Evaluating driver comprehension of the roadway environment to retain accountability of safety during driving automation

Driver comprehension is a substantial component of situation awareness that involves the ability of an individual to understand the significance of an object, traffic sign, or hazard while driving. An increase in crashes related to autonomous driving systems has raised a concern regarding the safety of other roadway users due to the diminishing accountability resulting from a general lack of understanding of the limitations or disregard of the safety protocols by users. To keep drivers vigilant when engaged in partial automated systems, a methodology to monitor real-time driver comprehension was proposed. A driving simulator study consisting of 90 participants, equally split between males and females, was executed to establish driver comprehension in six different variations of driving difficulty. Joint probability density functions were created by considering percent time spent gazing, answers to probe questions, and driving performance. Based on these density functions, five levels of comprehension were devised and assigned thresholds. Overall, as task difficulty increased, a non-linear deterioration in driving speed along with an increase in total gaze duration was observed before comprehension was attained. A two-step validation protocol was also proposed to ensure similar levels of comprehension to non-automated driving from the human driver, when engaged in early forms of automation. The proposed real-time driver comprehension monitoring constitutes a first step toward developing a methodology to reinstate the accountability of safety of other roadway users when engaged in driver-in-the-loop automation systems.     

Safe driving and road-crossing tasks: A particular case of successful transfer of learning

The current study examines whether crucial safe driving skills are associated with safe road-crossing skills as pedestrians. The main research question was whether skills that are acquired from the point of view of a driver are associated with the skills of pedestrians in different platforms or settings. Furthermore, the study examines whether task performance on one platform (driving) primes an operator for task performance on another (road-crossing as a pedestrian) or vice versa. Sixty people took part in this study and completed a demographic questionnaire, a Driving Behavior Questionnaire, a Pedestrian Behavior Scale and two computerized tests – a Hazard Perception Test for Drivers and a Hazard Perception Test for Pedestrians.We found that the better the participants detect hazards on the road as drivers, the better they detect hazards as pedestrians as well, and that most of the participants’ self-reported values regarding their driving and their road-crossing as pedestrians are correlated. The study revealed an association between years of seniority in driving and the number of driving hours per week, and some behavioral variables as pedestrians – meaning that exposure to the road as a driver may be related to safer behavior as a pedestrian.     

Relationships between personality facets and accident involvement among truck drivers

Prior research on the personality characteristics of truck drivers and accident involvement has relied primarily on the Big Five personality factors (e.g., Extraversion), and has largely focused on self-reported number of accidents rather than more objective, independent records. We examined the association between personality characteristics and accidents among professional truck drivers at the facet level of personality using company records of accidents over time. Analyses suggested that more empathetic individuals had lower rates of accident involvement, whereas more anxious, guilt-prone, exhibitionistic, and risk-taking individuals had higher rates. We discuss implications for decreasing rates of accidents, the selection of drivers, and use in other industries where physical safety is a concern.     

Analysis of driver’s decision distance and merging distance in work zone area based on parametric survival models: With the aid of a driving simulator experiment

Work zones affect traffic safety and efficiency by changing the road condition and drivers’ maneuver. Therefore, it is important to fully understand drivers’ merging behavior in work zone related areas. In this study, a model framework composed of decision-distance analysis and merging-distance analysis was proposed, which could describe both decision-making and lane-changing process of merging behavior. A road environment with work zone was developed based on a driving simulator, and six scenarios composed of two levels of traffic volume and three different lane-end sign’s locations were designed. Forty-two licensed participants, including 21 females (10 professional drivers vs. 11 normal drivers) and 21 males (15 professional drivers vs. 6 normal drivers) finally completed the experiment. Based on the experimental data, parametric survival models were established to analyze the effects of traffic sign location, traffic situation and driver characteristics on drivers’ decision distance and merging distance. The results showed that: (i) the lane-end sign’s location affected the decision point of lane changing and further affected the merging distance. However, the effect was weakened when the sign was placed far away from the work zone; (ii) merging distance in high traffic volume condition was shorter than that in low traffic volume condition; (iii) work zone posed greater challenges for female drivers as they merged later than males, and females were reluctant to adjust their merging distance according to different gap conditions. The findings shed some light on the future improvement of traffic design and management in work zones.     

The effects of secondary tasks that involve listening and speaking on young adult drivers with traits associated with autism spectrum disorders: A pilot study with driving simulation

A driver’s license is key to independence for many young adults, including those with autism spectrum disorders (ASDs). However, individuals with ASDs may face special challenges when learning to drive. If effective driver training is to be devised for this demographic, it is important to determine the nature of these challenges. Driving inherently requires multitasking (e.g. steering, speed maintenance, navigation, hazard detection) and drivers are routinely obligated to combine driving with the demands of listening and responding to others, as occurs during driving lessons. Given that individuals who display traits associated with ASDs may have special difficulties with secondary tasks and especially those that involve socialization, we examined the effects of secondary tasks that involve listening and responding to questions while driving. We compared performance when simply driving (the control condition), driving while listening (the audiobook condition), and driving while listening and speaking (the prompt: answer condition). The autism spectrum quotient (AQ:Baron-Cohen, Wheelwright, Skinner, Martin, & Clubley, 2001), a commonly used self-report questionnaire intended to measure traits associated with ASDs in research, was used to identify young drivers with more and fewer traits related to ASDs in a community sample, (None had a clinical diagnosis of ASD.) Consistent with studies of drivers clinically diagnosed with ASDs, we found that high AQ scorers reported greater mental and physical demand, effort, and frustration when driving, and showed more moment-to-moment variability in lane position and hazard reaction compared to low AQ scorers as measured in a driving simulator. Differences between the low and high scorers were typically largest when secondary tasks were imposed, but the predicted interaction between drive condition and AQ group only emerged in terms of steering variability.     

