Illumination Intelligent Adaptation and Analysis Framework: A comprehensive solution for enhancing nighttime driving fatigue monitoring.

Nighttime driving presents a critical challenge to road safety due to insufficient lighting and increased risk of driver fatigue. Existing methods for monitoring driver fatigue, mainly focusing on behavioral analysis and biometric monitoring, face significant challenges under low-light conditions. Their effectiveness, especially in dynamic lighting environments, is limited by their dependency on specific environmental conditions and active driver participation, leading to reduced accuracy and practicality in real-world scenarios. This study introduces a novel 'Illumination Intelligent Adaptation and Analysis Framework (IIAAF)', aimed at addressing these limitations and enhancing the accuracy and practicality of driver fatigue monitoring under nighttime low-light conditions. The IIAAF framework employs a multidimensional technology integration, including comprehensive body posture analysis and facial fatigue feature detection, per-pixel dynamic illumination adjustment technology, and a light variation feature learning system based on Convolutional Neural Networks (CNN) and time-series analysis. Through this integrated approach, the framework is capable of accurately capturing subtle fatigue signals in nighttime driving environments and adapting in real-time to rapid changes in lighting conditions. Experimental results on two independent datasets indicate that the IIAAF framework significantly improves the accuracy of fatigue detection under nighttime low-light conditions. This breakthrough not only enhances the effectiveness of driving assistance systems but also provides reliable scientific support for reducing the risk of accidents caused by fatigued driving. These research findings have significant theoretical and practical implications for advancing intelligent driving assistance technology and improving nighttime road safety.

Traffic jam by GPS: A systematic analysis of the negative social externalities of large-scale navigation technologies.

The increased usage of navigation technologies has caused conflicts in local traffic management, resulting in congested residential areas among other challenges for residents. This paper uses content analysis to investigate such negative social externalities within local communities and neighbourhoods. Through a corpus of 90 news articles about traffic incidents caused by navigation technologies, we identified negative traffic and safety-related externalities, including congestion, damage, pollution, and accidents. We also report on countermeasures by local communities and governments, including street closures, speed limit reduction, and turn bans. Based on our results, we discuss the implications for designing mobile navigation technologies that reduce negative social externalities.

Personalizing driver safety interfaces via driver cognitive factors inference.

Recent advances in AI and intelligent vehicle technology hold the promise of revolutionizing mobility and transportation through advanced driver assistance systems (ADAS). Certain cognitive factors, such as impulsivity and inhibitory control have been shown to relate to risky driving behavior and on-road risk-taking. However, existing systems fail to leverage such factors in assistive driving technologies adequately. Varying the levels of these cognitive factors could influence the effectiveness and acceptance of ADAS interfaces. We demonstrate an approach for personalizing driver interaction via driver safety interfaces that are are triggered based on the inference of the driver's latent cognitive states from their driving behavior. To accomplish this, we adopt a data-driven approach and train a recurrent neural network to infer impulsivity and inhibitory control from recent driving behavior. The network is trained on a population of human drivers to infer impulsivity and inhibitory control from recent driving behavior. Using data collected from a high-fidelity vehicle motion simulator experiment, we demonstrate the ability to deduce these factors from driver behavior. We then use these inferred factors to determine instantly whether or not to engage a driver safety interface. This approach was evaluated using leave-one-out cross validation using actual human data. Our evaluations reveal that our personalized driver safety interface that captures the cognitive profile of the driver is more effective in influencing driver behavior in yellow light zones by reducing their inclination to run through them.

Enhancing Driving Safety through User Experience Evaluation of the C-ITS Mobile Application: A Case Study of the DARS Traffic Plus App in a Driving Simulator Environment.

