Study on the Driver Visual Workload in High-Density Interchange-Merging Areas Based on a Field Driving Test.

A visual workload model was constructed to determine and evaluate drivers' visual workload characteristics in high-density interchange-merging areas. Five interchanges were selected, and a real-vehicle driving test was conducted with 47 participants. To address the differences in drivers' visual characteristics in the interchange cluster merging areas, the Criteria Importance Through Intercriteria Correlation (CRITIC) objective weighting method was employed. Six visual parameters were selected to establish a comprehensive evaluation model for the visual workload in high-density interchange-merging areas. The results show that the average scanning frequency and average pupil area change rate are most strongly correlated with the visual workload, whereas the average duration of a single gaze has the lowest weight in the visual workload assessment system. Different driver visual workloads were observed depending on the environment of the interchange-merging areas, and based on these, recommendations are proposed to decrease drivers' workload, thereby increasing road safety.

Road traffic accidents involvement among commercial taxi drivers in Nigeria: Structural equation modelling approach.

Taxis are essential to economic growth due to the ease and comfort they offer passengers. This is evident as most cities, especially in Africa, are dominated by taxis providing door-to-door services. However, their susceptibility to road traffic accidents (RTA) raises serious concerns due to their risky driving behaviours. In contrast, studies on taxi driver involvement in RTA due to their risky driving behaviours are sparse, especially in African countries. Consequently, the study examined the relationship between risky driving behaviour and traffic accident involvement among Nigerian commercial taxi drivers using the structural equation modeling (SEM) approach. Prior to the structural model analysis, the modified driver behaviour questionnaire (DBQ) was valid. This was assessed through the measurement model, and the results showed that the composite reliability, average variance extracted, and discriminant validity were greater than 0.7, greater than 0.5, and less than 0.90, respectively. Furthermore, the structural equation modeling results show that the driving violation and driving error constructs influenced road traffic accidents among taxi drivers, while inattention error was insignificant (p > 0.05). Although driving violations and errors significantly increase the chances of RTA among taxi drivers, driving violations had a more substantial influence than driving errors. Also, the regression coefficient indicates the risky driving behaviour of commercial taxi drivers accounts for 5.2 % of the RTAs in Nigeria. This research contributed to validating the DBQ for commercial taxi drivers in Nigeria, examining the influence of their driving violations, driving errors, and inattention errors on accident involvement and that inattention error may not necessarily influence accidents, which will aid policymakers in formulating mitigative strategies for RTA reductions. Moreso, it will guide driver trainers in curriculum development for specific commercial taxi driver training.

Understanding aberrant driving intentions based on the Theory of Planned Behavior: Literature review and Meta-Analysis.

INTRODUCTION: Despite deployed efforts to establish strict road safety standards, human factors is still the leading cause of road crashes. To identify determinants of driver's behavior, TPB (Theory of Planned Behavior) is widely used as a prominent theory of behavior change. However, the existence of different aberrant driving behaviors (decision errors, recognition errors, violations, and physical condition related errors) and several studies using TPB to understand driving behavior, makes it important to conduct a literature review and a meta-analysis of existing studies to use their results in effective driving behavior change interventions. METHOD: The selection process provided 125 relevant studies that were published between 1991 and 2022, and that used TPB for the understanding of aberrant driving behavior. Five fundamental research questions were defined to identify information to be discovered from the literature review and from the meta-analysis. RESULTS: In addition to the standard TPB constructs (attitudes, subjective norms, and perceived behavioral control), past behavior, moral norms, and descriptive norms were used in studies for a more comprehensive understanding of aberrant driving intention. This analysis demonstrated a significant correlation between aberrant driving intentions and past behavior. Also, moral norms construct was correlated with violations and recognition errors, whereas descriptive norms construct was correlated just with recognition errors. CONCLUSIONS: The results of this study highlight the strength of TPB in the prediction of aberrant driving intention and its potential effectiveness to guide interventions aimed at changing aberrant driving behaviors. The study contributes to the comprehension of the relevant psychological factors influencing the engagement of drivers in each category of aberrant driving behaviors. PRACTICAL APPLICATIONS: Researchers can use the results of this study to select the relevant psychological factors adapted to their interventions of driving behavior change. The results of the meta-analysis can also be used in the prediction of driver's intentions.

