Search

• Signals from DMS, Mobileye, and CAN Bus were synchronized into a Bayesian generalized linear model to assess gaze-context relationship in highway driving. • Gaze fixation is shorter on more eccentric regions of the road scene. • Larger headway changes lead to longer fixations on the road center. • Higher speed or greater acceleration/deceleration increases the duration of fixation on the lead vehicle regardless of be in manual or assisted driving. The paper aims to integrate interior and exterior sensing signals to explore gaze-context connections for more context-aware driver attention management. Driving context is important for crash risk assessment, but little is known about how it modulates attention requirements for developing driver monitoring systems. Twenty-four participants drove a Tesla Model S equipped with Autopilot on the highway, during which driver gaze, headway, speed, and driving mode were sampled from the driver monitoring system, Mobileye, and CAN Bus. These signals were processed and synchronized over each single gaze fixation and incorporated into a Bayesian generalized linear model to assess the effects of dynamic contextual factors on the duration of individual gaze fixation. During car following, gaze fixations on eccentric locations in the road scene were shorter. Changes in headway led to longer fixations on the lead vehicle. Moreover, higher vehicle speed and larger acceleration/deceleration, regardless of being in the manual or assisted driving mode, led to longer fixations on the road center. In addition, driving mode itself had a small effect on fixation duration. Sensor fusion, along with computation models, explains the connections between driver attention and dynamic context in real-world driving. Application : The gaze-context connections provide insight into developing more context-sensitive gaze metrics to support adaptive driver attention management. [ABSTRACT FROM AUTHOR]

• Mobile phone use while driving remains a road safety concern for road transport authorities. • The driving context plays a role in the decision to engage in mobile phone use while driving. • Even after the intention to use the mobile phone while driving is formed, the moment where engagement occurs will be determined by the demands of the driving context. Mobile phone use is one of the most frequent causes of distraction among drivers. While there have been a significant number of studies that have examined individuals' intentions to use a mobile phone while driving, the influence of individuals' in-situ judgement of driving conditions has received considerably less attention. The aim of this investigation was to provide a systematic understanding of how factors associated with the driving context and environment influence a driver's decision to engage in mobile phone use while driving. Following a systematic classification scheme, 41 research articles from the years 2011 to 2020 were reviewed and synthesised to identify the contextual determinants of mobile phone distraction. Overall, the findings provided support for the role that contextual features play in influencing individuals' mobile phone use engagement. This finding was particularly the case in instances where mobile phone tasks required relatively high cognitive and physical demands on an individual, such as texting and/or reading mails. The findings also indicated that as contextual complexity increases, mobile phone use decreases as well. A deeper understanding of the relationship between contextual factors and phone use while driving may aid in the design of more efficient driver support systems and the development of distraction-sensitive road design guides. This understanding can also assist in the identification of mobile phone use hotspots and the improvement of law enforcement and educational strategies to prevent the behaviour. [ABSTRACT FROM AUTHOR]

The automotive glazing projection display pertains to projecting information onto unique glazing materials in a car through projection equipment, a new direction of Human-Computer Interaction (HCI) in the intelligent cockpit. The core issue in glazing projection is determining what information should be projected onto the car's glazing and the area to which it should be projected. To address this issue, we conducted a focus group comprising 12 people. We distributed 1082 questionnaires to investigate future autonomous driving contexts, user information demands based on glazing projection, and regional preferences for displaying such information. We selected five contexts and nine high-rated features to design a driver-specific display interface. We conducted eye-movement experiments to investigate the effect of the projection interface on the driver's gaze behaviors under different display areas and subsequently modified the display areas. This study confirms the feasibility of the glazing projection display and provides theoretical support for HCI development in the intelligent cockpit. [ABSTRACT FROM AUTHOR]

