Metraipolis › archive › dc_a430199078df
When Delay Meets Drift: Physical Safety of Robot Foundation Models Is a Cross-Layer Problem — arXiv:2611.02101
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02101
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:43:43.893Z
- SHA-256 of the archived text
733d8329e9d78f457a580967b5d246acaea81559450693ccd2303813a080f775- Stable URL of this page
https://metraipolis.com/documento/dc_a430199078df
How to cite
When Delay Meets Drift: Physical Safety of Robot Foundation Models Is a Cross-Layer Problem — arXiv:2611.02101 — arXiv (en), https://arxiv.org/abs/2611.02101 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a430199078df (Metraipolis archive dc_a430199078df, sha256 733d8329e9d78f457a580967b5d246acaea81559450693ccd2303813a080f775)
BibTeX
@misc{dca430199078df,
title = {When Delay Meets Drift: Physical Safety of Robot Foundation Models Is a Cross-Layer Problem — arXiv:2611.02101},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02101},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a430199078df; sha256 733d8329e9d78f457a580967b5d246acaea81559450693ccd2303813a080f775},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02101. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Robot foundation models now act in a closed loop, yet their safety is evaluated one variation at a time: robustness benchmarks perturb the scene while assuming instantaneous inference, and real-time execution methods study inference delay in nominal scenes. We argue that physical safety is not a property of the model alone, but emerges from how variations in the physical environment, the model, the computing platform, and execution interact in closed loop. We formalize this as cross-layer variation propagation across these system layers and use an interaction contrast to measure when joint variation creates more risk than the sum of its parts. In 4,000 paired closed-loop episodes of the pi0.5 vision-language-action model on LIBERO, a 400 ms inference delay raises the safety-violation rate by 3.5 percentage points under the training viewpoint but by 37 percentage points under a 60-degree camera shift: 33.5 percentage points (95% CI: 25-43) more than the two effects combined. We close with a research agenda toward predictable physical intelligence: predicting when variation becomes risk, and adapting compute, power, and control accordingly. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV); Emerging Technologies (cs.ET). Pagina del lavoro: https://arxiv.org/abs/2611.02101 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T11:06:37.688Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).