Metraipolis › archive › dc_6bef60f92c67

X-Fly: Learning to Reach and Stop in Full-Chunk Aerial Vision-Language Navigation — arXiv:2610.21450

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21450
License (as archived)
CC0-1.0
Archived
2026-10-16T09:19:40.463Z
SHA-256 of the archived text
aff44aaf114bab960c5735877a9598b46820f2d9ecb88fd7ad028adc00ecf339
Stable URL of this page
https://metraipolis.com/documento/dc_6bef60f92c67

How to cite

X-Fly: Learning to Reach and Stop in Full-Chunk Aerial Vision-Language Navigation — arXiv:2610.21450 — arXiv (en), https://arxiv.org/abs/2610.21450 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6bef60f92c67 (Metraipolis archive dc_6bef60f92c67, sha256 aff44aaf114bab960c5735877a9598b46820f2d9ecb88fd7ad028adc00ecf339)
BibTeX
@misc{dc6bef60f92c67,
  title = {X-Fly: Learning to Reach and Stop in Full-Chunk Aerial Vision-Language Navigation — arXiv:2610.21450},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21450},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6bef60f92c67; sha256 aff44aaf114bab960c5735877a9598b46820f2d9ecb88fd7ad028adc00ecf339},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21450. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Aerial vision-language navigation (VLN) agents built on large vision-language models are expensive to query. Executing a complete predicted action chunk before replanning amortizes this cost, reducing model inference from 195 to 42 ms per executed waypoint for our policy. It also moves the states at which the policy is queried away from expert demonstrations, which supervise neither recovery from these states nor termination at the learner's own arrival. On OpenFly test-seen, no-stop failures account for 47.78% of full-chunk behavior cloning (BC) outcomes. We present X-Fly, a staged training framework for full-chunk aerial VLN. Recovery DAgger labels learner-visited decision states with smooth chunks that reconnect to future expert segments and with STOP at the first in-region state. Flow-GRPO then jointly refines the chunked flow controller and a Bernoulli STOP policy from same-task closed-loop outcomes, supplemented by outcome-verified stopping supervision. With eight controls per decision, X-Fly reaches 74.18% SR on test-seen and 51.73% on test-unseen, compared with 16.45% and 18.43% for full-chunk BC and 32.04% and 29.46% for DreamFly.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.21450 — 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 2026-10-16T08:44:17.951Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).