Metraipolis › archive › dc_28f41ff19df3

Sensor-Layout-Agnostic Navigation via Geometric Observation Canonicalization — arXiv:2610.08306

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.08306
License (as archived): CC0-1.0
Archived: 2026-10-07T13:12:20.882Z
SHA-256 of the archived text: 08a582c1f13a77f6551a1806a37bdd76df605f9c8d5199903738c5e1e963ae21
Stable URL of this page: https://metraipolis.com/documento/dc_28f41ff19df3

How to cite

Sensor-Layout-Agnostic Navigation via Geometric Observation Canonicalization — arXiv:2610.08306 — arXiv (en), https://arxiv.org/abs/2610.08306 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_28f41ff19df3 (Metraipolis archive dc_28f41ff19df3, sha256 08a582c1f13a77f6551a1806a37bdd76df605f9c8d5199903738c5e1e963ae21)

BibTeX

@misc{dc28f41ff19df3,
  title = {Sensor-Layout-Agnostic Navigation via Geometric Observation Canonicalization — arXiv:2610.08306},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08306},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_28f41ff19df3; sha256 08a582c1f13a77f6551a1806a37bdd76df605f9c8d5199903738c5e1e963ae21},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08306. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Existing visual navigation policies are inherently bound to fixed camera configurations, creating a fundamental barrier to zero-shot deployment across heterogeneous robot sensor layouts. To overcome this limitation, we present an embodiment-informed navigation policy capable of generalizing across diverse depth sensor configurations on a specific aerial platform. Instead of implicitly learning spatial alignments, our approach explicitly unprojects depth measurements from arbitrary depth sensor payloads, varying in sensor count, mounting extrinsics, and intrinsics, into a shared robot-centric frame, stitching them into a unified spherical range image and a binary validity mask. This mask allows the downstream policy to explicitly distinguish covered space from unobserved blind spots. Trained via reinforcement learning with aggressive camera randomization, our policy generalizes zero-shot to unseen layouts featuring up to seven cameras, scaling success rates from 78% to 95% as total spatial sensing coverage increases. Finally, real-world flight trials on a physical quadrotor, conducted in an obstacle-filled corridor and an outdoor forest, validate the policy's zero-shot transfer across camera configurations and its resilience to sudden online sensor dropouts.

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/2610.08306 — 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 2026-10-07T12:42:33.615Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).