Metraipolis › archive › dc_c8a446501e43
PointPilot: Unified Robotic Manipulation via Object-Centric 3D Point Flow Prediction — arXiv:2611.02930
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02930
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:57:22.075Z
- SHA-256 of the archived text
db2b55bb668d3dc804a463249bf5ec83aafb2b26ad3822b5e3ec327a21dc9872- Stable URL of this page
https://metraipolis.com/documento/dc_c8a446501e43
How to cite
PointPilot: Unified Robotic Manipulation via Object-Centric 3D Point Flow Prediction — arXiv:2611.02930 — arXiv (en), https://arxiv.org/abs/2611.02930 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c8a446501e43 (Metraipolis archive dc_c8a446501e43, sha256 db2b55bb668d3dc804a463249bf5ec83aafb2b26ad3822b5e3ec327a21dc9872)
BibTeX
@misc{dcc8a446501e43,
title = {PointPilot: Unified Robotic Manipulation via Object-Centric 3D Point Flow Prediction — arXiv:2611.02930},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02930},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c8a446501e43; sha256 db2b55bb668d3dc804a463249bf5ec83aafb2b26ad3822b5e3ec327a21dc9872},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02930. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generalization remains a central challenge in robotics, calling for policies that address domain variations from multiple dimensions such as diverse embodiments, camera poses, and/or scene layouts. In order to approach this problem, we introduce PointPilot, a task-focused and 3D aligned manipulation framework built on a 3D space point-flow prediction. Rather than modeling the global scene, PointPilot only represents task-focused objects (robot grippers treated as objects), avoiding the prediction of potentially redundant scene parts unrelated to the manipulation tasks. Moreover, PointPilot aligns 3D spatial representation in one unified coordinate and supports closed-loop and fully automatic action execution across different manipulation modes from object point flow without a separately trained action expert, while existing works typically need an extra action head or are (semi-)automatic and single-arm mode specific. Given sensor observations and language instructions, our model jointly learns subtask planning, task-relevant object grounding, and 3D point flow prediction in an end-to-end way. By processing heterogeneous data in a shared 3D point flow space, PointPilot is able to absorb demonstrations from different embodiments. Extensive simulative and real world experiments validate our method. Notably, we demonstrate zero-shot embodiment generalization with PointPilot. A single trained policy can be deployed on previously unseen embodiments and successfully complete manipulation tasks without any additional fine-tuning. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2611.02930 — 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 2026-11-03T18:17:07.761Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).