The role of subjective risk perception and self-esteem in the relationship between sensation seeking and aberrant behaviors on the road: A moderated-moderation model.

INTRODUCTION: Road crashes are still one of the main causes of death around the world. Risky behavior has been proposed as one of the foremost predictors, with the theoretical framework of aberrant behavior emerging as a predominant approach for its examination. Sensation seeking has been pointed out as one of the main personality predictors of aberrant behavior. The current research aimed to investigate the moderated-moderation effect of both risk perception and self-esteem in the relationship between sensation seeking and aberrant behavior. METHOD: Two studies were conducted. The first study aimed to analyze the psychometric properties of the Spanish version of the Risk Perception Scale (RPS), a 10-item self-report to assess risk perception. A sample composed of 471 Spanish drivers (319 female, Mage = 29.75) completed the RPS. In the second study, a different sample of 236 Spanish drivers (129 female, Mage = 38.49) completed a set of self-reports aiming both to analyze the concurrent and divergent validity of the RPS, and to test the main moderated-moderation hypothesis. RESULTS: With respect to the first study, the confirmatory factor analysis (CFA) supported a 7-item version which fitted in a single reliable factor (α = .74). Regarding the second study, the results supported both the concurrent and divergent validity of the RPS. Likewise, it was verified the moderated-moderation effect in the case of ordinary violations (R2 = .34), aggressive violations (R2 = .20), and lapses (R2 = .12). CONCLUSIONS: The RPS is a useful self-report to assess subjective risk perception in Spanish drivers. Both self-esteem and risk perception affect the relationship between sensation seeking and aberrant driving behavior. PRACTICAL IMPLICATIONS: Intervention programs aiming to reduce aberrant driving behavior should be focused on reducing sensation seeking tendencies while simultaneously enhancing both risk perception skills and self-esteem.

Development of an algorithm for analysis of routes: Case studies using novice and older drivers.

INTRODUCTION: This study addresses the lack of methods to quantify driver familiarity with roadways, which poses a higher risk of crashes. METHOD: We present a new approach to assessing driving route diversity and familiarity using data from the DrivingApp, a smartphone-based research tool that collects trip-level information, including driving exposure and global positioning system (GPS) data, from young novice drivers (15-19 years old) to older drivers (67-78 years old). Using these data, we developed a GPS data-based algorithm to analyze the uniqueness of driving routes. The algorithm creates same route trip (SRT) arrays by comparing each trip of an identified user, employing statistically determined thresholds for GPS coordinate proximity and trip overlap. The optimal thresholds were established using a General Linear Model (GLM) to examine distance, and repeated observations. The Adjusted Breadth-First Search method is applied to the SRT arrays to prevent double counting or trip omission. The resulting list is classified as geographically distinct routes, or unique routes (URs). RESULTS: Manual comparison of algorithm output with geographical maps yielded an overall precision of 0.93 and accuracy of 0.91. The algorithm produces two main outputs: a measure of driving diversity (number of URs) and a measure of route-based familiarity derived from the Rescorla-Wagner model. To evaluate the utility of these measures, a Gaussian mixture model clustering algorithm was used on the young novice driver dataset, revealing two distinct groups: the low-frequency driving group with lower route familiarity when having higher route diversity, whereas the high-frequency driving group with the opposite pattern. In the older driver group, there was a significant correlation found between the number of URs and Geriatric Depression Score, or walking gait speed. PRACTICAL APPLICATIONS: These findings suggest that route diversity and familiarity could complement existing measures to understand driving safety and how driving behavior is related to physical and psychological outcomes.

Mobile phone conversation during nighttime driving: Effects on driving behavior.

