ImagineUAV: 世界モデルと運動力学的計画による空中視覚言語ナビゲーション
ImagineUAV: Aerial Vision-Language Navigation via World-Action Modeling and Kinodynamic Planning
UAVの視覚言語ナビゲーションにおいて、潜在ビデオ拡散モデルで未来の観測を想像し、そこから6自由度の動作を抽出して衝突回避軌道を計画するフレームワークを提案。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Xuchen Liu, Jiawei Huang, Shihao Xia, Bingxi Liu, Jinqiang Cui, Jiankun Yang
分類: cs.RO
原文アブストラクト
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.
