AUTOSTRADA is a mobile application developed in-house as part of the Pavement Management System service that we offer.
The application collects positioning and accelerometer data as well as regular manual driver inputs. Smartphone application data is correlated with KPIs determined using pavement defect and International roughness Index data collected with a Laser Crack Measuring System. Statistical and machine learning models are developed for the approximation of KPIs from smartphone data, and then the resulting models are used to predict pavement KPIs beyond the training dataset. The performance of alternative models is also examined.
This cost-saving approach informs the deployment and running of a highly optimized Pavement Asset Management System that can be applied to roads and motorways, as well as airport runways and ocean freight terminals.
How it works
Each studied road section is divided into 100m-long segments. Using the smartphone app data geo-referencing, ROMDAS LCMS surveys are performed over these segments.
While driving on a road that is being studied, users of the app generate inputs whereby they rate the state of the pavement. Each user assigns the severity of rutting, linear cracking, area cracking, raveling, and potholes using a star system. This data is then aggregated for each segment, and the pavement KPI is calculated.
Improvements are being made to reduce the length of the segment in order to establish more accurate results.