Driver behavior is an important contributing factor in road crashes. It is influenced by various factors. Cultural orientations, such as individualism and collectivism, shape attitudes toward traffic rules and drivers' risk-taking behaviors. However, their interaction with perceived driving skills and national context has received limited attention. The present study examined how individualism-collectivism relates to driver behavior and whether these relationships are moderated by driving skills across two national contexts. Participants completed the questionnaires assessing cultural orientations, driving skills, and driver behaviors. A total of 527 drivers from Türkiye (Mage = 33.36, SD = 9.61; 44.2% female) and 326 drivers from Belgium (Mage = 29.35, SD = 12.29; 47.5% female) participated in the study. Moderated moderation analyses were conducted to examine the interactions between cultural orientations, driving skills, and country on driver behaviors. The findings showed that individualism was positively associated with driving violations in both countries. However, this relationship varied depending on perceptual-motor skills and country. In Türkiye, individualism was positively associated with violations across all levels of perceptual-motor skills. In Belgium, individualism predicted violations only among drivers who perceived their perceptual-motor skills as higher. In addition, collectivism was associated with fewer violations only among Belgian drivers with high perceptual-motor skills. There were no significant interaction effects for errors or positive driver behaviors. Overall, the findings show the importance of considering cultural orientations and driving skills together when examining driving behavior across different traffic contexts.

Research on autism and driving expanded about a decade ago, initially focusing on the risks and challenges autistic drivers face compared to non-autistic drivers. Today, researchers recognize the importance of considering both the strengths and limitations of autistic drivers, leading to a more balanced perspective and improved insights for inclusive driver education. Driving often involves frustrating events, which can lead to aggressive driving behavior and impact road safety. Little attention has been given to the impact of frustrating driving events on autistic individuals, although their driving could be impacted by emotion regulation issues (i.e., aggression or anxiety). Alternatively, compared to non-autistic individuals, they can display safer driving behavior due to rule adherence. This study aims to compare the responses of autistic and non-autistic participants when subjected to a series of frustrating simulated driving events. Behavioral (i.e., driving parameters) and physiological measures are complemented by self-reports to allow insights into underlying mechanisms of driver responses. A total of 60 male participants, mostly pre-drivers, took part in this study, 23 autistic and 37 non-autistic individuals. Findings revealed that autistic participants’ driving behavior was impacted by the frustrating events, as indicated in an increased maximum deceleration. However, they also displayed safer driving behaviors, as indicated by a higher mean following distance. Taking all driving measures and known safety cut-off values into account, the impact on traffic safety was comparable between both groups. However, autistic participants experienced higher electrodermal activity (EDA) than their non-autistic counterparts during the simulated frustrating driving events. The results together suggest that while autistic participants can cope with frustrating driving situations, they likely experience higher levels of stress. The current study provides important insights for inclusive driver education programs, which could focus on the best ways to deal with frustrating driving events. However, future studies including more licensed drivers and more challenging circumstances are warranted.

Road traffic crashes remain a major global public health and economic challenge, with heavy vehicle drivers disproportionately involved in severe incidents, particularly in low- and middle-income countries. In Ethiopia, limited access to continuous professional training constrains efforts to improve drivers’ safety-related knowledge and awareness. This study explored the impact potential and user acceptance of gamified e-learning modules designed to enhance heavy vehicle drivers’ knowledge and awareness of fatigue management, speed-related behavior, and eco-driving practices. A randomized pretest–post-test control-group design was employed, in which professional drivers were assigned to either an intervention group that completed three gamified e-learning modules or a control group that received no training. Data were analyzed using mixed repeated-measures analysis of variance. The results revealed significant time × group interaction effects across all domains (p < 0.001), with substantially greater improvements in the intervention group and large effect sizes. Participants also reported high perceived usefulness, behavioral intention, and trust in the system. These findings provide preliminary evidence that gamified e-learning may be a feasible and promising approach for improving short-term safety-related knowledge among professional heavy vehicle drivers. Further research is needed to determine whether these improvements are sustained over time and translate into behavioral change and measurable road safety outcomes before broader implementation can be recommended.

