Adaptivity of a Multi-robot Coordination System Based on Functional Expressions Using Large Language Models

Sueoka, Yuichiro; Kato, Yuki; Yoshida, Takahiro; Osuka, Koichi; Yajima, Ryosuke; Chikushi, Shota; Nagatani, Keiji; Asama, Hajime

doi:https://doi.org/10.1007/978-3-032-04584-3_25

Adaptivity of a Multi-robot Coordination System Based on Functional Expressions Using Large Language Models

Sueoka, Yuichiro; Kato, Yuki; Yoshida, Takahiro et al.

Springer Proceedings in Advanced Robotics, 2025, 34, 365-379

アクセス数:62件（2026-02-16 02:07 集計）

固定URL: https://hdl.handle.net/11094/103484

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
SpringerProcAdvRobot_34_365	pdf	なし	4.78 MB		2026.11.02

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

タイトル	Adaptivity of a Multi-robot Coordination System Based on Functional Expressions Using Large Language Models
著者	NRID 1000050756509 1000050756509 researchmap permalink yuichiro_sueoka yuichiro_sueoka Scopus Author ID 36665429400 36665429400 著者名 Sueoka, Yuichiro
	著者名 Kato, Yuki
	著者名 Yoshida, Takahiro
	NRID 1000050191937 1000050191937 著者名 Osuka, Koichi
	NRID 1000010869598 1000010869598 著者名 Yajima, Ryosuke
	NRID 1000060756047 1000060756047 著者名 Chikushi, Shota
	NRID 1000080314649 1000080314649 著者名 Nagatani, Keiji
	NRID 1000050184156 1000050184156 著者名 Asama, Hajime
キーワード等	Adaptive Coordination System
	Embodiment
	Functional Expression
	Large Language Model
内容	Sueoka Y., Kato Y., Yoshida T., et al. Adaptivity of a Multi-robot Coordination System Based on Functional Expressions Using Large Language Models. Springer Proceedings in Advanced Robotics 34, 365 (2026); https://doi.org/10.1007/978-3-032-04584-3_25.
内容	This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-032-04584-3_25
抄録	In this paper, we examine the adaptability of a multi-robot coordination system in which distributed autonomous robots respond to unexpected situations based on functional expressions using large language models (LLMs). In recent years, there has been growing interest in systems where multiple autonomous distributed construction machines (robots) collaborate and adaptively perform tasks in open and unknown environments, including disaster sites. In open environments, unforeseen events that cannot be predicted in advance may occur, and it is challenging to address these events solely with existing model-based approaches. In this paper, we leverage the high environment comprehension capabilities of foundation models to understand unforeseen situations and develop a system that enables adaptive coordinated actions by flexibly integrating the functions of multiple robots using LLMs. Additionally, we account for the embodiment (interactions between the robots and their environment). Our experiments demonstrate that the designed system is capable of adaptively responding to three types of unforeseen situations, including path obstructions caused by either an obstacle or a robot. In cases of path obstructions caused by obstacles of varying weights, the system can exhibit appropriate obstacle removal behaviors by reflecting the torque capability of the robot as one aspect of its embodiment.
出版者	Springer Nature
収録物名	Springer Proceedings in Advanced Robotics
巻(号)	34
ページ	365-379
刊行年月	2025-11-02
言語	英語
ハンドルURL	https://hdl.handle.net/11094/103484
PISSN	25111256
eISSN	25111264
関連情報 (isVersionOf)	DOI (出版社版) https://doi.org/10.1007/978-3-032-04584-3_25
アクセス権	embargoed access
権利情報	The full-text file will be made open to the public on 2 November 2026 in accordance with the publisher's policy.
権利情報	© The Authors, under exclusive license to Springer Nature Switzerland AG 2026.
出版タイプ	Accepted Manuscript
カテゴリ	会議発表論文 Conference Paper

資源タイプ	会議発表論文
ローカル資源タイプ	会議発表論文
DCMI資源タイプ	text
DCTERMS.bibliographicCitation	Springer Proceedings in Advanced Robotics. 2025, 34, p. 365-379
DC.title	Adaptivity of a Multi-robot Coordination System Based on Functional Expressions Using Large Language Models
DC.creator	Sueoka, Yuichiro
	Kato, Yuki
	Yoshida, Takahiro
	Osuka, Koichi
	Yajima, Ryosuke
	Chikushi, Shota
	Nagatani, Keiji
	Asama, Hajime
DC.publisher	Springer Nature
DC.language' scheme='DCTERMS.RFC1766	英語
DC.type' scheme='DCTERMS.DCMIType	text
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2025-11-02
DC.identifier	https://doi.org/10.1007/978-3-032-04584-3_25
DC.subject	Adaptive Coordination System
	Embodiment
	Functional Expression
	Large Language Model
DC.description	Sueoka Y., Kato Y., Yoshida T., et al. Adaptivity of a Multi-robot Coordination System Based on Functional Expressions Using Large Language Models. Springer Proceedings in Advanced Robotics 34, 365 (2026); https://doi.org/10.1007/978-3-032-04584-3_25.
DC.description	This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-032-04584-3_25
DCTERMS.abstract	In this paper, we examine the adaptability of a multi-robot coordination system in which distributed autonomous robots respond to unexpected situations based on functional expressions using large language models (LLMs). In recent years, there has been growing interest in systems where multiple autonomous distributed construction machines (robots) collaborate and adaptively perform tasks in open and unknown environments, including disaster sites. In open environments, unforeseen events that cannot be predicted in advance may occur, and it is challenging to address these events solely with existing model-based approaches. In this paper, we leverage the high environment comprehension capabilities of foundation models to understand unforeseen situations and develop a system that enables adaptive coordinated actions by flexibly integrating the functions of multiple robots using LLMs. Additionally, we account for the embodiment (interactions between the robots and their environment). Our experiments demonstrate that the designed system is capable of adaptively responding to three types of unforeseen situations, including path obstructions caused by either an obstacle or a robot. In cases of path obstructions caused by obstacles of varying weights, the system can exhibit appropriate obstacle removal behaviors by reflecting the torque capability of the robot as one aspect of its embodiment.
DC.rights	The full-text file will be made open to the public on 2 November 2026 in accordance with the publisher's policy.
DC.rights	© The Authors, under exclusive license to Springer Nature Switzerland AG 2026.
DC.format	103484
citation_title	Adaptivity of a Multi-robot Coordination System Based on Functional Expressions Using Large Language Models
citation_author	Sueoka, Yuichiro
	Kato, Yuki
	Yoshida, Takahiro
	Osuka, Koichi
	Yajima, Ryosuke
	Chikushi, Shota
	Nagatani, Keiji
	Asama, Hajime
citation_publisher	Springer Nature
citation_language	英語
citation_date	2025-11-02
citation_journal_title	Springer Proceedings in Advanced Robotics
citation_volume	34
citation_firstpage	365
citation_lastpage	379
citation_doi	https://doi.org/10.1007/978-3-032-04584-3_25
citation_public_url	https://hdl.handle.net/11094/103484

Adaptivity of a Multi-robot Coordination System Based on Functional Expressions Using Large Language Models

閲覧可能ファイル

論文情報

論文詳細を表示