Driving Performance Data Research Articles

Roadway Weather Challenges Illuminate Real‐World Driving Biomarkers of Dementia Risk

AbstractBackgroundCognitive decline is a leading early predictor of dementia risk and may be evident in real‐world (RW) digital data even before patients ever present to clinic. This study examined the feasibility of using video and digital sensor profiles of real world (RW) driving in adverse weather as a marker of dementia risk.Method70 older drivers (mean age = 75.6 years) without dementia participated in a RW driving study for 2, 3‐month periods, one year apart (Wang, et al. 2021) . Self‐reported demographics and neuropsychological tests relevant to dementia and driving were collected at study start. Drivers were classed as cognitively neurotypical (N = 33) or impaired (N = 44) based on normed neuropsychological scores. Sensors installed in each driver’s vehicle collected video, speed, and GPS data across 405,104 miles driven. GIS data categorized roadway type (residential, commercial, interstate). A computer vision model (99% accuracy) we developed classed roads as clear or poor (rain, snow). Bayesian mixed‐effect logistic regressions assessed driver speed limit compliance (vehicle speed‐posted speed limit) across driver class, roadway, and weather.ResultDrivers were 8.01 times more likely to speed on interstates (95% CI: 7.61‐8.61) than residential roads (15‐25 mph). Impaired drivers were 15% more likely to drive slower than neurotypical drivers on clear roadways (95% C: 1.0413‐1.2829). This pattern reversed in poor weather with impaired drivers driving faster than neurotypical (b = 0.74, 95% CI: 0.57‐0.94)ConclusionDigital biomarkers from RW data show promise to screen for early dementia risk, advancing research and innovative clinical trials to prevent dementia. Driving challenges, like poor weather, discriminate cognitive decline before dementia. Impaired drivers showed self‐restriction by driving slower on clear roads and reduced self‐restriction by driving faster in poor weather despite risk. Big data strategies, like computer vision, complement driver performance data to identify RW environmental risk, paving the road for the car as a medical diagnostic device.

Evaluating the dissociation between drivers’ self-perceived and objective need for vehicle assistance during obstacle avoidance tasks

Driver-assistance systems are becoming more commonplace; however, the realized safety benefits of these technologies depend on whether a person accepts and adopts automated driving aids. One challenge to adoption could be a preference-performance dissociation (PPD), which is a mismatch between a self-perceived desire and an objective need for assistance. Research has reported PPD in driving but has not extensively leveraged driving performance data to confirm its existence. Thus, the goal of this study was to compare drivers’ self-reported need for vehicle assistance to their objective driving performance. Twenty-one participants drove on a simulated road and traversed challenging, real-world roadway obstacles. Afterwards, they were asked about their preference for automated vehicle assistance (e.g., steering and braking) during their drive. Overall, some participants exhibited PPD that included both over- and underestimating their need for a particular type of automated assistance. Findings can be used to develop shared control and adaptive automation strategies tailored to particular users and contexts across various safety-critical environments.

Silent failure detection in partial automation as a function of visual attentiveness

Objective Drivers using level 2 automation are able to disengage with the dynamic driving task, but must still monitor the roadway and environment and be ready to takeover on short notice. However, people are still willing to engage with non-driving related tasks, and the ways in which people manage this tradeoff are expected to vary depending on the operational design domain of the system and the nature of the task. Our aim is to model driver gaze behavior in level 2 partial driving automation when the driver is engaged in an email task on a cell phone. Both congested highway driving, traffic jams, and a hazard with a silent automation failure are considered in a driving simulator study conducted in the NADS-1 high-fidelity motion-based driving simulator. Methods Sequence analysis is a methodology that has grown up around social science research questions. It has developed into a powerful tool that supports intuitive visualizations, clustering analysis, covariate analyses, and Hidden Markov Models. These methods were used to create models for four different gaze behaviors and use the models to predict attention during the silent failure event. Results Predictive simulations were run with initial conditions that matched driver state just prior to the silent failure event. Actual gaze response times were observed to fall within distributions of predicted glances to the front. The three drivers with the largest glance response times were not able to take back manual control before colliding with the hazard. Conclusions The simulated glance response time distributions can be used in more sophisticated ways when combined with other data. The glance response time probability may be conditioned on other variables like time on task, time of day, prevalence of the current behavior for this driver, or other variables. Given the flexibility of sequence analysis and the methods it supports (clustering, HMMs), future studies may benefit from its application to gaze behavior and driving performance data.