The paper evaluates the DARS Traffic Plus mobile application within a realistic driving simulator environment to assess its impact on driving safety and user experience, particularly focusing on the Cooperative Intelligent Transport Systems (C-ITS). The study is positioned within the broader context of integrating mobile technology in vehicular environments to enhance road safety by informing drivers about potential hazards in real time. A combination of experimental methods was employed, including a standardised user experience questionnaire (meCUE 2.0), measuring quantitative driving parameters and eye-tracking data within a driving simulator, and post-experiment interviews. The results indicate that the mobile application significantly improved drivers' safety perception, particularly when notifications about hazardous locations were received. Notifications displayed at the top of the mobile screen with auditory cues were deemed most effective. The study concludes that mobile applications like DARS Traffic Plus can play a crucial role in enhancing road safety by effectively communicating hazards to drivers, thereby potentially reducing road accidents and improving overall traffic safety. Screen viewing was kept below the safety threshold, affirming the app's efficacy in delivering crucial information without distraction. These findings support the integration of C-ITS functionalities into mobile applications as a means to augment older vehicle technologies and extend the safety benefits to a broader user base.

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.

Does bike-sharing reduce traffic congestion? Evidence from three mega-cities in China.

This study employs a regression discontinuity design to systematically examine the governance effect of bike-sharing on urban traffic congestion, utilizing city-level data from Beijing, Shanghai, and Wuhan in China between 2016 and 2018. We discover that the introduction of bike-sharing services significantly mitigates traffic congestion in the short term. Our heterogeneity analysis reveals that the initial deployment of shared bicycles primarily alleviates urban congestion, while additional deployments have a limited impact. Further, mechanism test analysis demonstrates that bike-sharing leads to increased metro ridership in these cities, effectively explaining the reduction in road congestion. This study underscores the pivotal role of bike-sharing services in easing urban traffic congestion and provides vital policy insights for enhancing traffic management strategies in Chinese cities.

Study on ring-road incident duration based on latent class accelerated hazard model.

Accurately estimating the duration of freeway incidents can enhance emergency management practices and reduce the likelihood of secondary incidents. To investigate the mechanisms through which key factors influence incident duration, this study sorted out the characteristics and variables of the incident duration on a special freeway in Zhejiang Province, that is, the ring road, and developed a latent class accelerated hazard model. Heterogeneity was incorporated into the model. Three distributions (Weibull, Log-normal, and Log-logistic) were compared, and the Log-logistic distribution exhibited superior performance. The analysis revealed two distinct latent classes: Latent Class 1 and Class 2, had class membership probability of 0.53 and 0.47, respectively, with a total of 11 variables being statistically significant at the 0.05 significance level. It is worth noting that, some neglected explanatory variables are discussed in depth in this study. For example, the mechanism of which specific lane is closed has an impact on the incident duration, rather than a general discussion of the number of lane closures. Furthermore, the way in which the driver involved in the incident reports to the police has a significant impact on the duration of incidents. Notably, potential heterogeneity and its influencing mechanism are captured in the model. Additionally, by predicting class membership using posterior probabilities, it was determined that most data points were more likely to belong to Class 1, and the incident duration primarily ranged between 0 and 60 minutes. These findings are helpful to reduce the duration of incidents on ring-roads and freeways in China, and provide theoretical support for the formulation of freeway incident management and treatment policies.

Evaluation of the effectiveness of three different interventions on older driver safety over a 12-month period: study protocol for a randomised controlled trial.

INTRODUCTION: The growing population of older drivers presents challenges for road safety attributed to age-related declines and increased crash fatality rates. However, enabling older people to maintain their health and independence through continued safe driving is important. This study focuses on the urgent need for cost-effective interventions that reduce crash risk while supporting older drivers to remain driving safely for longer. Our study aims to evaluate the effectiveness of three behavioural interventions for older driver safety. These include an online road-rules refresher workshop, tailored feedback on driving performance and two tailored driving lessons. METHODS AND ANALYSIS: A single-blind three-parallel group superiority randomised controlled trial will be conducted with 198 urban licensed drivers aged 65 years and older, allowing for 4% attrition. This sample size provides 80% power to detect a difference with an alpha of 0.05. Participants will be selected based on a standardised on-road test that identifies them as moderately unsafe drivers. Interventions, spanning a 3-month period, aim to improve driving safety. Their effectiveness will be assessed through a standardised on-road assessment of driving safety at 3 months (T1) and 12 months postintervention (T2). Additionally, monthly self-reported driving diaries will provide data on crashes and incidents.This trial has the potential to identify cost-effective approaches for improving safety for older drivers and contribute to evidence-based health policy, clinical practice and guidelines. ETHICS AND DISSEMINATION: Ethical approval was obtained by the University of New South Wales Human Research Ethics Committee (HC190439, 22 August 2019). The results of the study will be disseminated in peer-reviewed journals and research conferences. TRIAL REGISTRATION NUMBER: ACTRN12622001515785.

