking
    Fan, Dongyu
    Shen, Haikuo
    Dong, Lijing
    [J]. ACTUATORS, 2021, 10 (10)