A Review of Research on Driving Styles and Road Safety

Once a driver, always a driver - Manual driving style persists in automated driving takeover

As automated vehicles require human drivers to resume control in critical situations, predicting driver takeover behaviour could be beneficial for safe transitions of control. While previous research has explored predicting takeover behaviour in relation to driver state and traits, little work has examined the predictive value of manual driving style. We hypothesised that drivers' behaviour during manual driving is predictive of their takeover behaviour when resuming control from an automated vehicle. We assessed 38 drivers with varying experience in a high-fidelity driving simulator. After completing manual driving sessions to assess their driving style, participants performed an automated driving task, typically on a subsequent date. Measures of driving style from manual driving sessions, including headway and lane change speed, were found to be predictive of takeover behaviour. The level of driving experience was associated with the behavioural measures, but correlations between measures of manual driving style and takeover behaviour remained after controlling for driver experience. Our findings demonstrate that how drivers reclaim control from their automated vehicle is not an isolated phenomenon but is associated with manual driving behaviour and driving experience. Strategies to improve takeover safety and comfort could be based on driving style measures, for example by the automated vehicle adapting its behaviour to match a driver's driving style.

Multigroup invariance of measure for angry drivers (MAD) scale using a representative sample of drivers in Australia

INTRODUCTION

Driver anger and aggression have been linked to crash involvement and injury outcomes. Improved road safety outcomes may be achieved through understanding the causes of driver anger, and interventions designed to reduce this anger or prevent it from becoming aggression. Scales to measure anger propensities will be an important tool in this work. The measure for angry drivers (MAD; Stephens et al., 2019) is a contemporary scale designed to measure tendencies for anger across three types of driving scenarios: perceived danger from others, travel delays, and hostility or aggression from other drivers.

METHOD

This study aimed to validate MAD using a representative sample of Australian drivers, stratified across age, gender, and location. Participants completed a 10-minute online survey that included MAD, sought demographic information (age, gender, driving purpose, crash history), as well as the frequency of aggressive driving. Multigroup confirmatory factor analyses (MGCFA) assessed how stable the structure of the MAD was across drivers of different ages, gender, purposes for driving and those who do or do not display anger aggressively. MAD was invariant across all groups, showing that all drivers interpreted and responded to MAD in the same way.

RESULTS

A comparison of latent means showed anger tendencies were higher for men compared to women, for younger drivers compared to older drivers, and for those who drive mainly for work compared to those who mainly drive for other reasons. When controlling for driver factors, driving anger was associated with increased odds of being aggressive while driving.

PRACTICAL APPLICATIONS

Overall, this study demonstrated that MAD is an appropriate scale to measure anger tendencies and can be used to support interventions, and evaluation of interventions, to reduce anger and aggressive driving.

Road safety attitude and behaviour among motorcycle riders in Ghana: A focus on traffic locus of control and health belief

Road traffic accident is a leading cause of death and various life deformities worldwide. This burden is even higher among motorcycle riders in lower-to-middle-income countries. Despite the various interventions made to address the menace, the fatalities continue to be on the ascendency. One major area that has received little attention is the attitude and behaviour of motorcycle riders. The present study aimed to examine the contribution of traffic Locus of Control (LoC) and health belief on road safety attitude and behaviour. 317 motorcycle riders participated in the study. The participants completed a questionnaire comprising various sections such as motorcycle riding behaviour, road safety attitude, risk perception, the intention to use helmets, and traffic LoC. The results showed a significant positive correlation between road safety attitude and behaviour (r (295) = .33, p < .001). Drifting towards internal LoC was associated with more positive behaviour on the roads (r (295) = -.23, p < .001). Intention to use helmet, health motivation, perceived susceptibility, perceived benefits, and perceived barriers were the factors in the health belief model that were associated with road safety attitude (r (295) = .404, p < .001). Finally, the multiple linear regression model showed that road safety attitude and traffic LoC made significant contributions to road user behaviour [F(3, 293) = 13.73, p < .001]. These findings have important implications towards shaping responsible behaviour among motorcycle riders.

Fostering Drivers' Trust in Automated Driving Styles: The Role of Driver Perception of Automated Driving Maneuvers

OBJECTIVE

This study investigated the impact of driving styles of drivers and automated vehicles (AVs) on drivers' perception of automated driving maneuvers and quantified the relationships among drivers' perception of AV maneuvers, driver trust, and acceptance of AVs.

BACKGROUND

Previous studies on automated driving styles focused on the impact of AV's global driving style on driver's attitude and driving performance. However, research on drivers' perception of automated driving maneuvers at the specific driving style level is still lacking.

METHOD

Sixteen aggressive drivers and sixteen defensive drivers were recruited to experience twelve driving scenarios in either an aggressive AV or a defensive AV on the driving simulator. Their perception of AV maneuvers, trust, and acceptance was measured via questionnaires, and driving performance was collected via the driving simulator.

RESULTS

Results revealed that drivers' trust and acceptance of AVs would decrease significantly if they perceived AVs to have a higher speed, larger deceleration, smaller deceleration, or shorter stopping distance than expected. Moreover, defensive drivers perceived significantly greater inappropriateness of these maneuvers from aggressive AVs than defensive AVs, whereas aggressive drivers didn't differ significantly in their perceived inappropriateness of these maneuvers with different driving styles.

CONCLUSION

The driving styles of automated vehicles and drivers influenced drivers' perception of automated driving maneuvers, which influence their trust and acceptance of AVs.

APPLICATION

This study suggested that the design of AVs should consider drivers' perceptions of automated driving maneuvers to avoid undermining drivers' trust and acceptance of AVs.

Calibrated to drive: Measuring self-assessed driving ability and perceived workload after prolonged sitting and sleep restriction

Self-assessed driving ability may differ from actual driving performance, leading to poor calibration (i.e., differences between self-assessed driving ability and actual performance), increased risk of accidents and unsafe driving behaviour. Factors such as sleep restriction and sedentary behaviour can impact driver workload, which influences driver calibration. This study aims to investigate how sleep restriction and prolonged sitting impact driver workload and driver calibration to identify strategies that can lead to safer and better calibrated drivers. Participants (n = 84, mean age = 23.5 ± 4.8, 49 % female) undertook a 7-day laboratory study and were randomly allocated to a condition: sitting 9-h sleep opportunity (Sit9), breaking up sitting 9-h sleep opportunity (Break9), sitting 5-h sleep opportunity (Sit5) and breaking up sitting 5-h sleep opportunity (Break5). Break9 and Break5 conditions completed 3-min of light-intensity walking on a treadmill every 30 min between 09:00-17:00 h, while participants in Sit9 and Sit5 conditions remained seated. Each participant completed a 20-min simulated commute in the morning and afternoon each day and completed subjective assessments of driving ability and perceived workload before and after each commute. Objective driving performance was assessed using a driving simulator measuring speed and lane performance metrics. Driver calibration was analysed using a single component and 3-component Brier Score. Correlational matrices were conducted as an exploratory analysis to understand the strength and direction of the relationship between subjective and objective driving outcomes. Analyses revealed participants in Sit9 and Break9 were significantly better calibrated for lane variability, lane position and safe zone-lane parameters at both time points (p < 0.0001) compared to Sit5 and Break5. Break5 participants were better calibrated for safe zone-speed and combined safe zone parameters (p < 0.0001) and speed variability at both time points (p = 0.005) compared to all other conditions. Analyses revealed lower perceived workload scores at both time points for Sit9 and Break9 participants compared to Sit5 and Break5 (p = <0.001). Breaking up sitting during the day may reduce calibration errors compared to sitting during the day for speed keeping parameters. Future studies should investigate if different physical activity frequency and intensity can reduce calibration errors, and better align a driver's self-assessment with their actual performance.

