AIR-VLA: Vision-Language-Action Systems for Aerial Manipulation

TL;DR

This paper introduces AIR-VLA, a comprehensive benchmark and dataset for vision-language-action modeling in aerial manipulation, addressing unique challenges of UAV dynamics and multi-step tasks, and evaluating current models' capabilities.

Contribution

It presents the first VLA benchmark tailored for aerial manipulation, including a simulation environment, a multimodal dataset, and systematic evaluation of existing models.

Findings

Current VLA models show limited performance on aerial tasks.

The benchmark reveals specific challenges in UAV mobility and manipulator control.

AIR-VLA provides a foundation for future aerial robotics research.

Abstract

While Vision-Language-Action (VLA) models have achieved remarkable success in ground-based embodied intelligence, their application to Aerial Manipulation Systems (AMS) remains a largely unexplored frontier. The inherent characteristics of AMS, including floating-base dynamics, strong coupling between the UAV and the manipulator, and the multi-step, long-horizon nature of operational tasks, pose severe challenges to existing VLA paradigms designed for static or 2D mobile bases. To bridge this gap, we propose \textbf{AIR-VLA}, the first VLA benchmark specifically tailored for aerial manipulation. We construct a physics-based simulation environment and release a high-quality multimodal dataset comprising 3000 manually teleoperated demonstrations, covering base manipulation, object \& spatial understanding, semantic reasoning, and long-horizon planning. Leveraging this platform, we systematically evaluate mainstream VLA models and state-of-the-art VLM models. Our experiments not only validate the feasibility of transferring VLA paradigms to aerial systems but also, through multi-dimensional metrics tailored to aerial tasks, reveal the capabilities and boundaries of current models regarding UAV mobility, manipulator control, and high-level planning. \textbf{AIR-VLA} establishes a standardized testbed and data foundation for future research in general-purpose aerial robotics. The resource of AIR-VLA will be available at https://github.com/SpencerSon2001/AIR-VLA.