Pedestrians are amongst the most vulnerable road user groups. Efforts to enhance pedestrian safety have mainly focused on intersections and midblock crossings. This study investigated the effect of bus stop environments on pedestrian safety in Kumasi, an area with a high incidence of pedestrian fatalities in Ghana. Crashes within a 50 m radius of bus stops were extracted using a spatial join. The Negative Binomial regression model was applied to model pedestrian crashes around bus stops as a function of three distinct non-collinear independent variable groups: road design features, bus stop characteristics, and pedestrian exposure measures. Formal bus stops were associated with higher crash rates than informal ones. The presence of medians and crosswalks was associated with lower crash rates, whereas wider carriageways were associated with higher crash rates. Higher crashes were linked to passing pedestrians and waiting pedestrians, while crossing pedestrians were associated with reduced crashes. These findings suggest that the combined effects of infrastructure and behavioural factors influence pedestrian safety at bus stops. Prioritising low-cost safety treatments, such as guard-railed waiting areas, marked crosswalks, medians, and raised crossings, around bus stops will yield substantial safety benefits for resource-constrained contexts and advance sustainable urban mobility.

This study examines crash involvement, safety training exposure, and e-learning readiness among commercial heavy goods vehicle (HGV) drivers in Ethiopia. Data were collected through a cross-sectional survey of 202 male drivers operating along the Addis Ababa–Djibouti trade corridor, a high-risk freight route that carries approximately 95% of Ethiopia’s international trade and serves as the country’s primary gateway to global markets. The survey assessed crash history, safety training experiences, perceived safety challenges, and barriers to and motivators for e-learning adoption. Results indicate persistently high crash involvement despite widespread participation in conventional classroom-based training, suggesting a gap between training provision and real-world safety outcomes. Older and mid-career drivers exhibited higher crash involvement, highlighting a gap between training provision and behavioral or operational safety outcomes, while younger and more educated drivers showed greater readiness for technology-enhanced training. Although most drivers valued safety training, many perceived existing programs as repetitive, insufficiently interactive, and poorly aligned with operational demands. Key facilitators for e-learning adoption included flexible schedules, ease of use, and motivational support, whereas limited digital skills and low perceived usefulness remained barriers for some groups. The findings highlight the need for age-responsive, flexible, and interactive e-learning approaches to complement traditional training and address persistent safety risks, such as fatigue and unsafe driving behaviors. These approaches also support scalable, technology-enhanced interventions tailored to Ethiopia’s high-risk freight corridors, while guiding future research directions.

BACKGROUND AND AIM:Bilateral vestibulopathy (BV) is a rare disorder characterized by loss of vestibular function, leading to unsteadiness and blurred vision during head movements, particularly in visually challenging settings such as driving. Although difficulties with driving have been suggested in BV patients, this pilot study aims to further explore and quantify self-reported driving ability and behavior in this population using both generic and disease-specific questionnaires. METHODS:Twenty adults with confirmed BV (mean age 61.6 years) were recruited from a tertiary center. Participants completed a novel disease-specific questionnaire, developed collaboratively by ENT specialists and driving research experts to identify traffic situations that are particularly challenging for patients with BV. In addition, they completed the Driver Behavior Questionnaire (DBQ) and the Multidimensional Driving Style Inventory (MDSI). Participants also rated their driving competence and reported on crash involvement and traffic violations. RESULTS:Most patients reported little difficulty while driving in familiar daytime environments but experienced challenges during night driving, in poor weather conditions, on uneven roads, and while multitasking. Ordinary violations were the most common maladaptive behaviors per the DBQ, though errors and lapses were rare. The MDSI showed patient and careful driving styles predominated, with anxious and distress-reduction styles reported by a minority. Only one patient attributed a traffic accident to BV, and few reported recent violations. CONCLUSION:BV patients mostly adopt safe, adaptive driving behaviors, a pattern also commonly observed among older drivers. However, specific situations requiring stable gaze and spatial orientation pose particular challenges for individuals with BV. Findings are limited by self-reporting and small sample size. Future research using objective driving assessments and control groups is needed to inform evidence-based guidelines for counseling BV patients about driving.

The i-DREAMS project set up a platform and system that provides real-time and post-trip interventions (including gamification elements) to keep drivers within safe margins. While the effectiveness of interventions has been widely studied, limited research has explored their interaction. Specifically, it remains unclear how engagement with post-trip interventions influences adherence to real-time interventions and how such engagement and adherence impact individual driving risk. Moreover, the factors contributing to variation in intervention engagement and adherence across drivers remain underexplored. In addition, most existing evaluations of intervention effectiveness have been conducted within a single-country context, with a limited focus on cross-national differences, which are crucial for understanding variation in intervention performance across different national contexts. This study aims to assess the impact of real-time and post-trip interventions on drivers' individual driving risk across European countries, examine cross-national differences, and explore their underlying causes. The results show that the i-DREAMS interventions significantly reduced traffic offense risk and kinematic driving risk, although cross-national differences were observed between Belgium and the UK. The real-time interventions significantly reduced kinematic driving risk among UK drivers, whereas gamified post-trip interventions were more effective for Belgian drivers. Additionally, the real-time interventions effectively reduced traffic offense risk in both countries. A strong negative association was found between adherence to real-time interventions and traffic offense risk, and engagement with post-trip interventions was negatively associated with kinematic driving risk. Gamification elements enhanced engagement with post-trip interventions. The insights gained from this study help enhance the customization of i-DREAMS interventions and application strategies.