The effect of the emotional state on driving performance in a simulated car-following task

Emotion is an important factor that influences driving behavior, but the mechanism is unclear. This research explored the effect of the emotional state on simulated driving behavior. Thirty-five licensed drivers participated in this study and completed a car-following task. The angry, happy and neutral states were manipulated during the task. The participants’ driving performance and risk perception were recorded under each emotional state. Trait anger and driving experience were also measured to explore the possible mediating effect. The results showed that the drivers in an angry or happy emotional state tended to maintain less time to collision and take a longer time to brake while following a lead vehicle than the drivers under the neutral condition, suggesting that drivers in emotional states are more dangerous those in neutral states. Moreover, the happy state rendered the drivers more dangerous, which manifested as a lower perceived accident risk than that among the drivers in the angry and neutral states. More specifically, experienced drivers in happy states performed worse with respect to vehicle lateral position control. Recommendations and implications for safety education and further research are discussed.     

Cyclist strategies and behaviour at intersections. Conscious and un-conscious strategies regarding positioning

Severe and even fatal accidents between cyclists and motor vehicles commonly occur at intersections. Many of these accidents occur with right-turning vehicles, with drivers not observing an adjacent cyclist. Few structured investigations exist regarding the interaction between cyclist and motor vehicle, and factors in need of study are how infrastructure and vehicle properties affect human decision-making and cycling behaviour. Therefore, a bicycle simulator study was performed, where vehicle type, presence of lane markings and lane width were systematically varied in a scenario with a cyclist approaching a vehicle from behind, at a signalized city intersection. 33 participants cycled through 8 intersection variants each. Data on cycling trajectories, stopping points and speed was coupled with survey data from the participants, and semantically categorized verbal responses to questions regarding strategy for choice of stopping point. Results show that all three factors (vehicle type, lane markings and available vehicle-adjacent space) significantly affects cyclists’ behaviour and conscious strategies. Participants were more cautious in the presence of a truck than a car, reflected in choice of position when cycling and stopping, and in explicit verbalisations regarding perilous aspects of the situation and their conscious and strategic choice of positioning. Available lateral space also affected stop positions and feeling of safety (expressed verbally). Presence of bicycle lane markings made the cyclists inclined to continue into the space to the right of the vehicle. This was revealed by their positioning and speed, and also apparent in the verbal expressions, especially the positive remarks on the situation and conditions. However, the perceived comfort with lane markings present was actually lower than when they were missing. Cyclist type (slow, moderate, or fast) matters with the self-reported faster cyclists being more prone to stop to the right than the slower one.     

Identification of driving simulator sessions of depressed drivers: A comparison between aggregated and time-series classification

Depression has been found to significantly increase the probability of risky driving and involvement in traffic collisions. The majority of studies correlating depressive symptoms with driving, pursue to predict the differences in driving behavior if the driver has already been diagnosed. Little evidence can be found, however, on how mental and psychological disorders can be identified from driving data, and usually analyses utilize simple models and aggregated data. This study aims at utilizing microscopic data from a driving simulator to detect sessions belonging to “depressed” drivers by utilizing powerful machine learning classifiers. Driving simulator sessions from 11 older drivers with symptoms of depression and 65 healthy drivers were utilized towards that aim. Random Forests, an ensemble classifier, with proven efficiency among transportation applications, are then trained on highly disaggregated data describing the mean and standard deviation of speed and lateral or longitudinal acceleration of drivers in the simulator. The kinematic data were aggregated in 30-seconds, 1-minute and 5-minute intervals, but the corresponding time-series of the measurements were also taken into account. Furthermore, classifiers were treated with imbalanced learning techniques to address the scarcity of depressed drivers among the healthy. Time-series of mean speed and the standard deviation of longitudinal acceleration even with a duration of 30-seconds have proven to be the best predictors of driving sessions belonging to depressed drivers with a very low rate of false alarms. The results outperform previous approaches, and indicate that naturalistic driving data or deep learning could prove even more efficient in detecting depression.     

Mild functional decline and driving performance of older drivers without a diagnosed dementia: Study of leukoaraiosis and cognitive function

Motor vehicle collisions involving older drivers have increased and become an important social issue. It is known that the decline of cognitive function, including dementia, affects driving performance. A series of studies using the Mini-Mental State Examination (MMSE) and other tests of dementia have attempted to prevent motor vehicle collisions by identifying as early as possible older drivers who may be unable to maintain their driving performance. Further, the performance of older drivers may deteriorate even if they do not have a diagnosis of dementia. Therefore we focused on the relationship between cognitive functioning assessed by the MMSE and diagnosis of leukoaraiosis (LA), or changes in the cerebral white matter, with different aspects of driving behavior resulting from aging. Qualified driving instructors evaluated participants’ driving behaviors on an outdoor driving course at a driving school. Visual search duration and angle at intersections were obtained by wearable wireless sensors. Vehicle speed and minimum vehicle speed were recorded from vehicle speed pulse signals. Duration of signaling and visual searches at unsignalized intersections were recorded using an in-vehicle camera. We assessed instructors’ evaluations and the scores on two instruments to evaluate the effects of MMSE scores and the grade of LA on driving performance were verified. The results suggest that lower MMSE scores and higher LA grade can predict some aspects of poor driving performance in older drivers before they experience dementia or an evident decline in cognitive functioning. Based on these results, we discuss countermeasures that may prevent motor vehicle collisions involving older drivers.