Metraipolis › archive › dc_bf1398bb8504

One MLLM, One Call: Efficient Zero-Shot Vision-and-Language Navigation via Spatial-Aware Waypoints — arXiv:2609.06476

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.06476
License (as archived)
CC0-1.0
Archived
2026-10-16T15:07:05.427Z
SHA-256 of the archived text
da0310362508999c151889e12183ccc471d6fcc1951a6be618a6c8922cc55cde
Stable URL of this page
https://metraipolis.com/documento/dc_bf1398bb8504

How to cite

One MLLM, One Call: Efficient Zero-Shot Vision-and-Language Navigation via Spatial-Aware Waypoints — arXiv:2609.06476 — arXiv (en), https://arxiv.org/abs/2609.06476 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf1398bb8504 (Metraipolis archive dc_bf1398bb8504, sha256 da0310362508999c151889e12183ccc471d6fcc1951a6be618a6c8922cc55cde)
BibTeX
@misc{dcbf1398bb8504,
  title = {One MLLM, One Call: Efficient Zero-Shot Vision-and-Language Navigation via Spatial-Aware Waypoints — arXiv:2609.06476},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06476},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf1398bb8504; sha256 da0310362508999c151889e12183ccc471d6fcc1951a6be618a6c8922cc55cde},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06476. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-and-Language Navigation in Continuous Environments (VLN-CE) requires an embodied agent to navigate unseen environments by following natural language instructions. Current zero-shot VLN-CE methods either rely on pre-trained waypoint predictors or require multiple queries to large models per step. To address prohibitive inference latency and computational overhead, we propose O2C-Nav, an efficient zero-shot navigation framework that calls only a single large model once per decision step. Our approach introduces a training-free structured waypoint generator and a novel abstract representation that projects sparse, history-aware candidate waypoints directly onto RGB images as visual markers. The MLLM selects a waypoint or generates a fallback target bounding box at each step, while a low-level Fast Marching Method (FMM) planner converts the selected target into an executable collision-free path. This paradigm provides the model with concrete spatial perception and explicit memory while significantly reducing the visual processing load. Extensive evaluations on the R2R-CE and RxR-CE benchmarks demonstrate that O2C-Nav outperforms current state-of-the-art zero-shot methods, highlighting its great potential for real-time robotic deployment. Code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.06476 — 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 2026-10-16T14:49:57.089Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).