Simulation-based optimization of Path Planning for camera-equipped UAV considering construction activities

Abstract

Automated progress monitoring of construction sites using cameras has been proposed in recent years. However, collecting images or videos using fixed or pan-tilt-zoom cameras is still limited by the inability to adapt to the dynamic construction environment. Therefore, considerable attention has been paid to using camera-equipped unmanned aerial vehicles (CE-UAVs), which provide mobility to the camera over the construction site. Previous studies in this area proposed methods for capturing the as-built BIM model by using structure from motion (SFM). However, data collection of construction activities of workers and equipment using CE-UAVs has not been discussed before. This paper proposes a method to perform simulation-based optimization of path planning for CE-UAVs to allow automated and effective data collection of construction activities based on a high 4D-LOD as-planned BIM, which includes a detailed micro-schedule and the corresponding workspaces. This method can identify the most informative views of the workspaces and the optimal path for data capturing. The proposed method considers the following requirements and constraints: (1) The fields of view should be optimized to cover the areas of interest and to ensure visibility of the targets considering occlusions according to the 4D BIM model; (2) The path of the UAV should be optimized to allow the data collection from multiple dynamic targets over a large construction site considering the location of activities on the site at specific times and their importance level while reducing the travel cost; and (3) The data collection should consider the requirements for computer vision processes. A case study is developed to demonstrate the feasibility of the proposed method.