Metraipolis › archive › dc_e38fb4fa9182
WorldContact: A Contact-Centric World Model for Scalable Robot Learning — arXiv:2609.19600
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.19600
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T05:25:28.954Z
- SHA-256 of the archived text
f1e85bbd43fb3b8ed9b686216fa32e5d2ca1680a3b9d21c06bb78fcefc098aa7- Stable URL of this page
https://metraipolis.com/documento/dc_e38fb4fa9182
How to cite
WorldContact: A Contact-Centric World Model for Scalable Robot Learning — arXiv:2609.19600 — arXiv (en), https://arxiv.org/abs/2609.19600 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e38fb4fa9182 (Metraipolis archive dc_e38fb4fa9182, sha256 f1e85bbd43fb3b8ed9b686216fa32e5d2ca1680a3b9d21c06bb78fcefc098aa7)
BibTeX
@misc{dce38fb4fa9182,
title = {WorldContact: A Contact-Centric World Model for Scalable Robot Learning — arXiv:2609.19600},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.19600},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e38fb4fa9182; sha256 f1e85bbd43fb3b8ed9b686216fa32e5d2ca1680a3b9d21c06bb78fcefc098aa7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19600. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Adapting robots to new objects and tasks requires interaction experience that can be costly to obtain. We present WorldContact, a contact-centric world model for deformable-object manipulation, constructed from a limited set of high-quality trajectories to generate additional training data efficiently. It predicts object dynamics using larger time steps than the source numerical simulator, which requires small integration steps to resolve rapid motion and prevent interpenetration. We evaluate WorldContact across 16 shopping-bag manipulation tasks. State-rollout measurements on a single H100 GPU show a $10\times$ speedup over the source simulator, excluding rendering and disk I/O. We use the generated data to fine-tune an existing vision-language-action policy and deploy it directly on a real robot. In bag lifting, the same policy achieves 65% single-attempt success when fine-tuned on source simulation data alone, compared with 95% when fine-tuned on the dataset expanded with WorldContact. These results support efficient data generation with WorldContact for robot policy adaptation. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.19600 — 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 2026-10-10T04:47:38.838Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).