arXiv cs.AI· Yuze Wu, Mo Zhu, Xingxing Li, Yuheng Du, Zhaoqi Wang, Yuxin Fan, Wenjun Li, Kenghou Hoi, Zhichao Han, Xin Zhou, Fei Gao·· 10 小时前AI 评分32
VLN-AR:面向复杂环境空中机器人的分层视觉-语言-导航框架
A Hierarchical Onboard Vision-Language-Navigation Framework for Aerial Robots in Complex Environments
AI 导读
研究团队提出 VLN-AR 分层视觉-语言-导航框架,将多模态推理与底层控制解耦,实现 3D 位姿指令与导航意图的结构化预测并转化为动态可行动作。该框架用基于 3D Gaussian Splatting 的全自动流程生成可扩展的逼真 UAV 导航数据,并采用三阶段渐进训练策略。
正文 · 原文
Authors:Yuze Wu, Mo Zhu, Xingxing Li, Yuheng Du, Zhaoqi Wang, Yuxin Fan, Wenjun Li, Kenghou Hoi, Zhichao Han, Xin Zhou, Fei Gao
Abstract:Unmanned Aerial Vehicles (UAVs) are expected to achieve semantic reasoning, intelligent decision-making, and long-horizon navigation under strict onboard constraints. While recent foundation-model-driven approaches have shown promising progress toward this goal, existing methods remain limited by challenges in 3D data availability, trajectory feasibility, long-horizon reasoning, and computational efficiency in complex environments. To bridge these gaps, we propose VLN-AR, a hierarchical vision-language-navigation (VLN) framework for aerial robots. VLN-AR decouples multimodal reasoning and low-level control, enabling structured prediction of 3D pose commands and navigation intentions that are translated into dynamically feasible actions. To mitigate data scarcity and domain gaps, we introduce a fully automated 3D Gaussian Splatting (3DGS)-based pipeline to generate scalable photorealistic UAV navigation data. A progressive three-stage training strategy further enhances grounding, scene reasoning, and complex navigation. In addition, a lightweight cognitive agent improves long-horizon reasoning via memory-aware task decomposition. Finally, we design onboard optimization techniques, including token sparsification and model lightweighting, achieving 7.1x-9.4x speedup while maintaining high navigation performance on resource-limited UAV platforms. Experiments show great improvements over existing methods in both simulation and real-world UAV navigation. Project website: this https URL
| Comments: | 20 pages, 14 figures |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.23930 [cs.RO] |
| (or arXiv:2611.23930v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23930 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | IEEE Transactions on Robotics, 2026 |
| Related DOI: | https://doi.org/10.1109/TRO.2026.3754505
DOI(s) linking to related resources |
Submission history
From: Yuze Wu [view email]
[v1]
Wed, 18 Nov 2026 06:21:08 UTC (7,576 KB)
来源:arXiv cs.AI · arxiv.org