ActiveFly-Bench: Aligning Embodied Question Answering with Vision-Language-Action for Aerial Embodied Perception
2026-07-11 • Robotics
RoboticsArtificial Intelligence
AI summaryⓘ
The authors created ActiveFly-Bench, a new test platform to help drones (UAVs) learn how to see and understand their surroundings while doing tasks. They broke this down into three levels: answering questions about what the drone sees, planning what the drone should look at next, and controlling the drone's movements based on language instructions. They collected data from both real and simulated outdoor places and built a drone system called ActiveFly that combines seeing, understanding, and controlling. Their tests show that current drone systems still find it hard to plan actions and adjust viewpoints accurately, making this benchmark useful for future improvements.
UAVActive PerceptionEmbodied Question AnsweringBehavior PlanningVisual-Language ModelsFine-grained ControlSimulated EnvironmentsClosed-loop ControlAerial Intelligence
Authors
Weichen Zhang, Shiquan Yu, Yinan Zhu, Peizhi Tang, Shilong Ji, Zhiyuan Deng, Tianyi Lyu, Haoyang Wang, Xin Zeng, Chen Gao, Yong Li, Xinlei Chen
Abstract
We introduce ActiveFly-Bench, the first benchmark to bridge cyberspace reasoning and physical-world interaction for UAV embodied perception. The benchmark decomposes active perception into three hierarchical tasks: Aerial Embodied Question Answering (Air-EQA), Observation Behavior Planning (OBP), and Fine-grained Language-guided UAV Control (FLUC), explicitly connecting high-level task understanding, behavior planning, and low-level control. The datasets are collected from both real-world and simulated outdoor environments for training and evaluation. We further develop ActiveFly, a closed-loop UAV agent that integrates visual-language reasoning with fine-grained control, and deploy it on a physical UAV platform. Experiments with representative VLMs and VLA models show that current UAV agents still struggle with behavior planning, viewpoint adjustment, and robust task completion in active perception. These results establish ActiveFly-Bench as a new testbed for embodied aerial intelligence.