Understanding risky driving behaviors among young novice drivers in Nigeria: A latent class analysis coupled with association rule mining approach

Traffic crashes are significant public health concern in Nigeria, particularly among young drivers. The study aims to explore the underlying pattern of risky driving behaviors and the associations with demographic factors among young drivers in Nigeria. A combined approach of Latent Class Analysis (LCA) and Association Rule Mining is applied to the dataset comprising responses from 684 young drivers who complete the "Behavior of Young Novice Drivers Scale" (BYND) questionnaires. The LCA identifies four distinct classes of drivers based on the risky behavior profiles: Reckless-Speedsters, Cautious Drivers, Distracted Multitaskers, and Emotion-impacted Drivers. Association rule mining further connects these driver classes to demographic and driving history variables, uncovering intriguing insights. Reckless-Speedsters predominantly consist of young males who engage in riskier driving behaviors, including exceeding speed limits and disregarding traffic rules. Conversely, Cautious Drivers, also predominantly young males, exhibit a safer driving profile marked by rule adherence and a notably lower crash rate. Distracted Multitaskers, sharing a demographic profile with Cautious Drivers, diverge significantly due to their higher crash involvement, hinting at a propensity for distracted driving practices. Lastly, Emotion-Impacted Drivers, primarily comprising young employed males, display behaviors influenced by emotions, shorter driving distances, and prior unsupervised driving experience. Most of the behaviors are attributed to inadequate traffic control, absence of traffic signs in most of the roads, preferential treatment, and lack of strict law enforcement in the country. The findings hold substantial implications for road safety interventions in Nigeria, urging targeted approaches to address the unique challenges presented by each driver class. With acknowledging the study limitations and advocating for future research in objective measures and emotion-behavior interactions, the comprehensive approach provides a robust foundation for enhancing road safety in the Nigerian context.

Trends and Characteristics of Human Casualties in Wildlife-Vehicle Accidents in Lithuania, 2002-2022

We analyzed 474 human casualties in wildlife-vehicle accidents (WVAs) that occurred between 2002 and 2022 in Lithuania, which is a small northern European country. The study revealed the escalating trend of WVAs, since 2018 surpassing other transport accidents, although the number of casualties per WVA was ca. 100 times lower compared to other transport accidents. Moose was the primary contributor, responsible for 66.7% of fatalities and 47.2% of injuries, despite much lower species abundance compared to roe deer, which is the main species involved in WVAs without human casualties. Temporal patterns highlighted seasonal, daily, and hourly variations, with the majority of casualties occurring during dusk or dawn in May and September, on weekends, and between 20:00 and 22:00. Spatially, main roads with high traffic density exhibited the highest casualties per unit length. Most casualties occurred after hitting an animal directly with cars and motorcycles being most vulnerable vehicles. The effectiveness of WVA prevention measures was inconclusive: 9.5% of fatalities and 1.4% of injuries were registered in the area of the warning sign, and 10.4% of all casualties occurred on fenced road segments. These findings suggest the need for a critical evaluation of the current prevention strategies in reducing human casualties associated with WVAs.

The effect of guardrail color on driver behavior based on driving style along mountain curves

OBJECTIVE

Mountain highways are linearly complex, with extensive curves and high accident injury rates, how to improve driving safety is the key to traffic safety management on mountain highways, and it also meets the need for harmonious and sustainable development of the society. Therefore, this study investigates the effects of different guardrail color configurations on the driving behavior of different styles of drivers when driving on mountainous curves from the perspective of improving road aids - guardrails.

METHODS

A virtual reality experiment was designed using a driving simulator and VR technology, and 64 subjects were recruited to participate and complete the experiment.

RESULTS

Drivers with non-adaptive driving styles (Reckless, Angry, Anxious) traveled at significantly higher speeds than subjects with adaptive driving styles (Cautious) on mountainous roads; drivers with Cautious styles had better lane-keeping ability when passing through different radii of curves as compared to non-adaptive drivers; and the red and yellow guardrails were more effective in decreasing the speeds at which drivers passed and in increasing the stability of lane-keeping.

CONCLUSIONS

The results of the study show that the effectiveness of red and yellow guardrails is better, which provides a reference for the traffic management department to propose a standardized color setting of guardrails in mountainous areas, which is conducive to the development of more precise traffic management measures to reduce the occurrence of traffic accidents.

Effects of driving style on takeover performance during automated driving: Under the influence of warning system factors

Driving style has been proposed to be a critical factor in automated driving. However, the role of driving style in the process of taking over during automated driving needs further investigation. The main purpose of this study was to investigate the influence of driving style on takeover performance under the influence of warning system factors. In addition, this study also explored whether the impact of driving style on reaction time varies over time and the role of driving style on a comprehensive takeover quality indicator. Two driving simulation experiments with different takeover request (TOR) designs were conducted. In experiment 1, content warning information was provided in the TOR with different warning stage designs; in experiment 2, countdown warning information was provided in the TOR with different warning stage designs. Sixty-four participants (32 for experiment 1 and 32 for experiment 2) were classified into two groups based on their driving style (i.e., aggressive, or defensive) using the Chinese version of the Multidimensional Driving Style Inventory (the brief MDSI-C). The results suggested that drivers' driving style had significant effects on takeover performance, but the effects were influenced by warning system designs. Specifically, defensive participants performed better takeover performance, i.e., shorter reaction time and cautious vehicle control behaviors, than aggressive participants in most warning conditions. The content and countdown warning information and warning stage design affected the roles of driving style on takeover performance: 1) compared to the one-stage warning design, the two-stage warning design significantly shortened the reaction time of the participants with different driving styles, 2) compared to the countdown warning information design, the design of content warning information can shorten the reaction time of aggressive participants and lengthen the reaction time of defensive participants in the two-stage warning conditions, and 3) compared to the content warning information design, countdown warning information can improve the safe takeover performance of defensive participants. This study provides a better understanding of the role of driving style on takeover performance, and driving style should be considered when designing warning systems for autonomous vehicles.

Comparing Subjective Similarity of Automated Driving Styles to Objective Distance-Based Similarity

OBJECTIVE

This study explores subjective and objective driving style similarity to identify how similarity can be used to develop driver-compatible vehicle automation.

BACKGROUND

Similarity in the ways that interaction partners perform tasks can be measured subjectively, through questionnaires, or objectively by characterizing each agent's actions. Although subjective measures have advantages in prediction, objective measures are more useful when operationalizing interventions based on these measures. Showing how objective and subjective similarity are related is therefore prudent for aligning future machine performance with human preferences.

METHODS

A driving simulator study was conducted with stop-and-go scenarios. Participants experienced conservative, moderate, and aggressive automated driving styles and rated the similarity between their own driving style and that of the automation. Objective similarity between the manual and automated driving speed profiles was calculated using three distance measures: dynamic time warping, Euclidean distance, and time alignment measure. Linear mixed effects models were used to examine how different components of the stopping profile and the three objective similarity measures predicted subjective similarity.

RESULTS

Objective similarity using Euclidean distance best predicted subjective similarity. However, this was only observed for participants' approach to the intersection and not their departure.

CONCLUSION

Developing driving styles that drivers perceive to be similar to their own is an important step toward driver-compatible automation. In determining what constitutes similarity, it is important to (a) use measures that reflect the driver's perception of similarity, and (b) understand what elements of the driving style govern subjective similarity.

Bibliometric review of telematics-based automobile insurance: Mapping the landscape of research and knowledge

Telematics technology and its implementation in auto insurance have received great interest due to their potential to transform the insurance sector and promote safer driving practices. By implementing telematics technology, insurers may tailor insurance premiums to individual drivers, taking into account their real driving habits and performance, ultimately leading to improved road safety, cost savings, and an empowered driving community. The current study, through bibliometric analysis, carefully identifies and evaluates the existing body of scholarly literature on this subject for the last 21 years, including journal articles, conference papers, and related publications. The analysis uncovers key research studies, influential authors, top publication outlets, top countries with collaborations, and prolific research fields, providing useful insights into the evolution and growth of telematics-based insurance research. Furthermore, thematic mapping, cluster analysis, and critical analysis of top recent studies aided in identifying key research clusters and themes, as well as potential gaps and areas for further exploration, guiding future researchers and policymakers in advancing this transformative technology.