OBJECTIVES: This study aims to investigate the impact of mobile phone use (specifically, conversation), considering various use modes, on driving behavior at night. Mobile phone use is a source of driver distraction and has been associated with increased accident risk. Driving at night also entails higher accident risk and severity compared to daytime driving. Several studies have investigated the impact of mobile phone use on driving behavior; however, only a few have explored the differences between the different use modes. Most present studies involved daytime driving, although mobile phone use at night is equally if not more prevalent. METHOD: A driving simulator experiment was designed in which 55 participants drove under nighttime simulator conditions, in different road environments (urban and rural) and under different types of distraction: no distraction, handheld, wired earphone, and speaker mode. The drives were performed during late afternoon and evening hours to resemble nighttime conditions both in the simulator and in the actual environment. Participants also completed a questionnaire for collection of different types of data. RESULTS: Results highlight the effect of mobile phone use on driving behavior, through specific indicators. Mobile phone use resulted in reduced 85th percentile driving speed and 85th percentile acceleration and increased reaction time and lateral deviation. However, safer stopping distance was observed in rural roads. Parameters relative to mobile phone use familiarity and exposure were found to mitigate mobile phone use effects. CONCLUSIONS: Mobile phones affect driving behavior at night in a similar manner to that noted in several different studies considering daytime driving. The hands-free regulation should be revisited, because driver distraction also occurred under this particular use mode. Further research is required considering mobile phone use familiarity and exposure and effects of mobile phone use, because the latter is reduced with an increase in the former. Stopping distance, an understudied but more immediate surrogate measure of road safety, was increased with mobile phone use, mainly as a result of the risk compensation behavior that drivers adopt, indicating that more research is required in this field.

Enhancing highway Loop Safety Level through proactive risk-based assessment of geometric configuration using lateral acceleration.

OBJECTIVE: Loop ramps are complex due to their combination of horizontal curves and vertical alignments. Analyzing driving behavior and measuring safety levels can provide insights for designers, helping to improve the performance and alignment of design assumptions with actual driving behavior on loops. Therefore, the primary objective of this research is to explore the safety, performance and geometric configuration of the main body and general shape of free-flow loop ramps in the free-following mode. METHODS: The study uses data from a UAV to investigate vehicle demand behavior. Maximum lateral acceleration (ay,i) in loops is used as a Surrogate Safety Measure (SSM), along with a new parameter, the a/b ratio, to determine the general shape of loop bodies. The study presents the Loop Safety Level (LSL), an approach for proactive risk analysis and ranking that relies on threshold lateral acceleration (at), 85th percentile maximum lateral acceleration (ay,max,85%), and crash analysis. RESULTS: A higher LSL value points to a more critical safety concern regarding the loop's shape in relation to lateral acceleration caused by driving behaviors. Comparing crash statistics with lateral acceleration results enables the LSL to provide appropriate safety ratings and diagnose loop segment safety. A prediction model for maximum lateral acceleration, based on loop geometry, demonstrates a good fit (R2=0.88) between observed and predicted data. CONCLUSIONS: The study enhances understanding of safety considerations in geometric configuration and general shape enhancement of loops during the design process.

The Impact of Cybersecurity Attacks on Human Trust in Autonomous Vehicle Operations.

OBJECTIVE: This study examines the extent to which cybersecurity attacks on autonomous vehicles (AVs) affect human trust dynamics and driver behavior. BACKGROUND: Human trust is critical for the adoption and continued use of AVs. A pressing concern in this context is the persistent threat of cyberattacks, which pose a formidable threat to the secure operations of AVs and consequently, human trust. METHOD: A driving simulator experiment was conducted with 40 participants who were randomly assigned to one of two groups: (1) Experience and Feedback and (2) Experience-Only. All participants experienced three drives: Baseline, Attack, and Post-Attack Drive. The Attack Drive prevented participants from properly operating the vehicle in multiple incidences. Only the "Experience and Feedback" group received a security update in the Post-Attack drive, which was related to the mitigation of the vehicle's vulnerability. Trust and foot positions were recorded for each drive. RESULTS: Findings suggest that attacks on AVs significantly degrade human trust, and remains degraded even after an error-less drive. Providing an update about the mitigation of the vulnerability did not significantly affect trust repair. CONCLUSION: Trust toward AVs should be analyzed as an emergent and dynamic construct that requires autonomous systems capable of calibrating trust after malicious attacks through appropriate experience and interaction design. APPLICATION: The results of this study can be applied when building driver and situation-adaptive AI systems within AVs.

Exploring high-emission driving behaviors of heavy-duty diesel vehicles based on engine principles under different road grade levels.

