Metraipolis › archive › dc_302b1b59109f

Beyond Trial-and-Error: A Geospatial-Guided Active Reasoning Framework for Robust Aerial Vision-and-Language Navigation — arXiv:2610.41446

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41446
License (as archived)
CC0-1.0
Archived
2026-11-03T08:21:42.775Z
SHA-256 of the archived text
f44a5a467b9b52c07d00e0e22d2412b3c46799324153ad98177a01a21decb2c9
Stable URL of this page
https://metraipolis.com/documento/dc_302b1b59109f

How to cite

Beyond Trial-and-Error: A Geospatial-Guided Active Reasoning Framework for Robust Aerial Vision-and-Language Navigation — arXiv:2610.41446 — arXiv (en), https://arxiv.org/abs/2610.41446 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_302b1b59109f (Metraipolis archive dc_302b1b59109f, sha256 f44a5a467b9b52c07d00e0e22d2412b3c46799324153ad98177a01a21decb2c9)
BibTeX
@misc{dc302b1b59109f,
  title = {Beyond Trial-and-Error: A Geospatial-Guided Active Reasoning Framework for Robust Aerial Vision-and-Language Navigation — arXiv:2610.41446},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41446},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_302b1b59109f; sha256 f44a5a467b9b52c07d00e0e22d2412b3c46799324153ad98177a01a21decb2c9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41446. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Aerial Vision-and-Language Navigation (VLN) requires UAVs to locate language-specified goals in large-scale urban environments, where objects often appear small and visually ambiguous from high-altitude viewpoints. Existing methods largely follow a reactive paradigm common in indoor VLN, repeatedly updating navigation states from local observations while underutilizing the geospatial structure that remains stable during navigation. As a result, visually similar distractors can cause a reactive goal search to repeatedly reinforce locally plausible goal hypotheses based on passively accumulated evidence, leading to unreliable localization. To address this, we propose GeoReasoner, a robust framework that shifts the paradigm of Aerial VLN from reactive trial-and-error to geospatial-guided active reasoning. Specifically, GeoReasoner first performs pre-search geospatial reasoning to derive region-level priors and constrain the goal hypothesis space. Building on these, it further conducts hypothesis-driven exploration to actively acquire discriminative evidence and refine competing goal hypotheses. Finally, consistency-aware goal verification adversarially assesses complementary evidence sources before stopping, hence reducing premature or erroneous goal confirmations. Experiments on the real-world CityNav benchmark demonstrate that GeoReasoner sets a new SOTA among zero-shot Aerial VLN methods while competing favorably with supervised approaches.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.41446 — 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 2026-11-03T08:06:38.831Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).