How drivers perform under different scenarios: Ability-related driving style extraction for large-scale dataset

The extraction and analysis of driving style are essential for a comprehensive understanding of human driving behaviours. Most existing studies rely on subjective questionnaires and specific experiments, posing challenges in accurately capturing authentic characteristics of group drivers in naturalistic driving scenarios. As scenario-oriented naturalistic driving data collected by advanced sensors becomes increasingly available, the application of data-driven methods allows for a exhaustive analysis of driving styles across multiple drivers. Following a theoretical differentiation of driving ability, driving performance, and driving style with essential clarifications, this paper proposes a quantitative determination method grounded in large-scale naturalistic driving data. Initially, this paper defines and derives driving ability and driving performance through trajectory optimisation modelling considering various cost indicators. Subsequently, this paper proposes an objective driving style extraction method grounded in the Gaussian mixture model. In the experimental phase, this study employs the proposed framework to extract both driving abilities and performances from the Waymo motion dataset, subsequently determining driving styles. This determination is accomplished through the establishment of quantifiable statistical distributions designed to mirror data characteristics. Furthermore, the paper investigates the distinctions between driving styles in different scenarios, utilising the Jensen-Shannon divergence and the Wilcoxon rank-sum test. The empirical findings substantiate correlations between driving styles and specific scenarios, encompassing both congestion and non-congestion as well as intersection and non-intersection scenarios.

Driver-Automated Vehicle Interaction in Mixed Traffic: Types of Interaction and Drivers' Driving Styles

OBJECTIVE

This study investigated drivers' subjective feelings and decision making in mixed traffic by quantifying driver's driving style and type of interaction.

BACKGROUND

Human-driven vehicles (HVs) will share the road with automated vehicles (AVs) in mixed traffic. Previous studies focused on simulating the impacts of AVs on traffic flow, investigating car-following situations, and using simulation analysis lacking experimental tests of human drivers.

METHOD

Thirty-six drivers were classified into three driver groups (aggressive, moderate, and defensive drivers) and experienced HV-AV interaction and HV-HV interaction in a supervised web-based experiment. Drivers' subjective feelings and decision making were collected via questionnaires.

RESULTS

Results revealed that aggressive and moderate drivers felt significantly more anxious, less comfortable, and were more likely to behave aggressively in HV-AV interaction than in HV-HV interaction. Aggressive drivers were also more likely to take advantage of AVs on the road. In contrast, no such differences were found for defensive drivers indicating they were not significantly influenced by the type of vehicles with which they were interacting.

CONCLUSION

Driving style and type of interaction significantly influenced drivers' subjective feelings and decision making in mixed traffic. This study brought insights into how human drivers perceive and interact with AVs and HVs on the road and how human drivers take advantage of AVs.

APPLICATION

This study provided a foundation for developing guidelines for mixed transportation systems to improve driver safety and user experience.

Spanish adaptation and validation of the Dula Dangerous Driving Index (DDDI)

The Dula Dangerous Driving Index (DDDI) is a widely used questionnaire that measures the tendency to drive dangerously on the road through three different types of behaviors: aggressive driving, risky driving, and experiencing negative emotions while driving. This study aimed to develop a Spanish version of the DDDI and verify the reliability and validity of this questionnaire in the Spanish population. A community sample of 2174 Spanish participants (51.1% male; age range: 18-79 years) completed the 28-item Spanish version of the DDDI. Confirmatory factor analysis revealed that a three-factor model fitted adequately to the data. Analysis of internal consistency, test-retest reliability, and convergent validity showed that the Spanish adaptation of the DDDI had good psychometric properties and retains the theoretical consistency of the original scale. Gender and age differences were observed. The Spanish version of the DDDI can be considered a good instrument for assessing dangerous driving behavior, thus contributing to the cross-cultural study of these types of behaviors and the possible development of intervention programs aimed at reducing road traffic accidents.

Evasive actions to prevent pedestrian collisions in varying space/time contexts in diverse urban and non-urban areas

This study aims to identify driver-safe evasive actions associated with pedestrian crash risk in diverse urban and non-urban areas. The research focuses on the integration of quantitative methods and granular naturalistic data to examine the impacts of different driving contexts on transportation system performance, safety, and reliability. The data is derived from real-life driving encounters between pedestrians and drivers in various settings, including urban areas (UAs), suburban areas (SUAs), marked crossing areas (MCAs), and unmarked crossing areas (UMCAs). By determining critical thresholds of spatial/temporal proximity-based safety surrogate techniques, vehicle-pedestrian conflicts are clustered through a K-means algorithm into different risk levels based on drivers' evasive actions in different areas. The results of the data analysis indicate that changing lanes is the key evasive action employed by drivers to avoid pedestrian crashes in SUAs and UMCAs, while in UAs and MCAs, drivers rely on soft evasive actions, such as deceleration. Moreover, critical thresholds for several Safety Surrogate Measures (SSMs) reveal similar conflict patterns between SUAs and UMCAs, as well as between UAs and MCAs. Furthermore, this study develops and delivers a pseudo-code algorithm that utilizes the critical thresholds of SSMs to provide tangible guidance on the appropriate evasive actions for drivers in different space/time contexts, aiming to prevent collisions with pedestrians. The developed research methodology as well as the outputs of this study could be potentially useful for the development of a driver support and assistance system in the future.

Driving safety: Investigating the cognitive foundations of accident prevention

Driving is a crucial aspect of personal independence, and accurate assessment of driving skills is vital for ensuring road safety. This study aimed to identify reliable cognitive predictors of safe driving through a driving simulator experiment. We assessed the driving performance of 66 university students in two distinct simulated driving conditions and evaluated their cognitive skills in decision-making, attention, memory, reasoning, perception, and coordination. Multiple regression analyses were conducted to determine the most reliable cognitive predictor of driving outcome. Results revealed that under favorable driving conditions characterized by good weather and limited interactions with other road users, none of the variables tested in the study were able to predict driving performance. However, in a more challenging scenario with adverse weather conditions and heavier traffic, cognitive assessment scores demonstrated significant predictive power for the rate of traffic infractions committed. Specifically, cognitive skills related to memory and coordination were found to be most predictive. This study underscores the significance of cognitive ability, particularly memory, in ensuring safe driving performance. Incorporating cognitive evaluations in driver licensing and education/training programs can enhance the evaluation of drivers' competence and promote safer driving practices.

Novel semi-quantitative risk model based on AHP: A case study of US driving risks

Road safety is a priority, worldwide. The European Commission aims to reduce fatalities by 2030. The same goal was set for the US. These goals stem from the World Health Organization's (WHO's) broader global context, which has distinctly emphasized a substantial reduction in road traffic injuries. Although different risk factors were observed in different geographical locations, the major risk factors for all locations were similar. They involve influencing human behavior, such as speeding or driving. Several methods have been used to better understand and extract risk factors. However, the complexity of road traffic implies the need for a multi-criteria method. As a result, the analytical hierarchy process (AHP) has emerged as a potential method for this type of risk. The AHP is commonly associated with the use of qualitative methods such as surveys. We propose a novel semi-quantitative multi-criteria risk model (SMCRisk) based on the AHP, deployed in a quantitative and partially qualitative manner by adding a severity factor. The multi-level framework differentiates between the driver's behavior and the driver's state. Our method results correspond to a real situation and confirm that driver behavior and state are major risk factors. In future, this method will lay the foundation for integrating a fully quantitative method by considering the potential use of data originating directly from the IoT, which is a part of our research on holistic risk assessment.