Cognitive workload evaluation of landmarks and routes using virtual reality.

Investigating whether landmarks and routes affect navigational efficiency and learning transfer in traffic is essential. In this study, a virtual reality-based driving system was employed to determine the effects of landmarks and routes on human neurocognitive behavior. The participants made four (4) journeys to predetermined destinations. They were provided with different landmarks and routes to aid in reaching their respective destinations. We considered two (2) groups and conducted two (2) sessions per group in this study. Each group had sufficient and insufficient landmarks. We hypothesized that using insufficient landmarks would elicit an increase in psychophysiological activation, such as increased heart rate, eye gaze, and pupil size, which would cause participants to make more errors. Moreover, easy and difficult routes elicited different cognitive workloads. Thus, a high cognitive load would negatively affect the participants when trying to apply the knowledge acquired at the beginning of the exercise. In addition, the navigational efficiency of routes with sufficient landmarks was remarkably higher than that of routes with insufficient landmarks. We evaluated the effects of landmarks and routes by assessing the recorded information of the drivers’ pupil size, heart rate, and driving performance data. An analytical strategy, several machine learning algorithms, and data fusion methods have been employed to measure the neurocognitive load of each participant for user classification. The results showed that insufficient landmarks and difficult routes increased pupil size and heart rate, which caused the participants to make more errors. The results also indicated that easy routes with sufficient landmarks were deemed more efficient for navigation, where users’ cognitive loads were much lower than those with insufficient landmarks and difficult routes. The high cognitive workload hindered the participants when trying to apply the knowledge acquired at the beginning of the exercise. Meanwhile, the data fusion method achieved higher accuracy than the other classification methods. The results of this study will help improve the use of landmarks and design of driving routes, as well as paving the way to analyze traffic safety using the drivers’ cognition and performance data.

Perceived risk vs actual driving performance during distracted driving: A comparative analysis of phone use and other secondary distractions

The present study attempts to explore the association of drivers’ risk perception towards phone usage as well as other everyday distractions (operating a music player and eating during driving), and their driving performance observed during these distracted conditions. For this purpose, driving simulator experiments were conducted with 90 participants to collect their driving performance data and a questionnaire was conducted to obtain their basic details along with their risk perceptions. Firstly, the driving performance was divided into clusters using hierarchical clustering and the clustered subgroups were compared for crash and non-crash cases to identify the groups having significant performance degradation. Based on this comparison, the driving performance subgroups were then divided into the following crash risk probabilities: High risk, Moderate risk and Low risk. Further, the associations of perceived risk with these performance subgroups and other potential factors were analyzed using association rules mining technique. Most of the drivers (72.06%) reported texting as an extremely risky task. But, surprisingly none of them considered conversation as an extremely risky task. However, in case of conversation, it was found that even though the professional drivers reported the task to be not at all risky, the observed crash risk was high for them (S = 5.21%, C = 67.86%), indicating an underestimation of the associated risk by the drivers. Similarly, the results revealed that for music player and eating tasks, drivers reported the distracting tasks to be less risky, but, in some instances, their driving performance was associated with higher chances of crash occurrence. Many interesting associations of risk perception and driving performance with respect to demographic and driving characteristics were also obtained. The findings can be useful while designing the awareness programs related to distracted driving with an aim to reduce such practices.

Effects of Neuro-Cognitive Load on Learning Transfer Using a Virtual Reality-Based Driving System

Understanding the ways different people perceive and apply acquired knowledge, especially when driving, is an important area of study. This study introduced a novel virtual reality (VR)-based driving system to determine the effects of neuro-cognitive load on learning transfer. In the experiment, easy and difficult routes were introduced to the participants, and the VR system is capable of recording eye-gaze, pupil dilation, heart rate, as well as driving performance data. So, the main purpose here is to apply multimodal data fusion, several machine learning algorithms, and strategic analytic methods to measure neurocognitive load for user classification. A total of ninety-eight (98) university students participated in the experiment, in which forty-nine (49) were male participants and forty-nine (49) were female participants. The results showed that data fusion methods achieved higher accuracy compared to other classification methods. These findings highlight the importance of physiological monitoring to measure mental workload during the process of learning transfer.

