Capability-Driven Skill Generation with LLMs: A RAG-Based Approach for Reusing Existing Libraries and Interfaces

Modern automation systems increasingly rely on modular architectures, with capabilities and skills as one solution approach. Capabilities define the functions of resources in a machine-readable form and skills provide the concrete implementations that realize those capabilities. However, the develop...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE International Conference on Emerging Technologies and Factory Automation) s. 1 - 8
Hlavní autoři: Vieira Da Silva, Luis Miguel, Koche, Aljosha, Konig, Nicolas, Gehlhoff, Felix, Fay, Alexander
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 09.09.2025
Témata:
ISSN:1946-0759
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Modern automation systems increasingly rely on modular architectures, with capabilities and skills as one solution approach. Capabilities define the functions of resources in a machine-readable form and skills provide the concrete implementations that realize those capabilities. However, the development of a skill implementation conforming to a corresponding capability remains a time-consuming and challenging task. In this paper, we present a method that treats capabilities as contracts for skill implementations and leverages large language models to generate executable code based on natural language user input. A key feature of our approach is the integration of existing software libraries and interface technologies, enabling the generation of skill implementations across different target languages. We introduce a framework that allows users to incorporate their own libraries and resource interfaces into the code generation process through a retrieval-augmented generation architecture. The proposed method is evaluated using an autonomous mobile robot controlled via Python and ROS 2, demonstrating the feasibility and flexibility of the approach.
AbstractList Modern automation systems increasingly rely on modular architectures, with capabilities and skills as one solution approach. Capabilities define the functions of resources in a machine-readable form and skills provide the concrete implementations that realize those capabilities. However, the development of a skill implementation conforming to a corresponding capability remains a time-consuming and challenging task. In this paper, we present a method that treats capabilities as contracts for skill implementations and leverages large language models to generate executable code based on natural language user input. A key feature of our approach is the integration of existing software libraries and interface technologies, enabling the generation of skill implementations across different target languages. We introduce a framework that allows users to incorporate their own libraries and resource interfaces into the code generation process through a retrieval-augmented generation architecture. The proposed method is evaluated using an autonomous mobile robot controlled via Python and ROS 2, demonstrating the feasibility and flexibility of the approach.
Author Konig, Nicolas
Gehlhoff, Felix
Vieira Da Silva, Luis Miguel
Koche, Aljosha
Fay, Alexander
Author_xml – sequence: 1
  givenname: Luis Miguel
  surname: Vieira Da Silva
  fullname: Vieira Da Silva, Luis Miguel
  email: miguel.vieira@hsu-hh.de
  organization: Helmut Schmidt University,Institute of Automation Technology,Hamburg,Germany
– sequence: 2
  givenname: Aljosha
  surname: Koche
  fullname: Koche, Aljosha
  email: aljosha.koecher@hsu-hh.de
  organization: Helmut Schmidt University,Institute of Automation Technology,Hamburg,Germany
– sequence: 3
  givenname: Nicolas
  surname: Konig
  fullname: Konig, Nicolas
  organization: Helmut Schmidt University,Institute of Automation Technology,Hamburg,Germany
– sequence: 4
  givenname: Felix
  surname: Gehlhoff
  fullname: Gehlhoff, Felix
  email: felix.gehlhoff@hsu-hh.de
  organization: Helmut Schmidt University,Institute of Automation Technology,Hamburg,Germany
– sequence: 5
  givenname: Alexander
  surname: Fay
  fullname: Fay, Alexander
  email: alexander.fay@rub.de
  organization: Ruhr University,Chair of Automation,Bochum,Germany
BookMark eNo1kN1KwzAcxaMoOOfeQDAv0Jk0SZN4V-c2BxVh7n6kyb8uWtOS1I-9vRP16hwO_A6Hc45OQhcAoStKppQSfT3fLMpCCKqmOcnFIcuJkDk_QhMttWKMCsEUU8doRDUvMiKFPkOTlF4IIQe-0EyPUD8zval964d9dhf9BwT89OrbFi8hQDSD7wL-9MMOV9VDusElXpfL7NYkcLjs-9gZu8NNF_Ea3pMPz3j-5dPwYypfRxM9JGyCw6swQGyMhXSBThvTJpj86RhtFvPN7D6rHperWVllXrMhA0bAcXuYaGsBXIqCO2VpoyyrlSaGcWW4lo4KJ4lpJLWqACecAu4YKxwbo8vfWg8A2z76NxP32_-P2DdicF2s
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ETFA65518.2025.11205724
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE/IET Electronic Library (IEL) (UW System Shared)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331553838
EISSN 1946-0759
EndPage 8
ExternalDocumentID 11205724
Genre orig-research
GroupedDBID 6IE
6IF
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
OCL
RIE
RIL
RNS
ID FETCH-LOGICAL-i93t-e30ed4c939cb5e47564d8c1f8c3b890a348a497d15d70af71c86ed5d8e4d336d3
IEDL.DBID RIE
IngestDate Wed Oct 29 06:13:06 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-e30ed4c939cb5e47564d8c1f8c3b890a348a497d15d70af71c86ed5d8e4d336d3
PageCount 8
ParticipantIDs ieee_primary_11205724
PublicationCentury 2000
PublicationDate 2025-Sept.-9
PublicationDateYYYYMMDD 2025-09-09
PublicationDate_xml – month: 09
  year: 2025
  text: 2025-Sept.-9
  day: 09
PublicationDecade 2020
PublicationTitle Proceedings (IEEE International Conference on Emerging Technologies and Factory Automation)
PublicationTitleAbbrev ETFA
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0001096939
Score 2.3160486
Snippet Modern automation systems increasingly rely on modular architectures, with capabilities and skills as one solution approach. Capabilities define the functions...
