The i-DREAMS project focuses on establishing a framework known as the ‘Safety Tolerance Zone (STZ)’ to ensure drivers operate within safe boundaries. This study compares Long-Short-Term-Memory Networks and shallow Neural Networks to assess participants’ safety levels during i-DREAMS on-road trials. Thirty German drivers’ trips and Forty-Three Belgian drivers were analyzed using these methods, revealing factors contributing to risky behavior. Results indicate i-DREAMS interventions significantly enhance driving behavior, with Neural Networks displaying superior performance among the algorithms considered.

@en

Naturalistic driving studies (NDS) have recently gained attention as a way of instrumenting vehicles in an unobtrusive way and collecting driving data over long periods of time. Aiming at eventually modeling driving behavior, NDS are often a part of larger scale studies. These studies involve several stakeholders who are responsible for different components of the data collection and analysis, and thus are inevitably confronted with challenges in the data management pipeline. The aim of this paper is to develop standard protocols that could be used as guidelines for data handling in the context of NDS. In the development of these protocols, we first review data handling strategies used in previous studies, focusing on data collection, preparation, storage, as well as ethical and legal considerations. This review helps us draw lessons, based on which methods are developed to answer the gaps and challenges arising from handling NDS data. We then introduce a case study, the i–DREAMS project, to show the applicability of the data handling framework. Finally, we showcase standard protocols for data handling, that could serve as data handling guidelines for future studies.@en

Sleepiness is a common human factor among truck drivers resulting from sleep loss or time of day and causing impairment in vigilance, attention, and driving performance. While driver sleepiness may be associated with increased risk on the road, sleepy drivers may drive more cautiously as a result of risk-compensating behaviour. This endogeneity has been overlooked in the previous driver behaviour studies and may provide new insight into the effects of sleepiness on driving performance. In addition, the Karolinska Sleepiness Scale (KSS) has been widely used to quantify sleepiness. However, the KSS is a subjective self-reported measure and is reliant on honest reporting and understanding of the scale. An alternative way of quantifying sleepiness is using drivers’ heart rate and correlating it with their sleepiness. While recent advances in data collection technologies have made it possible to collect heart rate data in real-time and in an unobtrusive way, their application in measuring sleepiness particularly among truck drivers has been unexplored.

This study aims to address these gaps and contribute to analytic methods in road safety research by collecting truck drivers’ heart rate data in real-time, measuring sleepiness from those data, and using it in an instrumental variable modelling framework to investigate its effect on driving performance. To this end, a driving simulator experiment was conducted in Belgium and heart rate data were collected for 35 truck drivers via sensors installed on the steering wheel of the simulator. Additional demographic data were collected using a questionnaire before the experiment. An instrumental variable model consisting of a discrete binary logit and a continuous generalized linear model with grouped random parameters and heterogeneity in their means was then developed to study the effects of driver sleepiness on headway. Results indicate that age, years of holding driver licence, road type, type of truck transport, and weekly distance travelled are significantly associated with sleepiness among the participants of this study. Sleepy driving is associated with reduced headway for 30.5% of the drivers and increased headway for the other 69.5%, and night-time shift is associated with such varied effects. These findings indicate that there may be group- or context-specific risk patterns which cannot be explicitly addressed by hours of service regulations and therefore, transport operators, driver trainers and fleet managers should identify and handle such context-specific high risk patterns in order to ensure safe operations.@en

Editorial@en

“Everything somewhere” or “something everywhere” is the classic dilemma concerning the development and implementation of the future generation of vehicles, i.e., automated vehicles (AVs). Both strategies include diverse policy options that could significantly impact road networks’ planning, design, operation, and utilization. Until now, no significant research has been conducted concerning their implications. In this paper, we aim to examine how ready the current physical infrastructure is by identifying the requirements of each strategy and then applying them in a com-mon type of intersection. The study’s findings demonstrate that AVs’ performance can be affected by policy implementation decisions and adds further weight to the argument of AVs separation or no-separation from no-AVs traffic. Furthermore, the insignificant improvements in traffic performance imply the low readiness of the current road networks in urban areas to accommodate the new technology. This study contributes to determining that research on the readiness of the road infrastructure and the deployment of AVs in urban areas is inevitable. It also identifies that roads’ geometric design can dramatically affect AVs’ operation and the difficulties of implementing dedi-cated lanes in urban areas due to space availability.

