A COLREGs compliance reinforcement learning approach for USV manoeuvring in track-following and collision avoidance problems

Simple item page
dc.contributor.authorSonntag, Valentin
dc.contributor.authorPerrusquía, Adolfo
dc.contributor.authorTsourdos, Antonios
dc.contributor.authorGuo, Weisi
dc.date.accessioned2025-01-09T14:15:58Z
dc.date.available2025-01-09T14:15:58Z
dc.date.freetoread2025-01-09
dc.date.issued2025-01-15
dc.date.pubOnline2024-12-02
dc.description.abstractThe development of new technologies for autonomous platforms has allowed their integration into sea mine countermeasures. This has allowed to remove the personnel from the potential danger by having the mine search task performed by an unmanned surface vessel (USV). Traditional intelligent systems are built by agglomerating hand-coded behaviours that determine how a good manoeuvre looks like. This induces cognitive bias into the pre-defined behaviours that can violate safety and regulatory rules imposed by the COLREGs. To alleviate this issue, this paper proposes a COLREGs compliant reinforcement learning (RL) approach that gives a solution for the autonomous navigation of USVs. A custom simulation environment is developed. The RL agents are trained to deal with path-following problem with obstacle avoidance capabilities. A custom reward function is defined to consider the turning disks for the agent's decision process. A smoothing decision feature is used to smooth the transitions between consecutive actions. The results demonstrate good convergence and high performance under different scenarios. The collision avoidance with COLREGs compliances shows the effectiveness of the proposed approach under several scenarios with static and moving obstacles.
dc.description.journalNameOcean Engineering
dc.identifier.citationSonntag V, Perrusquía A, Tsourdos A, Guo W. (2025) A COLREGs compliance reinforcement learning approach for USV manoeuvring in track-following and collision avoidance problems. Ocean Engineering, Volume 316, January 2025, Article number 119907
dc.identifier.elementsID560119
dc.identifier.issn0029-8018
dc.identifier.paperNo119907
dc.identifier.urihttps://doi.org/10.1016/j.oceaneng.2024.119907
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/23344
dc.identifier.volumeNo316
dc.languageEnglish
dc.language.isoen
dc.publisherElsevier
dc.publisher.urihttps://www.sciencedirect.com/science/article/pii/S0029801824032451?via%3Dihub
dc.rightsAttribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subject4012 Fluid Mechanics and Thermal Engineering
dc.subject4005 Civil Engineering
dc.subject4015 Maritime Engineering
dc.subject40 Engineering
dc.subject14 Life Below Water
dc.subjectCivil Engineering
dc.subject4005 Civil engineering
dc.subject4012 Fluid mechanics and thermal engineering
dc.subject4015 Maritime engineering
dc.subjectUSV
dc.subjectCOLREGs
dc.subjectReinforcement learning
dc.subjectReward design
dc.subjectSmoothing decision feature
dc.titleA COLREGs compliance reinforcement learning approach for USV manoeuvring in track-following and collision avoidance problems
dc.typeArticle
dc.type.subtypeJournal Article
dcterms.dateAccepted2024-11-22

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
A_COLREGs_compliance-2024.pdf
Size:
3.46 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Plain Text
Description:
Download

Collections

Staff publications (SATM)