The Obstacle Detection and Avoidance Dataset for Drones

We introduce the Obstacle Detection and Avoidance Dataset for Drones, aiming at providing raw data obtained in a real indoor environment with sensors adapted for aerial robotics. Our micro air vehicle (MAV) is equipped with the following sensors: (i) an event-based camera, the dynamic performance of which make it optimized for drone applications; (ii) a standard RGB camera; (iii) a 24-GHz radar sensor to enhance multi-sensory solutions; and (iv) a 6-axes IMU. The ground truth position and attitude are provided by the OptiTrack motion capture system. The resulting dataset consists in more than 1350 samples obtained in four distinct conditions (one or two obstacles, full or dim light). It is intended for benchmarking algorithmic and neural solutions for obstacle detection and avoidance with UAVs, but also course estimation and therefore autonomous navigation. For further information, please visit: https://github.com/tudelft/ODA_Dataset

本文提出面向无人机的障碍物检测与规避数据集（Obstacle Detection and Avoidance Dataset for Drones），旨在提供适配空中机器人的传感器在真实室内环境中采集的原始数据。本研究使用的微型无人机（micro air vehicle, MAV）搭载了以下传感器：（i）事件相机（event-based camera），其动态性能优异，专为无人机应用场景优化；（ii）标准RGB相机；（iii）24GHz雷达传感器，用于优化多传感器融合方案；（iv）六轴惯性测量单元（6-axes IMU）。数据集的真实位置与姿态真值由OptiTrack动作捕捉系统提供。最终构建的数据集包含超过1350条样本，采集自四种不同场景：单障碍物或双障碍物环境、明亮或昏暗光照条件。本数据集可用于开展无人机（Unmanned Aerial Vehicle, UAV）障碍物检测与规避算法、神经网络方案的基准测试，同时也可用于航迹估计乃至自主导航相关研究。如需获取更多信息，请访问：https://github.com/tudelft/ODA_Dataset

搜集汇总

背景与挑战

背景概述

该数据集是一个专为无人机设计的障碍物检测与避障数据集，发布于2021年，包含在真实室内环境中通过多种传感器（如事件相机、RGB相机、雷达和IMU）采集的原始数据，并提供了超过1350个样本，覆盖不同光照和障碍物数量的条件。它主要用于基准测试算法和神经解决方案，以支持无人机的自主导航、障碍物检测与避障研究，适用于人工智能和航空航天工程领域。