Safety in higher level automated vehicles: Investigating edge cases in crashes of vehicles equipped with automated driving systems.

With emerging Automated Driving Systems (ADS) representing Automated Vehicles (AVs) of Level 3 or higher as classified by the Society of Automotive Engineers, several AV manufacturers are testing their vehicles on public roadways in the U.S. The safety performance of AVs has become a major concern for the transportation industry. Several ADS-equipped vehicle crashes have been reported to the National Highway Traffic Safety Administration (NHTSA) in recent years. Scrutinizing these crashes can reveal rare or complex scenarios beyond the normal capabilities of AV technologies called "edge cases." Investigating edge-case crashes helps AV companies prepare vehicles to handle these unusual scenarios and, as such, improves traffic safety. Through analyzing the NHTSA data from July 2021 to February 2023, this study utilizes an unsupervised machine learning technique, hierarchical clustering, to identify edge cases in ADS-equipped vehicle crashes. Fifteen out of 189 observations are identified as edge cases, representing 8 % of the population. Injuries occurred in 10 % of all crashes (19 out of 189), but the proportion rose to 27 % for edge cases (4 out of 15 edge cases). Based on the results, edge cases could be initiated by AVs, humans, infrastructure/environment, or their combination. Humans can be identified as one of the contributors to the onset of edge-case crashes in 60 % of the edge cases (9 out of 15 edge cases). The main scenarios for edge cases include unlawful behaviors of crash partners, absence of a safety driver within the AV, precrash disengagement, and complex events challenging for ADS, e.g., unexpected obstacles, unclear road markings, and sudden and unexpected changes in traffic flow, such as abrupt road congestion or sudden stopped traffic from a crash. Identifying and investigating edge cases is crucial for improving transportation safety and building public trust in AVs.

The role of driver head pose dynamics and instantaneous driving in safety critical events: Application of computer vision in naturalistic driving.

This paper investigates the role of driver behavior especially head pose dynamics in safety-critical events (SCEs). Using a large dataset collected in a naturalistic driving study, this paper analyzes the head pose dynamics and driving behavior in moments leading up to crashes or near-crashes. The study uses advanced computer vision and mixed logit modeling techniques to identify patterns and relationships between drivers' head pose dynamics and crash involvement. The results suggest that driver-head pose dynamics, especially poses that indicate distraction and movement volatility, are important factors that can contribute to undesirable safety outcomes. Marginal effects show that angular deviation for head pose dynamics indicated by yaw, pitch and roll increase the likelihood of crash intensity by 4.56%, 4.92% and 8.26% respectively. Furthermore, traffic flow and lane changing also contribute to increase in likelihood of crash intensity. These findings provide new insights into pre-crash factors, especially human factors and safety-critical events. The study highlights the importance of considering human factors in designing driver assistance systems and developing safer vehicles. This research contributes by examining naturalistic driving data at the microscopic level with early detection of behaviors that lead to SCEs and provides a basis for future research on automation.

How is the duration of distraction related to safety-critical events? Harnessing naturalistic driving data to explore the role of driving instability.

INTRODUCTION: Due to a variety of secondary tasks performed by drivers, distracted driving has become a critical concern. At 50 mph, sending/reading a text for 5 seconds is equivalent to driving the length of a football field (360 ft) with eyes closed. A fundamental understanding of how distractions lead to crashes is needed to develop appropriate countermeasure strategies. A key question is whether distraction increases driving instability, which then further contributes to safety-critical events (SCEs). METHODS: By harnessing newly available microscopic driving data and using the safe systems approach, a subsample of naturalistic driving study data were analyzed, collected through the second strategic highway research program. Rigorous path analysis (including Tobit and Ordered Probit regressions) is used to jointly model the instability in driving (using coefficient of variation of speed) and event outcomes (including baseline, near-crash, and crash). The marginal effects from the two models are used to compute direct, indirect, and total effects of distraction duration on SCEs. RESULTS: Results indicate that a longer duration of distraction was positively but non-linearly associated with higher driving instability and higher chances of SCEs. Where, the chance of a crash and near-crash was higher by 34% and 40%, respectively, with a unit increase in driving instability. Based on the results, the chance of both SCEs significantly increases non-linearly with an increase in distraction duration beyond 3 seconds. For instance, the chance of a crash is 16% for a driver distracted for 3 seconds, which increases to 29% if a driver is distracted for 10 seconds. CONCLUSIONS AND PRACTICAL APPLICATIONS: Using path analysis, the total effects of distraction duration on SCEs are even higher when its indirect effects on SCEs through driving instability are considered. Potential practical implications including traditional countermeasures (changes in roadway environments) and vehicle technologies are discussed in the paper.