To reveal the outstanding high-emission problems that occur when heavy-duty diesel vehicles (HDDV) pass uphill and downhill, this study proposes a method to depict the nitrogen oxides (NOx) and carbon dioxide (CO2) high-emission driving behaviors caused by slopes from the perspective of engine principles. By calculating emission and grade data of HDDV based on on-board diagnostic (OBD) data and digital elevation model (DEM) data, the 262 short trips including uphill, flat-road and downhill are firstly obtained through the rule-based short trip segmentation method, and the significant correlation between the road grade and emissions of the short trips is verified by Kendall's Tau and K-means clustering. Secondly, by comparing the distribution changes of three speed categories (acceleration state, constant speed state and deceleration state), the differences in HDDV operating states under different grade levels are discussed. Finally, the machine learning models (Random Forest, XGBoost and Elastic Net), are used to develop the NOx and CO2 emission estimation model, identifying high-emission driving behaviors, particularly during uphill driving, which showed the highest proportion of high-emission. Explained by the feature importance and SHapley Additive exPlanations (SHAP) model that large accelerator pedal opening, frequent aggressive acceleration, and high engine load have positive effects both on NOx and CO2 emissions. The difference is in the air-fuel ratio that the engine in the rich or slightly lean burning state will increase CO2 emissions and the lean burning state will increase NOx emissions. In addition, due to the uncertainty of the actual uphill, drivers often undergo a rapid "deceleration-uniform-acceleration" process, which significantly contributes to high NOx and CO2 emissions from the engine perspective. The findings provide insights for designing driving strategies in slope scenarios and offer a novel perspective on depicting driving behaviors.

A comprehensive evaluation of the frog effect on drivers in mountain highway tunnels - The effect of low-volume intermittent information.

OBJECTIVE: The driver's inability to fully absorb and react to operational cues while driving is like boiling a frog in warm water. With intermittent, low-volume information, drivers can underreact by ignoring these minor but continuous changes. This paper aims to provide an opportunity to test the effects of intermittently occurring low-volume information on drivers. METHODS: A real vehicle test with naturalistic driving was used to collect driving speed data from 40 drivers on a highway tunnel section in Chongqing, China, where nine tunnels are located. Drivers were classified into three categories according to the degree of compliance of their driving speed with the speed limit required by traffic signs, and drivers were analyzed in terms of their sensitivity to traffic signs and their reaction to driving maneuvers. RESULTS: Conservative drivers are the most absorbent of low-volume intermittent information, and the cumulative effect of the frog effect does not exceed 2.00 km; eager drivers tend to ignore this information, and the cumulative effect of the frog effect reaches 2.91 km; and the general type of driver is in the middle of these two types of drivers, and the frog effect gradually penetrates the driving speed in a weakly increasing manner, up to a maximum of 9.8 km. CONCLUSION: At the beginning of a journey, drivers are most sensitive to traffic signs, and low-volume intermittent information can also play a role in guiding driving operations effectively at this time. However, as the driving distance increases, the effect of the frog effect on different types of drivers gradually increases, even exceeding the effect caused by the black-and-white hole effect, especially when driving in tunnel groups. Considering the driving characteristics of different types of drivers to improve the deployment of low-volume intermittent information and reduce the distance of the frog effect can effectively improve driving safety.

Design and Implementation of a Two-Wheeled Vehicle Safe Driving Evaluation System.

The delivery market in Republic of Korea has experienced significant growth, leading to a surge in motorcycle-related accidents. However, there is a lack of comprehensive data collection systems for motorcycle safety management. This study focused on designing and implementing a foundational data collection system to monitor and evaluate motorcycle driving behavior. To achieve this, eleven risky behaviors were defined, identified using image-based, GIS-based, and inertial-sensor-based methods. A motorcycle-mounted sensing device was installed to assess driving, with drivers reviewing their patterns through an app and all data monitored via a web interface. The system was applied and tested using a testbed. This study is significant as it successfully conducted foundational data collection for motorcycle safety management and designed and implemented a system for monitoring and evaluation.

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.

Recognition of aggressive driving behavior under abnormal weather based on Convolutional Neural Network and transfer learning.