• A data-driven analytic approach was applied to full trip data of 44 drivers who reported engaging in risky driving behaviors. • Cumulative idling and frequency of speeding emerged as key contextual factors influencing the propensity to speed. • Cluster analysis revealed 82% of drivers fell into categories where contextual factors were the key contributing factors. • Attitudes toward phone use and speeding behavior also had an influence on speeding behavior. The present analysis used full-trip naturalistic driving data along with driver behavioral and psychosocial surveys to understand the individual and contextual predictors of speeding. The data were collected over a three-week period from 44 drivers and contain 3,798 full trips, with drivers speeding 7.8 % of the time. Speeding events were identified as periods when participants traveled at a velocity greater than five mph over the speed limit for at least five seconds. Data were analyzed using the Comprehensive Driver Profile (CDP) framework which uses principal component analysis (dimensionality reduction), random forest (predictive modeling), k-means clustering (grouping and profiling), and bootstrapping (profile stability) to decompose the predictive variables and driver characteristics. The final dataset included 188 candidate independent variables from the CDP framework and one dependent variable (speeding). Nine variables emerged as significant predictors of speeding onset with an AUC of 0.88, including the percent of trip time spent idling and speeding, highway driving in low traffic conditions, and positive attitudes toward phone use. Percent of trip speeding was associated with a higher likelihood of speeding by up to 42 percent, and percent trip idling was associated with it by up to 30 percent. Driver profile clusters revealed four types: Traffic & Idling Speeders, Infrequent Speeders, Frequent Speeders, and Situational Speeders. The present analysis demonstrates the importance of situational factors and individual differences in motivating speeding behavior. Countermeasures targeting speeding may be more effective if they address the root causes of the behavior in addition to the behavior itself. [ABSTRACT FROM AUTHOR]

Automated Driver Assistance Systems (ADAS) are designed to support the driver and enhance the driving experience. Due to ADAS limitations associated with the driving context, the intended use of ADAS functions is often non-transparent for the end-user. The system performance capabilities affected by the continuously changing driving context influence ADAS usage. However, the cumulative effect of the driving context on driver behavior and ADAS usage is insufficiently covered in the ongoing research. This paper aims to investigate and understand how the driving context affects the use of ADAS. Throughout this research, data from a Naturalistic Driving (ND) study was collected and analyzed. The analysis of the ND data helped to register how drivers use ADAS in different driving conditions and indicated several issues associated with ADAS usage. To be able to clarify the outcomes of quantitative sensor-based data analysis, an explanatory sequential mixed-method design was implemented. The method facilitated the subsequent design of qualitative in-depth interviews with the drivers. The combined data analysis allowed a holistic interpretation and evaluation of the findings regarding the effect of the driving context on ADAS usage. The findings warrant consideration of the driving context as a key factor enabling the effective development of ADAS functions.

Recently the automotive industry has made a huge leap forward in Automated Driver Assistance Systems (ADAS) development, increasing the level of driving processes automation. However, ADAS design does not imply any individual support to the driver; this results in a poor understanding of how the ADAS works and its limitations. This type of driver uncertainty regarding ADAS performance can erode the user's trust in the system and result in decreasing situations when the system is in use. This paper presents the design of a data-driven communication framework that can utilize historical and real-time vehicle data to support ADAS users. The data-driven communication framework aims to illustrate the ADAS capabilities and limitations and suggests effective use of the system in real-time driving situations. This type of assistance can improve a driver's understanding of ADAS functionality and encourage its usage. [ABSTRACT FROM AUTHOR]

Quantitative estimation of a driver's vigilance level has a great value for improving driving safety and preventing accidents. Previous studies have identified correlations between electroencephalogram (EEG) spectrum power and a driver's mental states such as vigilance and alertness. Studies have also built classification models that can estimate vigilance state changes based on data collected from drivers. In the present study, we propose a system to detect vigilance level using not only a driver's EEG signals but also driving contexts as inputs. We combined a support vector machine with particle swarm optimization methods to improve classification accuracy. A simulated driving task was conducted to demonstrate the reliability of the proposed system. Twenty participants were assigned a 2-h sustained-attention driving task to identify a lead car's brake events. Our system was able to account for 84.1% of experimental reaction times with 162-ms prediction errors. A newly introduced driving context factor, road curves, improved the prediction accuracy by 2–5% with 30–80 ms smaller errors. These findings demonstrated the potential value of the proposed system for estimating driver vigilance level on a time scale of seconds. [ABSTRACT FROM PUBLISHER]

