Skip to content

Publication System Design Laboratory

Home Publication Thesis
✔ 뷰어로 보기
M.Sc. Thesis
2026.03.19 13:39

Seong-Won Choi, "An Improved Method for Ship Collision Avoidance Based on Deep Reinforcement Learning Using Attention Module and Mixture-of-Experts", M.Sc. Thesis, Seoul National University, 2026.02.25

SyDLab
조회 수 66
Atachment
첨부 '1'
?

단축키

Prev이전 문서

Next다음 문서

가 크게 작게 위로 아래로 댓글로 가기 인쇄
?

단축키

Prev이전 문서

Next다음 문서

가 크게 작게 위로 아래로 댓글로 가기 인쇄
Extra Form
Abstract In complex maritime environments, numerous ships operate simultaneously with overlapping routes, and the presence of confined waters, such as ports and coastal areas, increases the risk of collisions. In such environments, inappropriate maneuvers caused by human factors can lead to severe maritime accidents, including collisions and groundings. Therefore, autonomous navigation technology is essential for safe collision avoidance even in complex situations. Previous studies on traditional collision avoidance methods have explored rule-based methods such as RVO (Reciprocal Velocity Obstacles). However, in crowded environments with multiple ships, available maneuver options are limited, leading to excessively conservative decision-making. Furthermore, uncertainty due to sensor errors may degrade performance.
To overcome these limitations, this study proposes an improved collision avoidance method based on DRL (Deep Reinforcement Learning) using the SAC (Soft Actor-Critic) algorithm. Previous studies using CPA (Closest Point of Approach)-based collision risk assessment often encountered numerical instability when the relative velocity between a TS (target ship) and OS (own ship) approached zero. Furthermore, processing multiple obstacle inputs using CNN (Convolutional Neural Network)-based methods was inefficient. Another issue involved discontinuities in action, as smooth transitions between path following and collision avoidance were not achieved. To address these challenges, this study introduces an AR (Approach Rate)-based collision risk assessment method to ensure numerical stability. The inputs from multiple obstacles are processed using an attention module, enabling the proposed method to efficiently reflect variable obstacle information and facilitate decision-making focused on critical data. Additionally, a MoE (Mixture of-Experts) structure is applied to flexibly manage transitions between path following and collision avoidance, thereby enhancing learning efficiency.
The proposed method was validated through real-time simulations in a virtual environment and evaluated under conditions similar to those in actual sea areas by accounting for sensor error uncertainty. The validation results demonstrated that, compared with previous studies and the RVO method, the proposed method achieved a high collision avoidance success rate even in complex encounter situations and uncertain environments. Furthermore, it ensured robust, safe collision avoidance by maintaining a clearance distance during the approach to arrival.
Publication Date 2026-02-25

Seong-Won Choi, "An Improved Method for Ship Collision Avoidance Based on Deep Reinforcement Learning Using Attention Module and Mixture-of-Experts", M.Sc. Thesis, Seoul National University, 2026.02.25

위로 아래로 댓글로 가기 인쇄
에디터 선택하기
?

  1. Yun-Sik Kim, "An Improved Method for Detection and Tracking of Maritime Obstacles Based on Multiple Sensor Fusion", M.Sc. Thesis, Seoul National University, 2026.02.25

    CategoryM.Sc. Thesis
    Read More

  2. Seong-Won Choi, "An Improved Method for Ship Collision Avoidance Based on Deep Reinforcement Learning Using Attention Module and Mixture-of-Experts", M.Sc. Thesis, Seoul National University, 2026.02.25

    CategoryM.Sc. Thesis
    Read More

  3. Do-Hyun Chun, "A Method for Collision Avoidance of a Ship Based on Reinforcement Learning in Complex Maritime Situations", Ph.D. Thesis, Seoul National University, 2024.02.29

    CategoryPh.D. Thesis
    Read More

  4. Dong-Gyu Park, "An Optimization Method of Initial Principal Particulars of Small Naval Ships Considering Design Requirements", M.Sc. Thesis, Seoul National University, 2025.02.26

