Metraipolis › archive › dc_c4988ba2fa66
PointCast: One World Model for Rigid, Articulated, and Deformable Object Manipulation — arXiv:2609.28393
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.28393
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:53:58.179Z
- SHA-256 of the archived text
3588c11f2c799f58ac53e6af3417defdb8eb4d79b57a37e823ce76a20c88bcd7- Stable URL of this page
https://metraipolis.com/documento/dc_c4988ba2fa66
How to cite
PointCast: One World Model for Rigid, Articulated, and Deformable Object Manipulation — arXiv:2609.28393 — arXiv (en), https://arxiv.org/abs/2609.28393 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c4988ba2fa66 (Metraipolis archive dc_c4988ba2fa66, sha256 3588c11f2c799f58ac53e6af3417defdb8eb4d79b57a37e823ce76a20c88bcd7)
BibTeX
@misc{dcc4988ba2fa66,
title = {PointCast: One World Model for Rigid, Articulated, and Deformable Object Manipulation — arXiv:2609.28393},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.28393},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c4988ba2fa66; sha256 3588c11f2c799f58ac53e6af3417defdb8eb4d79b57a37e823ce76a20c88bcd7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28393. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
World models are useful for robotic manipulation because robots can predict how actions change the states of objects before executing them. We present PointCast, a point-set world model that spans rigid, articulated, and deformable object manipulation. Its state is a set of 3D points on the object and the end-effector, mesh-free and topology-agnostic. Each point keeps its identity and is supervised on its own trajectory, which teaches the model where every point goes rather than only the shape the points form. Its backbone is a diffusion transformer that denoises a short window of future point positions, conditioned on the points' recent history and the commanded end-effector motion. The backbone's attention alternates between local and global, and cross-attention to the end-effector carries the coupling. This one architecture at 19.8M parameters and one training recipe cover four regimes, rigid objects, cloth, rope, and multi-joint cabinets, with a separate checkpoint trained for each. Trained on randomized simulation and scored against four baselines on the same metric, it is best on three of four regimes and second on rigid. Trained on a real-world robot teleoperation dataset, it has the lowest mean error in four of its six categories, is second in the other two, and improves on the dataset's own model in all six; zero-shot, its simulation checkpoints are best on two of four captures. Frozen inside sampling-based model-predictive control at one network evaluation per window, it plans four simulated tasks over 64 episodes, competitive with or outperforming every baseline on each. Project website at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.28393 — 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 2026-10-08T12:21:19.515Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).