PROBLEM:
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.
Solution:
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.
TECHNOLOGY READINESS:
Level 4-6
TECHNOLOGIES:
Driving behavior modeling, ADAS, smartphone driving behavior data collection
Problem:
whatever -- this is a test
PROBLEM:
Out of the numerous traffic mortalities happening every year, a vast majority of them caused by driver negligence and distraction. With the improvement of novel technologies in diver assistant, driver warning and auto control systems in the last decades, yet many of vehicles are not equipped because of the expense and complexity of these systems.
Solution:
In this research, we studied driver performance under real world conditions with the help of image-based information which can be simply captured from a camera installed on the vehicle’s wind shield. Driver assessment has been done based on driver’s following distance to other vehicles and pedestrians and off-center lane rates. Providing a driver assessment and risk grading system helps drivers to improve their performance over the time. This system is of course subjective to have a consistent distance estimation of the following car during the time. By achieving a long-term distance pattern, we can then split the results into 3 different zones of risk. The driver assessment system can be extended later to on board vehicle heads up displays or UTDrive application features.
TECHNOLOGY READINESS:
Level 3-5
TECHNOLOGIES:
ADAS, Image-based techniques, Driving behavior analysis
PROBLEM:
Every driver has his or her own distinct driving style. The driver's driving experience, vehicle handling skill, emotional and physical state, as well as the weather and traffic, all influence how the maneuver is completed. Identifying and evaluating movements are part of a series of tasks that help to narrow the search space of all possible driving scenarios in order to detect driver distractions.
Solution:
Deviations from the regular execution pattern appear as yellow or red squares in the feature space of this move. The classifier still recognizes these "odd" instances of the maneuver as type "x," but the intra class separation suggests they can be tagged as outliers.
TECHNOLOGY READINESS:
Level 3-4
TECHNOLOGIES:
Driving safety, Driving behavior assessment
