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
International Conference
2019.08.06 15:07
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 2019, Rotterdam, Netherlands, pp. 85-88, 2019.09.24-26
조회 수 272
| 첨부 '1' |
|---|
| 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 |
-
Read More
김진혁, 노명일, 김기수, 여인창, 남정우, 이상현, 장영훈, "딥 러닝을 이용한 선형 성능의 우열 관계 예측", 2021년도 대한조선학회 춘계학술발표회, 인천, pp. 572, 2021.05.13-14
CategoryDomestic Conference -
Read More
여인창, 노명일, 김진혁, 김기수, "선형 성능의 정성적 평가를 위한 딥 러닝 기반 이미지 시각화 방법", 2021년도 대한조선학회 춘계학술발표회, 인천, pp. 573, 2021.05.13-14
CategoryDomestic Conference -
Read More
이종혁, 노명일, 김기수, 이혜원, "선박 및 해양 구조물의 자동 접이안 시뮬레이션 방법", 2021년도 대한조선학회 춘계학술발표회, 인천, pp. 562, 2021.05.13-14
CategoryDomestic Conference -
Read More
하지상, 노명일, 김진혁, 김기수, "경로 탐색 알고리즘과 전문가 시스템을 활용한 배관 경로 생성 최적화 방법", 2021년도 대한조선학회 춘계학술발표회, 인천, pp. 409, 2021.05.13-14
CategoryDomestic Conference -
Read More
노명일, "선박 설계, 생산 및 운용 단계에서의 딥 러닝 활용 예, 2020년도 선박해양플랜트구조연구회 워크샵, 2021.02.18
CategoryDomestic Conference -
Read More
김기수, 김종웅, 노명일, "대기 행렬과 DEVS 기반 함정의 승조원 운영 최적화 방법", 2020년도 한국CDE학회 동계학술발표회, 제주, pp. 311, 2020.11.25-28
CategoryDomestic Conference -
Read More
Ki-Su Kim, Myung-Il Roh, "Optimization of the Arrangement Design of a Ship Considering the Multiple Performance", Proceedings of ACSMO 2020, Seoul, Korea, pp. 167, 2020.11.23-25
CategoryInternational Conference -
Read More
Jisang Ha, Myung-Il Roh, Hye-Won Lee, Jong-Ho Eun, Jong-Jin Park, Hyun-Joe Kim, "A Method of the Collision Avoidance of a Ship Using Real-time AIS Data", Proceedings of ACSMO 2020, Seoul, Korea, pp. 106, 2020.11.23-25
CategoryInternational Conference -
Read More
하지상, 노명일, 김기수, "전문가 시스템과 최적화 기법 기반 배관 라우팅 방법", 2020년도 대한조선학회 추계학술발표회, 창원, pp. 402, 2020.11.05-06
CategoryDomestic Conference -
Read More
이준범, 노명일, 김기수, 한기민, 이갑헌, "딥 러닝을 이용한 해기상 및 소요 마력 예측 모델 개발", 2020년도 대한조선학회 추계학술발표회, 창원, pp. 453-454, 2020.11.05-06
CategoryDomestic Conference