Motorcyclists are one of the most vulnerable road user groups, with crash rates and fatalities consistently exceeding those of other vehicle users. This study investigates the behavioral and perceptual factors influencing motorcycle crashes, near-crashes, and traffic fines in Croatia using an extended version of the Motorcycle Rider Behavior Questionnaire (MRBQ). The survey, conducted among 842 Croatian motorcyclists, explored risky behaviors, protective practices, and perceptions of road infrastructure. Principal Component Analysis (PCA) identified a five-factor structure of rider behavior: Violations, Errors, Stunts, Personal Protective Equipment (PPE), and Intoxication. Errors emerged as the strongest predictor of crash and near-crash involvement, while violations and stunts significantly predicted traffic fines. Analyses revealed that younger riders exhibited higher rates of risky behaviors, including speeding and stunts. In comparison, older riders and those with children demonstrated safer riding patterns and greater PPE use. Riders' perceptions of road infrastructure, particularly inadequate road markings and surface conditions, also highlighted safety concerns. The findings emphasize the need for targeted interventions: advanced rider training focusing on control errors, strict enforcement against violations and substance use, infrastructure improvements, and incentive programs for PPE adoption. Addressing these factors through evidence-based strategies can reduce motorcyclist crash risks and promote safer riding behaviors.

Driver-related factors, such as driving style and traffic offenses, are key contributors to road crashes, with driving risk varying substantially among individuals. Accurate assessment of individual driving risk and identification of high-risk driver characteristics are essential to reducing road crashes. Despite numerous studies on driving risk assessment, most rely solely on the frequency of single-threshold events, making them insufficiently comprehensive. Moreover, these studies neglect the repetitive nature of driving scenarios and differences in exposure, leading to imprecise assessments when using distance traveled as a measure of exposure. To address these shortcomings, we collected 18 weeks of naturalistic driving data from 100 participants (50 from the UK, 50 from Belgium) and developed a framework for assessing individual driving risk, consisting of three parts: (1) identification of risky driving scenarios, (2) assessment of individual driving risks, and (3) analysis of group risk differences to identify high-risk driver characteristics. Risky driving scenarios were characterized by critical events with high risk propensity and high heterogeneity among individual driving risks. Driving scenario indicators were developed that measure risk propensity and heterogeneity, enabling risk assessments based on the probability of critical events occurring in such scenarios. Individual driving risk was measured by the weighted probability of multi-threshold events (WPMTE) in risky driving scenarios and adjusted for differences in driving exposure. WPMTE provides a comprehensive and precise assessment of individual driving risks, aiding in the identification of high-risk drivers. Finally, statistical tests revealed significantly higher risks for young drivers (19-30) compared to middle-aged (46-60) and elderly drivers (61-79), as well as higher risks for Belgian drivers compared to UK drivers. These findings inform the development of tailored safety education and proactive interventions, promoting safer driving behaviors and reducing crash rates.

While mobility and safety of drivers are challenged by behavioral changes, the increasingly complex road environment has placed a higher demand on their adaptability. The ultimate goal of this paper was to identify the impact that the balance between task complexity and coping capacity had on crash risk. Towards that aim, an integrated model for understanding the effect of the interrelationship of task complexity and coping capacity with risk was developed. A vast library of data from a naturalistic driving experiment was created in three countries (i.e., Belgium, UK and Germany) to investigate the most prominent driving behavior indicators available, including speeding, headway, overtaking, duration, distance and harsh events. In order to fulfil the aforementioned objectives, exploratory analysis, such as Generalized Linear Models (GLMs) were developed, and the most appropriate variables associated to the latent variable "task complexity" and "coping capacity" were estimated from the various indicators. Additionally, Structural Equation Models (SEMs) were used to explore how the model variables were inter-related, allowing for both direct and indirect relationships to be modelled. The analyses revealed that higher task complexity levels lead to higher coping capacity by drivers. Additionally, the effect of task complexity on risk was greater than the impact of coping capacity in Belgium and Germany, while mixed results were observed in the UK.

