Metraipolis › archive › dc_caee9c76b8fe

SafeLoop: Risk-Aware Rollback for Vision-Language-Action Manipulation — arXiv:2609.26313

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.26313
License (as archived)
CC0-1.0
Archived
2026-10-08T16:43:54.521Z
SHA-256 of the archived text
93a11d048284b730fb922f2d6f5b60b853eef6b0843f64cb1ef4604d0613fe00
Stable URL of this page
https://metraipolis.com/documento/dc_caee9c76b8fe

How to cite

SafeLoop: Risk-Aware Rollback for Vision-Language-Action Manipulation — arXiv:2609.26313 — arXiv (en), https://arxiv.org/abs/2609.26313 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_caee9c76b8fe (Metraipolis archive dc_caee9c76b8fe, sha256 93a11d048284b730fb922f2d6f5b60b853eef6b0843f64cb1ef4604d0613fe00)
BibTeX
@misc{dccaee9c76b8fe,
  title = {SafeLoop: Risk-Aware Rollback for Vision-Language-Action Manipulation — arXiv:2609.26313},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26313},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_caee9c76b8fe; sha256 93a11d048284b730fb922f2d6f5b60b853eef6b0843f64cb1ef4604d0613fe00},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26313. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent vision-language-action (VLA) models are promising for general-purpose manipulation, but long-horizon execution remains fragile. Small state-estimation or control errors can lead to irreversible failures (e.g., collisions and object drops). Avoiding these risks requires a proactive safety mechanism capable of anticipating hazards. In this paper, we introduce SafeLoop, a non-invasive external wrapper that adds hazard prediction and rollback-based recovery to a VLA model without changing its parameters. SafeLoop trains a risk predictor from vision and proprioception to output four values: the probability and time-to-hazard for body collisions and for object failures. A lightweight controller then chooses one of three actions based on the predicted risk: continue execution (noop), save a safety checkpoint (record), or retreat in joint space (rollback). Rollback moves the robot back to a recent safe waypoint and queries the base policy again, which may yield an alternative continuation. Across 24 LIBERO tasks (16 random seeds each) and three real-robot tasks (25 rollouts each), SafeLoop achieves a stronger overall safety-success trade-off than alternative methods, reducing hazard cases by roughly 70% while preserving task success and the base-policy control rate. Project code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-23 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.26313 — 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 2026-10-08T15:56:53.494Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).