Construction Digital Twins for automated digital construction site monitoring

The construction industry must lower failure costs that are caused by delays and construction errors. To this end, the progress and quality of construction sites must be systematically and digitally monitored and the designs updated to as-built conditions. 

The objective of this project is to fulfil the above needs by conceiving construction digital twins –a novel BIM that models the life-cycle of the construction’s execution phase using periodic monitoring information. The necessary geometric and visual inputs of these construction digital twins will be extracted from remote sensing through high innovative machine learning.

The starting point of our research is the development of multi-modal semantic segmentation models that process the periodically captured point clouds and imagery of construction sites. Concretely, we will design the new groundbreaking deep learning architecture needed for this segmentation and generalize it for the different building domains. 

The second stage of the research is the unsupervised extraction of the progress and quality of the objects and the integration with BIM to create the construction digital twins. Concretely, we will develop the novel methodology needed to determine and represent the built status and quality (shape, appearance) of the objects and their components in consecutive construction phases. Upon project completion, the construction digital twins also constitute the mandatory as-built BIM for post-construction processes.