Masino, J.
Thumm, J.
Frey, M.
Gauterin, F.

Journal of Traffic and Transportation Engineering, Elsevier, Amsterdam, Netherlands, 2017

The condition of the road infrastructure has severe impacts on the road safety, driving comfort, and on the rolling resistance. Therefore, the road infrastructure must be monitored comprehensively and in regular intervals to identify damaged road segments and road hazards. Methods haven been developed to comprehensively and automatically digitize the road infrastructure and estimate the road quality, which are based on vehicle sensors and a supervised machine learning classification. Since different types of vehicles have various suspension systems with different response functions, one classifier cannot be taken over to other vehicles. Usually, a high amount of time is needed to acquire training data for each individual vehicle and classifier. To address this problem we have developed methods to collect training data automatically for new vehicles based on the comparison of trajectories of untrained and trained vehicles. Our results show that the method based on a kd-tree and Euclidean distance performs best and is robust in transferring the information of the road surface from one vehicle to another. Furthermore, our method offers the possibility to merge the output and road infrastructure information from multiple vehicles to enable a more robust and precise prediction of the ground truth.