Metraipolis › archive › dc_fd4e3c635f27

PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation — arXiv:2609.34759

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34759
License (as archived)
CC0-1.0
Archived
2026-10-07T23:52:25.117Z
SHA-256 of the archived text
e412067e83738a771e3757403b7cf33b3fe3d2ac1fad0d32ce69bb925a0e433f
Stable URL of this page
https://metraipolis.com/documento/dc_fd4e3c635f27

How to cite

PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation — arXiv:2609.34759 — arXiv (en), https://arxiv.org/abs/2609.34759 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fd4e3c635f27 (Metraipolis archive dc_fd4e3c635f27, sha256 e412067e83738a771e3757403b7cf33b3fe3d2ac1fad0d32ce69bb925a0e433f)
BibTeX
@misc{dcfd4e3c635f27,
  title = {PanoVLN: Towards Effective Panoramic Vision-and-Language Navigation — arXiv:2609.34759},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34759},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fd4e3c635f27; sha256 e412067e83738a771e3757403b7cf33b3fe3d2ac1fad0d32ce69bb925a0e433f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34759. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent vision-language models (VLMs) have advanced vision-and-language navigation (VLN), enabling models to predict navigation actions from visual observations and language instructions. In this work, we explore VLN with panoramic observations and introduce PanoVLN. The motivation is straightforward: more complete visual context should enable better-informed navigation decisions. For example, a panorama can reveal a passage outside a perspective camera's field of view, allowing the model to identify the intended route without additional exploration. However, we find that simply replacing perspective images with panoramas yields only limited gains. Our diagnosis suggests that fully exploiting wider visibility requires modifications to action prediction, training supervision, and visual representation. First, wider visibility supports longer-horizon action planning. We make the model predict longer action sequences, enabling larger turns and subsequent movement from a single panorama. Specifically, we introduce a confidence-guided execution (CGE) strategy that dynamically determines how many predicted actions to execute before replanning. Second, wider visibility also brings more complex route choices. We therefore construct training routes with frequent branching points and clear instructions to provide targeted supervision for route selection. Third, panoramic navigation requires understanding spatial relationships across viewing directions, beyond recognizing individual landmarks. We combine semantic and geometric features from RGB panoramas to capture both scene content and spatial layout without adding visual tokens. With a 4B backbone and RGB-only input, PanoVLN surpasses the previous SOTA by 11.9% and 8.7% in success rate on R2R-CE and RxR-CE Val-Unseen. Real-world experiments on a quadruped further demonstrate faster navigation with fewer pauses than prior VLN methods.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.34759 — 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 2026-10-07T23:29:27.448Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).