Process for the Development of a Digital Twin of a Local Road – A Case Study

Virtual replicas of infrastructure can be used to run simulations and optimize the construction, management and maintenance of such assets throughout its entire lifecycle. These Digital Twins (defined as integrated multi-physics, multiscale, and probabilistic simulations of a complex product) mirror the behavior and environmental responses of its corresponding twin. Digital reconstruction techniques using optical sensor technologies and mobile sensor platforms are providing viable, low-cost alternatives to develop Digital Twins of physical infrastructure. In previous work, the digital twinning of asphalt pavement surfacings using visual Simultaneous Localization And Mapping (vSLAM) was investigated and successfully demonstrated on a small area of an asphalt surfacing. In this paper, a larger study was pursued to demonstrate the successful implementation of micro-twinning and macro-twinning of a local road. Light Detection And Ranging (LIDAR), Unmanned Aerial Vehicles (UAVs) and traffic counting Artificial Intelligence (AI) allows for quantification of the road geometry and infrastructure utilization over large areas (macro-twinning), whereas the photogrammetric reconstruction technique based on a Neural Network (NN) and a proprietary environmental condition sensor (SNOET) were used to acquire the surface texture and environmental conditions respectively (micro-twinning). These entry-level instrumentation and techniques accurately measured the geometry, surface characteristics and utilization of the generic road section. The addition of advanced environmental monitoring sensors provide management data that can assist in the maintenance of such roads.