Work

OS-RFODG: Open-source ROS2 framework for outdoor UAV dataset generation

Year: 2025

Type: article

Abstract: Accurate localization is critical for Unmanned Aerial Vehicles (UAVs) in applications such as military operations, search and rescue, and environmental monitoring. However, existing open-source UAV datasets often lack the synchronization and detail necessary for high-precision localization in complex outdoor environments. To address this limitation, we introduce the Open-Source ROS2 Framework for Outdoor UAV Dataset Generation (OS-RFODG), a cost-effective solution for creating high-quality UAV localization datasets. OS-RFODG integrates the ROS2 platform with PX4 autopilot, Gazebo simulation, and QGroundControl to generate synchronized sensor data, including LiDAR, GPS, IMUs, cameras, and barometers. The framework also incorporates geospatial data from Blender and QGIS to produce detailed 3D digital maps, enhancing terrain representation and global mapping accuracy. Experimental results show that OS-RFODG achieves a root mean square error (RMSE) below 19.5 meters across diverse terrains, closely aligning trajectories with real-world conditions. This framework offers a practical solution to overcome data quality limitations, which can enhance UAV localization techniques and develop more robust AI-driven navigation systems.

Source: Results in Engineering

DOI: 10.1016/j.rineng.2025.106613