Metraipolis › archive › dc_eb2aa56381b2

CARE: Experience-Guided Atomic Corrective Execution for Vision-Language-Action Policies — arXiv:2609.24118

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24118
License (as archived)
CC0-1.0
Archived
2026-10-09T22:24:15.516Z
SHA-256 of the archived text
92df88878c7ce01df000603ad4b3a32c631b6c666a6506224e2d53c2122ca7c9
Stable URL of this page
https://metraipolis.com/documento/dc_eb2aa56381b2

How to cite

CARE: Experience-Guided Atomic Corrective Execution for Vision-Language-Action Policies — arXiv:2609.24118 — arXiv (en), https://arxiv.org/abs/2609.24118 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eb2aa56381b2 (Metraipolis archive dc_eb2aa56381b2, sha256 92df88878c7ce01df000603ad4b3a32c631b6c666a6506224e2d53c2122ca7c9)
BibTeX
@misc{dceb2aa56381b2,
  title = {CARE: Experience-Guided Atomic Corrective Execution for Vision-Language-Action Policies — arXiv:2609.24118},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24118},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eb2aa56381b2; sha256 92df88878c7ce01df000603ad4b3a32c631b6c666a6506224e2d53c2122ca7c9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24118. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language-Action (VLA) policies achieve strong performance in robotic manipulation but remain brittle once execution deviates from nominal trajectories. We propose CARE (Corrective Atomic Robotic Execution), a framework that improves recovery by learning from failures encountered during execution. Instead of generating corrective data from manually designed or random perturbations, CARE collects failed rollouts, models stage-conditioned post-failure deviations, and uses the resulting empirical distributions to synthesize representative failure states and corrective demonstrations. At inference time, CARE combines stage-wise planning with physically grounded 3D monitoring to trigger atomic adjustments or re-operations while preserving task progress. We further introduce the Failure State Recovery Benchmark (FSR-Bench), which evaluates recovery from intermediate failure states under local deviations and structural anomalies. Experiments across multiple VLA backbones, simulation benchmarks, and real-world dual-arm tasks show consistent improvements, with average task-success gains of 14.5 points in simulation and 15.9 points in the real world. Code, models, and data are available at this https URL

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.24118 — 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 2026-10-09T21:59:59.677Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).