Autonomous uav-based 3d-reconstruction of structures for aerial physical interaction

Abstract

We introduce a fully automated only path planning approach especially for drones. This novel method relies on usage of a stereo camera mounted at the bottom of a hexagonal drone for real-time point cloud reconstruction and localization. The real-time point cloud is analyzed in a software loop where the entropy of the point cloud and the surface normals are calculated. The low entropy positions (which indicate the 3D areas with less point density and less information) and the surface normals are used for calculating the next inspection point which can be targeted by the drone in order to enhance the point cloud best. Path planning to these automatically selected target points is done during the flight (quite real-time) and automatically. The initial experiments are performed on Gazebo simulation environment within the ROS system using realistic parameters of our real drone and real stereo camera.