Path Planning for Automatic Berthing Using Ship-Maneuvering Simulation-Based Deep Reinforcement Learning

被引:3
|
作者
Vo, Anh Khoa [1 ]
Mai, Thi Loan [2 ]
Yoon, Hyeon Kyu [2 ]
机构
[1] Changwon Natl Univ, Dept Smart Environm Energy Engn, Chang Won 51140, South Korea
[2] Changwon Natl Univ, Dept Naval Architecture & Marine Engn, Chang Won 51140, South Korea
来源
APPLIED SCIENCES-BASEL | 2023年 / 13卷 / 23期
关键词
path planning; deep reinforcement learning; TD3; maneuvering simulation; automatic berthing;
D O I
10.3390/app132312731
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Despite receiving much attention from researchers in the field of naval architecture and marine engineering since the early stages of modern shipbuilding, the berthing phase is still one of the biggest challenges in ship maneuvering due to the potential risks involved. Many algorithms have been proposed to solve this problem. This paper proposes a new approach with a path-planning algorithm for automatic berthing tasks using deep reinforcement learning (RL) based on a maneuvering simulation. Unlike the conventional path-planning algorithm using the control theory or an advanced algorithm using deep learning, a state-of-the-art path-planning algorithm based on reinforcement learning automatically learns, explores, and optimizes the path for berthing performance through trial and error. The results of performing the twin delayed deep deterministic policy gradient (TD3) combined with the maneuvering simulation show that the approach can be used to propose a feasible and safe path for high-performing automatic berthing tasks.
引用
收藏
页数:16
相关论文
共 50 条
  • [1] Graph Search-Based Path Planning for Automatic Ship Berthing
    Liu, Xiaocheng
    Hu, Zhihuan
    Yang, Ziheng
    Zhang, Weidong
    JOURNAL OF MARINE SCIENCE AND ENGINEERING, 2024, 12 (06)
  • [2] Ship path planning based on Deep Reinforcement Learning and weather forecast
    Artusi, Eva
    2021 22ND IEEE INTERNATIONAL CONFERENCE ON MOBILE DATA MANAGEMENT (MDM 2021), 2021, : 258 - 260
  • [3] Motion Planning Using Reinforcement Learning Method for Underactuated Ship Berthing
    Zhang, Haoran
    Yin, Chenkun
    Zhang, Yanxin
    2020 IEEE 16TH INTERNATIONAL CONFERENCE ON CONTROL & AUTOMATION (ICCA), 2020, : 354 - 359
  • [4] Path planning for a maritime suface ship based on Deep Reinforcement Learning and weather data
    Artusi, Eva
    Chaillan, Fabien
    Napoli, Aldo
    OCEANS 2021: SAN DIEGO - PORTO, 2021,
  • [5] Automatic berthing using supervised learning and reinforcement learning
    Shimizu, Shoma
    Nishihara, Kenta
    Miyauchi, Yoshiki
    Wakita, Kouki
    Suyama, Rin
    Maki, Atsuo
    Shirakawa, Shinichi
    OCEAN ENGINEERING, 2022, 265
  • [6] Transferable multi-objective factory layout planning using simulation-based deep reinforcement learning
    Klar, Matthias
    Schworm, Philipp
    Wu, Xiangqian
    Simon, Peter
    Glatt, Moritz
    Ravani, Bahram
    Aurich, Jan C.
    JOURNAL OF MANUFACTURING SYSTEMS, 2024, 74 : 487 - 511
  • [7] Robot path planning based on deep reinforcement learning
    Long, Yinxin
    He, Huajin
    2020 IEEE CONFERENCE ON TELECOMMUNICATIONS, OPTICS AND COMPUTER SCIENCE (TOCS), 2020, : 151 - 154
  • [8] A storage expansion planning framework using reinforcement learning and simulation-based optimization
    Tsianikas, Stamatis
    Yousefi, Nooshin
    Zhou, Jian
    Rodgers, Mark D.
    Coit, David
    APPLIED ENERGY, 2021, 290
  • [9] SIMULATION-BASED DEEP REINFORCEMENT LEARNING FOR MODULAR PRODUCTION SYSTEMS
    Feldkamp, Niclas
    Bergmann, Soeren
    Strassburger, Steffen
    2020 WINTER SIMULATION CONFERENCE (WSC), 2020, : 1596 - 1607
  • [10] UCAV Path Planning Algorithm Based on Deep Reinforcement Learning
    Zheng, Kaiyuan
    Gao, Jingpeng
    Shen, Liangxi
    IMAGE AND GRAPHICS, ICIG 2019, PT II, 2019, 11902 : 702 - 714