Better safe than sorry - Understanding the attitude and habits of drivers can help mitigating animal-vehicle collisions

The rapidly growing global road networks put serious pressures on terrestrial ecosystems and increase the number and severity of human-wildlife conflicts, which in most cases manifest in animal-vehicle collisions (AVCs). AVCs pose serious problems both for biodiversity conservation and traffic safety: each year, millions of vertebrates are roadkilled globally and the related economic damage is also substantial. For a comprehensive understanding of factors influencing AVC it is essential to explore the human factor, that is, the habits and attitude of drivers; however, to date, comprehensive surveys are lacking on this topic. Here we addressed this knowledge gap and surveyed the habits of drivers and their experience and attitude towards AVCs by a comprehensive questionnaire covering a large geographical area and involving a large number of respondents (1942 completed questionnaires). We aimed to reveal how driving habits affect the chance of AVC, and explored the attitude of the drivers regarding AVC. We found that the number of lifetime AVC cases was higher for male drivers, for those who drove longer distances per year, had more driven years, used country roads or drove large vehicles. Our results showed that almost half of the drivers surveyed had experienced at least one AVC in their lifetime. Drivers' attitudes towards the importance of nature conservation or traffic safety in the aspect of AVC, and fear of collision showed a significant correlation with experienced AVC cases. Drivers' opinions indicated that the most trusted and desired AVC prevention measures were physical objects such as fences and wildlife crossings. Our research provides guidelines for developing targeted initiatives in the future to increase awareness about the significance of AVC and target those drivers who are most vulnerable to AVC.

Feature selection for driving style and skill clustering using naturalistic driving data and driving behavior questionnaire

Driver's driving style and driving skill have an essential influence on traffic safety, capacity, and efficiency. Through clustering algorithms, extensive studies explore the risk assessment, classification, and recognition of driving style and driving skill. This paper proposes a feature selection method for driving style and skill clustering. We create a supervised machine learning model of driver identification for driving behavior data with no ground truth labels on driving style and driving skill. The key features are selected based on permutation importance with the underlying assumption that the key features for clustering should also play an important role in characterizing individual drivers. The proposed method is tested on naturalistic driving data. We introduce 18 feature extraction methods and generate 72 feature candidates. We find five key features: longitudinal acceleration, frequency centroid of longitudinal acceleration, shape factor of lateral acceleration, root mean square of lateral acceleration, and standard deviation of speed. With the key features, drivers are clustered into three groups: novice, experienced cautious, and experienced reckless drivers. The ability of each feature to describe individuals' driving style and skill is evaluated using the Driving Behavior Questionnaire (DBQ). For each group, the driver's response to DBQ key questions and their distribution of key features are analyzed to prove the validity of the feature selection result. The feature selection method has the potential to understand driver's characteristics better and improve the accuracy of driving behavior modeling.

Psychological predictors of risky driving: the role of age, gender, personality traits (Zuckerman's and Gray's models), and decision-making styles

The present study was planned to study the relationships between age, personality (according to Zuckerman's and Gray's psychobiological models) and decision-making styles in relation to risky driving behaviors. The participants were habitual drivers, 538 (54.3%) men and 453 (45.7%) women, with a mean age around 45 years and mainly of middle socioeconomic status. The results indicate that the youngest men and women reported more Lapses, Ordinary violations, and Aggressive violations than the oldest men and women. Women reported more Lapses (d = -0.40), and men more Ordinary (d = 0.33) and Aggressive violations (d = 0.28) when driving. Linear and non-linear analysis clearly support the role of both personality traits and decision-making styles in risky driving behaviors. Aggressiveness, Sensitivity to Reward, Sensation Seeking played the main role from personality traits, and Spontaneous and Rational decision-making style also accounted for some variance regarding risky driving behaviors. This pattern was broadly replicated in both genders. The discussion section analyses congruencies with previous literature and makes recommendations on the grounds of observed results.

Effect of CannEpil® on simulated driving performance and co-monitoring of ocular activity: A randomised controlled trial

BACKGROUND

Medicinal cannabis products containing Δ9-tetrahydrocannabinol (THC) are increasingly accessible. Yet, policy guidelines regarding fitness to drive are lacking, and cannabinoid-specific indexations of impairment are underdeveloped.

AIMS

To determine the impact of a standardised 1 mL sublingual dose of CannEpil^®, a medicinal cannabis oil containing 100 mg cannabidiol (CBD) and 5 mg THC on simulated driving performance, relative to placebo and whether variations in vehicle control can be indexed by ocular activity.

METHODS

A double-blind, within-subjects, randomised, placebo-controlled, crossover trial assessed 31 healthy fully licensed drivers (15 male, 16 female) aged between 21 and 58 years (M = 38.0, SD = 10.78). Standard deviation of lateral position (SDLP), standard deviation of speed (SDS) and steering variability were assessed over time and as a function of treatment during a 40 min simulated drive, with oculomotor parameters assessed simultaneously. Oral fluid and plasma were collected at 30 min and 2.5 h.

RESULTS

CannEpil did not significantly alter SDLP across the full drive, although increased SDLP was observed between 20 and 30 min (p < 0.05). CannEpil increased SDS across the full drive (p < 0.05), with variance greatest at 20-30 min (p < 0.001). CannEpil increased fixation duration (p < 0.05), blink rate (trend p = 0.051) and decreased blink duration (p < 0.001) during driving. No significant correlations were observed between biological matrices and performance outcomes.

CONCLUSIONS

CannEpil impairs select aspects of vehicle control (speed and weaving) over time. Alterations to ocular behaviour suggest that eye tracking may assist in determining cannabis-related driver impairment or intoxication. Australian and New Zealand Clinician Trials Registry, https://anzctr.org.au(ACTRN12619000932167).

A proactive crash risk prediction framework for lane-changing behavior incorporating individual driving styles

Driving style may have an important effect on traffic safety. Proactive crash risk prediction for lane-changing behaviors incorporating individual driving styles can help drivers make safe lane-changing decisions. However, the interaction between driving styles and lane-changing risk is still not fully understood, making it difficult for advanced driver-assistance systems (ADASs) to provide personalized lane-changing risk information services. This paper proposes a personalized risk lane-changing prediction framework that considers driving style. Several driving volatility indices based on vehicle interactive features have been proposed, and a dynamic clustering method is developed to determine the best identification time window and methods of driving style. The Light Gradient Boosting Machine (LightGBM) based on Shapley additive explanation is used to predict lane-changing risk for cautious, normal, and aggressive drivers and to analyze their risk factors. The highD trajectory dataset is used to evaluate the proposed framework. The obtained results show that i) spectral clustering and a time window of 3 s can accurately identify driving styles during the lane-changing intention process; ii) the LightGBM algorithm outperforms other machine learning methods in personalized lane-changing risk prediction; iii) aggressive drivers seek more individual driving freedom than cautious and normal drivers and tend to ignore the state of the car behind them in the target lane, with a greater lane-changing risk. The research conclusion can provide basic support for the development and application of personalized lane-changing warning systems in ADASs.

An exploration of the role of driving experience on self-reported and real-world aberrant driving behaviors

A significant proportion of global road crashes are attributed to unsafe driving behaviors. The current study aimed to explore potential differences in driving behaviors across experienced and novice drivers using two separate approaches; a questionnaire study and an instrumented vehicle study (IVS). The analysis of 260 questionnaires and 1,372 traffic interactions within the IVS revelated that driving experience affects driving performance for different driving tasks. Factor analysis of the questionnaire data revealed the impact of driving errors, lapses, violations, and aggressive violations on the behavior of novice and experienced drivers. Behavioral models of novice and experienced drivers encountering other road users were determined using binary logistic regression. The results showed that novice drivers were more likely to engage in driving violations while experienced drivers were more likely to engage in aggressive violations. Unauthorized speeding, zigzag movements, using a mobile phone while driving, and unauthorized overtaking on roads were the most frequent driving violations by novice drivers. The most frequent aggressive violations by experienced drivers were tempting other drivers to create a race and chasing other drivers. These findings may be used as a framework to facilitate safer driving behaviors by reducing errors, lapses, violations and aggressive violations, and facilitating safety-promoting attitudes.

