研究人员首次演示了在轨使用零样本视觉语言模型进行自主地球观测。部署在航天器上的 NAVI-Orbital 系统能够对场景进行分类、生成文本描述，并响应自然语言提示，而无需针对特定仪器进行微调或下载所有数据。这种方法实现了太空观测的语义压缩，解决了数据生成与处理能力之间日益增长的差距。 AI
影响 实现太空中的自主决策和数据压缩，可能减少下行带宽需求并加速地球观测的情报收集。
排序理由 该集群描述了发表在 arXiv 上的研究，详细介绍了一种新颖的 AI 模型应用。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2606.18271v1 Announce Type: new Abstract: As Earth Observation data generation outpaces downlink bandwidth and human-in-the-loop processing, a widening gap has emerged between onboard collection and actionable ground intelligence. This paper presents NAVI-Orbital, a softwar…
arXiv:2606.15427v1 Announce Type: cross Abstract: Spaceborne inspection systems often deploy perception models prior to launch, after which updating model weights or expanding fixed label sets becomes operationally impractical. While supervised models can be integrated pre-flight…
🤖 Satellite AI Takes Off: Zero-Shot Models Run Onboard in Orbit Spacecraft are now capable of running zero shot vision language models entirely onboard, enabling autonomous multi modal inference in Low Earth Orbit. This development was marked by the deployment of NAVI Orbital, a …