Preliminary Eye-Tracking Data as a Nonintrusive Marker for Blood Δ-9-Tetrahydrocannabinol Concentration and Drugged Driving.

Background: Cannabis is one of the drugs most often found in drivers involved in serious motor vehicle collisions. Validity and reliability of roadside cannabis detection strategies are questioned. This pilot study aimed to investigate the relationship between eye characteristics and cannabis effects in simulated driving to inform potential development of an alternative detection strategy. Materials and Methods: Multimodal data, including blood samples, eye-tracking recordings, and driving performance data, were acquired from 10 participants during a prolonged single-session driving simulator experiment. The study session included a baseline driving trial before cannabis exposure and seven trials at various times over ∼5 h after exposure. The multidimensional eye-tracking recording from each driving trial for each participant was segmented into nonoverlapping epochs (time windows); 34 features were extracted from each epoch. Blood Δ-9-tetrahydrocannabinol (THC) concentration, standard deviation of lateral position (SDLP), and mean vehicle speed were target variables. The cross-correlation between the temporal profile of each eye-tracking feature and target variable was assessed and a nonlinear regression analysis evaluated temporal trend of features following cannabis exposure. Results: Mean pupil diameter (r=0.81-0.86) and gaze pitch angle standard deviation (r=0.79-0.87) were significantly correlated with blood THC concentration (p<0.01) for all epoch lengths. For driving performance variables, saccade-related features were among those showing the most significant correlation (r=0.61-0.83, p<0.05). Epoch length significantly affected correlations between eye-tracking features and speed (p<0.05), but not SDLP or blood THC concentration (p>0.1). Temporal trend analysis of eye-tracking features after cannabis also showed a significant increasing trend (p<0.01) in saccade-related features, including velocity, scanpath, and duration, as the influence of cannabis decreased by time. A decreasing trend was observed for fixation percentage and mean pupil diameter. Due to the lack of placebo control in this study, these results are considered preliminary. Conclusion: Specific eye characteristics could potentially be used as nonintrusive markers of THC presence and driving-related effects of cannabis. clinicaltrials.gov (NCT03813602).

Evaluation of fog warning system on driving under heavy fog condition based on driving simulator

Purpose Heavy fog results in low visibility, which increases the probability and severity of traffic crashes, and fog warning system is conducive to the reduction of crashes by conveying warning messages to drivers. This paper aims at exploring the effects of dynamic message sign (DMS) of fog warning system on driver performance. Design/methodology/approach First, a testing platform was established based on driving simulator and driver performance data under DMS were collected. The experiment route was consisted of three different zones (i.e. warning zone, transition zone and heavy fog zone), and mean speed, mean acceleration, mean jerk in the whole zone, ending speed in the warning zone and transition zone, maximum deceleration rate and mean speed reduction proportion in the transition zone and heavy fog zone were selected. Next, the one-way analysis of variance was applied to test the significant difference between the metrics. Besides, drivers’ subjective perception was also considered. Findings The results indicated that DMS is beneficial to reduce speed before drivers enter the heavy fog zone. Besides, when drivers enter a heavy fog zone, DMS can reduce the tension of drivers and make drivers operate more smoothly. Originality/value This paper provides a comprehensive approach for evaluating the effectiveness of the warning system in adverse conditions based on the driving simulation test platform. The method can be extended to the evaluation of vehicle-to-infrastructure technology in other special scenarios.

Can't simply roll it out: Evaluating a real-world virtual reality intervention to reduce driving under the influence.