Near miss road traffic accidents and associated factors among truck drivers in Gamo zone, southern Ethiopia by using a contributory factors interaction model.

Background: Road traffic accidents (RTAs) are among the leading causes of injuries, fatalities, and the resulting increase in financial burdens worldwide. Every year, RTAs cause numerous serious injuries and fatalities in Ethiopia. it is important to understand how prevalent near-miss crash accidents are, and which by definition could have injured the victim but did not result in an actual accident. The determinants of these near-misses are essential in road crash accident reduction strategies. In spite of the fact that near-miss accidents are much more common than actual losses or injuries, very little research has been conducted on them. Thus, this study was intended to assess the near-miss accidents and associated factors among truckers in Gamo zone, southern Ethiopia. Methodology: The community-based cross-sectional study was employed from May 12 to July 10,2022, using a structured interviewer-administered questionnaire. A simple random sampling technique was used to select participants. The data were analyzed using the statistical package for social sciences. A binary and multivariate logistic regression model was used to identify the determinants of near-miss accidents. A statistical significance level was set at p < 0.05. Results: About 72.5% of truckers had experienced near-miss road traffic accidents. The majority of the near-miss accidents were caused by speeding, followed by driving on the wrong side of the road and skidding, 65 (22.6%), 39 (13.5%), and 38 (13.2%), respectively. Driving frequency per week, location of accidents, condition of the road, sleeping status, and weather conditions were significantly associated with near-miss accidents. Conclusion: The prevalence of near-miss accidents is high in the Gamo zone. Being a younger and less educated driver, high driving frequency per week, driving on major roads and junctions, foggy weather, and inadequate sleep all contribute to the occurrence of accidents. Road safety measures that could address these identified factors are required to mitigate potential RTAs.

Modeling of drinking and driving behaviors among adolescents and young adults in the United States: Complexities and Intervention outcomes.

Alcohol-impaired driving is a formidable public health problem in the United States, claiming the lives of 37 individuals daily in alcohol-related crashes. Alcohol-impaired driving is affected by a multitude of interconnected factors, coupled with long delays between stakeholders' actions and their impacts, which not only complicate policy-making but also increase the likelihood of unintended consequences. We developed a system dynamics simulation model of drinking and driving behaviors among adolescents and young adults. This was achieved through group model building sessions with a team of multidisciplinary subject matter experts, and a focused literature review. The model was calibrated with data series from multiple sources and replicated the historical trends for male and female individuals aged 15 to 24 from 1982 to 2020. We simulated the model under different scenarios to examine the impact of a wide range of interventions on alcohol-related crash fatalities. We found that interventions vary in terms of their effectiveness in reducing alcohol-related crash fatalities. In addition, although some interventions reduce alcohol-related crash fatalities, some may increase the number of drinkers who drive after drinking. Based on insights from simulation experiments, we combined three interventions and found that the combined strategy may reduce alcohol-related crash fatalities significantly without increasing the number of alcohol-impaired drivers on US roads. Nevertheless, related fatalities plateau over time despite the combined interventions, underscoring the need for new interventions for a sustained decline in alcohol-related crash deaths beyond a few decades. Finally, through model calibration we estimated time delays between actions and their consequences in the system which provide insights for policymakers and activists when designing strategies to reduce alcohol-related crash fatalities.

Investigating the features of risky driving behaviors on expressway diverge area based on conflict and modeling analysis.