Effects of Distracting Behaviors on Driving Workload and Driving Performance in a City Scenario

Distractors faced by drivers grow continuously, and concentration on driving becomes increasingly difficult, which has detrimental influences on road traffic safety. The present study aims to investigate changes in driving workload and driving performance caused by distracting tasks. The recruited subjects were requested to drive along a city route in a real vehicle and perform three secondary tasks sequentially. Electrocardiography and driving performance were measured. Heart rate variability (HRV) was adopted to quantitatively analyze the driving workload. Findings show that: (i) increments are noticed in the root mean square differences of successive heartbeat intervals (RMSSD), the standard deviation of normal-to-normal peak (SDNN), the heart rate growth rate (HRGR), and the ratio of low-frequency to high-frequency powers (LF/HF) compared to undistracted driving; (ii) the hands-free phone conversation task has the most negative impacts on driving workload; (iii) vehicle speed reduces due to secondary tasks while changes in longitudinal acceleration exhibit inconsistency; (iv) the experienced drivers markedly decelerate during hands-free phone conversation, and HRGR shows significant differences in both driving experience and gender under distracted driving conditions; (v) correlations exist between HRV and driving performance, and LF/HF correlates positively with SDNN/RMSSD in the hands-free phone conversation and chatting conditions while driving.

Modeling the Impact of Driving Styles on Crash Severity Level Using SHRP 2 Naturalistic Driving Data

Previous studies have examined driving styles and how they are associated with crash risks relying on self-report questionnaires to categorize respondents based on pre-defined driving styles. Naturalistic driving studies provide a unique opportunity to examine this relationship differently. The current study aimed to study how driving styles, derived from real-road driving, may relate to crash severity. To study the relationship, this study retrieved safety critical events (SCEs) from the SHRP 2 database and adopted joint modelling of the number of the aggregated crash severity levels (crash vs. non-crash) using the Diagonal Inflated Bivariate Poisson (DIBP) model. Variables examined included driving styles and various driver characteristics. Among driving styles examined, styles of maintenance of lower speeds and more adaptive responses to driving conditions were associated with fewer crashes given an SCE occurred. Longer driving experiences, more miles driven last year, and being female also reduced the number of crashes. Interestingly, older drivers were associated with both an increased number of crashes and increased number of non-crash SCEs. Future work may leverage more variables from the SHRP 2 database and widen the scope to examine different traffic conditions for a more complete picture of driving styles.

Over-speeding trend across self-reported driving aberrant behaviors: A simulator study

The aim of the present study is to investigate the relation between self-reported aberrant behaviors as measured by using the Italian version of the Manchester Driver Behavior Questionnaire (DBQ) and actual driving performance during a virtual simulation, focusing particularly on over-speeding. Individual variables are considered based on participants’ behavior, and driving styles are derived from both the self-report questionnaire and the kinematic variables obtained through a moped simulator after the simulated driving task. The experiment was carried out on an Italian sample of 79 individuals aged between 18 and 35 who had to drive throughout virtual road environments. A cluster analysis of the kinematic variables provided by the simulator was used to individuate two different groups of drivers: 45 fell into the cluster named “Prudent” and 34 participants fell into the “Imprudent” cluster. The Prudent participants were characterized by lower acceleration, lower speed, better overall evaluations, and a smaller number of accidents. Correlations showed that self-report responses correlated positively with performance variables in terms of acceleration, speed, and over-speeding. Furthermore, the results from a MANOVA supported and complemented this evidence by emphasizing the usefulness of the integrated approach employed. Overall, these results reflect the suitability of experimental sample-splitting into two clusters, pointing out the appropriateness and relevance of self-report DBQ use with particular emphasis on Ordinary Violations and Lapses. The integrated use of the driving simulator and the self-report DBQ instrument with reference to driving behavior made it possible to support previous theoretical considerations regarding the relations between on-road aberrant behaviors and over-speeding behaviors. It also enabled the addition of evidence on the effectiveness of the simulator in detecting drivers’ actual performance. These results are relevant to allow the integration of useful information to expand intervention and training designs that can be used to reduce risky behavior and promote road safety.

Effects of working conditions and safety awareness on job satisfaction of truck drivers in Korea

BACKGROUND: Truck driving is one of the occupations with high injury rates. OBJECTIVE: This study investigates the relationships between age, work experience, workdays, monthly income, perceived job risk, satisfaction of working conditions, safety awareness, and job satisfaction of truck drivers. Also, this study analyzes the effects of satisfaction of working conditions and safety awareness on the job satisfaction of truck drivers. METHODS: This study interviewed 278 truck drivers and surveyed age, work experience, workdays, monthly income, perceived job risk, satisfaction of working conditions, safety awareness, and job satisfaction. A regression analysis was performed to determine leading factors affecting safety and satisfaction and the relationships. RESULTS: The results showed that the number of workdays was related to monthly income, perceived job risk, and job satisfaction. The monthly income of truck drivers was increased according to workdays and age. Perceived job risk increased with number of days worked. Safety awareness decreased with the monthly income, and job satisfaction decreased with perceived job risk level, workdays, and work experience. Finally, job satisfaction was directly affected by satisfaction with working conditions and indirectly affected by safety awareness. CONCLUSIONS: The results suggest that an increase in satisfaction of working conditions can enhance safety awareness and job satisfaction.

Feasibility study of personalized speed adaptation method based on mental state for teleoperated robots

The teleoperated robotic system can support humans to complete tasks in high-risk, high-precision and difficult special environments. Because this kind of special working environment is easy to cause stress, high mental workload, fatigue and other mental states of the operator, which will reduce the quality of operation and even cause safety accidents, so the mental state of the people in this system has received extensive attention. However, the existence of individual differences and mental state diversity is often ignored, so that most of the existing adjustment strategy is out of a match between mental state and adaptive decision, which cannot effectively improve operational quality and safety. Therefore, a personalized speed adaptation (PSA) method based on policy gradient reinforcement learning was proposed in this paper. It can use electroencephalogram and electro-oculogram to accurately perceive the operator’s mental state, and adjust the speed of the robot individually according to the mental state of different operators, in order to perform teleoperation tasks efficiently and safely. The experimental results showed that the PSA method learns the mapping between the mental state and the robot’s speed regulation action by means of rewards and punishments, and can adjust the speed of the robot individually according to the mental state of different operators, thereby improving the operating quality of the system. And the feasibility and superiority of this method were proved. It is worth noting that the PSA method was validated on 6 real subjects rather than a simulation model. To the best of our knowledge, the PSA method is the first implementation of online reinforcement learning control of teleoperated robots involving human subjects.

Temporal impacts of road safety interventions: A structural-shifts-based method for road accident mortality analysis

Extensive prior research has statistically analyzed the impact of infrastructural, policy, and environmental factors on road accidents, injuries, and mortalities. Most of these studies assumed long-term temporal stability in road safety data. These studies were later criticized for ignoring structural shifts in data over time caused by varying systemic influences such as socioeconomic and environmental factors, as well as major changes to road safety rules and networks. In this work, we proposed a novel four-phase methodology that identifies structural shifts or breaks in the road safety data and subsequently evaluates the role of various factors (including road safety interventions) in causing these breaks. The method is generalized, allowing different modeling bases and assumptions on the underlying data distribution. To demonstrate the merits of this methodology, we used it to investigate road accident mortality patterns in the Eastern Province of Saudi Arabia and its subregions for the period 2010-2020, when a series of road safety interventions were introduced. The case study analysis revealed the varying impact of these interventions at both the provincial and governorate levels. These results can be used to evaluate the efficacy of road safety interventions. The lessons learned can help to develop more robust road safety management programs.