Driving under the influence (DUI) increases the risk of crashes. Emerging technologies, such as virtual reality (VR), represent potentially powerful and attractive tools for the prevention of risky behaviours, such as DUI. Therefore, they are embraced in prevention efforts with VR interventions primed to grow in popularity in near future. However, little is known about the actual effectiveness of such DUI-targeting VR interventions. To help fill the knowledge gap, this study explored the effects of one VR intervention as delivered in the real world. Using pre and post test design, including an intervention group (n = 98) and a control group (n = 39), the intervention evaluation examined young drivers' (aged 18 to 25, no known history of DUI) intention and self-reported behaviour three months after the intervention as compared to the baseline. The results did not provide evidence for statistically significant effects of the VR intervention on self-reported DUI behaviour during the three months post intervention and DUI intention at three months post intervention. Such results might be due to the fact that the recruited participants generally self-reported little DUI behaviour, i.e. positively changing behaviour that is already positive is inherently challenging. Nevertheless, the results question the utility of funding the roll-out of arguably attractive technologies without a thorough understanding of their effectiveness in particular settings. To improve the potential for future positive outcomes of such interventions, we provide suggestions on how VR software might be further developed and, subsequently, leveraged in future research to improve the likelihood for behavioural change, e.g. by collecting, analysing and presenting objective driving performance data. Alternatively, future endeavours might focus on participants with known DUI history and examine the effects of the VR intervention for this particular higher-risk group.

Research on Distracted Driving Identification of Truck Drivers Based on Simulated Driving Experiment

Trucks drivers may be distracted during long-distance transportation, which may threaten the safety of themselves and surrounding vehicles. In this regard, this article first investigates the types of distracted driving that frequently occur in China and select typical distracted driving behaviors to carry out the simulated driving experiment and collect driving performance data. The independent sample T-test was used to select the distracted driving identification indicators. An integrated distracted driving identification model based on Binary Logistic Regression and Fisher discriminant analysis was established. The accuracy of the integrated model in identifying the driver’s distracted driving state is 94.79%. This research can provide a basis for the driver assistance systems that reflect the degree of driver distraction.

Influence of following vehicle’s tailway and classification on subject driver’s response to the circular yellow indication

Traffic crashes at signalized intersections are frequently linked to driver behavior at the onset of the circular yellow (CY) indication. To better understand behavioral factors that influence a driver’s decision to stop or go at an intersection, this study analyzed the behavior of the driver of a subject vehicle at the onset of the CY indication. Driver performance data from 53 participants were collected in the Oregon State University Driving Simulator, simulating scenarios of driving through high-speed intersections under various conditions. Data included interactions where the driver stopped at the stop line (n = 644) or proceeded through the intersection (n = 628) in response to a CY indication. Data were analyzed as panel data while considering 12 indicator variables related to the driver’s stop/go decision. These indicator variables included time to stop line (TTSL), tailway time, following vehicle type, vehicle speed at the onset of the CY indication, and demographics (age, gender, driving experience, level of education, personal vehicle type, number of times driving per week, number of miles driving last year, participation in previous simulation studies. A random-parameter binary logit model was used to determine contributing factors for driver decision making at the onset of CY indication while accounting for unobserved heterogeneity. Four indicator variables were significantly related to the driver’s stop/go decision, but three factors varied across observations. Findings showed that a driver’s stop/go decision in response to a CY indication was associated with the time to the stop line (TTSL), tailway time to the following vehicle, subject vehicle speed at the onset of the CY indication, and driver’s age (20–36 years), but was not significantly associated with classification of the following vehicle. Also, the findings indicated that a shorter tailway increased a subject driver’s red-light running frequency. These findings provide insights into variables that affect driver decisions in a vehicle-following situation at the onset of the CY indication. This information can help make better decisions in smart traffic control systems such as to extend/decrease the green interval slightly to avoid decisions that are more difficult.

The Prediction of Collisions in Connected Vehicle Systems with A Long Short-Term Memory Model

The advances in connected vehicle systems (CVS) allow vehicles to communicate with each other and with infrastructures via wireless communication networks. This technology enables vehicles to detect potential hazards on the road, generate warnings, and assist the driver in taking preventive actions. To date, few mathematical models have been developed to predict the collision rates in connected vehicle systems. In this work, a Long Short-Term Memory model (LSTM) using time-series data of human drivers was developed to predict the collision rates in CVS by quantifying warning parameters and hazard scenario features. The model was validated with the driving performance data before and after warnings from thirty-two drivers in a behavioral experiment. The results indicated the LSTM model showed a prediction accuracy of 74% higher than SVM and logistic regression models. The LSTM model showed the potential to help optimize the warning algorithm in the connected vehicle systems to improve driver safety.

