Metraipolis › archive › dc_edc79c36035b
Spatial Grafting: Grounding 3D Features for Flow-Matching Robot Policies — arXiv:2609.35249
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35249
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:03:25.807Z
- SHA-256 of the archived text
7c66de40c6defbb839310e4a28daee2fa616195a28063b864bffff821648f48c- Stable URL of this page
https://metraipolis.com/documento/dc_edc79c36035b
How to cite
Spatial Grafting: Grounding 3D Features for Flow-Matching Robot Policies — arXiv:2609.35249 — arXiv (en), https://arxiv.org/abs/2609.35249 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_edc79c36035b (Metraipolis archive dc_edc79c36035b, sha256 7c66de40c6defbb839310e4a28daee2fa616195a28063b864bffff821648f48c)
BibTeX
@misc{dcedc79c36035b,
title = {Spatial Grafting: Grounding 3D Features for Flow-Matching Robot Policies — arXiv:2609.35249},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35249},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_edc79c36035b; sha256 7c66de40c6defbb839310e4a28daee2fa616195a28063b864bffff821648f48c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35249. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Pretrained robot manipulation policies such as vision-language-action models (VLAs) or world-action models (WAMs) leave interaction-relevant metric geometry implicit. Recent breakthroughs in spatial reconstruction can supply the necessary geometry reliably, but their features describe local shape without stating where it lies with respect to the robot. How best to deliver these features to a pretrained policy remains unresolved. We propose Spatial Grafting, a versatile, lightweight spatial module that binds frozen reconstruction features to metric, robot-relative geometry. Spatial Grafting constructs metric-grounded spatial tokens and injects them into the flow-matching action expert through cross-attention, without modifying the host's perceptual pathway, so the host retains the full benefit of its pretraining. We evaluate it more broadly than any geometry-aware policy we compare against: one graft architecture, with no per-host redesign, on two VLAs and two WAMs, across four simulation benchmarks that span short-horizon manipulation, visual robustness, clutter and long-horizon mobile manipulation, and on three real-robot platforms with single- and dual-arm configurations. On RoboTwin 2.0, a dual-arm manipulation benchmark, the graft improves every host across VLAs and WAMs. Grafted $\pi_{0.5}$ gains 11.3% and 15.6% on clean and randomized scenes, reaching 94.0% and 92.4%, above the strongest published 3D-conditioned policy, WAM4D (93.8% and 89.9%). The margin widens as the horizon lengthens: on tasks from BEHAVIOR-1K, a dual-arm mobile manipulation challenge scored by average task progress, it surpasses the 2025 challenge winner on five of six tasks,by up to 0.47 Q-score, and exceeds a map-conditioned spatial policy on average across the three tasks both report.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.35249 — 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 2026-10-07T20:29:03.302Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).