Metraipolis › archive › dc_7cccbf423bad

What Should a Navigator Remember? Spatiotemporal Memory for Zero-Shot Vision-Language Navigation — arXiv:2610.38318

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.38318
License (as archived): CC0-1.0
Archived: 2026-10-31T06:12:43.754Z
SHA-256 of the archived text: 05e96c53e87dd9f6f59ae1f581d6611871d6d998cb73a4eadc00b5beae60ac58
Stable URL of this page: https://metraipolis.com/documento/dc_7cccbf423bad

How to cite

What Should a Navigator Remember? Spatiotemporal Memory for Zero-Shot Vision-Language Navigation — arXiv:2610.38318 — arXiv (en), https://arxiv.org/abs/2610.38318 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7cccbf423bad (Metraipolis archive dc_7cccbf423bad, sha256 05e96c53e87dd9f6f59ae1f581d6611871d6d998cb73a4eadc00b5beae60ac58)

BibTeX

@misc{dc7cccbf423bad,
  title = {What Should a Navigator Remember? Spatiotemporal Memory for Zero-Shot Vision-Language Navigation — arXiv:2610.38318},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.38318},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7cccbf423bad; sha256 05e96c53e87dd9f6f59ae1f581d6611871d6d998cb73a4eadc00b5beae60ac58},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38318. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Zero-shot vision-and-language navigation (VLN) requires an agent to use past observations without navigation-specific training. We study what information an 8B-scale navigation system should retain and how it should be organized for subsequent decisions. Our agent combines instruction progress, hierarchically compressed observation history anchored to poses, and accumulated geometry in complementary task, temporal, and spatial memories. An 8B observer summarizes observations, and an 8B reasoner uses the memories to select waypoint intents or request additional views, a geometric controller executes the selected targets. A semantic information perspective motivates the distinction between retaining evidence, making it accessible to the reasoner, and acquiring further observations. On R2R-CE val-unseen, the complete system achieves the highest among the evaluated Qwen3-based zero-shot baselines. Removing temporal memory reduces SR and sharply increases average path length from 16.9 to 39.1m, removing the spatial-map and planning component reduces SR as well. Real-world experiments on a Unitree Go2 show that our zero-shot method achieves higher success rates than the post-trained baseline in both corridor and office environments, suggesting better transfer to the evaluated real-world settings. As a complementary evaluation, LAW2 uses paired instruction interventions to examine behavioral responses, instruction following ability beyond endpoint success. These results support preserving task progress, observation history, and geometry in structured memory for zero-shot navigation with smaller open models.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.38318 — 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 2026-10-31T06:07:08.645Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).