Heterogeneous ensemble learning for enhanced crash forecasts - A frequentist and machine learning based stacking framework.

INTRODUCTION: This study aims to increase the prediction accuracy of crash frequency on roadway segments that can forecast future safety on roadway facilities. A variety of statistical and machine learning (ML) methods are used to model crash frequency with ML methods generally having a higher prediction accuracy. Recently, heterogeneous ensemble methods (HEM), including "stacking," have emerged as more accurate and robust intelligent techniques providing more reliable and accurate predictions. METHODS: This study applies "Stacking" to model crash frequency on five-lane undivided (5 T) segments of urban and suburban arterials. The prediction performance of "Stacking" is compared with parametric statistical models (Poisson and negative binomial) and three state-of-the-art ML techniques (Decision tree, random forest, and gradient boosting), each of which is termed as the base-learner. By employing an optimal weight scheme to combine individual base-learners through stacking, the problem of biased predictions in individual base-learners due to differences in specifications and prediction accuracies is avoided. Data including crash, traffic, and roadway inventory were collected and integrated from 2013 to 2017. The data are split into training (2013-2015), validation (2016), and testing (2017) datasets. After training five individual base-learners using training data, prediction outcomes are obtained for the five base-learners using validation data that are then used to train a meta-learner. RESULTS: Results of statistical models reveal that crashes increase with the density (number per mile) of commercial driveways whereas decrease with average offset distance to fixed objects. Individual ML methods show similar results - in terms of variable importance. A comparison of out-of-sample predictions of various models or methods confirms the superiority of "Stacking" over the alternative methods considered. CONCLUSIONS AND PRACTICAL APPLICATIONS: From a practical standpoint, "stacking" can enhance prediction accuracy (compared to only one base-learner with a particular specification). When applied systemically, stacking can help identify more appropriate countermeasures.

Crash harm before and during the COVID-19 pandemic: Evidence for spatial heterogeneity in Tennessee.

Major concerns have been raised about road safety during the COVID-19 pandemic in the US, as the crash fatalities have increased, despite the substantial reduction in traffic. However, a comprehensive analysis of safety-critical events on roadways based on a broader set of traffic safety metrics and their correlates is needed. In addition to fatalities, this study uses changes in total crashes and total monetary harm as additional measures of safety. A comprehensive and unique time-series database of crashes and socio-economic variables is created at the county level in Tennessee. Statistics show that while fatal crashes increase by 8.2%, total crashes decrease by 15.3%, and the total harm cost is lower by about $1.76 billion during COVID-19 (2020) compared with pre-COVID-19 conditions (2019). Several models, including generalized least squares linear, Poisson, and geographically weighted regression models using the differences between 2020 and 2019 values, are estimated to rigorously quantify the correlates of fatalities, crashes, and crash harm. The results indicate that compared to the pre-pandemic periods, fatal crashes that occurred during the pandemic are associated with more speeding & reckless behaviors and varied across jurisdictions. Fatal crashes are more likely to happen on interstates and dark-not-lighted roads and involve commercial trucks. These same factors largely contribute to crash harm. In addition, a greater number of long trips per person not staying home during COVID-19 is found to be associated with more crashes and crash harm. These results can inform policymaking to strengthen traffic law enforcement through appropriate countermeasures, such as the placement of warning signs and the reduction of the speed limit in hotspots.

