A MODEL FOR THE ESTIMATION OF ROAD ROUGHNESS CONDITION FROM SENSOR DATA COLLECTED BY ANDROID SMARTPHONES

抄録

Road roughness condition information is very important for the maintenance planning and management of road infrastructure. Collecting such information is time and resource consuming because it usually requires either, if not all, skillful manpower, substantial budget, and sophisticated equipment. Therefore, collecting and updating road roughness condition is viewed as a big challenge for many road authorities. The final goal of our research is to explore for a low cost and easy to use approach for the aforementioned purpose by using Android smartphones to estimate road roughness and traffic conditions. In this study we develop a model based on a relationship function of smartphone sensor data and road roughness condition. The relationship function is drawn from our experiment in Vientiane, Laos, in which we have found that the acceleration data from smartphones has a linear relationship with road roughness condition and the significant of the relationship also partly depends on speed. The most important and unique feature of the model is the ability to estimate road roughness condition using data obtained from anonymous drivers. Preliminary numerical examples and simulations using real sensor data have been carried out whereas the findings show that performance of the model and results are very promising.