The concept of "intelligent mobility" is gaining traction among the general public as well as researchers working to improve automobile and transportation safety in general. In the future, we can expect a transportation system that is quick, efficient, and convenient. The automatic car, which has made some development, is a vital component of this system. However, in order to produce more delicate automatic vehicles in the long run, a more comprehensive study of people's driving behavior is required. Modeling driving behavior is a difficult issue since it requires a link between the vehicle, the driver, and the traffic situation. Furthermore, even when the same driver operates the same vehicle on the same road, his or her driving behavior can change over time.
We propose in this study to extend the capabilities of an Android mobile platform to provide on-the-fly driver/driving behavior assessment and modeling. The data collecting, modeling, and assessment/scoring procedures for the UTDrive-MOBILE-App will be discussed. We go over how to create an early driver measuring solution as well as how to deliver useful feedback in the form of data visualization. We also run a number of tests to verify and compare results in a variety of driving conditions. Finally, machine learning is used to investigate richer multi-modal driver study by combining the potential for real-time driving behavior data collecting and on-the-fly measurement solutions.
Driving behavior modeling, ADAS, smartphone driving behavior data collection
whatever -- this is a test