In recent years, drones have become prominent in inspection works, largely due to their high mobility. This study focuses on the use of drones for the inspection of infrastructure in indoor environments, such as inside factories or industrial buildings. However, it is difficult to perform inspection tasks manually, so developing stable and effective methods using autonomous flight is essential. Therefore, a navigation algorithm for a drone system equipped with LiDAR was investigated to enable autonomous inspection in indoor environments where GPS is unavailable. In general inspection tasks, capturing images of the surroundings is the primary objective, thus the drone should fly near objects or walls while maintaining a certain distance and perpendicular to them. As a solution, a path planning algorithm using point cloud data from LiDAR was developed to automatically generate flight paths in an indoor environment. It generates the flight path including waypoints with coordinates and yaw angles based on pre-acquired 3D point cloud data. Also, validation experiments were conducted. Demonstrating the system’s usability through two main tests: The First test was autonomous flight using LiDAR, and the second was generation of inspection paths in the experimental environment, followed by autonomous flights along these generated paths for inspection tasks. Furthermore, a 3D model was created using RGB and depth images data captured during the autonomous flights.
Autonomous Flight and Path Planning for an Indoor Inspection Drone Using LiDAR
Lect.Notes Mechanical Engineering
International Conference on Mechanical, System and Control Engineer ; 2024 ; Bangkok, Thailand November 20, 2024 - November 22, 2024
Proceedings of The 7th International Conference on Mechanical, System and Control Engineering ; Kapitel : 14 ; 141-149
26.05.2025
9 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch