AI RESEARCH
UAV-Track VLA: Embodied Aerial Tracking via Vision-Language-Action Models
arXiv CS.CV
•
ArXi:2604.02241v1 Announce Type: new Embodied visual tracking is crucial for Unmanned Aerial Vehicles (UAVs) executing complex real-world tasks. In dynamic urban scenarios with complex semantic requirements, Vision-Language-Action (VLA) models show great promise due to their cross-modal fusion and continuous action generation capabilities. To benchmark multimodal tracking in such environments, we construct a dedicated evaluation benchmark and a large-scale dataset encompassing over 890K frames, 176 tasks, and 85 diverse objects.