AutoFly：面向野外无人机自主导航的视觉-语言-动作模型
AutoFly: Vision-Language-Action Model for UAV Autonomous Navigation in the Wild
AI总结：
AutoFly是一种面向野外无人机自主导航的视觉-语言-动作模型，通过伪深度编码器和渐进两阶段训练策略，实现自主避障和规划，提升导航成功率。
摘要：
视觉-语言导航（VLN）要求智能体通过解读语言指令和视觉观测来导航环境，是具身人工智能的核心任务。当前无人机（UAV）的VLN研究依赖于详细的、预先指定的指令来引导无人机沿预定路线飞行。然而，现实世界户外探索通常发生在未知环境中，详细导航指令不可用。相反，只能提供粗粒度的位置或方向指导，要求无人机通过连续规划和避障自主导航。为此，我们提出了AutoFly，一种端到端的视觉-语言-动作（VLA）模型，用于自主无人机导航。AutoFly集成了一个伪深度编码器，从RGB输入中推导出深度感知特征以增强空间推理，结合了渐进的两阶段训练策略，有效对齐视觉、深度和语言表示与动作策略。此外，现有VLN数据集对真实世界自主导航有根本性的局限性，源于其对显式指令遵循的依赖远大于自主决策，以及数据的不足。为了解决这些问题，我们构建了一个新的自主导航数据集，通过：（1）轨迹收集强调连续避障、自主规划和识别流程；（2）全面的现实世界数据整合，将范式从指令遵循转向自主行为建模。实验结果表明，AutoFly在与现有最先进VLA基线相比，成功率达到3.9%的提升，在模拟和真实环境中均表现出一致的性能。
英文摘要：
Vision-language navigation (VLN) requires intelligent agents to navigate environments by interpreting linguistic instructions alongside visual observations, serving as a cornerstone task in Embodied AI. Current VLN research for unmanned aerial vehicles (UAVs) relies on detailed, pre-specified instructions to guide the UAV along predetermined routes. However, real-world outdoor exploration typically occurs in unknown environments where detailed navigation instructions are unavailable. Instead, only coarse-grained positional or directional guidance can be provided, requiring UAVs to autonomously navigate through continuous planning and obstacle avoidance. To bridge this gap, we propose AutoFly, an end-to-end Vision-Language-Action (VLA) model for autonomous UAV navigation. AutoFly incorporates a pseudo-depth encoder that derives depth-aware features from RGB inputs to enhance spatial reasoning, coupled with a progressive two-stage training strategy that effectively aligns visual, depth, and linguistic representations with action policies. Moreover, existing VLN datasets have fundamental limitations for real-world autonomous navigation, stemming from their heavy reliance on explicit instruction-following over autonomous decision-making and insufficient real-world data. To address these issues, we construct a novel autonomous navigation dataset that shifts the paradigm from instruction-following to autonomous behavior modeling through: (1) trajectory collection emphasizing continuous obstacle avoidance, autonomous planning, and recognition workflows; (2) comprehensive real-world data integration. Experimental results demonstrate that AutoFly achieves a 3.9% higher success rate compared to state-of-the-art VLA baselines, with consistent performance across simulated and real environments.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
