A pavement rating system based on machine learning

Abstract

The evaluation of roadways utilizing complex contemporary datasets is currently conducted periodically because of the collection methods’ high cost. The study presents a data-driven framework on the use of a vehicle, a smartphone, an on-board diagnostic (OBD) device and machine learning for the rating of pavement surfaces. The proposed system architecture has been field-tested for the detection of pavement anomalies and the classification of five rating categories. Further, the proposed system may provide daily information on roadway pavement surface conditions, which can be used by engineers for automating the planning of pavement maintenance operations and improving public safety.