DynFly: 面向城市环境无人机视觉语言导航的动态感知连续轨迹生成
DynFly: Dynamic-Aware Continuous Trajectory Generation for UAV Vision-Language Navigation in Urban Environments
AI总结：
提出DynFly框架，通过B样条控制点空间表示和Spline-DiT生成器，结合无人机动态感知监督，将高层导航意图转化为连续可执行轨迹，显著提升导航性能和轨迹质量。
摘要：
多模态大模型的最新进展通过增强高层感知和推理能力，显著提升了无人机视觉语言导航（UAV-VLN）。然而，现有方法主要关注预测离散动作、局部目标或稀疏航点，而从导航意图到可执行无人机运动的连续转换仍然建模不足。这种运动接口差距限制了生成轨迹的连续性、稳定性和可执行性。为解决这一问题，我们提出DynFly，一种动态感知的连续轨迹生成框架，桥接了高层导航推理与可执行无人机运动。DynFly通过轻量级轨迹生成层连接高层导航意图和连续无人机运动。具体而言，它将专家轨迹表示为B样条控制点空间，并采用Spline-DiT生成器通过流匹配学习条件轨迹生成。此外，我们引入了面向无人机的动态感知监督，包括位置、有限差分速度、有限差分加速度、航向一致性和局部目标对齐，使生成的轨迹更好地满足无人机运动特性。我们的轨迹生成框架还可以与现有的UAV-VLN框架集成，同时保留其原始的视觉语言推理流程。在OpenUAV UAV-VLN基准上的大量实验表明，DynFly同时提升了导航性能和轨迹质量。在Test Unseen Full分割上，DynFly相比最强基线提升了4.69 NDTW、2.40 SDTW、2.14 SR点和4.87 OSR点，同时NE降低了4.51米。
英文摘要：
Recent advances in multimodal large models have significantly improved UAV vision-language navigation (UAV-VLN) by enhancing high-level perception and reasoning. However, existing methods mainly focus on predicting discrete actions, local targets, or sparse waypoints, while the continuous transition from navigation intent to executable UAV motion remains weakly modeled. This motion-interface gap limits the continuity, stability, and executability of generated UAV trajectories. To address this gap, we propose DynFly, a dynamic-aware continuous trajectory generation framework that bridges high-level navigation reasoning and executable UAV motion. DynFly bridges high-level navigation intent and continuous UAV motion through a lightweight trajectory generation layer. Specifically, it represents expert trajectories in B-spline control-point space and employs a Spline-DiT generator to learn conditional trajectory generation via flow matching. Furthermore, we introduce UAV-oriented dynamic-aware supervision over position, finite-difference velocity, finite-difference acceleration, heading consistency, and local target alignment, enabling the generated trajectories to better satisfy UAV motion characteristics. And our trajectory generation framework can also be integrated with an existing UAV-VLN framework while preserving its original visual-language reasoning pipeline. Extensive experiments on the OpenUAV UAV-VLN benchmark show that DynFly improves both navigation performance and trajectory quality. On the Test Unseen Full split, DynFly improves the strongest baseline by 4.69 NDTW, 2.40 SDTW, 2.14 SR points and 4.87 OSR points, while reducing NE by 4.51 m.
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。