Driving behaviors are important cause of expressway crash. In this study, method based on modified time-to-collision (MTTC) to identify risky driving behaviors on an expressway diverge area is proposed, thus investigating the impact of velocity and acceleration features of risky driving behavior. Firstly, MTTC is applied to judge whether the behavior is risky. Then, the relationships between velocity, acceleration and different driving behavior on the expressway diverge area were fit by binary logistic regression models (BLR) with L2 regularization and random forests (RF) models, and the models were interpreted by feature importance plots and partial dependency plots. The results show that the AUC metric of 4 RF models for 4 types of driving behaviors, namely, left lane change, right lane change, acceleration and deceleration, are 0.932, 0.845, 0.846 and 0.860 separately. The interpretation of models demonstrates that velocity and absolute value of acceleration greatly affect the risk of the driving behaviors. Different driving behaviors with a certain acceleration have a range of safety speed range. The range will get narrower with the growth of maximum absolute value of acceleration rate, and will be nearly non-exist when the acceleration is over 5 m/s2. In conclusion, this study provided a methodology to measure the risk of driving behaviors and establish a model to recognize of risky driving behaviors. The results can lay the foundation for making countermeasures to prevent risky driving behaviors by managing the vehicle speed.

Evaluating current and future pedestrian mid-block crossing safety treatments using virtual reality simulation.

Virtual reality (VR) simulation offers a proactive, cost effective, immersive, and low risk platform for studying pedestrian safety. Within immersive virtual environments (IVEs), existing and alternative design conditions and intelligent transportation systems (ITS) technologies can be directly compared, prior to real-world implementation, to assess the impacts alternatives may have on pedestrian safety, perception, and behavior. Environmental factors can be controlled within IVEs so that test trials are replicable and directly comparable. Coupled with stated preference feedback, participants' observed preferences and behavior provide a comprehensive understanding of the impacts of proposed design alternatives. This research presents a case study of pedestrian behavior with three different mid-block crossing safety treatments modeled within a one-to-one scale IVE replication of a real-world location in Charlottesville, Virginia. The three safety treatments consider both passive and active collision avoidance designs and technologies, including (1) the existing painted crosswalk, (2) the addition of rectangular rapid flashing beacons (RRFBs), and (3) a pedestrian to everything (P2X) ITS phone application. Additionally, this paper demonstrates a VR simulation experimental design and framework for testing pedestrian safety treatments within naturalistic and replicable IVEs to assess both stated and observed preferences and behaviors of pedestrians. Repeated measures ANOVA indicated changes in both accepted gap size (p = 0.001) and crossing speed (p < 0.001) with alternative safety treatments. Generalized mixed models showed that pedestrians waited for statistically larger gap sizes (p = 0.02) without the assistance of alternative safety technologies (RRFBs and P2X application) and pedestrians crossed the street significantly faster (p = 0.001) without the alternative safety technologies, leading to unsafe dashing behavior. Through post-experiment surveys, it was found that participants perceived the As Built environment to be the least safe of the three treatments and that their sense of risk within the IVE was realistic. Considering both the observed crossing behavior and stated feedback, pedestrians exhibited intentionally unsafe darting behavior without assistive safety technology. This study demonstrates how VR simulation may be leveraged to study both stated preferences and observed behavior for understanding the safety implications of alternative roadway designs, providing a proactive approach for assessing and designing for pedestrian safety.

Driving risk identification of urban arterial and collector roads based on multi-scale data.

Urban arterial and collector roads, while interconnected within the urban transportation network, serve distinct purposes, leading to different driving risk profiles. Investigating these differences using advanced methods is of paramount significance. This study aims to achieve this by primarily collecting and processing relevant vehicle trajectory data alongside driver-vehicle-road-environment data. A comprehensive risk assessment matrix is constructed to assess driving risks, incorporating multiple conflict and traffic flow indicators with statistically temporal stability. The Entropy weight-TOPSIS method and the K-means algorithm are employed to determine the risk scores and levels of the target arterial and collector roads. Using risk levels as the outcome variables and multi-scale features as the explanatory variables, random parameters models with heterogeneity in means and variances are developed to identify the determinants of driving risks at different levels. Likelihood ratio tests and comparisons of out-of-sample and within-sample prediction are conducted. Results reveal significant statistical differences in the risk profiles between arterial and collector roads. The marginal effects of significant parameters are then calculated separately for arterial and collector roads, indicating that several factors have different impacts on the probability of risk levels for arterial and collector roads, such as the number of movable elements in road landscape pictures, the standard deviation of the vehicle's lateral acceleration, the average standard deviation of speed for all vehicles on the road segment, and the number of one-way lanes on the road segment. Some practical implications are provided based on the findings. Future research can be implemented by expanding the collected data to different regions and cities over longer periods.

