CoNav-UAV: Cooperative Dual-Altitude Aerial Navigation via Stackelberg Learning

📄 arXiv: 2608.01802v1 📥 PDF

作者: Junru Song, Wenhao Zhang, Yang Yang, Xuekai Qiu, Feifei Wang, Weien Zhou, Tingsong Jiang, Ying Wen, Yang Li, Wen Yao

分类: cs.AI, cs.RO

发布日期: 2026-08-03

💡 一句话要点

提出CoNav-UAV以解决无人机协同导航问题

🎯 匹配领域: 支柱二：RL算法与架构 (RL & Architecture) 支柱九：具身大模型 (Embodied Foundation Models)

关键词: 无人机导航 视觉与语言导航 Stackelberg博弈 协同学习 迭代学习 多模态输入 运动控制 专家蒸馏

📋 核心要点

  1. 现有方法在无人机目标导向导航中存在效率低下和缺乏协同适应的问题，难以实现有效的全球探索与接近目标。
  2. 本文提出CoNav-UAV，通过将任务建模为高空领导者与低空跟随者的Stackelberg博弈，利用机载输入进行自主导航。
  3. 实验结果表明，CoNav-UAV在AerialVLN基准测试中，成功率在学习场景中提高了30.8个百分点，跨场景转移时提高了9.0个百分点。

📝 摘要（中文）

目标导向的视觉与语言导航（VLN）在无人机（UAV）平台上的应用日益受到关注，尤其是在灾难救援、基础设施检查和安全巡逻等任务中。该任务要求无人机根据目标的外观和环境描述进行定位，涉及全球探索与接近目标的过程。现有方法多依赖于地面VLN范式，且在低空无人机的探索效率上存在不足。本文提出CoNav-UAV，通过将任务建模为高空领导者与低空跟随者之间的Stackelberg博弈，利用机载视觉和语言输入进行导航。我们引入了迭代Stackelberg学习，使得领导者的高层次视觉语言推理和跟随者的精确运动控制得以相互优化，从而实现了更高的成功率和更少的适应数据需求。

🔬 方法详解

问题定义：本文旨在解决无人机在目标导向视觉与语言导航中的协同导航问题。现有方法多依赖于外部信息，且缺乏有效的互适应机制，导致导航效率低下。

核心思路：论文将任务建模为高空领导者与低空跟随者之间的Stackelberg博弈，利用机载视觉和语言输入进行导航，强调两者之间的相互作用与优化。

技术框架：整体架构包括高空领导者和低空跟随者两个模块。领导者负责高层次的视觉语言推理，跟随者则进行精确的运动控制。通过迭代Stackelberg学习，两个模块交替优化，达到博弈均衡。

关键创新：引入了迭代Stackelberg学习机制，使得领导者与跟随者能够在没有外部信息的情况下进行有效的协同，显著提升了导航性能。

关键设计：在技术细节上，领导者使用基于记忆的上下文学习来优化推理过程，而跟随者则通过DAgger风格的专家蒸馏进行运动控制更新，确保两者的学习动态互补。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

实验结果显示，CoNav-UAV在AerialVLN基准测试中，成功率在学习场景中提高了30.8个百分点，跨场景转移时提高了9.0个百分点，同时使用的适应数据减少了约3倍，验证了其有效性与优越性。

🎯 应用场景

该研究的潜在应用领域包括灾难救援、基础设施检查和安全巡逻等场景，能够显著提升无人机在复杂环境中的自主导航能力。未来，该方法有望推广到更多无人机协作任务中，提升整体任务效率与安全性。

📄 摘要（原文）

Target-oriented vision-and-language navigation (VLN) on aerial platforms is attracting growing attention for missions such as disaster rescue, infrastructure inspection, and security patrol. In this task, an unmanned aerial vehicle (UAV) needs to locate targets given only a concise description of their appearance and surroundings. This requires global exploration and grounding as well as collision-free close-range approach, two interleaved processes difficult to reconcile within a single agent. Most existing methods transfer the ground VLN paradigm to a low-altitude UAV and compensate for its inefficient exploration with external assistance. A recent attempt deploys two UAVs at complementary altitudes yet still relies on privileged information and trains its two agents independently, precluding any mutual adaptation essential for cooperation. Here we propose CoNav-UAV, which explicitly models the task as a Stackelberg game between a high-altitude leader and a low-altitude follower, with the system operating on onboard visual and linguistic inputs alone. To solve this game, we introduce Iterative Stackelberg Learning. The leader's high-level vision-language reasoning is refined via memory-based in-context learning, while the follower's precise motion control is updated via DAgger-style expert distillation. The alternation drives both agents toward a Stackelberg equilibrium. CoNav-UAV consistently outperforms single- and dual-agent baselines across three high-fidelity urban scenes from the AerialVLN benchmark. Success rate improves by up to 30.8 points on the learning scene, and 9.0 points under cross-scene transfer while using about 3x less adaptation data. Further analyses validate the complementary gains of the leader and follower updates and reveal robust gains yet distinct learning dynamics across VLM backbones.