@en

Driver sleepiness and fatigue are important contributors to many transport incidents and significantly increase crash risk. Recently, detection systems have been developed which aim to monitor the state of the driver and detect increasing levels of fatigue. However, there has been less focus on appropriate intervention strategies for drivers once fatigue and sleepiness have been detected. This paper describes the i-DREAMS fatigue intervention strategies, which aim to keep drivers within a safe driving zone. Interventions will be provided both in real-time and post-trip and can be customized to be used with a variety of transport modes. Real-time interventions will measure fatigue through trip duration, and driver sleepiness through heart-rate variability (HRV) information, obtained by means of sensors in the steering wheel or a wearable device, and attributed to Karolinska Sleepiness Score (KSS) bands. Thresholds for warnings will map onto phases of a ‘Safety Tolerance Zone’ and will be dynamic – changing as the driver state and driving situation develops. Post-trip interventions will aggregate data throughout the duration of the drive and aim to provide customized feedback and coping tips related to driver levels of fatigue and sleepiness, to improve driving behavior. Goals and challenges will add a gamified aspect to the post-trip interventions. The next stage of the development of the i-DREAMS fatigue intervention strategy is to test the concept in a series of simulator and field trials. Future research should explore acceptance and compliance of interventions and frequency of alerts.@en

Automated vehicles (AVs) promise to improve road safety, reduce traffic congestion and emissions, and enhance mobility. However, evidence regarding their safety benefits has not been systematically investigated and documented. In this study, we utilise a scoping review approach to investigate and synthesise the existing literature on higher levels of AVs’ safety implications. This aids future relevant studies by identifying the research gaps and reporting the methodological approaches used. The review focused not only on peer-reviewed articles but also on grey literature to provide a comprehensive overview of the current research state. In total, 5724 articles were identified, and 4167 records were screened after duplicates and dual publications removal, from which 27 were found eligible for review. Ultimately, 24 studies met all the inclusion criteria and were considered for the review. The reported evidence was focused on changes in road safety levels after the deployment of AVs in transport networks. The data was extracted and charted by one reviewer using tables to create a descriptive summary of the results and address the scoping review's questions and objectives. In general, the findings suggest that AVs hold the potential to improve the overall safety on roads, although the existing evidence is not mainly based on real data but assumptions regarding vehicles’ capabilities and behaviour. The limited number of studies and the fact that all of them were published or conducted after 2014 indicate that the research on AVs’ safety impacts is just emerging.

@en

Professionals from various disciplines have been investing huge efforts in the last few decades in the development and deployment of connected and automated vehicles (CAVs). It is believed that CAVs can mitigate the main drawbacks of transport issues such as safety, emissions, and congestion. The main objective of this paper is to examine how intersection control types will affect the operation of automated vehicles (AVs) in urban areas. Since AVs implementation is still in its first steps and empirical data is not yet available, the microscopic traffic flow simulation software PTV Vissim was utilized. Different case studies based on commonly occurring intersection types were investigated in PTV Vissim under various AVs penetration rates. The results show that the introduction of AVs had a greater effect in the performance of uncontrolled intersections. Further research is required on the impact of AVs on safety and their interactions with vulnerable road users.

@en

Automated vehicles (AVs) are expected to assist in decreasing road traffic fatalities, particularly among passenger cars. However, until now limited research has been conducted on how they will impact the safety of vulnerable road users (VRUs) (i.e., cyclists and pedestrians). Therefore, there is a clear need to start taking into account the interactions between AVs and VRUs as an integrated element of the transport network, especially in urban areas where they are dominant. The objective of this study is to verify whether the anticipated implementation of AVs can actually improve cyclists’ safety. For this purpose, the microscopic traffic flow simulation software PTV Vissim combined with the surrogate safety assessment model (SSAM) were utilized. The road network used for this analysis was generated based on a real study case in a medium-sized city in Belgium, where narrow streets in the city center are shared on many occasions between vehicles and cyclists. The findings of the analysis show a notable reduction in the total number of conflicts between cars, but also between cars and cyclists, compared to the current situation, assuming a 100% market penetration scenario for AVs. Moreover, the severity level of conflicts also decreased as a result of the lack of human-driven vehicles in the traffic streams. @en