A review of truck driver persona construction for safety management.

The trucking industry urgently requires comprehensive methods to evaluate driver safety, given the high incidence of serious traffic accidents involving trucks. The concept of a "truck driver persona" emerges as a crucial tool in enhancing driver safety and enabling precise management of road transportation safety. Currently, the road transport sector is only beginning to adopt the user persona approach, and thus the development of such personas for road transport remains an exploratory endeavor. This paper delves into three key aspects: identifying safety risk characteristic parameters, exploring methods for constructing personas and designing safety management interventions. Initially, bibliometric methods are employed to analyze safety risk factors across five domains: truck drivers, vehicles, roads, the environment, and management. This analysis provides the variables necessary to develop personas for road transportation drivers. Existing methods for constructing user personas are then reviewed, with a particular focus on their application in the context of road transportation. Integrating contemporary ideas in persona creation, we propose a framework for developing safety risk personas specific to road transportation drivers. These personas are intended to inform and guide safety management interventions. Moreover, the four stages of driver post-evaluation are integrated into the persona development process, outlining tailored safety management interventions for each stage: pre-post, pre-transit, in-transit, and on-post. These interventions are designed to be orderly and finely tuned. Lastly, we offer optimization recommendations and suggest future research directions based on safety risk factors, persona construction, and safety management interventions. Overall, this paper presents a safety management-oriented research technology system for constructing safety risk personas for truck drivers. We argue that improving the design of the persona index system, driven by big data, and encompassing the entire driver duty cycle-from pre-post to on-post-will significantly enhance truck driver safety. This represents a vital direction for future development in the field.

Bayesian hybrid gamma-GPD model for extreme traffic conflict threshold determination in the peak over threshold approach.

Extreme value theory (EVT) models have been frequently utilized to estimate crash risk from traffic conflicts with the peak over threshold commonly used to identify conflict extremes. However, a common problem for the peak over threshold method is the selection of a suitable threshold to distinguish general and extreme conflicts. Subjective and arbitrary selection of the threshold in peak over threshold method can result in bias and unstable estimation results. The primary objective of the study is to propose a hybrid modelling approach for the threshold determination in peak over threshold method. The hybrid model consists of a joint gamma distribution and generalized Pareto distribution (GPD). The gamma distribution is used to fit general conflicts while the GPD is used to fit extreme conflicts. Specially, discontinued, continued and differentiable gamma-GPD models are developed with the threshold being treated as a model parameter. Traffic conflict data collected from three signalized intersections in the city of Surrey, British Columbia were used for the study. The modified time to collision (MTTC) was employed as conflict indicator. The Bayesian approach was employed to estimate the threshold as well as other hybrid gamma-GPD model parameters. The results show that the discontinued gamma-GPD model is superior to the continued and differentiable gamma-GPD models for determining the threshold in terms of crash estimation accuracy and model fit. The crash estimates using the threshold determined by the hybrid gamma-GPD model outperform those estimated based on the traditional quantile plots method, indicating that the superiority of the proposed threshold determination approach based on gamma-GPD hybrid model. The proposed hybrid gamma-GPD model could determine the threshold parameter in peak over threshold method for traffic conflicts extremes automatically in an objective and quantitative way. It contributes to existing peak over threshold method for producing reliable crash estimation.

Analysis of pedestrian-two-wheeler conflicts at green light digital countdown signals: A random parameter ordered logit model approach.

