Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2606.01205 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914621428858880 |
|---|---|
| author | Liu, Xuchen Huang, Jiawei Xia, Shihao Liu, Bingxi Cui, Jinqiang Yang, Jiankun |
| author_facet | Liu, Xuchen Huang, Jiawei Xia, Shihao Liu, Bingxi Cui, Jinqiang Yang, Jiankun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_01205 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ImagineUAV: Aerial Vision-Language Navigation via World-Action Modeling and Kinodynamic Planning Liu, Xuchen Huang, Jiawei Xia, Shihao Liu, Bingxi Cui, Jinqiang Yang, Jiankun Robotics 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. |
| title | ImagineUAV: Aerial Vision-Language Navigation via World-Action Modeling and Kinodynamic Planning |
| topic | Robotics |
| url | https://arxiv.org/abs/2606.01205 |