Metraipolis › archive › dc_5e8a316fcd09

Knowing Where to Look: Interactive Object Search via Spatial-Semantic Fusion — arXiv:2611.00499

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00499
License (as archived)
CC0-1.0
Archived
2026-11-03T11:43:51.037Z
SHA-256 of the archived text
5141434a145e4501504da322a93e7d4e132c3246ee35d1937e471fd6c7f7f6b0
Stable URL of this page
https://metraipolis.com/documento/dc_5e8a316fcd09

How to cite

Knowing Where to Look: Interactive Object Search via Spatial-Semantic Fusion — arXiv:2611.00499 — arXiv (en), https://arxiv.org/abs/2611.00499 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5e8a316fcd09 (Metraipolis archive dc_5e8a316fcd09, sha256 5141434a145e4501504da322a93e7d4e132c3246ee35d1937e471fd6c7f7f6b0)
BibTeX
@misc{dc5e8a316fcd09,
  title = {Knowing Where to Look: Interactive Object Search via Spatial-Semantic Fusion — arXiv:2611.00499},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00499},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5e8a316fcd09; sha256 5141434a145e4501504da322a93e7d4e132c3246ee35d1937e471fd6c7f7f6b0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00499. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When searching for an object, humans naturally combine semantic intuition - reasoning about where the object is likely to be stored - with geometric awareness of what parts of the space are visible, occluded, or unexplored. Effective robot object search requires the same joint reasoning, yet existing methods rely on only one: geometric methods maintain principled spatial beliefs but lack deep semantic understanding, while language-model based methods leverage commonsense knowledge but maintain no explicit belief over space. We argue that jointly reasoning over semantic and geometric evidence in an explicit 3D belief enables human-like interactive object search that outperforms either modality alone. To test this claim, we build a system that accumulates per-object VLM plausibility scores and geometric occupancy evidence via Bayesian log-odds filtering into a unified 3D voxel belief field. High-belief regions in the combined belief field drive action selection at each step: taking a closer look from a different viewpoint, navigating toward an unexplored region of the workspace, or physically interacting with a closed cabinet. We deploy this system end-to-end on a bimanual mobile humanoid and find that it outperforms geometry-only search and LLM-based planning methods. Project website - this https URL

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/2611.00499 — 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 2026-11-03T11:06:52.234Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).