OBJECTIVES: Aggressive driving behavior can lead to potential traffic collision risks, and abnormal weather conditions can exacerbate this behavior. This study aims to develop recognition models for aggressive driving under various climate conditions, addressing the challenge of collecting sufficient data in abnormal weather. METHODS: Driving data was collected in a virtual environment using a driving simulator under both normal and abnormal weather conditions. A model was trained on data from normal weather (source domain) and then transferred to foggy and rainy weather conditions (target domains) for retraining and fine-tuning. The K-means algorithm clustered driving behavior instances into three styles: aggressive, normal, and cautious. These clusters were used as labels for each instance in training a CNN model. The pre-trained CNN model was then transferred and fine-tuned for abnormal weather conditions. RESULTS: The transferred models showed improved recognition performance, achieving an accuracy score of 0.81 in both foggy and rainy weather conditions. This surpassed the non-transferred models' accuracy scores of 0.72 and 0.69, respectively. CONCLUSIONS: The study demonstrates the significant application value of transfer learning in recognizing aggressive driving behaviors with limited data. It also highlights the feasibility of using this approach to address the challenges of driving behavior recognition under abnormal weather conditions.

Assessing the determinants of crash propensity using structural equation modeling: Role of distractions caused by fellow drivers.

INTRODUCTION: Aggressive behavior of drivers is a source of crashes and high injury severity. Aggressive drivers are part of the driving environment, however, excessive aggressive driving by fellow drivers may take the attention of the recipient drivers away from the road resulting in distracted driving. Such external distractions caused by the aggressive and discourteous behavior of other road users have received limited attention. These distractions caused by fellow drivers (DFDs) may agitate recipient drivers and ultimately increase crash propensity. Aggressive driving behaviors are quite common in South Asia and, thus, it is necessary to determine their contribution to distractions and crash propensity. METHOD: Our study aimed to evaluate the effects of DFDs using primary data collected through a survey conducted in Lahore, Pakistan. A total of 801 complete responses were obtained. Various hypotheses were defined to explore the associations between the latent factors such as DFDs, anxiety/stress (AS), anxiety-based performance deficits (APD), hostile behavior (HB), acceptability of vehicle-related distractions (AVRD), and crash propensity (CP). Structural Equation Modeling (SEM) was employed as a multivariate statistical technique to test these hypotheses. RESULTS: The results supported the hypothesis that DFDs lead to AS among recipient drivers. DFDs and AS were further found to have positive associations with APDs. Whereas, there was a significant negative association between DFD, AS, and AVRD. As hypothesized, DFD and AS had positive associations with CP, indicating that distractions caused by aggressive behaviors leads to stress and consequently enhances crash propensity. PRACTICAL APPLICATIONS: The results of this study provide a statistically sound foundation for further exploration of the distractions caused by the aggressive behaviors of fellow drivers. Further, the results of this study can be utilized by the relevant authorities to alter aggressive driving behaviors and reduce DFDs.

Driver drowsiness is associated with altered facial thermal patterns: Machine learning insights from a thermal imaging approach.

Driver drowsiness is a significant factor in road accidents. Thermal imaging has emerged as an effective tool for detecting drowsiness by enabling the analysis of facial thermal patterns. However, it is not clear which facial areas are most affected and correlate most strongly with drowsiness. This study examines the variations and importance of various facial areas and proposes an approach for detecting driver drowsiness. Twenty participants underwent tests in a driving simulator, and temperature changes in various facial regions were measured. The random forest method was employed to evaluate the importance of each facial region. The results revealed that temperature changes in the nasal area exhibited the highest value, while the eyes had the most correlated changes with drowsiness. Furthermore, drowsiness was classified with an accuracy of 88 % utilizing thermal variations in the facial region identified as the most important regions by the random forest feature importance model. These findings provide a comprehensive overview of facial thermal imaging for detecting driver drowsiness and introduce eye temperature as a novel and effective measure for investigating cognitive activities.

A modeling method for two-dimensional two-wheeler driving behavior during severe conflict interaction at intersections.

The safety of two-wheelers is a serious public safety issue nowadays. Two-wheelers usually have severe conflict interaction with vehicles at intersections, such as running red lights, which is very likely to cause traffic accidents. Therefore, a model of two-wheeler driving behavior in conflicting interactions can provide guidance for traffic safety management on one hand, and can be used for the development and testing of autonomous vehicles on the other. However, the existing models perform poorly when interacting with vehicles. To address the problems, this paper proposes a modeling method (an improved social force model, ISFM) for two-dimensional two-wheeler driving simulation for conflict interaction at intersections. Based on analysis of naturalistic driving study data, when two-wheelers encounter with vehicles, their driving intentions and trajectories can be categorized into two groups, which are yielding and overtaking. Therefore, the vehicle-related social forces are designed to be a set of two forces rather than a repulsion force in original SFM, which is a yielding force based on the relative distance between the two-wheeler and the vehicle, and an overtaking force based on the velocity of the two-wheeler itself. This opens up the possibilities for modeling the multi-modal driving intention of two-wheelers encountering with cross traffic. Based on ISFM, a bicycle model, a powered two-wheeler (PTW) model and a model of a group of PTWs, are then constructed. Compared to the original SFM, ISFM increases the precision of driving intention prediction by 19.7 % (yielding situation) and 25.0 % (overtaking situation), and reduces the root mean square error between simulated and actual trajectories by 7.8 % and 14.8 % on the bicycle model and the PTW model, respectively. Meanwhile, the model of a group of PTWs also performs well. Finally, the results of ablation experiments also validate the effectiveness of the social force designed based on velocity.

