AirVista-II: An Agentic System for Embodied UAVs Toward Dynamic Scene Semantic Understanding

AirVista-II: An Agentic System for Embodied UA Vs T oward Dynamic Scene Semantic Understanding Fei Lin 1, Y onglin Tian 2, Tengchao Zhang 1, Jun Huang 1, Sangtian Guan 1, and Fei-Y ue Wang 2, 1 Abstract -- Unmanned Aerial V ehicles (UA Vs) are increasingly important in dynamic environments such as logistics transportation and disaster response. However, current tasks often rely on human operators to monitor aerial videos and make operational decisions. This mode of human-machine collaboration suffers from significant limitations in efficiency and adaptability. In this paper, we present AirVista-II--an end-to-end agentic system for embodied UA Vs, designed to enable general-purpose semantic understanding and reasoning in dynamic scenes. The system integrates agent-based task identification and scheduling, multimodal perception mechanisms, and differentiated keyframe extraction strategies tailored for various temporal scenarios, enabling the efficient capture of critical scene information. Experimental results demonstrate that the proposed system achieves high-quality semantic understanding across diverse UA V-based dynamic scenarios under a zero-shot setting.