RESEARCH PAPER

ImagineUAV: Aerial Vision-Language Navigation via World-Action Modeling and Kinodynamic Planning

Liu, Xuchen; Huang, Jiawei; Xia, Shihao; Liu, Bingxi; Cui, Jinqiang; Yang, Jiankun

Classification

View four quadrants
Major category
WAMs
Architecture
Dual-system
Prediction paradigm
IDM
Source review status
Verified from primary sources
AT A GLANCE

Contribution

To address this, we propose ImagineUAV, an imagination-driven framework leveraging cascaded world-action modeling. 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.

Abstract

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.

Affiliations

Xuchen Liu, Jinqiang Cui and Jiankun Yang are with Pengcheng Laboratory, Shenzhen, Guangdong, China (e-mail: liuxch,cuijq,jiankun @pcl.ac.cn)

BibTeX