Deep reinforcement learning for integrated vessel path planning with safe anchorage allocation
This study addresses vessel path planning and anchorage allocation through a reinforcement learning approach. To improve maritime safety and efficiency, we developed an integrated system that combines Deep Q-Network and Artificial Potential Field concepts for path generation. The model implements a...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Faculty of Mechanical Engineering and Naval Architecture
2025-01-01
|
| Series: | Brodogradnja |
| Subjects: | |
| Online Access: | https://hrcak.srce.hr/file/480772 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850209688866521088 |
|---|---|
| author | Gil-Ho Shin Hyun Yang |
| author_facet | Gil-Ho Shin Hyun Yang |
| author_sort | Gil-Ho Shin |
| collection | DOAJ |
| description | This study addresses vessel path planning and anchorage allocation through a reinforcement learning approach. To improve maritime safety and efficiency, we developed an integrated system that combines Deep Q-Network and Artificial Potential Field concepts for path generation. The model implements a specialized grid extension method that accounts for actual vessel dimensions and wind direction, while incorporating differentiated safety distances for each anchorage area. Experimental validation using Automatic Identification System (AIS) data demonstrated that the system successfully generated efficient routes while maintaining all safety distance requirements during both navigation and anchoring phases. Additionally, the system ensured practicality through path simplification using the Douglas-Peucker algorithm while maintaining safety standards. The visualized optimal paths enhance navigational guidance, thereby improving both maritime traffic safety and port operational efficiency. |
| format | Article |
| id | doaj-art-ee90781fb81d4a09a068f9057ffdc64d |
| institution | OA Journals |
| issn | 0007-215X 1845-5859 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Faculty of Mechanical Engineering and Naval Architecture |
| record_format | Article |
| series | Brodogradnja |
| spelling | doaj-art-ee90781fb81d4a09a068f9057ffdc64d2025-08-20T02:09:56ZengFaculty of Mechanical Engineering and Naval ArchitectureBrodogradnja0007-215X1845-58592025-01-0176313210.21278/brod76305Deep reinforcement learning for integrated vessel path planning with safe anchorage allocationGil-Ho Shin0Hyun Yang1Graduate School of Korea Maritime and Ocean University, Busan, Republic of KoreaDivision of Maritime AI & Cyber Security, Korea Maritime and Ocean University, Busan, Republic of KoreaThis study addresses vessel path planning and anchorage allocation through a reinforcement learning approach. To improve maritime safety and efficiency, we developed an integrated system that combines Deep Q-Network and Artificial Potential Field concepts for path generation. The model implements a specialized grid extension method that accounts for actual vessel dimensions and wind direction, while incorporating differentiated safety distances for each anchorage area. Experimental validation using Automatic Identification System (AIS) data demonstrated that the system successfully generated efficient routes while maintaining all safety distance requirements during both navigation and anchoring phases. Additionally, the system ensured practicality through path simplification using the Douglas-Peucker algorithm while maintaining safety standards. The visualized optimal paths enhance navigational guidance, thereby improving both maritime traffic safety and port operational efficiency.https://hrcak.srce.hr/file/480772maritime safetyreinforcement learningvessel traffic services (vts)path planningdeep reinforcement learning |
| spellingShingle | Gil-Ho Shin Hyun Yang Deep reinforcement learning for integrated vessel path planning with safe anchorage allocation Brodogradnja maritime safety reinforcement learning vessel traffic services (vts) path planning deep reinforcement learning |
| title | Deep reinforcement learning for integrated vessel path planning with safe anchorage allocation |
| title_full | Deep reinforcement learning for integrated vessel path planning with safe anchorage allocation |
| title_fullStr | Deep reinforcement learning for integrated vessel path planning with safe anchorage allocation |
| title_full_unstemmed | Deep reinforcement learning for integrated vessel path planning with safe anchorage allocation |
| title_short | Deep reinforcement learning for integrated vessel path planning with safe anchorage allocation |
| title_sort | deep reinforcement learning for integrated vessel path planning with safe anchorage allocation |
| topic | maritime safety reinforcement learning vessel traffic services (vts) path planning deep reinforcement learning |
| url | https://hrcak.srce.hr/file/480772 |
| work_keys_str_mv | AT gilhoshin deepreinforcementlearningforintegratedvesselpathplanningwithsafeanchorageallocation AT hyunyang deepreinforcementlearningforintegratedvesselpathplanningwithsafeanchorageallocation |