Road safety progress has stalled in many high-income countries, prompting interest in the use of Advanced Driver Assistance Systems (ADAS) as a potential solution. However, limited evidence exists on real-world, long-term and cross-country impacts of ADAS. This study addresses these gaps through a naturalistic field trial in Belgium and Vietnam, focusing on driver behaviour across three driving-task specific domains: road sharing, speed management, and vehicle control. Eighteen Belgian drivers and fourteen Vietnamese drivers participated in a three-stage field driving experiment: baseline (no ADAS for three weeks), treatment (ADAS active for six weeks), and post-treatment (ADAS deactivated for three weeks). Risky driving behaviour events were collected, normalised per 100km and analysed separately for the two countries using a within-subject design. The findings suggest that the activation of ADAS results in safer driving behaviours, although the outcomes varied between countries and types of behaviour. Once ADAS was deactivated, many drivers reverted to their previous habits, lending support to the washout effect hypothesis. The study shows the importance of promoting the sustained use of ADAS and the need to tailor system designs to accommodate different cultural and traffic contexts.

The i-DREAMS project introduced the concept of a 'Safety Tolerance Zone,' i.e., a context-aware safety envelope designed to assist drivers. Using an ecosystem of sensors, i-DREAMS technology monitors factors that determine driving task complexity and coping capacity and calculates risk levels. Real-time and post-trip interventions are tailored to keep drivers from unsafe driving. Realtime interventions are provided via in-vehicle display, while post-trip interventions are delivered via a smartphone app with gamification provisions. This study focuses on the effectiveness (i.e., outcome evaluation) of real-time and post-trip interventions that involve 4 phases, including the baseline measurement phase. The paper presents a comparative analysis using the data collected from car drivers from three countries: Belgium (n = 48), the UK (n = 49), and Germany (n = 25). Overall, drivers showed a reduction in events per 100 km after exposure to the i-DREAMS technology. So, there was an improved safety outcome. However, differences were found between the countries analyzed. The highest number of events per 100 km was noted for UK drivers, with the reduction pattern consistent across 4 phases. The interventions were more promising for 'road sharing' and 'speeding' events for Belgian and German drivers. Driver-level analysis revealed that two-thirds of drivers in each country showed a consistent decrease in events/100 km.

The integration of Artificial Intelligence (AI) into Advanced Driver Assistance Systems (ADAS) is transforming vehicle safety and autonomy, improving real-time decision making for safe and efficient driving. Several previous works have surveyed the use of AI in ADAS and the service-based view of the system. However, no works have surveyed the combined subject of AI-powered, service-based ADAS (AiSDAS). We aim to bridge this gap by systematically surveying AiSDAS. Within the scope of this work, we present a preliminary systematic literature review of the subject. Through the lens of microservice architecture, we explore how AI-driven services enable scalable and flexible ADAS implementations by leveraging advanced AI techniques, such as machine learning and deep learning. Our survey discovers both functional and non-functional requirements of AiSDAS, the frequently cited technical sub-features of each type of requirement, and several research directions that would benefit researchers interested in the subject.

Motorcyclists represent a vulnerable group of road users, often exhibiting elevated crash severity risk due to speeding and limited physical protection. This study explores speeding behavior among motorcyclists using smartphone-based naturalistic data, a relatively novel approach in motorcycle safety research. The aim of the study was to examine which factors influence rider speeding behavior. A total of 1,853 trips (36,169.3 km) from 19 participants were recorded via a phone application capable of detecting speeding and other riding dynamics in real-world traffic conditions. Linear regression was applied to investigate the effect of several potential predictors, including road type, average speed, speed over the limit, indicators of aggressive maneuvers (acceleration, braking), and contextual variables (daytime, weekend). The model explained 72% of the variance in speeding behavior, with the percentage of trip duration spent speeding as a dependent variable. Key predictors included the average speed over the limit, which was strongly positively associated with the observed outcome, and the proportion of motorway driving, displaying a negative association. Harsh accelerations also had a significant positive effect, while factors such as daylight and weekends did not yield significant effects. Findings highlight the potential of smartphone-based data collection for monitoring speeding in naturalistic settings. While several limitations were acknowledged, this study offers a valuable starting point for broader applications of mobile sensing in road safety, with potential implications for tailored feedback, rider coaching, and intelligent transport systems.