• This study analyses the link between the driving context (where people drive) and risk. • The impacts of the contextual factors on the predictions are ranked and interpreted using SHAP. • It is found that the driving context has significant power in predicting driving risk. • High-speed roads in warm temperatures increase the likelihood of harsh acceleration and braking. • Speed limit, temperature, traffic conditions, and road slope are the leading contexts for most risk events. Usage-based insurance has allowed insurers to dynamically tailor insurance premiums by understanding when and how safe policyholders drive. However, telematics information can also be used to understand the driving contexts experienced by the driver within each trip (e.g., road types, weather, traffic). Since different combinations of these conditions affect exposure to accidents, this understanding introduces predictive opportunities in driving risk assessment. This paper investigates the relationships between driving context combinations and risk using a naturalistic driving dataset of 77,859 km. In particular, XGBoost and Random Forests are used to determine the predictive significance of driving contexts for near-misses, speeding and distraction events. Moreover, the most important contextual factors in predicting these risky events are identified and ranked through Shapley Additive Explanations. The results show that the driving context has significant power in predicting driving risk. Speed limit, weather temperature, wind speed, traffic conditions and road slope appear in the top ten most relevant features for most risky events. Analysing contextual feature variations and their influence on risky events showed that low-speed limits increase the predicted frequency of speeding and phone unlocking events, whereas high-speed limits decrease harsh accelerations. Low temperatures decrease the expected frequency of harsh manoeuvres, and precipitations increase harsh acceleration, harsh braking, and distraction events. Furthermore, road slope, intersections and pavement quality are the most critical factors among road layout attributes. The methodology presented in this study aims to support road safety stakeholders and insurers by providing insights to study the contextual risk factors that influence road accident frequency and driving risk. [ABSTRACT FROM AUTHOR]

Introduction Visual–manual (VM) phone tasks (i.e., texting, dialing, reading) are associated with an increased crash/near-crash risk. This study investigated how the driving context influences drivers' decisions to engage in VM phone tasks in naturalistic driving. Method Video-recordings of 1,432 car trips were viewed to identify VM phone tasks and passenger presence. Video, vehicle signals, and map data were used to classify driving context (i.e., curvature, other vehicles) before and during the VM phone tasks (N = 374). Vehicle signals (i.e., speed, yaw rate, forward radar) were available for all driving. Results VM phone tasks were more likely to be initiated while standing still, and less likely while driving at high speeds, or when a passenger was present. Lead vehicle presence did not influence how likely it was that a VM phone task was initiated, but the drivers adjusted their task timing to situations when the lead vehicle was increasing speed, resulting in increasing time headway. The drivers adjusted task timing until after making sharp turns and lane change maneuvers. In contrast to previous driving simulator studies, there was no evidence of drivers reducing speed as a consequence of VM phone task engagement. Conclusions The results show that experienced drivers use information about current and upcoming driving context to decide when to engage in VM phone tasks. However, drivers may fail to sufficiently increase safety margins to allow time to respond to possible unpredictable events (e.g., lead vehicle braking). Practical applications Advanced driver assistance systems should facilitate and possibly boost drivers' self-regulating behavior. For instance, they might recognize when appropriate adaptive behavior is missing and advise or alert accordingly. The results from this study could also inspire training programs for novice drivers, or locally classify roads in terms of the risk associated with secondary task engagement while driving. [ABSTRACT FROM AUTHOR]

Naturalistic driving studies show that drivers engaged in complex visual-manual tasks face an increased risk of a crash or near-crash. Tasks that require many glances and a high proportion of long glances away from the road are of special concern for safety. Driving context (e.g. turning maneuvers, presence of lead or oncoming vehicles, vehicle speed) may also influence drivers’ glance behavior during normal driving, since the drivers may have to estimate curvature and anticipate potential threats (e.g., lead vehicle braking). However, the effect of driving context on glance behavior during visual-manual tasks has not yet been thoroughly investigated in naturalistic driving. The extent to which drivers adapt their glance behavior to changes in the road environment during secondary tasks is likely to influence their ability to compensate for and respond to changes in the road environment. The present study investigated for the first time the effect of both driving context and visual-manual phone tasks (i.e., dialing, texting, reading) on drivers’ glance behavior in naturalistic driving. This study shows that drivers indeed spend more time looking at the road and have a lower proportion of long off-road glances in complex driving contexts such as when turning and when lead or oncoming vehicles are present, both in normal driving and while engaged in a visual-manual phone task. In particular, these findings are more pronounced during turning maneuvers and in the presence of oncoming vehicles than in the presence of lead vehicles. Interestingly, driving speed influenced off-road glance durations during the phone tasks, but not during normal driving. The results from this study highlight the need to take driving context into account when evaluating the influence of different secondary tasks, in-vehicle user interfaces and glance metrics on driving safety, including the risk of crash involvement. The finding that glance behavior is context-dependent in a naturalistic setting has further implications for distraction detection algorithms, driver support systems, and driver training. Finally, driving contexts should be matched when comparing glance behavior, while driving with and without secondary tasks. [ABSTRACT FROM AUTHOR]