Atlas / L3 · Embodied Foundations

Vision-Language Navigation (VLN).视觉语言导航 (VLN).

Embodied spatial navigation that grounds natural language instructions into egocentric visual observations and 3D map exploration.将自然语言指令与第一视角视觉观测、三维空间记忆相结合的跨模态具身导航。

E05 · L3 · Standalone Domain · Cross-Modal Loop

Open in Full Interactive Atlas →在完整交互知识地图中打开 →