{
  "id": 13016,
  "url": "https://arxiv.org/abs/2607.20785",
  "title": "Robostral Navigate",
  "summary": "Deploying navigation systems at scale requires a recipe that minimizes sensor assumptions, generalizes across robot embodiments, and trains efficiently. Yet, today's best systems depend on depth sensors, multi-camera rigs, or pre-built maps, limiting the hardware they support and increasing deployment cost. We introduce Robostral Navigate, an 8B vision-language model built around this scalability objective. The model consumes only a stream of monocular RGB images - the most ubiquitous sensor acr",
  "authors": "Arjun Majumdar, Avinash Sooriyarachchi, Benjamin Tibi, Chris Bamford, Elliot Chane-Sane, Guillaume Lample",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-21T20:00:00.000Z",
  "fetched_at": "2026-07-25T05:10:48.796Z",
  "source_slug": "hf-daily",
  "source_name": "HuggingFace Daily Papers",
  "source_homepage": "https://huggingface.co/papers",
  "ethics_ai_record_url": "https://ethics.ai/record/13016",
  "original_url": "https://arxiv.org/abs/2607.20785",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}