Navigation and Obstacle Avoidance for USV in Autonomous Buoy Inspection: A Deep Reinforcement Learning Approach

To address the challenges of manual buoy inspection, this study enhances a previously proposed Unmanned Surface Vehicle (USV) inspection system by improving its navigation and obstacle avoidance capabilities using Proximal Policy Optimization (PPO). For improved usability, the entire system adopts a...

Full description

Saved in:
Bibliographic Details
Main Authors: Jianhui Wang, Zhiqiang Lu, Xunjie Hong, Zeye Wu, Weihua Li
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Journal of Marine Science and Engineering
Subjects:
Online Access:https://www.mdpi.com/2077-1312/13/5/843
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850126889266446336
author Jianhui Wang
Zhiqiang Lu
Xunjie Hong
Zeye Wu
Weihua Li
author_facet Jianhui Wang
Zhiqiang Lu
Xunjie Hong
Zeye Wu
Weihua Li
author_sort Jianhui Wang
collection DOAJ
description To address the challenges of manual buoy inspection, this study enhances a previously proposed Unmanned Surface Vehicle (USV) inspection system by improving its navigation and obstacle avoidance capabilities using Proximal Policy Optimization (PPO). For improved usability, the entire system adopts a fully end-to-end design, with an angular deviation weighting mechanism for stable circular navigation, a novel image-based radar encoding technique for obstacle perception and a decoupled navigation and obstacle avoidance architecture that splits the complex task into three independently trained modules. Experiments validate that both navigation modules exhibit robustness and generalization capabilities, while the obstacle avoidance module partially achieves International Regulations for Preventing Collisions at Sea (COLREGs)-compliant maneuvers. Further tests in continuous multi-buoy inspection tasks confirm the architecture’s effectiveness in integrating these modules to complete the full task.
format Article
id doaj-art-cc87a0a837c34f11a9d14ae6d8a7214d
institution OA Journals
issn 2077-1312
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Journal of Marine Science and Engineering
spelling doaj-art-cc87a0a837c34f11a9d14ae6d8a7214d2025-08-20T02:33:50ZengMDPI AGJournal of Marine Science and Engineering2077-13122025-04-0113584310.3390/jmse13050843Navigation and Obstacle Avoidance for USV in Autonomous Buoy Inspection: A Deep Reinforcement Learning ApproachJianhui Wang0Zhiqiang Lu1Xunjie Hong2Zeye Wu3Weihua Li4School of Intelligent Science and Engineering, Jinan University, Zhuhai 519000, ChinaSchool of International Energy, Jinan University, Zhuhai 519000, ChinaSchool of International Energy, Jinan University, Zhuhai 519000, ChinaSchool of International Energy, Jinan University, Zhuhai 519000, ChinaSchool of International Energy, Jinan University, Zhuhai 519000, ChinaTo address the challenges of manual buoy inspection, this study enhances a previously proposed Unmanned Surface Vehicle (USV) inspection system by improving its navigation and obstacle avoidance capabilities using Proximal Policy Optimization (PPO). For improved usability, the entire system adopts a fully end-to-end design, with an angular deviation weighting mechanism for stable circular navigation, a novel image-based radar encoding technique for obstacle perception and a decoupled navigation and obstacle avoidance architecture that splits the complex task into three independently trained modules. Experiments validate that both navigation modules exhibit robustness and generalization capabilities, while the obstacle avoidance module partially achieves International Regulations for Preventing Collisions at Sea (COLREGs)-compliant maneuvers. Further tests in continuous multi-buoy inspection tasks confirm the architecture’s effectiveness in integrating these modules to complete the full task.https://www.mdpi.com/2077-1312/13/5/843buoy inspectioncollision avoidancedeep reinforcement learning (DRL)proximal policy optimization (PPO)unmanned surface vehicle (USV)
spellingShingle Jianhui Wang
Zhiqiang Lu
Xunjie Hong
Zeye Wu
Weihua Li
Navigation and Obstacle Avoidance for USV in Autonomous Buoy Inspection: A Deep Reinforcement Learning Approach
Journal of Marine Science and Engineering
buoy inspection
collision avoidance
deep reinforcement learning (DRL)
proximal policy optimization (PPO)
unmanned surface vehicle (USV)
title Navigation and Obstacle Avoidance for USV in Autonomous Buoy Inspection: A Deep Reinforcement Learning Approach
title_full Navigation and Obstacle Avoidance for USV in Autonomous Buoy Inspection: A Deep Reinforcement Learning Approach
title_fullStr Navigation and Obstacle Avoidance for USV in Autonomous Buoy Inspection: A Deep Reinforcement Learning Approach
title_full_unstemmed Navigation and Obstacle Avoidance for USV in Autonomous Buoy Inspection: A Deep Reinforcement Learning Approach
title_short Navigation and Obstacle Avoidance for USV in Autonomous Buoy Inspection: A Deep Reinforcement Learning Approach
title_sort navigation and obstacle avoidance for usv in autonomous buoy inspection a deep reinforcement learning approach
topic buoy inspection
collision avoidance
deep reinforcement learning (DRL)
proximal policy optimization (PPO)
unmanned surface vehicle (USV)
url https://www.mdpi.com/2077-1312/13/5/843
work_keys_str_mv AT jianhuiwang navigationandobstacleavoidanceforusvinautonomousbuoyinspectionadeepreinforcementlearningapproach
AT zhiqianglu navigationandobstacleavoidanceforusvinautonomousbuoyinspectionadeepreinforcementlearningapproach
AT xunjiehong navigationandobstacleavoidanceforusvinautonomousbuoyinspectionadeepreinforcementlearningapproach
AT zeyewu navigationandobstacleavoidanceforusvinautonomousbuoyinspectionadeepreinforcementlearningapproach
AT weihuali navigationandobstacleavoidanceforusvinautonomousbuoyinspectionadeepreinforcementlearningapproach