Motorized Vehicle Safety

Traffic conflict can be identified by the presence of evasive actions or the amount of temporal (spatial) proximity measures like time-to-collision (TTC). However, it is not enough to use only one kind of measures in some scenarios and it is hard to set a threshold for those measures. This paper proposed a method to identify traffic conflict by learning the representation of TTC and driver maneuver profiles with deep unsupervised learning and clustering the representations into traffic conflict and non-conflict clusters. We first trained a transformer encoder to encode sequences of...

Restraint devices such as seat belts are a key element of motor vehicle occupant protection systems. Each year, NHTSA conducts the National Occupant Protection Use Survey (NOPUS) that measures, among many variables, the use of seat belts by occupants age eight and older. The 2019 NOPUS reported that seat belt use was 90.7 percent among front-seat passengers, a slight increase from the 89.6 percent observed in 2018. Additionally, the 2019 survey found that seat belt use increased during both weekday rush hours and non rush hours. Use during weekday rush hours increased from 89.3 percent in...