Robostral Navigate

  • 类型:arxiv
  • 标识:2607.20785
  • 链接:https://arxiv.org/abs/2607.20785
  • 主分类:multimodal
  • 形态:application
  • 被引:0
  • 被引来源:Semantic Scholar + OpenAlex
  • S2被引:0
  • OpenAlex被引:0
  • 影响力被引:0
  • TLDR:Robostral Navigate, an 8B vision-language model built around this scalability objective, is introduced, which consumes only a stream of monocular RGB images - the most ubiquitous sensor across robotic platforms and predicts waypoints by pointing to the next target location in the current camera view.
  • OpenAlex ID:W7170658200
  • OpenAlex DOI:10.48550/arxiv.2607.20785
  • DOI:10.48550/arxiv.2607.20785
  • DOI来源:OpenAlex
  • 开放获取:green
  • 开放获取链接:https://doi.org/10.48550/arxiv.2607.20785
  • OpenAlex更新:2026-08-24
  • 待LLM分类:否
  • 标题中文:Robostral Navigate
  • TLDR中文:提出 Robostral Navigate,一个围绕该可扩展性目标构建的 8B 视觉语言模型,仅消费单目 RGB 图像流——这是机器人平台中最普及的传感器——通过在当前相机画面中指向下一目标位置来预测航点。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-24-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • [OpenAlex backfill]