Collision probability reduction method for tracking control in automatic docking/berthing using reinforcement learning

Wakita, Kouki; Akimoto, Youhei; Rachman, Dimas M.; Miyauchi, Yoshiki; Maki, Atsuo

doi:https://doi.org/10.1007/s00773-023-00962-5

Collision probability reduction method for tracking control in automatic docking/berthing using reinforcement learning

Wakita, Kouki; Akimoto, Youhei; Rachman, Dimas M. et al.

Journal of Marine Science and Technology (Japan), 2023, 28, 844-861

アクセス数:420件（2025-07-27 06:54 集計）

固定URL: https://hdl.handle.net/11094/93224

閲覧可能ファイル

ファイル	フォーマット	利用条件	サイズ	閲覧回数	利用開始日	説明	information
JMarineSciTechnol	pdf	なし	3.25 MB	72	2023.12.04

Creative Commons : 表示

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

タイトル	Collision probability reduction method for tracking control in automatic docking/berthing using reinforcement learning
著者	ORCID 0000-0003-0363-1396 0000-0003-0363-1396 著者名 Wakita, Kouki
	NRID 1000020709654 1000020709654 著者名 Akimoto, Youhei
	著者名 Rachman, Dimas M.
	著者名 Miyauchi, Yoshiki
	NRID 1000050556496 1000050556496 ORCID 0000-0002-2819-1297 0000-0002-2819-1297 researchmap permalink atsuo_maki atsuo_maki Scopus Author ID 24503751100 24503751100 著者名 Maki, Atsuo
キーワード等	Berthing control
	Reinforcement learning
	TD3
	Trajectory tracking
	VecTwin rudder
内容	The version of record of this article, first published in Journal of Marine Science and Technology (Japan), is available online at Publisher’s website: https://doi.org/10.1007/s00773-023-00962-5
抄録	Automation of berthing maneuvers in shipping is a pressing issue as the berthing maneuver is one of the most stressful tasks seafarers undertake. Berthing control problems are often tackled by tracking a predefined trajectory or path. Maintaining a tracking error of zero under an uncertain environment is impossible; the tracking controller is nonetheless required to bring vessels close to desired berths. The tracking controller must prioritize the avoidance of tracking errors that may cause collisions with obstacles. This paper proposes a training method based on reinforcement learning for a trajectory tracking controller that reduces the probability of collisions with static obstacles. Via numerical simulations, we show that the proposed method reduces the probability of collisions during berthing maneuvers. Furthermore, this paper shows the tracking performance in a model experiment.
出版者	Springer
収録物名	Journal of Marine Science and Technology (Japan)
巻(号)	28
ページ	844-861
刊行年月	2023-10-19
言語	英語
ハンドルURL	https://hdl.handle.net/11094/93224
PISSN	09484280
関連情報 (isIdenticalTo)	DOI (出版社版) https://doi.org/10.1007/s00773-023-00962-5
アクセス権	open access
権利情報	This article is licensed under a Creative Commons Attribution 4.0 International License.
出版タイプ	Version of Record
カテゴリ	学術雑誌論文 Journal Article

資源タイプ	学術雑誌論文
ローカル資源タイプ	学術雑誌論文
DCMI資源タイプ	text
DCTERMS.bibliographicCitation	Journal of Marine Science and Technology (Japan). 2023, 28, p. 844-861
DC.title	Collision probability reduction method for tracking control in automatic docking/berthing using reinforcement learning
DC.creator	Wakita, Kouki
	Akimoto, Youhei
	Rachman, Dimas M.
	Miyauchi, Yoshiki
	Maki, Atsuo
DC.publisher	Springer
DC.language' scheme='DCTERMS.RFC1766	英語
DC.type' scheme='DCTERMS.DCMIType	text
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2023-10-19
DC.identifier	https://doi.org/10.1007/s00773-023-00962-5
DC.subject	Berthing control
	Reinforcement learning
	TD3
	Trajectory tracking
	VecTwin rudder
DC.description	The version of record of this article, first published in Journal of Marine Science and Technology (Japan), is available online at Publisher’s website: https://doi.org/10.1007/s00773-023-00962-5
DCTERMS.abstract	Automation of berthing maneuvers in shipping is a pressing issue as the berthing maneuver is one of the most stressful tasks seafarers undertake. Berthing control problems are often tackled by tracking a predefined trajectory or path. Maintaining a tracking error of zero under an uncertain environment is impossible; the tracking controller is nonetheless required to bring vessels close to desired berths. The tracking controller must prioritize the avoidance of tracking errors that may cause collisions with obstacles. This paper proposes a training method based on reinforcement learning for a trajectory tracking controller that reduces the probability of collisions with static obstacles. Via numerical simulations, we show that the proposed method reduces the probability of collisions during berthing maneuvers. Furthermore, this paper shows the tracking performance in a model experiment.
DC.rights	This article is licensed under a Creative Commons Attribution 4.0 International License.
DC.format	93224
citation_title	Collision probability reduction method for tracking control in automatic docking/berthing using reinforcement learning
citation_author	Wakita, Kouki
	Akimoto, Youhei
	Rachman, Dimas M.
	Miyauchi, Yoshiki
	Maki, Atsuo
citation_publisher	Springer
citation_language	英語
citation_date	2023-10-19
citation_journal_title	Journal of Marine Science and Technology (Japan)
citation_volume	28
citation_firstpage	844
citation_lastpage	861
citation_doi	https://doi.org/10.1007/s00773-023-00962-5
citation_public_url	https://hdl.handle.net/11094/93224

Collision probability reduction method for tracking control in automatic docking/berthing using reinforcement learning

閲覧可能ファイル

論文情報

論文詳細を表示