Comprehensive Ocean Information-Enabled AUV Motion Planning Based on Reinforcement Learning

被引:5
|
作者
Li, Yun [1 ,2 ]
He, Xinqi [3 ]
Lu, Zhenkun [3 ]
Jing, Peiguang [4 ]
Su, Yishan [4 ]
机构
[1] Guangxi Univ Finance & Econ, Sch Big Data & Artificial Intelligence, Nanning 530003, Peoples R China
[2] Guangxi Big Data Anal Taxat Res Ctr Engn, Nanning 530003, Peoples R China
[3] Guangxi Minzu Univ, Sch Elect Informat, Nanning 530006, Peoples R China
[4] Tianjin Univ, Sch Elect & Informat Engn, Weijin Rd, Tianjin 300072, Peoples R China
基金
中国国家自然科学基金;
关键词
Internet-of-Underwater-Things (IoUT); motion planning; reinforcement learning; autonomous underwater vehicle (AUV); POLICY; ALGORITHM;
D O I
10.3390/rs15123077
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Motion planning based on the reinforcement learning algorithms of the autonomous underwater vehicle (AUV) has shown great potential. Motion planning algorithms are primarily utilized for path planning and trajectory-tracking. However, prior studies have been confronted with some limitations. The time-varying ocean current affects algorithmic sampling and AUV motion and then leads to an overestimation error during path planning. In addition, the ocean current makes it easy to fall into local optima during trajectory planning. To address these problems, this paper presents a reinforcement learning-based motion planning algorithm with comprehensive ocean information (RLBMPA-COI). First, we introduce real ocean data to construct a time-varying ocean current motion model. Then, comprehensive ocean information and AUV motion position are introduced, and the objective function is optimized in the state-action value network to reduce overestimation errors. Finally, state transfer and reward functions are designed based on real ocean current data to achieve multi-objective path planning and adaptive event triggering in trajectorytracking to improve robustness and adaptability. The numerical simulation results show that the proposed algorithm has a better path planning ability and a more robust trajectory-tracking effect than those of traditional reinforcement learning algorithms.
引用
收藏
页数:22
相关论文
共 50 条
  • [21] Reinforcement learning based motion planning of dynamic manipulation task for manipulator
    Eng. Training Center, Shanghai Jiaotong Univ., Shanghai 200240, China
    Xitong Fangzhen Xuebao, 2006, 9 (2537-2540):
  • [22] SARSA-based reinforcement learning for motion planning in Serial Manipulators
    Aleo, Ignazio
    Arena, Paolo
    Patane, Luca
    2010 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS IJCNN 2010, 2010,
  • [23] Motion Planning for Human-Robot Collaboration based on Reinforcement Learning
    Yu, Tian
    Chang, Qing
    2022 IEEE 18TH INTERNATIONAL CONFERENCE ON AUTOMATION SCIENCE AND ENGINEERING (CASE), 2022, : 1866 - 1871
  • [24] Manipulator Motion Planning based on Actor-Critic Reinforcement Learning
    Li, Qiang
    Nie, Jun
    Wang, Haixia
    Lu, Xiao
    Song, Shibin
    2021 PROCEEDINGS OF THE 40TH CHINESE CONTROL CONFERENCE (CCC), 2021, : 4248 - 4254
  • [25] Harnessing Reinforcement Learning for Neural Motion Planning
    Jurgenson, Tom
    Tamar, Aviv
    ROBOTICS: SCIENCE AND SYSTEMS XV, 2019,
  • [26] Federated reinforcement learning for generalizable motion planning
    Yuan, Zhenyuan
    Xu, Siyuan
    Zhu, Minghui
    2023 AMERICAN CONTROL CONFERENCE, ACC, 2023, : 78 - 83
  • [27] Adaptive energy-efficient reinforcement learning for AUV 3D motion planning in complex underwater environments
    Wen, Jiayi
    Wang, Anqing
    Zhu, Jingwei
    Xia, Fengbei
    Peng, Zhouhua
    Zhang, Weidong
    OCEAN ENGINEERING, 2024, 312
  • [28] A Reinforcement Learning-Boosted Motion Planning Framework: Comprehensive Generalization Performance in Autonomous Driving
    Trauth, Rainer
    Hobmeier, Alexander
    Betz, Johannes
    2024 35TH IEEE INTELLIGENT VEHICLES SYMPOSIUM, IEEE IV 2024, 2024, : 2413 - 2420
  • [29] Development of Applicable Reinforcement Learning Compensator Using Ranking Information for AUV
    Yashiro, Yusuke
    Eguchi, Kazuki
    Imamura, Rintaro
    Arai, Sachiyo
    OCEANS 2022, 2022,
  • [30] Reinforcement Learning based Negotiation-aware Motion Planning of Autonomous Vehicles
    Wang, Zhitao
    Zhuang, Yuzheng
    Gu, Qiang
    Chen, Dong
    Zhang, Hongbo
    Liu, Wulong
    2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2021, : 4532 - 4537