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

Uložené v:
Podrobná bibliografia
Vydané v:Proceedings (IEEE International Conference on Emerging Technologies and Factory Automation) s. 1 - 8
Hlavní autori: Vieira Da Silva, Luis Miguel, Koche, Aljosha, Konig, Nicolas, Gehlhoff, Felix, Fay, Alexander
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 09.09.2025
Predmet:
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
ISSN:1946-0759
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí: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.
ISSN:1946-0759
DOI:10.1109/ETFA65518.2025.11205724