Metraipolis › archive › dc_f0ea87886b1f
VLA-Corrector: Stage-Aware Observable State Understanding for Prompt-Based Closed-Loop Recovery of Vision-Language-Action Policies — arXiv:2609.06508
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06508
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:30:56.548Z
- SHA-256 of the archived text
5b062b3b5671d3d800a6cb028914ca0df98eb5cd0c361ee1ce09a6b847e0162b- Stable URL of this page
https://metraipolis.com/documento/dc_f0ea87886b1f
How to cite
VLA-Corrector: Stage-Aware Observable State Understanding for Prompt-Based Closed-Loop Recovery of Vision-Language-Action Policies — arXiv:2609.06508 — arXiv (en), https://arxiv.org/abs/2609.06508 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f0ea87886b1f (Metraipolis archive dc_f0ea87886b1f, sha256 5b062b3b5671d3d800a6cb028914ca0df98eb5cd0c361ee1ce09a6b847e0162b)
BibTeX
@misc{dcf0ea87886b1f,
title = {VLA-Corrector: Stage-Aware Observable State Understanding for Prompt-Based Closed-Loop Recovery of Vision-Language-Action Policies — arXiv:2609.06508},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06508},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f0ea87886b1f; sha256 5b062b3b5671d3d800a6cb028914ca0df98eb5cd0c361ee1ce09a6b847e0162b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06508. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-horizon robot manipulation with Vision-Language-Action (VLA) policies remains vulnerable to execution-time deviations, as final task success provides little information for diagnosing and correcting failures caused by action noise, object displacement, or goal misalignment. We introduce a stage-aware failure verification and Prompt Recovery framework that enables closed-loop correction of a fixed VLA policy without parameter updates or privileged simulator states. The framework introduces an observable-history-based Learned Verifier that jointly estimates manipulation progress and execution risk by temporally modeling multi-view visual observations, proprioceptive states, and executed actions. To provide interpretable task understanding, we represent manipulation execution through semantic progress stages, including approach, alignment, grasp, transport, and placement, and identify stage-specific failure patterns. Upon detecting abnormal execution, the framework preserves the original instruction and generates a stage-conditioned recovery prompt, allowing the same frozen VLA policy to produce corrective actions. Extensive multi-round evaluations on LIBERO and LIBERO Plus demonstrate that the proposed approach substantially improves closed-loop reliability under diverse perturbations. Without access to privileged object or goal coordinates, the Learned Verifier achieves recovery performance close to that of the privileged rule-based verifier in the evaluated settings. These results show that observable visual-proprioceptive-action history is sufficient to infer latent task states and enable practical failure recovery for existing VLA policies. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.06508 — 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 2026-10-16T15:11:47.539Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).