The Analysis of Classification and Spatiotemporal Distribution Characteristics of Ride-Hailing Driver's Driving Style: A Case Study in China

Monitoring the driving styles of ride-hailing drivers is helpful for providing targeted training for drivers and improving the safety of the service. However, previous studies have lacked analyses of the temporal variation as well as spatial variation characteristics of driving styles. Understanding the variations can also help authorities formulate driver management policies. In this study, trajectory data are used to analyze driving styles in various temporal and spatial scenarios involving 34,167 drivers. The k-means method is used to cluster sample drivers. In terms of driving style time-varying, we found that only 31.79% of drivers could maintain a stable driving style throughout the day. Spatially, we divided the research area into two parts, namely, road segments and intersections, to analyze the spatial driving characteristics of drivers with different styles. The speed distribution, the acceleration and deceleration distributions are analyzed, results indicated that aggressive drivers display more aggressive driving styles in road segments, and conservative drivers exhibit more conservative driving styles at intersections. The findings of this study provide an understanding of temporal and spatial driving behavior factors for ride-hailing drivers and offer valuable contributions to ride-hailing driver training and road safety management.

A Fuzzy-Logic Approach Based on Driver Decision-Making Behavior Modeling and Simulation

The present study proposes a decision-making model based on different models of driver behavior, aiming to ensure integration between road safety and crash reduction based on an examination of speed limitations under weather conditions. The present study investigated differences in road safety attitude, driver behavior, and weather conditions I-69 in Flint, Genesee County, Michigan, using the fuzzy logic approach. A questionnaire-based survey was conducted among a sample of Singaporean (n = 100) professional drivers. Safety level was assessed in relation to speed limits to determine whether the proposed speed limit contributed to a risky or safe situation. The experimental results show that the speed limits investigated on different roads/in different weather were based on the participants’ responses. The participants could increase or keep their current speed limit or reduce their speed limit a little or significantly. The study results were used to determine the speed limits needed on different roads/in different weather to reduce the number of crashes and to implement safe driving conditions based on the weather. Changing the speed limit from 80 mph to 70 mph reduced the number of crashes occurring under wet road conditions. According to the results of the fuzzy logic study algorithm, a driver’s emotions can predict outputs. For this study, the fuzzy logic algorithm evaluated drivers’ emotions according to the relation between the weather/road condition and the speed limit. The fuzzy logic would contribute to assessing a powerful feature of human control. The fuzzy logic algorithm can explain smooth relationships between the input and output. The input–output relationship estimated by fuzzy logic was used to understand differences in drivers’ feelings in varying road/weather conditions at different speed limits.

Evaluation Method of Naturalistic Driving Behaviour for Shared-Electrical Car

Evaluation of driving behaviour is helpful for policy development, and for designing infrastructure and an intelligent safety system for a car. This study focused on a quantitative evaluation method of driving behaviour based on the shared-electrical car. The data were obtained from the OBD interface via CAN bus and transferred to a server by 4G network. Eleven types of NDS data were selected as the indexes for driving behaviour evaluation. Kullback–Leibler divergence was calculated to confirm the minimum data quantity and ensure the effectiveness of the analysis. The distribution of the main driving behaviour parameters was compared and the change trend of the parameters was analysed in conjunction with car speed to identify the threshold for recognition of aberrant driving behaviour. The weights of indexes were confirmed by combining the analytic hierarchy process and entropy weight method. The scoring rule was confirmed according to the distribution of the indexes. A score-based evaluation method was proposed and verified by the driving behaviour data collected from randomly chosen drivers.

A hybrid deep learning approach for driver anomalous lane changing identification

Reliable knowledge of driving states is of great importance to ensure road safety. Anomaly detection in driving behavior means recognizing anomalous driving states as a direct result of either environmental or psychological factors. This paper provides an efficient anomaly recognition approach to identify anomalous lane-changing events in a personalized manner. The proposed framework includes three unsupervised algorithms. First, a Recurrent-Convolutional Autoencoder extracts the spatio-temporal characteristics from a high-dimensional naturalistic driving dataset. Second, in order to recognize anomalous lane-changing events of individual drivers, the extracted latent feature space is analyzed using Pauta criterion-based reconstruction loss analysis, as well as one-class Support Vector Machine. Last, t-Distributed Stochastic Neighbor Embedding is employed to visualize the latent space for better understanding and interpretability. Temporal anomalies of lane-changing events were analyzed by a personalized grey relational coefficient analysis, to represent robust similarities for individual drivers. Validation and calibration were performed with a natural driving study dataset collected from 50 drivers with 59,372 lane change events. The results showed heterogeneity in the pattern of abnormal lane changing behavior across the sample. At the same time, each driver exhibited heterogeneous anomalous behaviors in both temporal and spatial sequences. Without prior labels, the proposed model effectively captures personalized driving patterns and abnormal lane-changing events from high-dimensional time-series data. This unsupervised hybrid approach is a novel attempt to complete personalized anomalous lane-changing behaviors identification based on naturalistic driving data involving various traffic environments. Our approach enables the extraction of natural individual lane-changing behavior patterns and provides insights for the improvement of personalized driving behavior monitoring systems.

Impact of Driving Behavior on Commuter’s Comfort during Cab Rides: Towards a New Perspective of Driver Rating

Commuter comfort in cab rides affects driver rating as well as the reputation of ride-hailing firms like Uber/Lyft. Existing research has revealed that commuter comfort not only varies at a personalized level but also is perceived differently on different trips for the same commuter. Furthermore, there are several factors, including driving behavior and driving environment, affecting the perception of comfort. Automatically extracting the perceived comfort level of a commuter due to the impact of the driving behavior is crucial for a timely feedback to the drivers, which can help them to meet the commuter’s satisfaction. In light of this, we surveyed around 200 commuters who usually take such cab rides and obtained a set of features that impact comfort during cab rides. Following this, we develop a system Ridergo  which collects smartphone sensor data from a commuter, extracts the spatial time series feature from the data, and then computes the level of commuter comfort on a five-point scale with respect to the driving. Ridergo  uses a Hierarchical Temporal Memory model-based approach to observe anomalies in the feature distribution and then trains a Multi-task learning-based neural network model to obtain the comfort level of the commuter at a personalized level. The model also intelligently queries the commuter to add new data points to the available dataset and, in turn, improve itself over periodic training. Evaluation of Ridergo  on 30 participants shows that the system could provide efficient comfort score with high accuracy when the driving impacts the perceived comfort.

Towards human-like speed control in autonomous vehicles: A mountainous freeway case

A driving strategy for autonomous vehicles (AVs) that is consistent with human behavior while demonstrating superior performance seems to have a good chance to be accepted by early AV users and be successful in the long run. Most of the past research focused on motion strategies affected by the presence of other vehicles. On the other hand, AV not constrained by other vehicles must select a safe and comfortable speed that is perceived as such by its occupants. This line of research is not well covered by the published work. The baseline speed, which is the speed AVs will follow without interaction with other vehicles, implemented via cruise control (CC) in modern vehicles is a constant speed consistent with speed limits and design speeds. A more advanced strategy of road-limiting speed control (RC) responds to influencing geometric features ahead of the AV's current position. Neither of the two strategies considers AV occupants' preferences. The current void in research is particularly obvious for free-flow conditions where baseline speeds must be implemented for extended periods of travel. Although the existing strategies have not been yet evaluated on roadways with demanding alignments and operating in free-flow conditions, the principles on which they are based provide a basis for skepticism if they can be acceptable to AV occupants. This study used the Tongji University driving simulator to evaluate the CC and RC strategies and their potential limitations in free-flow conditions on a mountainous freeway with complex alignments. Human speed-selection behavior was observed among a group of participating drivers. The clustering analysis of the data revealed three distinct driving styles: slow, fast, and consistent. The resulted analytical models provided human-focused road-dependent baseline speed profiles- a key element of the proposed human-like speed control (HC) strategy. The comparison of the existing speed-control strategies CC and RC with the proposed HC confirmed the limitations of the two existing ones if applied to roads with complex alignments. Considerable discrepancies were revealed between the baseline speeds produced with the existing and the proposed ones.

