Hao Xuan Zhang

Keeping an up-to-date 3D representation of buildings is a crucial yet time-consuming step for Building Information Modeling (BIM) and digital twins. To address this issue, we propose ICON drone, an unmanned aerial vehicle (UAV) designed to navigate indoor environments autonomously and generate point clouds. ICON drone is constructed using a 250mm quadcopter frame, a Pixhawk flight controller, an onboard computer, an RGB-D camera and an IMU sensor. The UAV navigates autonomously using a visual-inertial odometer (VIO) and frontier-based exploration. The collected RGB images during the flight are used for 3D reconstruction and semantic segmentation. The final outputs are point clouds with building components and material labelling for BIM generation. We tested the UAV in three scenes in an educational building: classroom, lobby, and lounge. Results show that the ICON drone could: 1) explore all three scenes autonomously, 2) generate absolute scale point clouds with mean point-to-point distances of 0.0644, 0.0518, 0.0727m compared to point clouds collected using a high-fidelity terrestrial LiDAR scanner, 3) label the point cloud with corresponding building components and material with mIoU of 0.588 and 0.629.