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.

Modeling distracted driving behavior considering cognitive processes.

The modeling of distracted driving behavior has been studied for many years, however, there remain many distraction phenomena that can not be fully modeled. This study proposes a new method that establishes the model using the queuing network model human processor (QN-MHP) framework. Unlike previous models that only consider distracted-driving-related human factors from a mathematical perspective, the proposed method reflects the information processing in the human brain, and simulates the distracted driver's cognitive processes based on a model structure supported by physiological and cognitive research evidence. Firstly, a cumulative activation effect model for external stimuli is adopted to mimic the phenomenon that a driver responds only to stimuli above a certain threshold. Then, dual-task queuing and switching mechanisms are modeled to reflect the cognitive resource allocation under distraction. Finally, the driver's action is modeled by the Intelligent Driver Model (IDM). The model is developed for visual distraction auditory distraction separately. 773 distracted car-following events from the Shanghai Naturalistic Driving Study data were used to calibrate and verify the model. Results show that the model parameters are more uniform and reasonable. Meanwhile, the model accuracy has improved by 57% and 66% compared to the two baseline models respectively. Moreover, the model demonstrates its ability to generate critical pre-crash scenarios and estimate the crash rate of distracted driving. The proposed model is expected to contribute to safety research regarding new vehicle technologies and traffic safety analysis.

Resolving uncertainty on the fly: modeling adaptive driving behavior as active inference.

Understanding adaptive human driving behavior, in particular how drivers manage uncertainty, is of key importance for developing simulated human driver models that can be used in the evaluation and development of autonomous vehicles. However, existing traffic psychology models of adaptive driving behavior either lack computational rigor or only address specific scenarios and/or behavioral phenomena. While models developed in the fields of machine learning and robotics can effectively learn adaptive driving behavior from data, due to their black box nature, they offer little or no explanation of the mechanisms underlying the adaptive behavior. Thus, generalizable, interpretable, computational models of adaptive human driving behavior are still rare. This paper proposes such a model based on active inference, a behavioral modeling framework originating in computational neuroscience. The model offers a principled solution to how humans trade progress against caution through policy selection based on the single mandate to minimize expected free energy. This casts goal-seeking and information-seeking (uncertainty-resolving) behavior under a single objective function, allowing the model to seamlessly resolve uncertainty as a means to obtain its goals. We apply the model in two apparently disparate driving scenarios that require managing uncertainty, (1) driving past an occluding object and (2) visual time-sharing between driving and a secondary task, and show how human-like adaptive driving behavior emerges from the single principle of expected free energy minimization.

A comparative analysis of distracted driving behavior among drivers of different income levels: A case study in huainan, China.

This research aims to investigate the differences and causes behind distracted driving behavior among drivers with varying income levels. A comparative survey of 1121 drivers in Huainan City, China, was conducted, including 562 drivers from high-end communities representing the high-income group, and 559 drivers from general communities representing the low-income group. Employing social norms, risk perception, and experience as independent variables, the study further examines the role of in-group bias as a mediating variable, with distracted driving behavior serving as the dependent variable, through the construction of two structural equation models for analysis. The study found that among the high-income driver group, in-group bias significantly mediates the impact of social norms, risk perception, and experience on distracted driving behavior; however, this mediating effect is less pronounced in the low-income driver group. This finding is crucial for understanding the potential distracted driving behaviors induced by in-group bias within the high-income driver group and for effectively promoting driving safety. In summary, this research provides new insights into reducing distracted driving behavior among the high-income driver group, thereby enhancing road safety.