Research paper
Learning Robot Safety from Sparse Human Feedback using Conformal Prediction
Conformal prediction uses human flags on policy trajectories to identify likely unsafe states and issue warnings. The archive reports quadcopter navigation experiments and policy improvement. Its statistical miss-rate statement depends on the method's assumptions and the supplied labels, which are not universal physical safety criteria.
Reviewed 2026-11-05 · Source and bibliography checked
- Original title
- Learning Robot Safety from Sparse Human Feedback using Conformal Prediction
- Publisher
- arXiv
- Authors
- Feldman, Aaron O., Vincent, Joseph A., Adang, Maximilian, Low, JunEn, Schwager, Mac
- DOI
- 10.48550/arxiv.2501.04823
- First archive posting
- 2025-01-08
- Source language
- en
- Source country
- US
- Edition
- v2
- Access
- Open archive metadata and manuscript
- Publication status
- Preprint
Related resources and engineering notes
Source overview
Conformal prediction uses human flags on policy trajectories to identify likely unsafe states and issue warnings. The archive reports quadcopter navigation experiments and policy improvement. Its statistical miss-rate statement depends on the method's assumptions and the supplied labels, which are not universal physical safety criteria.
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
Learning Robot Safety from Sparse Human Feedback using Conformal Prediction ↗
arXiv · v2
arXiv abstract, authors, submission history and DOI links; first posting 2025-01-08, abstract reviewed in v2. Publisher dates are separate.