Metraipolis › archive › dc_cff735c2d393

LIFD: Anchored Diffusion for 3D-Aware Scene Memory in Robotic Manipulation — arXiv:2609.19796

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19796
License (as archived)
CC0-1.0
Archived
2026-10-10T05:25:32.855Z
SHA-256 of the archived text
2d39e10b192961c0a1b511ffa7cf1639c7e83b1fe5a622068d61cacc70a11b4d
Stable URL of this page
https://metraipolis.com/documento/dc_cff735c2d393

How to cite

LIFD: Anchored Diffusion for 3D-Aware Scene Memory in Robotic Manipulation — arXiv:2609.19796 — arXiv (en), https://arxiv.org/abs/2609.19796 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cff735c2d393 (Metraipolis archive dc_cff735c2d393, sha256 2d39e10b192961c0a1b511ffa7cf1639c7e83b1fe5a622068d61cacc70a11b4d)
BibTeX
@misc{dccff735c2d393,
  title = {LIFD: Anchored Diffusion for 3D-Aware Scene Memory in Robotic Manipulation — arXiv:2609.19796},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19796},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cff735c2d393; sha256 2d39e10b192961c0a1b511ffa7cf1639c7e83b1fe5a622068d61cacc70a11b4d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19796. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

During manipulation, robot and scene motion can move previously observed regions outside the camera's field of view. Geometry-aware RGB features encode visible structure, while control under partial observability requires scene memory that integrates observation history and grounds inferred content in current evidence. We introduce \lifd{} (Look, Imagine, Focus, and Do), a framework for persistent, 3D-aware scene memory. LIFD learns scene tokens through multi-view agreement, then completes them from a single RGB view and recurrent memory using rectified flow. Anchor-Guided Cross-Attention anchors generation to current geometry-aware features, and compact slot features condition a visuomotor policy. Multi-view and geometric supervision are used during representation learning; deployment requires one RGB camera, proprioception, and a task instruction. LIFD (Staged) reaches 91.6\% average success on LIBERO and 79.8\% on MetaWorld, improving LIBERO average success by 11.1 percentage points over Joint training. After policy-head adaptation with ten demonstrations per family, LIFD achieves 56.0\% mean success across four UR5e task families, compared with 40.5\% for OpenVLA-7B.

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/2609.19796 — 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 2026-10-10T04:47:38.852Z 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).