Skip to content
Extra Form
Abstract Developing a high-level autonomous collision avoidance system for ships which can operate in an unstructured and unpredictable environment is a challenging task. Especially in the congested sea areas, each ship should continuously make decisions to avoid collisions with many other ships in the busy and complex waterway. Furthermore, recent reports indicate that a large number of collision accidents at sea are caused by or related to human decision failures with lack of situational awareness and failure to comply with International Regulations for Preventing Collisions at Sea (COLREGs). In this study, we propose a robust and efficient method to collision avoidance problems of multi-ships based on the deep reinforcement learning (DRL) algorithm. The proposed method directly maps the states of encountered ships to an ownship’s steering commands in terms of the rudder angle using a deep neural network (DNN). This DNN is trained over multi-ships on rich encountering situations using the policy gradient based DRL algorithm. To handle multiple encountered ships, we classify them into four regions based on COLREGs, and only consider the nearest ship in each region. We validate the proposed method in a variety of simulated scenarios thorough performance evaluations. The result shows that the proposed method can find time efficient, collision-free paths for multi-ships. Also, it shows that the proposed method has excellent adaptability to unknown complex environments.
Publication Date 2019-09-24

Luman Zhao, Myung-Il Roh, Hye-Won Lee, Do-Hyun Chun, Sung-Jun Lee, "A Collision Avoidance Method of Multi-ships Based on Deep Reinforcement Learning Considering COLREGs", Proceedings of ICCAS(International Conference on Computer Applications in Shipbuilding) 2019, Rotterdam, Netherlands, pp. 85-88, 2019.09.24-26


List of Articles
번호 분류 제목 Publication Date
506 International Conference Jisang Ha, Myung-Il Roh, Min-Chul Kong, Mijin Kim, Jeoungyoun Kim, Nam-Kug Ku, "An Automated Method for Pipe Routing in Ship Unit Modules", Proceedings of IMDC 2024, Amsterdam, Netherland, 2024.06.02-06 2024-06-02
505 International Conference Min-Chul Kong, Myung-Il Roh, In-Chang Yeo, In-Su Han, Dongki Min, Dongguen Jeong, "Methods for Graph Conversion and Pattern Recognition for P&IDs", Proceedings of IMDC 2024, Amsterdam, Netherland, 2024.06.02-06 2024-06-02
504 Domestic Conference 전도현, 노명일, 이혜원, "데이터 불확실성 기반 충돌 위험도 평가 및 강화 학습 기반 충돌 회피", 2024년도 스마트전기선박연구회 동계학술발표회, 부산, 2024.02.15-16 2024-02-16
503 Domestic Conference 박동규, 노명일, 하지상, "추진 체계 선정을 포함한 무인수상정 초기 제원 최적화 방법", 2024년도 한국CDE학회 동계학술발표회, 평창, p. 241, 2024.01.29-02.01 file 2024-01-31
502 Domestic Conference 공민철, 노명일, 하지상, 한인수, 김미진, 김정연, "선박 내 배관의 자동 배치를 위한 P&ID의 그래프 변환 방법", 2024년도 한국CDE학회 동계학술발표회, 평창, p. 129, 2024.01.29-02.01 file 2024-01-30
501 Domestic Conference 여인창, 노명일, 공민철, 유동훈, 진은석, "LIDAR를 이용한 선박의 위치 예측 알고리즘", 2024년도 한국CDE학회 동계학술발표회, 평창, p. 99, 2024.01.29-02.01 file 2024-01-30
500 Domestic Conference 한인수, 노명일, 공민철, 이정렬, 박서윤, "의미 유사도 기반의 선박 규정 검색 알고리즘", 2024년도 한국CDE학회 동계학술발표회, 평창, p.126, 2024.01.29-02.01 file 2024-01-30
499 Domestic Conference 김진혁, 노명일 ,여인창, "MLP 기반 상선의 선형 변환 방법", 2024년도 한국CDE학회 동계학술발표회, 평창, p.28, 2024.01.29-02.01 file 2024-01-30
498 Domestic Conference 김하연, 노명일, 하지상, "해상 장애물 추적을 위한 혼합 추적 방법", 2024년도 한국CDE학회 동계학술발표회, 평창, p. 94, 2024.01.29-02.01 file 2024-01-30
497 Domestic Conference 하지상, 노명일, 공민철, 한인수, 김미진, 김정연, "전문가 지식을 고려한 선박 유닛 모듈의 배관 배치 방법", 2024년도 한국CDE학회 동계학술발표회, 평창, pp. 124, 2024.01.29-02.01 file 2024-01-30
Board Pagination Prev 1 2 3 4 5 6 7 8 9 10 ... 51 Next
/ 51

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