Planning and scheduling in construction heavily depend on current information about the state of construction processes. However, the acquisition process for visual data requires human personnel to take photographs of construction objects. We propose using unmanned aerial vehicle (UAVs) for automated creation of images and point cloud data of particular construction objects. The method extracts locations of objects that require inspection from Four Dimensional Building Information Modelling (4D-BIM). With this information at hand viable flight missions around the known structures of the construction site are computed. During flight, the UAV uses stereo cameras to detect and avoid any obstacles that are not known to the model, for example moving humans or machinery. The combination of pre-computed waypoint missions and reactive avoidance ensures deterministic routing from takeoff to landing and operational safety for humans and machines. During flight, an additional software component compares the captured point cloud data with the model data, enabling automatic per-object completion checking or reconstruction. The prototype is developed in the Robot Operating System (ROS) and evaluated in Software-In-The-Loop (SITL) simulations for the sake of being executable on real UAVs.

I.A.A.R.C. - International Association for Automation and Robotics in Construction Civil Engineering

BIM-driven projects depend on structured as-built information with high availability, but the acquisition process for visual data involves too much manual labour. Apart from acquisition, the generation of data with laser scanners and other methods requires computationally intensive registration processes. Unmanned Aerial Vehicles (UAVs) have gained attention for all applications that involve re-mote sensing, but still require piloting personnel. UAVs with newly developed reactive autonomy, guided by stereo cameras in addition to standard GPS, enable both auto-mated operation and, more importantly, the generation of structured data that is aligned with the model. This work proposes a toolchain for producing structured point clouds of construction elements in progress.