Blink Rate as a Measure of Driver Workload during Simulated Driving

Cognitive distraction has been identified as a critical factor for automobile crashes in the United States. Previous research indicates that cognitive tasks such as phone conversations may take attention away from the driving task, degrading driving performance. One continuing issue with cognitive distraction research is establishing a reliable, continuous, online measure of driver workload. Blink rate is a potential candidate for such a measure. The present driving simulator experiment examines whether blink rate is sensitive to variations of driver workload while controlling the vehicle. Participants will navigate simulated environments while performing the auditory 0-and 2-back task with their blink and driving performance data continuously recorded during the drive. Blink and performance data will be compared not only between the different workload conditions, but also to predictions of a human driver performance workload model based on the Improved Performance Research Integration Tool (IMPRINT), developed by the US Army Research Laboratory.

Development of a Practical Method to Estimate the Eco-Level of Driver Performance

Motor vehicle’s fuel consumption is one of the main sources of energy consumption in road transportation and is highly influenced by driver performance in the process of driving. Eco-driving behavior has been proved to be an effective way to improve the fuel efficiency of vehicles. Essential to the efforts towards saving vehicle fuel is the need to estimate the eco-level of driver performance accurately and practically. Depending on on-board diagnostics and Global Position devices, individual vehicle’s instantaneous fuel consumption, engine revolution and torque, speed, acceleration, and dynamic location were collected. Back-propagation network was adopted to explore the relationship between vehicle fuel consumption and the parameters of driver performance. Taking 700 data samples in basic segments of urban expressways as our training set and 100 data samples as validation test, we found the optimal model structure and parameters through repeated simulation experiments. In addition to the average and standard deviation value, the fluctuation frequency of driver performance data was also viewed as influence factors in eco-level estimation model. The average estimation accuracy of our developed model has been tested to be 96.37%, which is quite higher than that of linear regression model. The study results provide a practical way to evaluate drivers’ performance from the perspective of fuel consumption and thus give basis for rewarding best drivers within eco-driving programs.

Overall performance impairment and crash risk due to distracted driving: A comprehensive analysis using structural equation modelling

Distracted driving leads to performance changes in both longitudinal and lateral control. However, driving performance, being a multidimensional phenomenon, is very difficult to be interpreted from individual performance measures. The present study aimed to exhibit the distraction impacts on overall driving performance estimated by a single measure rather than assessing distraction effects on individual performance metrics such as speed, acceleration, lateral variation, etc. The study also focused on modelling and quantifying the impacts of overall deteriorated driving performance on crash risk. To achieve the objectives, a comparative analysis of investigating phone and music player usage was conducted using Structural Equation Modelling (SEM). In total, 90 drivers’ demographic details and driving performance data in distracted and non-distracted driving environments were collected. Firstly, the latent variable “performance degradation” was derived from longitudinal and lateral performance measures. Then the structural model revealed a positive relationship between the distractions and the overall performance degradation. Finally, the crash risk was modelled against the presence of distraction and performance degradation. With a factor loading of 0.29, the impact of deteriorated driving performance (i.e., indirect impact) was found to be the highest among all the contributory factors of the crash risk. Further, the results showed that among the distractions (i.e., direct impact), texting had the highest impact (factor loading = 0.28) on crash risk followed by visual-manual tasks related to music player (factor loading = 0.21). Thus, the present study quantified the effects of deteriorated driving performance caused by distracted driving on the crash risk. Further, the study also presented quantified effects of each distracting activity on the crash risk which accounted for the factors that could not be considered through the performance degradation measure. The approach used in the present study can be adopted in designing the countermeasures using advanced driver warning systems.

