Metraipolis › archive › dc_6880cd913641
AnchorVLN: Geometry-Anchored Vision-Language Grounding Reasoning for Open-Vocabulary Navigation — arXiv:2609.12285
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12285
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:57:54.035Z
- SHA-256 of the archived text
98b44af81d3ae99cace9d7d6b185638294e65e23cae9f7f3e5a67ea67a36f18a- Stable URL of this page
https://metraipolis.com/documento/dc_6880cd913641
How to cite
AnchorVLN: Geometry-Anchored Vision-Language Grounding Reasoning for Open-Vocabulary Navigation — arXiv:2609.12285 — arXiv (en), https://arxiv.org/abs/2609.12285 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6880cd913641 (Metraipolis archive dc_6880cd913641, sha256 98b44af81d3ae99cace9d7d6b185638294e65e23cae9f7f3e5a67ea67a36f18a)
BibTeX
@misc{dc6880cd913641,
title = {AnchorVLN: Geometry-Anchored Vision-Language Grounding Reasoning for Open-Vocabulary Navigation — arXiv:2609.12285},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12285},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6880cd913641; sha256 98b44af81d3ae99cace9d7d6b185638294e65e23cae9f7f3e5a67ea67a36f18a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12285. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Vision-Language Navigation (VLN) in unseen indoor environments is useful in real-world robotics, where an agent must follow natural-language instructions, locate objects, and answer spatial questions without a pre-built map or fixed object vocabulary. Multimodal vision-language models (VLMs) provide strong open-vocabulary grounding and zero-shot reasoning, but struggle to emit reliable metric quantities such as range, bearing, and comparative spatial relations directly from images. Existing approaches address this by folding geometry into hand-engineered pipelines or asking models to output waypoints, requiring changes to the control stack for different robots, tasks, or vocabularies. We introduce AnchorVLN, an open-vocabulary VLN system built on a simple rule: the VLM proposes semantics; geometry decides metrics. It is realised as EMBODIED-NAV-MCP, a Model Context Protocol (MCP) server driven by a VLM agent through a compact set of callable tools. Since no tool accepts distance in metres or bearing in radians, the schema enforces the semantic-geometry boundary without modifying the downstream autonomy stack. We benchmark both tasks of the CMU Vision-Language Navigation Challenge 2026: 30 instruction-following questions over 15 scenes and a frozen 45-question object-reference set. The full system achieves 64.4 percent on instruction following, dropping by 13.3 percentage points without controller modeling (t = 2.77). On object reference, geometric anchoring clears the challenge overlap threshold on 10 of 45 questions, versus 0 of 45 for direct coordinate estimation, reducing median center error from 3.37 m to 2.48 m. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-14 in cs.CV). Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.12285 — 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 2026-10-16T03:44:26.344Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).