Metraipolis › archive › dc_1f3e64ef753e
Navi-Agent: Unlocalized Monocular Navigation Agent — arXiv:2609.20388
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20388
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T05:08:09.548Z
- SHA-256 of the archived text
a640b3420d13074781b5644ea30b802eec34e4e48c05c57afb79f6d69169bc7a- Stable URL of this page
https://metraipolis.com/documento/dc_1f3e64ef753e
How to cite
Navi-Agent: Unlocalized Monocular Navigation Agent — arXiv:2609.20388 — arXiv (en), https://arxiv.org/abs/2609.20388 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1f3e64ef753e (Metraipolis archive dc_1f3e64ef753e, sha256 a640b3420d13074781b5644ea30b802eec34e4e48c05c57afb79f6d69169bc7a)
BibTeX
@misc{dc1f3e64ef753e,
title = {Navi-Agent: Unlocalized Monocular Navigation Agent — arXiv:2609.20388},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20388},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1f3e64ef753e; sha256 a640b3420d13074781b5644ea30b802eec34e4e48c05c57afb79f6d69169bc7a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20388. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-Language Navigation in Continuous Environments (VLN-CE) requires an embodied agent to execute long-horizon instructions in unknown environments. Existing zero-shot VLN-CE systems typically maintain spatial states through geometric localization or coordinate-based representations. Recent geometry-constrained navigation removes depth and globally consistent coordinates, but maintaining persistent spatial awareness for place confirmation, progress verification, and recovery remains challenging. We present Navi-Agent, a zero-shot VLN-CE agent that constructs a coordinate-free spatial state from visual observations and executed motion histories. Navi-Agent organizes this state as a navigation topology, where nodes represent visual places and edges represent motion transitions. This representation enables observation-based approximate self-localization, task progress verification, and visual revisitation-based recovery. Navi-Agent performs closed-loop navigation by decomposing instructions into sub-goals, executing local visual navigation, and verifying visited places through the constructed spatial state. Experiments on zero-shot VLN-CE benchmark and real-world robot platforms show that Navi-Agent achieves state-of-the-art performance among geometry-constrained methods while remaining competitive with approaches relying on geometric localization. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-18 in cs.CV). Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.20388 — 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 2026-10-10T04:26:09.649Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).