Jul 2026
ActiveFly-Bench: Aligning Embodied Question Answering with Vision-Language-Action for Aerial Embodied Perception
The first benchmark to bridge cyberspace reasoning and physical-world interaction for UAV embodied perception is introduced, and ActiveFly, a closed-loop UAV agent that integrates visual-language reasoning with fine-grained control, is developed and deployed on a physical UAV platform.
Weichen Zhang, Shiquan Yu, Yinan Zhu et al.
· arXiv.org · 1 citation