AirAnchor: Bridging Local and Global Spatial Information for Zero-Shot Aerial Vision-and-Language Navigation

תקציר מקורי באנגליתarXiv:2609.08442v1 Announce Type: cross Abstract: Aerial Vision-and-Language Navigation requires drones to follow natural-language instructions and navigate through complex urban environments. Accurate navigation relies on both local and global spatial information, which support immediate action grounding and long-horizon path planning, respectively. However, existing zero-shot methods typically operate at a single spatial scale, relying either on local representations constructed online from current observations or on global memories built offline from historical experience. To address this limitation, we propose AirAnchor, a new paradigm that bridges local and global spatial information through spatial anchors and integrates both into a shared navigation framework, enabling comprehensive