Metraipolis › archive › dc_2de99608a540
3DWay: Generalizing Robot Manipulation via 3D Consistent Waypoints — arXiv:2609.08224
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.08224
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:31:18.188Z
- SHA-256 of the archived text
2b8b88f377d9e35e51812bad088a14f140e24e813dbd8b500b05e18e708d4f6d- Stable URL of this page
https://metraipolis.com/documento/dc_2de99608a540
How to cite
3DWay: Generalizing Robot Manipulation via 3D Consistent Waypoints — arXiv:2609.08224 — arXiv (en), https://arxiv.org/abs/2609.08224 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2de99608a540 (Metraipolis archive dc_2de99608a540, sha256 2b8b88f377d9e35e51812bad088a14f140e24e813dbd8b500b05e18e708d4f6d)
BibTeX
@misc{dc2de99608a540,
title = {3DWay: Generalizing Robot Manipulation via 3D Consistent Waypoints — arXiv:2609.08224},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.08224},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2de99608a540; sha256 2b8b88f377d9e35e51812bad088a14f140e24e813dbd8b500b05e18e708d4f6d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08224. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Intermediate representations are key to bridging the modality gap between generalizable manipulation policies and large-scale pretrained vision-language models (VLMs). Among these, trajectory-based representations compactly represent motion-relevant cues, yet most existing approaches predict trajectories in 2D image space, resulting in intrinsic 3D ambiguity. Moreover, using 2D trajectories with depth still leaves the free-space waypoints ambiguous, limiting reliable 3D reasoning. To address this, we propose predicting 3D consistent waypoints (3DWay) from multi-view images. By reformulating 3D waypoints prediction as generating multi-view consistent 2D waypoints followed by geometric triangulation, we enable explicit 3D motion specification while preserving the strong priors of pretrained VLMs. The predicted waypoints can guide existing VLA models for better generalization or be directly executed on simple tasks. Extensive experiments show that 3DWay substantially improves 3D spatial grounding and vision-language reasoning, demonstrating strong potential for generalizable robot manipulation. Codes will be released at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.RO). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.08224 — 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 2026-10-16T15:11:47.624Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).