Advancing investigation of automated vehicle crashes using text analytics of crash narratives and Bayesian analysis.

Vehicle automation, manifested in self-driving cars, promises to provide safe mobility by reducing human errors. While the testing of automated vehicles (AVs) has improved their performance in recent years, automation technologies face challenges such as uncertainty of safety impacts in mixed traffic with human-driven vehicles. This study aims to examine the gaps in AV safety performance and identify what will be required on a preferential basis for AVs to guarantee an acceptable level of safety performance, especially in mixed traffic, by conducting a thorough analysis of crashes involving levels 2-3 AVs. Based on 260 AV collision reports from California from 2019 to 2021, this study extracts crash-related variables from crash records in a standardized form, crash locations, and, notably, crash narratives reported by AV manufacturers. This study untangles the complex interrelationships among pre-crash conditions, AV driving modes, crash types, and crash outcomes by applying a path-analytic framework with the frequentist and Bayesian approaches. Results show that 51.9 percent of crashes were rear-ends. Particularly, AVs become more vulnerable to rear-end collisions in the automated driving mode than in the conventional mode, given a crash. Additionally, the automated driving mode would not significantly affect the chance of a sideswipe collision, injury, or AV damage levels. Another interesting finding is that manual disengagement is more likely to happen when an AV interacts with a transit vehicle right before a crash occurs while having a negative relationship with injury crashes. Moreover, to reduce injury crashes, AVs would need more thorough testing to adapt to the critical roadway and infrastructure features such as intersections, ramps, and slip lanes; and roadway infrastructure would require improvements to support transportation automation. The risk factors identified in this study can be considered in AV safety assessment scenarios and future operations of mixed traffic. This study demonstrates that AV crash narrative data can be leveraged to improve knowledge of AV safety in mixed traffic.

Exploring pathways from driving errors and violations to crashes: The role of instability in driving.

This study explores how different driving errors, violations, and roadway environments contribute to safety-critical events through instability in driving speed. We harness a subsample (N = 9239) of the naturalistic driving study (NDS) data collected through the Second Strategic Highway Research Program (SHRP2). From a methodological standpoint, we use the safe systems approach relying on path analysis to jointly model outcomes. This accounts for the potential correlation between unobserved factors associated with both instability in driving speed and epoch (video stream) outcomes, i.e., baseline or event-free driving, near-crashes, and crashes. Tobit and ordered Probit regressions are estimated to model the coefficient of variation (COV) of speed and epoch outcomes, respectively. Results from the Tobit model indicate that driving errors and violations are associated with instability in the driving speed of the subject driver (COV of speed). The Probit model reveals that driving errors, violations, and instability in driving speed are associated with higher chances of crashes and near-crashes. Our key finding is that driving errors and violations not only induce event risk directly but also indirectly through instability in driving speed. For instance, recognition errors associate with higher crash risk by 6.78 % but this error is accompanied by instability in driving speed, which further increases event risk by 4.73 %, bringing the total increase in risk to 11.51 %. Moreover, significant correlations were found between unobserved factors reflected in the error terms of the two models. Ignoring such correlations can lead to inefficient parameter estimates. Based on the findings, practical implications are discussed, which can lead to effective countermeasures that effectively reduce crash risk.

Predicting intersection crash frequency using connected vehicle data: A framework for geographical random forest.

