Research paper
How Can LLMs and Knowledge Graphs Contribute to Robot Safety? A Few-Shot Learning Approach
The paper proposes a language-model and knowledge-graph layer that checks generated drone-control code before simulated execution. It is useful for examining verification interfaces around generated actions. Model-generated checks in a simulator are not independent proof of physical safety or regulatory compliance.
Reviewed 2026-11-05 · Source and bibliography checked
- Original title
- How Can LLMs and Knowledge Graphs Contribute to Robot Safety? A Few-Shot Learning Approach
- Publisher
- arXiv
- Authors
- Althobaiti, Abdulrahman, Ayala, Angel, Gao, JingYing, Almutairi, Ali, Deghat, Mohammad, Razzak, Imran, Cruz, Francisco
- DOI
- 10.48550/arxiv.2412.11387
- First archive posting
- 2024-12-16
- Source language
- en
- Source country
- US
- Edition
- v1
- Access
- Open archive metadata and manuscript
- Publication status
- Preprint
Related resources and engineering notes
Source overview
The paper proposes a language-model and knowledge-graph layer that checks generated drone-control code before simulated execution. It is useful for examining verification interfaces around generated actions. Model-generated checks in a simulator are not independent proof of physical safety or regulatory compliance.
Use and review
Original summary of the primary archive abstract and bibliographic record. Specialist technical and native-language review remain pending. The reported method does not establish a deployed safety function or achieved PL.
Sources & editions
How Can LLMs and Knowledge Graphs Contribute to Robot Safety? A Few-Shot Learning Approach ↗
arXiv · v1
arXiv abstract, authors, submission history and DOI links; first posting 2024-12-16, abstract reviewed in v1. Publisher dates are separate.