AirAnchor improves drone navigation by linking local and global views
AirAnchor: Bridging Local and Global Spatial Information for Zero-Shot Aerial Vision-and-Language Navigation
Computer Vision and Pattern RecognitionArtificial IntelligenceRobotics
Summary
Drones need to follow spoken or written instructions to fly through cities, which is tricky because they must understand both nearby details and the bigger picture. Existing methods usually focus on either local sights or global maps, missing a complete understanding. The authors created AirAnchor, a system that connects close-up views with wider spatial knowledge using 'anchors' to help drones decide where to go. Their tests show this combined approach helps drones navigate more accurately without needing prior training in new environments.
Aerial vision-and-language navigationZero-shot learningLocal spatial informationGlobal spatial memorySpatial anchorsNatural language instructionsPath planningLandmark recognitionAutonomous dronesNavigation agent
Authors
Shanwei Fan, Bin Zhang, Zhiwei Xu, Yingxuan Teng, Siqi Dai, Lin Cheng, Guoliang Fan
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 spatial grounding for decision-making. AirAnchor consists of three core components: (1) Query-Driven Spatial Anchor Grounding, which identifies decision-relevant anchors from visual observations and organizes them into local spatial representations; (2) Persistent Object Spatial Memory, which incrementally maintains an object knowledge base as persistent global spatial memory and retrieves landmark-related spatial priors; and (3) a Spatially-Informed Navigation Agent, which explicitly integrates both local and global spatial information into an agentic framework for decision-making. Extensive experiments on AerialVLN demonstrate that AirAnchor substantially outperforms existing zero-shot baselines, validating the effectiveness and efficiency of the proposed paradigm.