No abstract

No abstract

Objective: Drowsiness is a major cause of driver impairment leading to crashes and fatalities. Research has established the ability to detect drowsiness with various kinds of sensors. We studied drowsy driving in a high-fidelity driving simulator and evaluated the ability of an automotive production-ready driver monitoring system (DMS) to detect drowsy driving. Additionally, this feature was compared to and combined with signals from vehicle-based sensors. Methods: The National Advanced Driving Simulator was used to expose drivers to long, monotonous drives. Twenty participants drove for about 4 h in the simulator between 10 p.m. and 2 a.m. They were allowed to use cruise control and traffic was sparse and semirandom, with both slowerand faster-moving vehicles. Observational ratings of drowsiness (ORDs) were used as the ground truth for drowsiness, and several dependent measures were calculated from vehicle and DMS signals. Drowsiness classification models were created that used only vehicle signals, only driver monitoring signals, and a combination of the 2 sources. Results: The model that used DMS signals performed better than the one that used only vehicle signals; however, the combination of the two performed the best. The models were effective at discriminating low levels of drowsiness from moderate to severe drowsiness; however, they were not effective at telling the difference between moderate and severe levels. A binary model that lumped drowsiness into 2 classes had an area under the receiver operating characteristic (ROC) curve of 0.897. Conclusions: Blinks and saccades have been shown to be predictive of microsleeps; however, it may be that detection of microsleeps and lane departures occurs too late. Therefore, it is encouraging that the model was able to distinguish mild from moderate drowsy driving. The use of automation may make vehicle-based signals useless for characterizing driver states, providing further motivation for a DMS. Future improvements in impairment detection systems may be expected through a combination of improved hardware, physiological measures from unobtrusive sensors and wearables, and the intelligent integration of environmental variables like time of day and time on task.

No abstract

Driver models have been developed to capture collision-avoidance behaviors, yet there is a lack of understanding of what perceptual processes influence drivers’ choices to brake or steer. A statistical model of these decisions was developed with cluster analysis and multinomial logistic regression with data from a simulator study of drivers’ responses to rear-end collisions. Drivers’ choices of responses were clustered on the basis of the maximum values of the magnitude of braking and steering forces, starting from the time at which the driver looked back to the road, just before initiating the avoidance maneuver, to the end of the maneuver. The clusters identified three types of responses: medium to high braking with medium to high steering, medium to high braking with mild steering, and mild braking with medium to high steering. The perceptual variables such as the optical angle, the expansion rate of the optical angle, and their ratio were used to predict the drivers’ choice of response. The results show that, of the perceptual variables, the combination of optical angle and tau performs as well as or better than others in predicting the choice of response. The mode and timing of an alert from a collision-warning system did not influence the drivers’ choices. These results can inform driver behavior models to guide design and assess benefits of advanced driver assistance systems.