Metraipolis › archive › dc_ccd65cb2a561

RAFAIL: Relationship-Aware Failure Detection for Robotic Manipulation — arXiv:2609.18324

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.18324
License (as archived): CC0-1.0
Archived: 2026-10-15T16:55:51.537Z
SHA-256 of the archived text: 91429175f923490e68ed3b954392a15d36380c730175a42667e9addf283268eb
Stable URL of this page: https://metraipolis.com/documento/dc_ccd65cb2a561

How to cite

RAFAIL: Relationship-Aware Failure Detection for Robotic Manipulation — arXiv:2609.18324 — arXiv (en), https://arxiv.org/abs/2609.18324 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ccd65cb2a561 (Metraipolis archive dc_ccd65cb2a561, sha256 91429175f923490e68ed3b954392a15d36380c730175a42667e9addf283268eb)

BibTeX

@misc{dcccd65cb2a561,
  title = {RAFAIL: Relationship-Aware Failure Detection for Robotic Manipulation — arXiv:2609.18324},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18324},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ccd65cb2a561; sha256 91429175f923490e68ed3b954392a15d36380c730175a42667e9addf283268eb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18324. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Detecting failures during execution is essential for reliable robotic manipulation. Vision-language models (VLMs) can assess task outcomes semantically but add runtime computation, whereas out-of-distribution (OOD) detectors may respond to harmless scene variations rather than failure-relevant deviations. We introduce RAFAIL, a framework for detecting execution failures during robotic manipulation. RAFAIL identifies failures by detecting anomalies in task-relevant relationships between entities, such as a gripper and an object or an object and its target. By focusing OOD detection on relevant parts of the observation, RAFAIL reduces sensitivity to task-irrelevant scene variation. Offline, a VLM annotates successful demonstrations with task progress and relationship importance, which are used to learn point-cloud-based relationship representations without relying on policy-internal features. At runtime, relationship-specific OOD detectors evaluate these representations while relationship importance and task progress are predicted without VLM inference. RAFAIL requires no failure data and achieves 73.4% balanced accuracy across three real-world robotic manipulation tasks, outperforming the strongest evaluated OOD- and uncertainty-based baselines.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.18324 — 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 2026-10-15T16:13:27.285Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).