Skip to content
Extra Form
Abstract Developing a collision avoidance system which can operate in an unpredictable environment is a
challenging task. Especially in congested sea areas, each ship should continuously make decisions to
avoid collisions with other ships while complying with the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs). In this study, we proposed a robust and efficient method to collision avoidance for multi-ships based on the Deep Reinforcement Learning (DRL). The proposed method directly maps the states of the encountered target ships to an own ship’s steering commands related to rudder angle using the Deep Neural Network (DNN). This DNN is trained over the multi-ships on various situations using the policy gradient based DRL algorithm. However, the typical feedforward DNNs used in the domain require a fixed-dimensional input. To handle the multi-ship collision avoidance problem, we category the encountered target ships into four regions in terms of COLREGs for the purpose of fixing the input size. We performed a variety of simulation scenarios to verify the effectiveness and efficiency of the proposed method. The simulation results show that the proposed method has the capabilities to guarantee the collision avoidance of multi-ships while ensuring following their predefined paths.
Publication Date 2019-05-16

조로만, 노명일, "강화 학습 기반의 다 선박 충돌 회피 알고리즘 연구", 2019년도 대한조선학회 춘계학술발표회, 제주, pp. 186, 2019.05.15-17


List of Articles
번호 분류 제목 Publication Date
506 Conference Chairman Advanced Ship Tech V: Design, Analysis & Construction 1, ISOPE(International Society of Offshore and Polar Engineers) 2016, Rhodes, Greece, 2016.06.26-07.01 2016-06-30
505 Conference Chairman Advanced Ship Tech VIII: Shipbuilding Simulation: ISOPE(International Society of Offshore and Polar Engineers) 2015, Hawaii, USA, 2015.06.21-26 2015-06-25
504 International Conference Bo-Hyun Lee, Kyoung-Sik Chang, Bum-Sang Yoon, Joo-Sung Lee, Myung-Il Roh, "Large Eddy Simulation of Fully Turbulent Channel Flow Using Variational Multiscale Method", Proceedings of the 23rd Asian-Pacific TEAM(Technical Exchange and Advisory Meeting on Marine Structures) 2009, Kaohsiung, Taiwan, pp. 93-97, 2009.11.30-12.03 file 2009-11-30
503 Conference Chairman Computational Design and Optimization 4, ACDDE(Asian Conference on Design and Digital Engineering) 2018, Okinawa, Japan, 2018.11.01-03 2018-11-02
502 Conference Chairman Computational Design and Optimization I, ACDDE(Asian Conference on Design and Digital Engineering) 2017, Zhangjiajie, China, 2017.08.24-27 2017-08-25
501 Conference Chairman Day 4, SUTTC(The Society for Underwater Technology Technical Conference) 2016, Beijing, China, 2016.09.26-09.30 2016-09-29
500 Conference Chairman Design & Architecture & Shipbuilding I, ACDDE (Asian Conference on Design and Digital Engineering) 2016, Jeju, Korea, 2016.10.25-28 2016-10-26
499 Conference Chairman Design and Production in Maritime Engineering I, PRADS(International Symposium on Practical Design of Ships and Other Floating Structures) 2016, Copenhagen, Denmark, 2016.09.04-09.08 2016-09-07
498 Conference Chairman Digital Manufacturing, 2013년도 한국CAD/CAM학회 하계학술발표회, 서울, 2013.08.14 2013-08-14
497 International Conference Do-Hyun Chun, Myung-Il Roh, Hye-Won Lee, "Deep Reinforcement Learning-Based Ship Collision Avoidance Considering Collision Risk", Proceedings of TEAM 2022, Istanbul, Turkey, pp. 268, 2021.12.06-07 file 2021-12-07
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