Machine learning techniques to identify mind-wandering and predict hazard response time in fully immersive driving simulation

This work presents machine learning-based techniques for detecting mind-wandering and predicting hazard response time in driving using only easily measurable driving performance data (speed, horizontal and frontal acceleration, lane gap, and brake pressure). Such classifiers are relevant as research tools in the driving simulation community. We present a simple method, and a feature extraction-based method, of representing time-series driving performance data that both support machine learning-based predictions. We use the two types of representations to compare the effectiveness of support vector machines, random forest, and multi-layer perceptrons on data from 117 drives performed by 39 participants during a previous study in the high-fidelity driving simulator at the University of Guelph. Classification of mind-wandering and prediction of hazard response time was successful when compared to baseline measures. Specifically, random forest methods were most effective in both types of prediction and feature extraction supported the strongest random forest prediction of hazard response time. A discussion of the reasoning for this is included. While this has previously been studied using a single screen experimental setup, to our knowledge this is the first driving pattern-based classification of mind-wandering in a fully immersive driving simulator.

Technology, Innovative Approaches Enhance Road Safety for the Oil and Gas Industry

This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 199467, “Applying Technology and Innovative Solutions To Enhance Driver Engagement and Performance,” by Freddy Perez, Kirsty Walker, SPE, and Junaid Parkar, Schlumberger, prepared for the 2020 SPE International Conference and Exhibition on Health, Safety, Environment, and Sustainability, originally scheduled to be held in Bogota, Colombia, 28-30 July. The paper has not been peer reviewed. The complete paper describes a service company’s approach to the development and application of technology and innovative solutions to improve driving performance on the basis of extensive data analysis. Driving-performance data identified potential scenarios in which outcome-focused solutions can be used to influence driver behavior. Tailored approaches were implemented, ranging from vehicle enhancements to mobile applications. Introduction The International Association of Oil and Gas Producers reports that land-transportation-related incidents historically have been the single largest cause of fatalities in its member company operations. Since 2000, such incidents have accounted for 22% of all work-related fatalities reported by the members. The service company Schlumberger has a long-standing commitment to road safety, including mandatory driver safety training for all employees and contractors who drive on company business. The company has also invested in providing global journey-management centers to support company driving activities.

Support vector machines for the identification of real-time driving distraction using in-vehicle information systems

IVIS (In-vehicle Information System) is an important factor causing driver distraction. To study the driver distraction detection method when operating IVIS, the effectiveness of driving performance indicators in the identification of driving distraction was verified by the method of variance analysis. Forty participants were selected to conduct the driver distraction experiment when operating IVIS, and the data of driving performance indicators such as eye movement, speed, et al. were obtained. According to the driving performance data of IVIS, a real-time detection of distraction based on driving performance was built by using support vector machine, and three kernel functions of the model were conducted comparative analysis and validation. The results show that SVM models can effectively evaluate the degree of drivers’ distraction. At the same time, when the Radial Basis Function is used as a kernel function, the accuracy for recognizing driver distraction is 89.9%, which is higher than when the sigmoid polynomial kernel function and SAVE-IT model are used. The research could be applied in the design of adaptive in-vehicle systems and the evaluation of driving distraction, providing theoretical support and reference for the development of vehicle-mounted information systems and the management of driver distraction prevention measures. Highlights We verify the effectiveness of driving performance indicators as decision variables for driving distraction. We use driving performance indicators as inputs to a distraction detection algorithm. We examine changes in the level of information about driving distraction. SVMs method can be used to detect driving distraction during IVIS operations in real time. The accuracy for using Radial Basis Function to recognizing the driver’s level of distraction is higher than the Radial Basis Function.

Research on the correlation of dangerous driving behaviors based on naturalistic driving experiment

In China, although road traffic safety has improved in recent years, the number of deaths caused by traffic accidents is still at a high level every year. Accidents due to drivers’ dangerous driving behavior account for a large proportion. This study designed and implemented a highway naturalistic driving experiment. The driving performance data and the observer record data obtained in the experiment were used to extract four dangerous driving behaviors: rapid acceleration, rapid deceleration, sudden steering and drowsy driving. The correlation between the three kinds of urgent behaviors and driving fatigue was analyzed qualitatively and quantitatively. Finally, the correlation model between the frequency of urgent behaviors and drowsy driving was built using Naive Bayes. The feasibility of using this method to identify drowsy driving behavior was discussed.

Characteristics of Manipulations by Railway Drivers who had made Train Stop Position Error at Station - Consideration based on Driving Performance Data-

Characteristics of Manipulations by Railway Drivers who had made Train Stop Position Error at Station - Consideration based on Driving Performance Data-