Metraipolis › archive › dc_d7e7f94bcdb5

ReVeal: A Reconstruction-Aware Real-to-Sim Framework for VLA Policy Evaluation — arXiv:2609.23910

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23910
License (as archived)
CC0-1.0
Archived
2026-10-09T22:24:08.838Z
SHA-256 of the archived text
d893cc3dbd9372d35e75e4c2d32b784006b32a7e1cffb47d9462e46e2463460b
Stable URL of this page
https://metraipolis.com/documento/dc_d7e7f94bcdb5

How to cite

ReVeal: A Reconstruction-Aware Real-to-Sim Framework for VLA Policy Evaluation — arXiv:2609.23910 — arXiv (en), https://arxiv.org/abs/2609.23910 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d7e7f94bcdb5 (Metraipolis archive dc_d7e7f94bcdb5, sha256 d893cc3dbd9372d35e75e4c2d32b784006b32a7e1cffb47d9462e46e2463460b)
BibTeX
@misc{dcd7e7f94bcdb5,
  title = {ReVeal: A Reconstruction-Aware Real-to-Sim Framework for VLA Policy Evaluation — arXiv:2609.23910},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23910},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d7e7f94bcdb5; sha256 d893cc3dbd9372d35e75e4c2d32b784006b32a7e1cffb47d9462e46e2463460b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23910. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Simulation-based evaluation provides a scalable and repeatable alternative to real-world evaluation of vision-language-action (VLA) policies. However, reconstruction errors can cause simulated policy performance to diverge from real-world performance, motivating the need to assess reconstructed environments for downstream VLA policy evaluation. We present ReVeal, a real-to-sim assessment framework combining workspace reconstruction, reconstruction-level assessment, and matched closed-loop policy evaluation. Novel-View Mesh Fidelity (NVMF) and Annotated Planar Geometry Fidelity (APGF) assess observation and planar geometric fidelity, respectively. We also develop PGSR-D, a reconstruction pipeline incorporating monocular depth supervision to improve geometry where multi-view visual cues are limited. Across 8 assessment scenes, NVMF and APGF consistently distinguish the fidelity of 2DGS, PGSR, and PGSR-D. Matched evaluations of GR00T, SmolVLA, and pi0.5 across 8 humanoid manipulation tasks show consistent ordering between reconstruction fidelity and real-sim performance agreement across pipelines. Further analysis of the evaluation workspaces shows that higher fidelity is associated with stronger real-sim agreement.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.RO).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.23910 — 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 2026-10-09T21:59:59.644Z 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).