Surface path tracking method of autonomous surface underwater vehicle based on deep reinforcement learning

被引:6
|
作者
Song, Dalei [1 ,2 ]
Gan, Wenhao [1 ]
Yao, Peng [1 ]
Zang, Wenchuan [3 ]
Qu, Xiuqing [1 ]
机构
[1] Ocean Univ China, Coll Engn, 238 Songling Rd, Qingdao 266100, Shandong, Peoples R China
[2] Ocean Univ China, Inst Adv Ocean Study, 238 Songling Rd, Qingdao 266100, Shandong, Peoples R China
[3] Ocean Univ China, Coll Informat Sci & Engn, 238 Songling Rd, Qingdao 266100, Shandong, Peoples R China
来源
NEURAL COMPUTING & APPLICATIONS | 2023年 / 35卷 / 08期
基金
中国国家自然科学基金;
关键词
Autonomous surface underwater vehicle; Dynamic model; Path tracking; Obstacle avoidance; Deep reinforcement learning; LEVEL CONTROL; GUIDANCE;
D O I
10.1007/s00521-022-08009-3
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The capability of path tracking and obstacle avoidance in a complex ocean environment is the basis of the autonomous ocean vehicle voyage. In this paper, a hybrid sea surface path tracking guidance and controller for the autonomous surface underwater vehicle based on the carrot-chasing (CC) and deep reinforcement learning (DRL) is proposed. Firstly, the reference heading angle is provided by the CC algorithm, and then the DRL algorithm is used to combine it with the vehicle-borne sensor information for decision and control. The vehicle's tracking capability is self-developed through a Markov decision process model that includes states, actions, and reward functions, so as to interact and train with the surrounding environment without prior knowledge. The simulation experiments are carried out in high-fidelity sea surface environments with wind, wave and current disturbances, and the experimental results show that the proposed method can converge effectively, has high tracking accuracy and flexible obstacle avoidance ability while avoiding the calculation of complex parameters.
引用
收藏
页码:6225 / 6245
页数:21
相关论文
共 50 条
  • [41] A novel reinforcement learning based tuna swarm optimization algorithm for autonomous underwater vehicle path planning
    Yan, Zheping
    Yan, Jinyu
    Wu, Yifan
    Cai, Sijia
    Wang, Hongxing
    MATHEMATICS AND COMPUTERS IN SIMULATION, 2023, 209 : 55 - 86
  • [42] Tracking Multiple Surface Vessels With an Autonomous Underwater Vehicle: Field Results
    Wolek, Artur
    McMahon, James
    Dzikowicz, Benjamin R.
    Houston, Brian H.
    IEEE JOURNAL OF OCEANIC ENGINEERING, 2022, 47 (01) : 32 - 45
  • [43] Research on Control of Unmanned Surface Vehicle Based on Deep Reinforcement Learning
    Li, Baoan
    Ship Building of China, 2020, 61 : 14 - 20
  • [44] A Method of Deep Reinforcement Learning for Simulation of Autonomous Vehicle Control
    Anh Huynh
    Ba-Tung Nguyen
    Hoai-Thu Nguyen
    Sang Vu
    Hien Nguyen
    ENASE: PROCEEDINGS OF THE 16TH INTERNATIONAL CONFERENCE ON EVALUATION OF NOVEL APPROACHES TO SOFTWARE ENGINEERING, 2021, : 372 - 379
  • [45] Research on the Agricultural Machinery Path Tracking Method Based on Deep Reinforcement Learning
    Li, Hongchang
    Gao, Fang
    Zuo, GuoCai
    SCIENTIFIC PROGRAMMING, 2022, 2022
  • [46] Tracking of Autonomous Underwater Vehicles using an Autonomous Surface Vehicle with Ranger Interrogator System
    Braginsky, Boris
    Baruch, Alon
    Guterman, Hugo
    OCEANS 2016 MTS/IEEE MONTEREY, 2016,
  • [47] Target Tracking Control of a Biomimetic Underwater Vehicle Through Deep Reinforcement Learning
    Wang, Yu
    Tang, Chong
    Wang, Shuo
    Cheng, Long
    Wang, Rui
    Tan, Min
    Hou, Zengguang
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (08) : 3741 - 3752
  • [48] LSTM-DPPO based deep reinforcement learning controller for path following optimization of unmanned surface vehicle
    XIA Jiawei
    ZHU Xufang
    LIU Zhong
    XIA Qingtao
    Journal of Systems Engineering and Electronics, 2023, 34 (05) : 1343 - 1358
  • [49] LSTM-DPPO based deep reinforcement learning controller for path following optimization of unmanned surface vehicle
    Xia, Jiawei
    Zhu, Xufang
    Liu, Zhong
    Xia, Qingtao
    JOURNAL OF SYSTEMS ENGINEERING AND ELECTRONICS, 2023, 34 (05) : 1343 - 1358
  • [50] Path Planning Based on Deep Reinforcement Learning for Autonomous Underwater Vehicles Under Ocean Current Disturbance
    Chu, Zhenzhong
    Wang, Fulun
    Lei, Tingjun
    Luo, Chaomin
    IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, 2023, 8 (01): : 108 - 120