SourceID ieee
SourceType Publisher
StartPage 1
SubjectTerms Capabilities
Code-Generation
Codes
Large language models
LLMs
Manufacturing automation
Mobile robots
Natural languages
Ontologies
Python
RAG
Retrieval augmented generation
Semantic Web
Skills
Software libraries
Title Capability-Driven Skill Generation with LLMs: A RAG-Based Approach for Reusing Existing Libraries and Interfaces
URI https://ieeexplore.ieee.org/document/11205724
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV09T8MwELVoxcAEiCK-5YHVbRI7sc0WSgtDqarSoVvl-GxUgdKqHwj-PbabUjEwsDmRIkVnOe_d5d07hG4ZAwuFjAgkmhPvP0KkAEpiZjJItae8Kgyb4P2-GI_loGpWD70wxpggPjNNvwz_8mGm175U1nLcwNGLhNVQjXO-adbaFVQcGZdUVhoud9XqjLp55h3HXBqYpM3t07_mqAQY6R7-8wWOUGPXkIcHP1BzjPZMeYLmbQd0Qdv6RR4W_quFX96m7-94YyXtI459mRX3es_LO5zjYf5I7h1qAc4rJ3HsKCseGi9-f8WdT3_e3aK3TaGxKgGHmqH1yq0GGnU7o_YTqQYokKmkK2JoZIBpFxRdpIbxNGMgdGyFpoWQkaJMKCY5xCnwSFkea5EZSEEYBpRmQE9RvZyV5gxhbSm4VDABqSlzqC6BZ9oWolDCqgLic9Tw0ZrMNxYZk22gLv64f4kO_J4EsZa8QvXVYm2u0b7-WE2Xi5uwsd8lb6Sr
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PT8IwFG4UTfSkRoy_7cFrYVu7rfU2EcQ4CMEduJGtryNEMgg_jP73tmVIPHjw1i1Zsrym-7739r3vIXTPGOSQCYeAJ0Ni_EeI4ECJy1QAvjSUN7XDJsJulw8Golc2q9teGKWUFZ-pmlnaf_kwlStTKqtrbqDphcd20Z7PmOeu27W2JRVNxwUVpYpLX9WbSSsKjOeYTgQ9v7Z5_tckFQskraN_vsIxqm5b8nDvB2xO0I4qTtGsoaHOqlu_yNPcfLfw2_t4MsFrM2kTc2wKrTiOO4sHHOF-9EweNW4BjkovcaxJK-4rI38f4eanOfF6EW-SaJwWgG3VMDfarSpKWs2k0SblCAUyFnRJFHUUMKmDIjNfsdAPGHDp5lzSjAsnpYynTITg-hA6aR66kgcKfOCKAaUB0DNUKaaFOkdY5hR0MuiBkJRpXBcQBjLPeJbyPM3AvUBVE63hbG2SMdwE6vKP-3fooJ104mH80n29Qodmf6x0S1yjynK-UjdoX34sx4v5rd3kb-Nap_I
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+%28IEEE+International+Conference+on+Emerging+Technologies+and+Factory+Automation%29&rft.atitle=Capability-Driven+Skill+Generation+with+LLMs%3A+A+RAG-Based+Approach+for+Reusing+Existing+Libraries+and+Interfaces&rft.au=Vieira+Da+Silva%2C+Luis+Miguel&rft.au=Koche%2C+Aljosha&rft.au=Konig%2C+Nicolas&rft.au=Gehlhoff%2C+Felix&rft.date=2025-09-09&rft.pub=IEEE&rft.eissn=1946-0759&rft.spage=1&rft.epage=8&rft_id=info:doi/10.1109%2FETFA65518.2025.11205724&rft.externalDocID=11205724