The rising prevalence of e-bikes and shared bikes in transportation modes adds complexity to pedestrian movement at intersections. The conflict technique is a substitute for collisions in analyzing pedestrian safety at digital countdown signal intersections. Pedestrian and two-wheeler trajectories were obtained using Unmanned Aerial Vehicle (UAV) and T-Analyst software. The severity of pedestrian-two-vehicle conflicts was assessed using indicators such as Time to Collision (TTC), Post Encroachment Time (PET), and Yaw Rate Ratio (YRR), along with the fuzzy C-mean clustering method. An analysis of the impact of pedestrian characteristics, cyclist characteristics, and road conflict factors on severity was conducted using a random parameter ordered logit model. A total of 630 valid conflicts were identified, comprising 105 potential conflicts, 242 minor conflicts, and 283 serious conflicts. More minor and serious conflicts occurred in Signal 1 and Signal 2. Serious conflicts mainly occurred in road Zone 2, Zone 3, and Zone 5, while minor conflicts were more frequent in Zone 4 and Zone 5. Pedestrian crossing at Signal 2 increased the conflict severity, and the refuge island had a similar effect. Cyclists passing the conflict point first reduced the probability of serious conflicts. Older adults are safer at countdown signal intersections than young people. It is essential to enhance the awareness of digital countdown signals among youth. Managers should consider diverting two-wheelers during peak hours and encourage cyclists to walk through crosswalks.

Estimating the effectiveness of marked sidewalks: An application of the spatial causality approach.

Various safety enhancements and policies have been proposed to enhance pedestrian safety and minimize vehicle-pedestrian accidents. A relatively recent approach involves marked sidewalks delineated by painted pathways, particularly in Asia's crowded urban centers, offering a cost-effective and space-efficient alternative to traditional paved sidewalks. While this measure has garnered interest, few studies have rigorously evaluated its effectiveness. Current before-after studies often use correlation-based approaches like regression, lacking effective consideration of causal relationships and confounding variables. Moreover, spatial heterogeneity in crash data is frequently overlooked during causal inference analyses, potentially leading to inaccurate estimations. This study introduces a geographically weighted difference-in-difference (GWDID) method to address these gaps and estimate the safety impact of marked sidewalks. This approach considers spatial heterogeneity within the dataset in the spatial causal inference framework, providing a more nuanced understanding of the intervention's effects. The simplicity of the modeling process makes it applicable to various study designs relying solely on pre- and post-exposure outcome measurements. Conventional DIDs and Spatial Lag-DID models were used for comparison. The dataset we utilized included a total of 13,641 pedestrian crashes across Taipei City, Taiwan. Then the crash point data was transformed into continuous probability values to determine the crash risk on each road segment using network kernel density estimation (NKDE). The treatment group comprised 1,407 road segments with marked sidewalks, while the control group comprised 3,097 segments with similar road widths. The pre-development program period was in 2017, and the post-development period was in 2020. Results showed that the GWDID model outperformed the spatial lag DID and traditional DID models. As a local causality model, it illustrated spatial heterogeneity in installing marked sidewalks. The program significantly reduced pedestrian crash risk in 43% of the total road segments in the treatment group. The coefficient distribution map revealed a range from -22.327 to 2.600, with over 95% of the area yielding negative values, indicating reduced crash risk after installing marked sidewalks. Notably, the impact of crash risk reduction increased from rural to urban areas, emphasizing the importance of considering spatial heterogeneity in transportation safety policy assessments.

Safety assessment for autonomous vehicles: A reference driver model for highway merging scenarios.

Driver models are crucial for the safety assessment of autonomous vehicles (AVs) because of their role as reference models. Specifically, an AV is expected to achieve at least the same level of safety performance as a careful and competent driver model. To make this comparison possible, quantitative modeling of careful and competent driver models is essential. Thus, the UNECE Regulation No. 157 proposes two driver models as benchmarks for AVs, enabling safety assessment of AV longitudinal behaviors. However, these two driver models are unable to be applied in non-car-following scenarios, limiting their applications in scenarios such as highway merging. To this end, we propose a careful and competent driver model for highway merging (CCDM2) scenarios using interpretable reinforcement learning-based decision-making and safety constraint control. We compare our model's safe driving capabilities with human drivers in challenging merging scenarios and demonstrate the "careful" and "competent" characteristics of our model while ensuring its interpretability. The results indicate the model's capability to handle merging scenarios with even better safety performance than human drivers. This model is of great value for AV safety assessment in merging scenarios and contributes to future reference driver models to be included in AV safety regulations.