    CategoryM.Sc. Thesis
    Read More

  5. In-Su Han, "A Method for Searching Ship Regulations Based on Generative AI Considering the Intent of User’s Query", M.Sc. Thesis, Seoul National University, 2025.02.26

    CategoryM.Sc. Thesis
    Read More

  6. Ha-Yun Kim, "An Improved Method for Tracking of Maritime Obstacles Using Sensor Data", M.Sc. Thesis, Seoul National University, 2024.02.26

    CategoryM.Sc. Thesis
    Read More

  7. Jisang Ha, "Optimal Arrangement Method of Equipment and Pipes in the Engine Room of a Ship", Ph.D. Thesis, Seoul National University, 2023.08.29

    CategoryPh.D. Thesis
    Read More

  8. Dong-Geun Jeong, "A Method for Hierarchical Route Planning of Small ships in Coastal Area Using Quadtree Chart", M.Sc. Thesis, Seoul National University, 2023.02.24

    CategoryM.Sc. Thesis
    Read More

  9. Jeong-Ho Park, "A Method for Detection and Tracking of Maritime Obstacles Based on Multi-Video", M.Sc. Thesis, Seoul National University, 2023.02.24

    CategoryM.Sc. Thesis
    Read More

  10. Hamin Song, "Optimization of Crew Manning Considering Operation Scenarios of a Naval Ship", M.Sc. Thesis, Seoul National University, 2023.02.24

    CategoryM.Sc. Thesis
    Read More

  11. Yeongmin Jo, "A Method for the Path Tracking of Surrounding Ships Using Multiple Sensors", M.Sc. Thesis, Seoul National University, 2022.02.25

    CategoryM.Sc. Thesis
    Read More

  12. Won-Jae Lee, "Image-based Object Detection and Tracking Method for the Awareness around the Ship", M.Sc. Thesis, Seoul National University, 2021.02.26

    CategoryM.Sc. Thesis
    Read More

  13. June-Beom Lee, "Development of Prediction Models of Ship Power and Ocean Environmental Data Based on Deep Learning", M.Sc. Thesis, Seoul National University, 2021.02.26

    CategoryM.Sc. Thesis
    Read More

  14. Hye-Won Lee, "Wire Rope Contact Model and Crane Control Method for the Advanced Simulation and Automation of Block Erection", Ph.D. Thesis, Seoul National University, 2020.02.26

    CategoryPh.D. Thesis
    Read More

  15. Ki-Su Kim, "Assessment Method of the Fitness of Initial Arrangement Design of a Naval Ship", Ph.D. Thesis, Seoul National University, 2019.08.29

    CategoryPh.D. Thesis
    Read More

  16. Sung-Woo Park, "Data Mining Method for Offshore Structures based on Big Data Technology", M.Sc. Thesis, Seoul National University, 2019.02.26

    CategoryM.Sc. Thesis
    Read More

  17. Luman Zhao, "Simulation Method to Support Autonomous Navigation and Installation Operation of an Offshore Support Vessel", Ph.D. Thesis, Seoul National University, 2019.02.26

    CategoryPh.D. Thesis
    Read More

  18. Joo-Pil Lee, "Design of Wreck Removal Considering Safety and Economy", M.Sc. Thesis, Seoul National University, 2019.02.26

    CategoryM.Sc. Thesis
    Read More

  19. Seung-Ho Ham, "Integrated Simulation Method Based on Multibody Dynamics for Production Design Verification in Ships and Offshore Structures", Ph.D. Thesis, Seoul National University, 2018.08.29

    CategoryPh.D. Thesis
    Read More

  20. Sang-Hyun Lee, "Integrated Method for Layout Design of LNG FPSO Based on Optimization Technique and Expert System", M.Sc. Thesis, Seoul National University, 2018.02.26

    CategoryM.Sc. Thesis
    Read More
Board Pagination Prev 1 2 Next
/ 2

Powered by Xpress Engine / Designed by Sketchbook

sketchbook5, 스케치북5

sketchbook5, 스케치북5

나눔글꼴 설치 안내


이 PC에는 나눔글꼴이 설치되어 있지 않습니다.

이 사이트를 나눔글꼴로 보기 위해서는
나눔글꼴을 설치해야 합니다.

설치 취소