This paper aims to provide a detailed overview of driving behaviour indicators during the implementation of the H2020 project i-DREAMS interventions in Greece. To fulfil this aim, a robust methodology utilizing a k-means clustering approach was employed to detect meaningful driving behaviour patterns within a dataset comprising 11,731 trips from 56 Greek car drivers. This exploratory analysis was complemented by an unsupervised pattern recognition algorithm, which aimed at identifying clusters based on safe or dangerous driving behaviour of the users. The assessment of driving behaviour encompassed indicators such as speeding events, harsh braking and accelerating events, and distraction events (phone in hand). This analysis provides valuable insights into the risky driving behaviour among the i-DREAMS naturalistic driving experiment Phases in Greece.

Lane change events are a critical focus for road safety research. Detecting the lane-changing or cut-in behavior of surrounding vehicles using dashcam video has significant potential for supporting driver behavior monitoring and timely interventions during such events. However, as this field has not yet been systematically reviewed in a dedicated literature survey, researchers often face the challenge of manually filtering through many studies with overlapping keywords to identify relevant work. To address this gap, after investing significant efforts to seek the target studies of this specific domain, this paper presents a detailed review of each recent novel study from 2019. These existing approaches were also innovatively categorized into two main directions: direct model inference and logical inference based on lane marking. Each category is analyzed to highlight the shared characteristics and key differences, offering researchers a clearer understanding of the field’s current landscape. Based on the analysis, several shared limitations specific to each direction were identified, and some open challenges that need to be solved by future research were proposed from both practical application and road safety perspectives. These include the heavy reliance on manually annotated data during preprocessing, the prevalent focus on evaluating algorithms only on event-specific video clips, and the lack of connection from detection methods to road safety research, among others. Addressing these issues is critical for advancing this field and strengthening its connection with real-world safety considerations.

The i-DREAMS project introduced the concept of a 'Safety Tolerance Zone', i.e., a context-aware safety envelope designed to assist drivers in maintaining self-regulated control within the boundaries of safe operations. Using an ecosystem of sensors, i-DREAMS technology continuously monitors factors determining driving task complexity and available coping capacity and calculates risk levels in real-time. Based on this information, both real-time and post-trip interventions are tailored to keep drivers from getting too close to the boundaries of unsafe driving. Real-time interventions are provided via in-vehicle display, while post-trip interventions are delivered via a smartphone app (and web-dashboard) with provisions for gamification. This study focuses on post-trip interventions, specifically user engagement with the i-DREAMS app. Data from 49 Belgian and 51 UK car drivers over a 10-week period showed a steady decline in drivers' engagement following the first day of app activation. However, when gamification features were activated, user interaction increased, suggesting they re-engaged users. UK drivers exhibited higher engagement than Belgians. Trips, scores and goals were the most visited features in both countries, while the leaderboard was popular among UK drivers only. Analysis showed a dose-response relationship, with intensive app users demonstrating better improvement in driving performance than less frequent users.

Along with the sharp increase in motorcycles over the past two decades, traffic crashes with small-displacement motorcycles have become a significant health concern in Vietnam. This study aimed to define practical safety countermeasures for enhancing road traffic safety for motorcycle users (both motorcycle riders and pillion passengers) in Vietnam. To that purpose, a qualitative study design was implemented, including a series of focus group discussions and in-depth interviews based on a semi-structured format with stakeholders involved in motorcyclist safety. The participants of the focus group discussions include motorcycle riders, automobile drivers, bicycle/e-bike riders, motorcycle trainers, and policymakers to define countermeasures to enhance traffic safety for motorcycle riders from the viewpoints of different road user groups and the local authorities. Besides, in-depth interviews were conducted with traffic police officers to define the essential and urgent solutions for reducing traffic crashes related to motorcyclists. The solutions for the leading risky behaviors of motorcyclists include tactical and operational strategies for motorcycle riders. Countermeasures for regulators and authorities to reduce the leading risky behaviors include engineering interventions, enforcement solutions, and education and training countermeasures. Strategies to avoid collisions when motorcyclists ride in pairs or groups include strategies for attitude change of motorcycle riders when riding, the behaviors motorcyclists should have when riding in pairs or in groups, and the appropriate riding skills for motorcyclists while riding in pairs or groups. Innovative strategies for enhancing motorcycle rider safety include strategies for motorcycle users and strategies for regulators and authorities. Providing hazard avoidance training for motorcyclists is the most significant and urgent solution that participants suggested for Vietnamese regulators and authorities in enhancing motorcycle users' safety. These findings imply that the riding training programs for motorcycle riders need to be adjusted and updated by traffic safety authorities, primarily focusing on hazard avoidance training to improve traffic safety for road users in general and motorcycle riders in particular.