Research paper
Analysis of Deep-Learning Methods in an ISO/TS 15066-Compliant Human-Robot Safety Framework
The framework compares four deep-learning perception approaches to adapt robot speed using separation and body-part information. Experiments report cycle-time benefits. The title's ISO/TS 15066 compliance wording is an author claim; sensor integrity, contact limits and the whole safety function need independent validation.
Reviewed 2026-11-05 · Source and bibliography checked
- Original title
- Analysis of Deep-Learning Methods in an ISO/TS 15066-Compliant Human-Robot Safety Framework
- Publisher
- arXiv
- Authors
- Bricher, David, Mueller, Andreas
- DOI
- 10.48550/arxiv.2511.19094
- First archive posting
- 2025-11-24
- Source language
- en
- Source country
- US
- Edition
- v1
- Access
- Open archive metadata and manuscript
- Publication status
- Archive manuscript · linked publication metadata
Related resources and engineering notes
Source overview
The framework compares four deep-learning perception approaches to adapt robot speed using separation and body-part information. Experiments report cycle-time benefits. The title's ISO/TS 15066 compliance wording is an author claim; sensor integrity, contact limits and the whole safety function need independent validation.
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
Analysis of Deep-Learning Methods in an ISO/TS 15066-Compliant Human-Robot Safety Framework ↗
arXiv · v1
arXiv abstract, authors, submission history and DOI links; first posting 2025-11-24, abstract reviewed in v1. Publisher dates are separate.