Understanding the potential of emerging digital technologies for improving road safety

Each year, 1.35 million people are killed on the world's roads and another 20-50 million are seriously injured. Morbidity or serious injury from road traffic collisions is estimated to increase to 265 million people between 2015 and 2030. Current road safety management systems rely heavily on manual data collection, visual inspection and subjective expert judgment for their effectiveness, which is costly, time-consuming, and sometimes ineffective due to under-reporting and the poor quality of the data. A range of innovations offers the potential to provide more comprehensive and effective data collection and analysis to improve road safety. However, there has been no systematic analysis of this evidence base. To this end, this paper provides a systematic review of the state of the art. It identifies that digital technologies - Artificial Intelligence (AI), Machine-Learning, Image-Processing, Internet-of-Things (IoT), Smartphone applications, Geographic Information System (GIS), Global Positioning System (GPS), Drones, Social Media, Virtual-reality, Simulator, Radar, Sensor, Big Data - provide useful means for identifying and providing information on road safety factors including road user behaviour, road characteristics and operational environment. Moreover, the results show that digital technologies such as AI, Image processing and IoT have been widely applied to enhance road safety, due to their ability to automatically capture and analyse data while preventing the possibility of human error. However, a key gap in the literature remains their effectiveness in real-world environments. This limits their potential to be utilised by policymakers and practitioners.

The Indicator of GDI Engine Operating Mode and Its Influence on Eco-Driving

Elements of car construction, especially the information available on a dashboard, can stimulate the way of driving. The experiment described in the paper aimed to examine how the information provided by the indicator, which informs about the operational mode of a gasoline direct injection (GDI) engine, can contribute to eco-driving and the possible learning of acceleration pedal operation by a driver. The analysis of the fuel injection process affected by driver behaviour was an essential part of the experiment. The experiment was divided into two parts. The first one (nine tests) consisted of driving without access to the indicator information. In the second part, the information on the mode of the engine run was available for the driver. The results confirmed that the information about the type of fuel mixture used for the supply of the GDI engine facilitates an economical driving style (about 10% fuel savings) and motivates the driver to engage in eco-driving.

A Framework for Building Comprehensive Driver Profiles

Conventional approaches to modelling driver risk have incorporated measures such as driver gender, age, place of residence, vehicle model, and annual miles driven. However, in the last decade, research has shown that assessing a driver’s crash risk based on these variables does not go far enough—especially as advanced technology changes today’s vehicles, as well as the role and behavior of the driver. There is growing recognition that actual driver usage patterns and driving behavior, when it can be properly captured in modelling risk, offers higher accuracy and more individually tailored projections. However, several challenges make this difficult. These challenges include accessing the right types of data, dealing with high-dimensional data, and identifying the underlying structure of the variance in driving behavior. There is also the challenge of how to identify key variables for detecting and predicting risk, and how to combine them in predictive algorithms. This paper proposes a systematic feature extraction and selection framework for building Comprehensive Driver Profiles that serves as a foundation for driver behavior analysis and building whole driver profiles. Features are extracted from raw data using statistical feature extraction techniques, and a hybrid feature selection algorithm is used to select the best driver profile feature set based on outcomes of interest such as crash risk. It can give rise to individualized detection and prediction of risk, and can also be used to identify types of drivers who exhibit similar patterns of driving and vehicle/technology usage. The developed framework is applied to a naturalistic driving dataset—NEST, derived from the larger SHRP2 naturalistic driving study to illustrate the types of information about driver behavior that can be harnessed—as well as some of the important applications that can be derived from it.

Effect of daily car-following behaviors on urban roadway rear-end crashes and near-crashes: A naturalistic driving study

The rear-end crash is one of the most common types of crashes, and key risk factors have been broadly identified in the car-following behaviors preceding a crash. However, the relationships between rear-end crash risk and daily car-following behaviors, or habits, have not been well examined. This study aims to identify the daily car-following behaviors on urban surface roads and urban expressways that have the most influence on rear-end crashes and near-crashes (CNC). Two months of naturalistic driving study data were used to investigate the daily car-following behavior of 54 drivers. A paired t-test and a Wilcoxon matched-pairs signed rank test were conducted to find the differences in behaviors on the two road types, and basic Poisson regression and Poisson hurdle regression models were used to explore significant risk factors. Results revealed that (1) drivers' longitudinal vehicle control, time control, and emergency behaviors are significantly different on urban surface roads and urban expressways; (2) for surface roads, three key influencing factors were ranked, in descending order, as the standard deviation of relative speed, percentage of time gap less than 1 s, and maximum acceleration; (3) for expressways, four key factors were ranked: minimum time gap, maximum deceleration, percentage of TTC less than 5 s, and the percentage of large positive jerk. The knowledge achieved on risky daily driving behaviors can be applied to training drivers to improve safe practices, assist insurance companies in creating usage-based insurance strategies, and support driver assistant systems design.

Assessing safety critical driving patterns of heavy passenger vehicle drivers using instrumented vehicle data - An unsupervised approach

Assessing the individual's driving profile and identifying the at-fault behaviors contributes to road safety, riding comfort, and driver assistance systems. This study proposes a framework to identify aggressive driving patterns in longitudinal control using real-time driving profiles of heavy passenger vehicle (HPV) drivers. The main objective is to detect and quantify the instantaneous driving decisions and classify the identified maneuvers (acceleration, braking) using unsupervised machine learning techniques without any prior-ground truth. To this end, total 8295 acceleration events, and 7151 braking events, were extracted from 142 driving profiles collected using high-resolution (10 Hz) GPS instrumentation. The principal component analysis was conducted on a multi-dimensional feature set, followed by a two-stage k-means clustering on the reduced feature subspace. The results showed that 86.5% of accelerations and 65.3% of braking maneuvers were characterized as non-aggressive, indicating safe or base-line driving behavior. However, 13.5% of accelerations and 34.7% of braking maneuvers were featured to be aggressive, indicative of the actual risky behaviors. Further analysis demonstrated the heterogeneity in drivers' trip-level frequency of aggressive maneuvers and highlighted the need for a continuous driving assessment. The study also revealed that the thresholds derived from the obtained clusters featuring the aggressive accelerations (+0.3 to +0.48 g) and aggressive braking (-0.42 to -0.27 g) maneuvers were beyond the acceptable limits of passenger safety and comfort. The insights from the study aids in developing driver assistance systems for personalized feedback provision and improve driver behavior.

Investigating the Effect of Social and Cultural Factors on Drivers in Malaysia: A Naturalistic Driving Study

Road accidents are increasing every year in Malaysia, and it is always challenging to collect reliable pre-crash data in the transportation community. Existing studies relied on simulators, police crash reports, questionnaires, and surveys to study Malaysia’s drivers’ behavior. Researchers previously criticized such methods for being biased and unreliable. To fill in the literature gap, this study presents the first naturalistic driving study in Malaysia. Thirty drivers were recruited to drive an instrumented vehicle for 750 km while collecting continuous driving data. The data acquisition system consists of various sensors such as OBDII, lidar, ultrasonic sensors, IMU, and GPS. Irrelevant data were filtered, and experts helped identify safety criteria regarding multiple driving metrics such as maximum acceptable speed limits, safe accelerations, safe decelerations, acceptable distances to vehicles ahead, and safe steering behavior. These thresholds were used to investigate the influence of social and cultural factors on driving in Malaysia. The findings show statistically significant differences between drivers based on gender, age, and cultural background. There are also significant differences in the results for those who drove on weekends rather than weekdays. The study presents several recommendations to various public and governmental sectors to help prevent future accidents and improve traffic safety.

