Semi-autopilot UAV flight path control for bridge structural health monitoring under GNSS-denied environment
Due to the rapid aging of bridges in Japan, there is a need for an advance and more reliable structural health monitoring techniques. This study conducted an unmanned aerial vehicle (UAV) semi-autopilot path flight controlled method by utilizing the DJI Software Development Kit (SDK) for inspection of Global Navigation Satelite System (GNSS)-denied parts of a bridge specifically in-between girders and other semi- closed and narrow areas. A mini- UAV’s path planning was pre-programmed under a known environment using waypoints and python programming language. A miniature low cost camera was attached as a payload and captured the images underneath the bridge deck aside from the captured images along the line of sight of the UAV. The UAV test flight was done in a pedestrian bridge located at Saitama University. The UAV successfully inspected underneath the bridge deck and some narrow parts in semi-autopilot mode. After that, corrosion, spalling, and crack damages were detected using two different vision based deep learning methods, YOLOv3 and Mask R-CNN. In addition, since the flight path plan was pre- programmed by measured commands, the location of the captured damages were easily located. To visualize the damage location, a 3D model underneath the decks was generated using structure from motion (SfM) and open sourced softwares. Due to the UAV’s small size and the ability to have a semi-autopilot controlled flight path, it eliminated the GNSS dependent problem in bridge damage inspection and been able to inspect narrow areas which were difficult to access. The combination of semi-autopilot inspection under gps-denied parts of bridge inspection, damage detection, and 3D model construction were the main focus of this research.