Vision-language navigation (VLN) for UAVs demands grounding free-form instructions into 6-DoF flight under partial observability. While Vision-Language-Action (VLA) models excel at semantic reasoning, they suffer from brittleness due to geometric inconsistency and dynamics mismatch. To address this, we propose ImagineUAV, an imagination-driven framework leveraging cascaded world-action modeling. Instead of direct regression, ImagineUAV employs a latent video diffusion model to generate instruction-conditioned future observations, explicitly imagining environmental evolution, from which 6-DoF motions are inferred via an action extractor. A kinodynamic planner then refines these estimates into collision-free trajectories. Additionally, a step-distilled inference pipeline ensures real-time execution. With only 1.3B parameters, ImagineUAV outperforms prior VLN and VLA baselines on benchmarks and real-world flights, validating the practicality of imagination-driven aerial navigation.

翻译：视觉-语言导航（VLN）要求无人机在部分可观测条件下，将自由形式的指令具身化为6自由度飞行。尽管视觉-语言-动作（VLA）模型在语义推理方面表现出色，但由于几何不一致性和动力学失配，其稳定性较差。为此，我们提出ImagineUAV——一种基于级联世界-动作建模的想象驱动框架。不同于直接回归，ImagineUAV采用潜在视频扩散模型生成指令条件下的未来观测，显式想象环境演化过程，并通过动作提取器从中推断6自由度运动。随后，动力学规划器将这些估计值优化为无碰撞轨迹。此外，步骤蒸馏推理管线确保实时执行。仅凭13亿参数，ImagineUAV在基准测试和实际飞行中均优于先前的VLN与VLA基线方法，验证了想象驱动空中导航的实用性。