Metraipolis › archive › dc_d2146f2bb374

Rethinking Learned Occupancy in Autonomous Active Mapping with Observation-Gated Filtering — arXiv:2609.09069

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.09069
License (as archived): CC0-1.0
Archived: 2026-10-16T15:12:47.452Z
SHA-256 of the archived text: 51e46d944af0d186259c660bddb8a17eaf30dfb2a4759c7cc9cfd8c39adef3d9
Stable URL of this page: https://metraipolis.com/documento/dc_d2146f2bb374

How to cite

Rethinking Learned Occupancy in Autonomous Active Mapping with Observation-Gated Filtering — arXiv:2609.09069 — arXiv (en), https://arxiv.org/abs/2609.09069 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d2146f2bb374 (Metraipolis archive dc_d2146f2bb374, sha256 51e46d944af0d186259c660bddb8a17eaf30dfb2a4759c7cc9cfd8c39adef3d9)

BibTeX

@misc{dcd2146f2bb374,
  title = {Rethinking Learned Occupancy in Autonomous Active Mapping with Observation-Gated Filtering — arXiv:2609.09069},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09069},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d2146f2bb374; sha256 51e46d944af0d186259c660bddb8a17eaf30dfb2a4759c7cc9cfd8c39adef3d9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09069. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autonomous 3D active mapping requires a space robot to choose where to sense while building the geometry needed for navigation. Learned occupancy completion extends spatial context beyond the current field of view, but one predicted map often serves two planning roles: it scores expected surface gain and constrains collision-free motion. Unsupported occupancy can therefore distort both where the robot looks and where it believes it can travel. We study this coupled interface in a controlled closed-loop benchmark by holding the active-mapping system fixed and varying only its planner-facing occupancy across observation-only, learned, oracle-corrected, and ground-truth conditions. Improving occupancy accuracy does not monotonically improve closed-loop coverage: across 25 starts, planning with ground-truth occupancy reaches 70% of the learned baseline's final coverage 12.7 steps earlier on average, while increasing final coverage by only 0.031. Guided by this diagnosis, we introduce an observation-gated filter that retains completion in insufficiently observed regions and suppresses predictions only after repeated frustum exposure without nearby RGB-D support. The filter improves both targeted failure-prone starts without retraining or ground truth. These results motivate online revision of planner-facing geometry during autonomous intervals between communication windows. The current study assumes benchmark RGB-D observations and sufficiently accurate pose estimates; planetary sensing conditions and accumulated localization drift remain to be evaluated.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.09069 — 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 2026-10-16T14:49:57.451Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).