SPAN-Nav: Generalized Spatial Awareness for Versatile Embodied Navigation
SPAN-Nav is an end-to-end foundation model that gives embodied navigation universal 3D spatial awareness using RGB video. It learns a single, compact spatial token from occupancy prediction tasks across many scenes. This token is then used in a Chain-of-Thought mechanism to explicitly guide action reasoning, allowing the model to generalize its spatial understanding even when explicit supervision is missing.