skip to content

Digital Roads of the Future


We need a step change in controlling and monitoring processes and anticipating and measuring their performance holistically to address the permanent budget shortfall of road authorities. This can be achieved with data science methods for (i) KPIs monitoring and control and (ii) deriving processes from product information in the digital twin that can enable direct control of robotic maintenance and repair operations. This WP focuses on the Data Science and Machine Learning methodology essential in synthesising DTs with new materials, novel sensing and measurement techniques for road assets at TRL2, as well as providing the means for control of robotic monitoring and communication exploiting data-rich feedback from new materials at TRL3. The challenges faced relate to data integration from diverse sources that are heterogeneous in fidelity, volume, coverage, quality, and levels of information available from material-based sensing systems, robotic systems, and digital twins. This WP is also driven by the need to ensure sound quantification of uncertainty in data, providing the means to couple self-sensing materials with computational digital twins and robotic processes. 

Future Roads ongoing projects

Title: Digital twin-driven Bayesian dynamic linear model and reinforcement learning for predictive maintenance of pavements 

Fellow: Yiming Zhang