Metraipolis › archive › dc_2bfe67e51517

VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation — arXiv:2610.12451

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.12451
License (as archived)
CC0-1.0
Archived
2026-10-09T06:30:58.017Z
SHA-256 of the archived text
4245d6107c04321dce39dbc461cf93ee43bf9ccd84b257f864bc0d786e68aa0d
Stable URL of this page
https://metraipolis.com/documento/dc_2bfe67e51517

How to cite

VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation — arXiv:2610.12451 — arXiv (en), https://arxiv.org/abs/2610.12451 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bfe67e51517 (Metraipolis archive dc_2bfe67e51517, sha256 4245d6107c04321dce39dbc461cf93ee43bf9ccd84b257f864bc0d786e68aa0d)
BibTeX
@misc{dc2bfe67e51517,
  title = {VersaCamVLA: Camera-Configurable VLA Policies for Robotic Manipulation — arXiv:2610.12451},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.12451},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bfe67e51517; sha256 4245d6107c04321dce39dbc461cf93ee43bf9ccd84b257f864bc0d786e68aa0d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.12451. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language-Action (VLA) models have emerged as powerful foundations for robotic manipulation, but their reliance on fixed camera configurations during training makes them brittle to changes in camera count or pose during deployment. To overcome these limitations, we propose VersaCamVLA, a camera-configurable framework that decouples camera-set representation from action learning. VersaCamVLA learns a unified scene-token interface that maps an arbitrary, variable set of posed RGB views into fixed-size latent scene tokens. This is achieved via multi-signal target-view prediction and Wrist-Augmented Pose Sampling (WAPS), which leverages natural wrist-camera motion for free pose diversity. At deployment, a lightweight spatial encoder injects these compact scene tokens into a pretrained base VLA as a supplementary visual condition, requiring no explicit 3D sensing or novel-view rendering. Experiments on RoboTwin, LIBERO, and a real-robot platform demonstrate that VersaCamVLA consistently outperforms prior VLA methods and direct multi-view baselines, maintaining robust performance across varying camera counts and unseen camera poses.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.12451 — 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 2026-10-09T05:55:07.785Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).