Deep reinforcement learning model for Multi-Ship collision avoidance decision making design implementation and performance analysis
Abstract This paper proposes a novel multi-ship collision avoidance decision-making model based on deep reinforcement learning (DRL). The model addresses the critical challenge of preventing ship collisions while maintaining efficient navigation in complex maritime environments. Our innovation lies...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-05636-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849402632812101632 |
|---|---|
| author | Rongjun Pan Wei Zhang Shijie Wang Shuhua Kang |
| author_facet | Rongjun Pan Wei Zhang Shijie Wang Shuhua Kang |
| author_sort | Rongjun Pan |
| collection | DOAJ |
| description | Abstract This paper proposes a novel multi-ship collision avoidance decision-making model based on deep reinforcement learning (DRL). The model addresses the critical challenge of preventing ship collisions while maintaining efficient navigation in complex maritime environments. Our innovation lies in the integration of a comprehensive state representation capturing key inter-ship relationships, a reward function that dynamically balances safety, efficiency, and COLREGs compliance, and an enhanced DQN architecture with dueling networks and double Q-learning specifically optimized for maritime scenarios. Experimental results demonstrate that our approach significantly outperforms state-of-the-art DRL methods, achieving a 30.8% reduction in collision rates compared to recent multi-agent DRL implementations, 20% improvement in safety distances, and enhanced regulatory compliance across diverse scenarios. The model shows superior scalability in high-density traffic, with only 12.6% performance degradation compared to 18.4–45.2% for baseline methods. These advancements provide a promising solution for autonomous ship navigation and maritime safety enhancement. |
| format | Article |
| id | doaj-art-1747a2deca1446adaca2ef009c79b7d7 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-1747a2deca1446adaca2ef009c79b7d72025-08-20T03:37:30ZengNature PortfolioScientific Reports2045-23222025-07-0115112110.1038/s41598-025-05636-3Deep reinforcement learning model for Multi-Ship collision avoidance decision making design implementation and performance analysisRongjun Pan0Wei Zhang1Shijie Wang2Shuhua Kang3School of Navigation, GongQing Institute of Science and TechnologyCollege of Transport & Communications, Shanghai Maritime UniversitySchool of Navigation, GongQing Institute of Science and TechnologySchool of Navigation and Transportation, QuanZhou Ocean InstituteAbstract This paper proposes a novel multi-ship collision avoidance decision-making model based on deep reinforcement learning (DRL). The model addresses the critical challenge of preventing ship collisions while maintaining efficient navigation in complex maritime environments. Our innovation lies in the integration of a comprehensive state representation capturing key inter-ship relationships, a reward function that dynamically balances safety, efficiency, and COLREGs compliance, and an enhanced DQN architecture with dueling networks and double Q-learning specifically optimized for maritime scenarios. Experimental results demonstrate that our approach significantly outperforms state-of-the-art DRL methods, achieving a 30.8% reduction in collision rates compared to recent multi-agent DRL implementations, 20% improvement in safety distances, and enhanced regulatory compliance across diverse scenarios. The model shows superior scalability in high-density traffic, with only 12.6% performance degradation compared to 18.4–45.2% for baseline methods. These advancements provide a promising solution for autonomous ship navigation and maritime safety enhancement.https://doi.org/10.1038/s41598-025-05636-3Deep reinforcement learningMaritime safetyCollision avoidanceMulti-Ship navigationDecision-MakingMaritime transportation |
| spellingShingle | Rongjun Pan Wei Zhang Shijie Wang Shuhua Kang Deep reinforcement learning model for Multi-Ship collision avoidance decision making design implementation and performance analysis Scientific Reports Deep reinforcement learning Maritime safety Collision avoidance Multi-Ship navigation Decision-Making Maritime transportation |
| title | Deep reinforcement learning model for Multi-Ship collision avoidance decision making design implementation and performance analysis |
| title_full | Deep reinforcement learning model for Multi-Ship collision avoidance decision making design implementation and performance analysis |
| title_fullStr | Deep reinforcement learning model for Multi-Ship collision avoidance decision making design implementation and performance analysis |
| title_full_unstemmed | Deep reinforcement learning model for Multi-Ship collision avoidance decision making design implementation and performance analysis |
| title_short | Deep reinforcement learning model for Multi-Ship collision avoidance decision making design implementation and performance analysis |
| title_sort | deep reinforcement learning model for multi ship collision avoidance decision making design implementation and performance analysis |
| topic | Deep reinforcement learning Maritime safety Collision avoidance Multi-Ship navigation Decision-Making Maritime transportation |
| url | https://doi.org/10.1038/s41598-025-05636-3 |
| work_keys_str_mv | AT rongjunpan deepreinforcementlearningmodelformultishipcollisionavoidancedecisionmakingdesignimplementationandperformanceanalysis AT weizhang deepreinforcementlearningmodelformultishipcollisionavoidancedecisionmakingdesignimplementationandperformanceanalysis AT shijiewang deepreinforcementlearningmodelformultishipcollisionavoidancedecisionmakingdesignimplementationandperformanceanalysis AT shuhuakang deepreinforcementlearningmodelformultishipcollisionavoidancedecisionmakingdesignimplementationandperformanceanalysis |