Metraipolis › archive › dc_4bf9b4b2fe92
MVG-WAM: Multiple View Geometry-Aware World-Action Modeling for Robotic Manipulation — arXiv:2609.37793
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.37793
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T19:15:46.822Z
- SHA-256 of the archived text
3bb4f70de285b39ad12be8f2a59c528465037245b6f91879035bb2a1f48c6e14- Stable URL of this page
https://metraipolis.com/documento/dc_4bf9b4b2fe92
How to cite
MVG-WAM: Multiple View Geometry-Aware World-Action Modeling for Robotic Manipulation — arXiv:2609.37793 — arXiv (en), https://arxiv.org/abs/2609.37793 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4bf9b4b2fe92 (Metraipolis archive dc_4bf9b4b2fe92, sha256 3bb4f70de285b39ad12be8f2a59c528465037245b6f91879035bb2a1f48c6e14)
BibTeX
@misc{dc4bf9b4b2fe92,
title = {MVG-WAM: Multiple View Geometry-Aware World-Action Modeling for Robotic Manipulation — arXiv:2609.37793},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.37793},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4bf9b4b2fe92; sha256 3bb4f70de285b39ad12be8f2a59c528465037245b6f91879035bb2a1f48c6e14},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37793. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
World-Action Models (WAMs) couple visual dynamics with action prediction, bringing the rich priors of pretrained video models to robotic manipulation. However, their multi-view interfaces typically tile images or concatenate tokens, leaving the geometric relationships among synchronized cameras implicit. This makes it harder to connect global scene context with the local geometry required for interaction. We introduce the Multi-View Geometry-Aware World-Action Model (MVG-WAM), which organizes these observations as related projections of one physical world rather than separate images on a canvas. Our model combines an epipolar-constrained global state with view-indexed geometric states jointly inferred from synchronized observations. Camera-aware routing supplies each video region with its corresponding geometric context and the shared global state, explicitly structuring the representation used for action prediction. We further ground the geometry-aware representation in metric scale through multi-horizon future-depth supervision, without requiring depth decoding during action rollout. MVG-WAM achieves average success rates of 99.1% on LIBERO and 92.07% on RoboTwin 2.0, demonstrating competitive performance across both benchmarks. Real-world experiments on Cobot Magic further demonstrate a 91.3% success rate across 150 trials spanning three manipulation tasks. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-30 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.37793 — 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 2026-10-07T18:40:59.542Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).