COLREGs-Compliant Multi-Ship Collision Avoidance Based on Multi-Agent Reinforcement Learning Technique
The congestion of waterways can easily lead to traffic hazards. Moreover, according to the data, the majority of sea collisions are caused by human error and the failure to comply with the Convention on the International Regulation for the preventing Collision at Sea (COLREGs). To avoid this situati...
Published in: | Journal of Marine Science and Engineering |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2022
|
Subjects: | |
Online Access: | https://doi.org/10.3390/jmse10101431 https://doaj.org/article/b1c2966365bc4db18ff5769ec93acdda |
id |
ftdoajarticles:oai:doaj.org/article:b1c2966365bc4db18ff5769ec93acdda |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:b1c2966365bc4db18ff5769ec93acdda 2023-05-15T17:53:28+02:00 COLREGs-Compliant Multi-Ship Collision Avoidance Based on Multi-Agent Reinforcement Learning Technique Guan Wei Wang Kuo 2022-10-01T00:00:00Z https://doi.org/10.3390/jmse10101431 https://doaj.org/article/b1c2966365bc4db18ff5769ec93acdda EN eng MDPI AG https://www.mdpi.com/2077-1312/10/10/1431 https://doaj.org/toc/2077-1312 doi:10.3390/jmse10101431 2077-1312 https://doaj.org/article/b1c2966365bc4db18ff5769ec93acdda Journal of Marine Science and Engineering, Vol 10, Iss 1431, p 1431 (2022) multi-ship collision avoidance COLREGs multi-agent reinforcement learning ORCA ship maneuverability Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581 article 2022 ftdoajarticles https://doi.org/10.3390/jmse10101431 2022-12-30T21:28:31Z The congestion of waterways can easily lead to traffic hazards. Moreover, according to the data, the majority of sea collisions are caused by human error and the failure to comply with the Convention on the International Regulation for the preventing Collision at Sea (COLREGs). To avoid this situation, ship automatic collision avoidance has become one of the most important research issues in the field of marine engineering. In this study, an efficient method is proposed to solve multi-ship collision avoidance problems based on the multi-agent reinforcement learning (MARL) algorithm. Firstly, the COLREGs and ship maneuverability are considered for achieving multi-ship collision avoidance. Subsequently, the Optimal Reciprocal Collision Avoidance (ORCA) algorithm is utilized to detect and reduce the risk of collision. Ships can operate at the safe velocity computed by the ORCA algorithm to avoid collisions. Finally, the Nomoto three-degrees-of-freedom (3-DOF) model is used to simulate the maneuvers of ships. According to the above information and algorithms, this study designs and improves the state space, action space and reward function. For validating the effectiveness of the method, this study designs various simulation scenarios with thorough performance evaluations. The simulation results indicate that the proposed method is flexible and scalable in solving multi-ship collision avoidance, complying with COLREGs in various scenarios. Article in Journal/Newspaper Orca Directory of Open Access Journals: DOAJ Articles Journal of Marine Science and Engineering 10 10 1431 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
multi-ship collision avoidance COLREGs multi-agent reinforcement learning ORCA ship maneuverability Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581 |
spellingShingle |
multi-ship collision avoidance COLREGs multi-agent reinforcement learning ORCA ship maneuverability Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581 Guan Wei Wang Kuo COLREGs-Compliant Multi-Ship Collision Avoidance Based on Multi-Agent Reinforcement Learning Technique |
topic_facet |
multi-ship collision avoidance COLREGs multi-agent reinforcement learning ORCA ship maneuverability Naval architecture. Shipbuilding. Marine engineering VM1-989 Oceanography GC1-1581 |
description |
The congestion of waterways can easily lead to traffic hazards. Moreover, according to the data, the majority of sea collisions are caused by human error and the failure to comply with the Convention on the International Regulation for the preventing Collision at Sea (COLREGs). To avoid this situation, ship automatic collision avoidance has become one of the most important research issues in the field of marine engineering. In this study, an efficient method is proposed to solve multi-ship collision avoidance problems based on the multi-agent reinforcement learning (MARL) algorithm. Firstly, the COLREGs and ship maneuverability are considered for achieving multi-ship collision avoidance. Subsequently, the Optimal Reciprocal Collision Avoidance (ORCA) algorithm is utilized to detect and reduce the risk of collision. Ships can operate at the safe velocity computed by the ORCA algorithm to avoid collisions. Finally, the Nomoto three-degrees-of-freedom (3-DOF) model is used to simulate the maneuvers of ships. According to the above information and algorithms, this study designs and improves the state space, action space and reward function. For validating the effectiveness of the method, this study designs various simulation scenarios with thorough performance evaluations. The simulation results indicate that the proposed method is flexible and scalable in solving multi-ship collision avoidance, complying with COLREGs in various scenarios. |
format |
Article in Journal/Newspaper |
author |
Guan Wei Wang Kuo |
author_facet |
Guan Wei Wang Kuo |
author_sort |
Guan Wei |
title |
COLREGs-Compliant Multi-Ship Collision Avoidance Based on Multi-Agent Reinforcement Learning Technique |
title_short |
COLREGs-Compliant Multi-Ship Collision Avoidance Based on Multi-Agent Reinforcement Learning Technique |
title_full |
COLREGs-Compliant Multi-Ship Collision Avoidance Based on Multi-Agent Reinforcement Learning Technique |
title_fullStr |
COLREGs-Compliant Multi-Ship Collision Avoidance Based on Multi-Agent Reinforcement Learning Technique |
title_full_unstemmed |
COLREGs-Compliant Multi-Ship Collision Avoidance Based on Multi-Agent Reinforcement Learning Technique |
title_sort |
colregs-compliant multi-ship collision avoidance based on multi-agent reinforcement learning technique |
publisher |
MDPI AG |
publishDate |
2022 |
url |
https://doi.org/10.3390/jmse10101431 https://doaj.org/article/b1c2966365bc4db18ff5769ec93acdda |
genre |
Orca |
genre_facet |
Orca |
op_source |
Journal of Marine Science and Engineering, Vol 10, Iss 1431, p 1431 (2022) |
op_relation |
https://www.mdpi.com/2077-1312/10/10/1431 https://doaj.org/toc/2077-1312 doi:10.3390/jmse10101431 2077-1312 https://doaj.org/article/b1c2966365bc4db18ff5769ec93acdda |
op_doi |
https://doi.org/10.3390/jmse10101431 |
container_title |
Journal of Marine Science and Engineering |
container_volume |
10 |
container_issue |
10 |
container_start_page |
1431 |
_version_ |
1766161184764985344 |