Profiling drivers to assess safe and eco-driving behavior - A systematic review of naturalistic driving studies

Road accidents and vehicular emissions are two significant issues related to road transportation, affecting both human life and the environment. Prior research suggests that driver behavior is a crucial factor in the majority of road crashes and is a significant factor influencing fuel consumption and vehicle emission. Significant improvement in driving behavior can be achieved by providing feedback to drivers about their driving behavior. An increasing interest among researchers to identify risky and non-economical driving maneuvers has led to the development of driver behavior profiling, i.e., rating/categorizing drivers into different categories based on how they drive. To get an insight into different parameters and methodology adopted by researchers for categorizing drivers into different categories, this paper presents a systematic review of studies on driver behavior profiling. In the present paper, PRISMA approach was adopted to shortlist the most relevant studies for systematic review out of 1231 initial studies, which were extracted using the relevant keywords. The findings from our study suggest that the selection of parameters for profiling the driver will depend on the application of the profiling scheme, type of device used for extracting data, and importance of parameter in rating criteria. Further, the findings suggest that significant improvement in driving behavior can be achieved by providing feedback to the drivers about their driving behavior and by implementing usage-based insurance schemes. It is also suggested that future studies shall focus on using smartphone devices for the collection of driver data as smartphones are nowadays easily accessible to everyone.

Speeding through the pandemic: Perceptual and psychological factors associated with speeding during the COVID-19 stay-at-home period

During the COVID-19 stay-at-home period there were observed increases in both the percentage of cars engaged in extreme speeding, and the percentage of cars traveling below the speed limit. These changes have been attributed to unusually low traffic volume during the stay-at-home period. We develop a novel theoretical account, based on existing empirical research, of perceptual and psychological processes that may account for changes in speeding behavior under low traffic volume conditions. These include impaired ability to accurately perceive and control speed due to change in visual information, decreased salience of certain norms about socially appropriate speeds, lower perceived risk of speeding, and increased boredom leading to risk-taking behaviors. Further, we consider that individual attitude functions may account for the observed split in speeding behavior.

Drivers trust, acceptance, and takeover behaviors in fully automated vehicles: Effects of automated driving styles and driver's driving styles

Automated Vehicle (AV) technology has the potential to significantly improve driver safety. Unfortunately, drivers could be reluctant to ride with AVs due to their lack of trust and acceptance of AVs' driving styles. The present study investigated the effects of the designed driving style of AV (aggressive/defensive) and driver's driving style (aggressive/defensive) on driver's trust, acceptance, and take-over behavior in a fully AV. Thirty-two participants were classified into two groups based on their driving styles using the Aggressive Driving Scale and experienced twelve driving scenarios in either an aggressive AV or a defensive AV. Results revealed that driver's trust, acceptance, and takeover frequency were significantly influenced by the interaction effects between AV's driving style and driver's driving style. General estimating equations were conducted to analyze the relationships between driver's trust, acceptance, and take over frequency. The results showed that the effect of driver's trust in AVs on takeover frequency was mediated by driver's acceptance of AVs. These findings implied that driver's trust and acceptance of AVs could be enhanced when the designed AV's driving style aligned with driver's own driving style, which in turn, reduce undesired take over behavior. However, the "aggressive" AV driving style should be designed carefully considering driver safety.

A systematic review on sensor-based driver behaviour studies: coherent taxonomy, motivations, challenges, recommendations, substantial analysis and future directions

In the plan and development of Intelligent Transportation Systems (ITS), understanding drivers behaviour is considered highly valuable. Reckless driving, incompetent preventive measures, and the reliance on slow and incompetent assistance systems are attributed to the increasing rates of traffic accidents. This survey aims to review and scrutinize the literature related to sensor-based driver behaviour domain and to answer questions that are not covered so far by existing reviews. It covers the factors that are required in improving the understanding of various appropriate characteristics of this domain and outlines the common incentives, open confrontations, and imminent commendations from former researchers. Systematic scanning of the literature, from January 2014 to December 2020, mainly from four main databases, namely, IEEEXplore, ScienceDirect, Scopus and Web of Science to locate highly credible peer-reviewed articles. Amongst the 5,962 articles found, a total of 83 articles are selected based on the author's predefined inclusion and exclusion criteria. Then, a taxonomy of existing literature is presented to recognize the various aspects of this relevant research area. Common issues, motivations, and recommendations of previous studies are identified and discussed. Moreover, substantial analysis is performed to identify gaps and weaknesses in current literature and guide future researchers into planning their experiments appropriately. Finally, future directions are provided for researchers interested in driver profiling and recognition. This survey is expected to aid in emphasizing existing research prospects and create further research directions in the near future.

Decision-adjusted driver risk predictive models using kinematics information

Accurate prediction of driving risk is challenging due to the rarity of crashes and individual driver heterogeneity. One promising direction of tackling this challenge is to take advantage of telematics data, increasingly available from connected vehicle technology, to obtain dense risk predictors. In this work, we propose a decision-adjusted framework to develop optimal driver risk prediction models using telematics-based driving behavior information. We apply the proposed framework to identify the optimal threshold values for elevated longitudinal acceleration (ACC), deceleration (DEC), lateral acceleration (LAT), and other model parameters for predicting driver risk. The Second Strategic Highway Research Program (SHRP 2) naturalistic driving data were used with the decision rule of identifying the top 1% to 20% of the riskiest drivers. The results show that the decision-adjusted model improves prediction precision by 6.3% to 26.1% compared to a baseline model using non-telematics predictors. The proposed model is superior to models based on a receiver operating characteristic curve criterion, with 5.3% and 31.8% improvement in prediction precision. The results confirm that the optimal thresholds for ACC, DEC and LAT are sensitive to the decision rules, especially when predicting a small percentage of high-risk drivers. This study demonstrates the value of kinematic driving behavior in crash risk prediction and the necessity for a systematic approach for extracting prediction features. The proposed method can benefit broad applications, including fleet safety management, use-based insurance, driver behavior intervention, as well as connected-vehicle safety technology development.

Using machine learning techniques to characterize sleep-deprived driving behavior

OBJECTIVE

Sleep deprivation is known to affect driving behavior and may lead to serious car accidents similar to the effects from e.g., alcohol. In a previous study, we have demonstrated that the use of machine learning techniques allows adequate characterization of abnormal driving behavior after alprazolam and/or alcohol intake. In the present study, we extend this approach to sleep deprivation and test the model for characterization of new interventions. We aimed to classify abnormal driving behavior after sleep deprivation, and, by using a machine learning model, we tested if this model could also pick up abnormal driving behavior resulting from other interventions.

METHODS

Data were collected during a previous study, in which 24 subjects were tested after being sleep-deprived and after a well-rested night. Features were calculated from several driving parameters, such as the lateral position, speed of the car, and steering speed. In the present study, we used a gradient boosting model to classify sleep deprivation. The model was validated using a 5-fold cross validation technique. Next, probability scores were used to identify the overlap of driving behavior after sleep deprivation and driving behavior affected by other interventions. In the current study alprazolam, alcohol, and placebo are used to test/validate the approach.

RESULTS

The sleep deprivation model detected abnormal driving behavior in the simulator with an accuracy of 77 ± 9%. Abnormal driving behavior after alprazolam, and to a lesser extent also after alcohol intake, showed remarkably similar characteristics to sleep deprivation. The average probability score for alprazolam and alcohol measurements was 0.79, for alcohol 0.63, and for placebo only 0.27 and 0.30, matching the expected relative drowsiness.

CONCLUSION

We developed a model detecting abnormal driving induced by sleep deprivation. The model shows the similarities in driving characteristics between sleep deprivation and other interventions, i.e., alcohol and alprazolam. Consequently, our model for sleep deprivation may serve as a next reference point for a driving test battery of newly developed drugs.