fengtt42/U2UData-2

Swarm_UAV_dataset_2是一个大规模群体无人机自主飞行数据集，专门为长航时任务设计。该数据集由15架无人机在自主协作飞行中捕获，包含12个场景、720个轨迹、120小时飞行时间、每个轨迹600秒、432万LiDAR帧和1296万RGB帧。数据集还包含了所有飞行路线的亮度、温度、湿度、烟雾和气流值。此数据集旨在支持定制模拟器、无人机、传感器、飞行算法、编队模式和长航时任务，并通过一个可视化控制窗口，允许用户通过一键在线部署收集定制数据集，并通过闭环模拟验证算法。数据集还包括了一个针对野生动物保护的长航时任务，并提供了9个最先进模型的全面基准。

Swarm_UAV_dataset_2 is a large-scale swarm UAV autonomous flight dataset designed for long-horizon tasks. Captured by 15 UAVs in autonomous collaborative flights, it includes 12 scenes, 720 trajectories, 120 hours of flight time, 600 seconds per trajectory, 4.32 million LiDAR frames, and 12.96 million RGB frames. The dataset also includes brightness, temperature, humidity, smoke, and airflow values for all flight routes. It is intended to support the customization of simulators, UAVs, sensors, flight algorithms, formation modes, and long-horizon tasks, and allows users to collect customized datasets through one-click online deployment and verify algorithms through closed-loop simulation via a visual control window. The dataset also introduces a long-horizon task for wildlife conservation and provides comprehensive benchmarks with 9 state-of-the-art models.