Accurate crash frequency prediction is critical for proactive safety management. The emerging connected vehicles technology provides us with a wealth of vehicular motion data, which enables a better connection between crash frequency and driving behaviors. However, appropriately dealing with the spatial dependence of crash frequency and multitudinous driving features has been a difficult but critical challenge in the prediction process. To this end, this study aims to investigate a new Artificial Intelligence technique called Geographical Random Forest (GRF) that can address spatial heterogeneity and retain all potential predictors. By harnessing more than 2.2 billion high-resolution connected vehicle Basic Safety Message (BSM) observations from the Safety Pilot Model Deployment in Ann Arbor, MI, 30 indicators of driving volatility are extracted, including speed, longitudinal and lateral acceleration, and yaw rate. The developed GRF was implemented to predict rear-end crash frequency at intersections. The results show that: 1) rear-end crashes are more likely to happen at intersections connecting minor roads compared to major roads; 2) a higher number of hard acceleration and deceleration events beyond two standard deviations in the longitudinal direction is a leading indicator of rear-end crashes; 3) the optimal GRF significantly outperforms Global Random Forest, with a 9% lower test error and a substantially better fit; and 4) geographical visualization of variable importance highlights the presence of spatial non-stationarity. The proposed framework can proactively identify at-risk intersections and alert drivers when leading indicators of driving volatility tend to worsen.

Incorporating driving volatility measures in safety performance functions: Improving safety at signalized intersections.

About 40 percent of motor vehicle crashes in the US are related to intersections. To deal with such crashes, Safety Performance Functions (SPFs) are vital elements of the predictive methods used in the Highway Safety Manual. The predictions of crash frequencies and potential reductions due to countermeasures are based on exposure and geometric variables. However, the role of driving behavior factors, e.g., hard accelerations and declarations at intersections, which can lead to crashes, are not explicitly treated in SPFs. One way to capture driving behavior is to harness connected vehicle data and quantify performance at intersections in terms of driving volatility measures, i.e., rapid changes in speed and acceleration. According to recent studies, driving volatility is typically associated with higher risk and safety-critical events and can serve as a surrogate for driving behavior. This study incorporates driving volatility measures in the development of SPFs for four-leg signalized intersections. The Safety Pilot Model Deployment (SPMD) data containing over 125 million Basic Safety Messages generated by over 2,800 connected vehicles are harnessed and linked with the crash, traffic, and geometric data belonging to 102 signalized intersections in Ann Arbor, Michigan. The results show that including driving volatility measures in SPFs can reduce model bias and significantly enhances the models' goodness-of-fit and predictive performance. Technically, the best results were obtained by applying Bayesian hierarchical Negative Binomial Models, which account for spatial correlation between signalized intersections. The results of this study have implications for practitioners and transportation agencies about incorporating driving behavior factors in the development of SPFs for greater accuracy and measures that can potentially reduce volatile driving.

Understanding the role of faster emergency medical service response in the survival time of pedestrians.

Fatalities and severe injuries among vulnerable road users, particularly pedestrians, are rising. In addition to the loss of life, about 6,000 annual pedestrian deaths in the U.S. cost society about $6 billion. Contrary to the assumption that all fatal pedestrian-involved crashes are similar, instantaneous death is substantially more severe than death that occurs several days after the crash. Instead of homogenizing all fatal pedestrian crashes, this study takes into account the severity of fatal injury crashes as a timeline based on the survival time of pedestrians. This study extracts valuable information from fatal crashes by examining pedestrians' survival time ranging from early death to death within 30 days of the crash. The Fatality Analysis Reporting System dataset is utilized from 2015 to 2018. The emergency medical service (EMS) response time is the key post-crash measure, while controlling for pedestrian, driver, roadway, and environmental characteristics. Notably, the response time and survival time can cause endogeneity, i.e., the response times may be shorter for more severe crashes. Due to the spatial and temporal nature of traffic crashes, to extract the association of different variables with pedestrians' survival time, a geographically and temporally weighted truncated regression with a two-stage residual inclusion treatment (local model) is estimated. The local model can overcome the endogeneity limitation (between EMS response time and survival time) and uncover the potentially spatially and temporally varying correlates of pedestrians' survival time with associated factors to account for unobserved heterogeneity. Moreover, to verify the variations are noticeable, a truncated regression with the two-stage residual inclusion treatment is developed (global model). The modeling results indicate that while capturing the unobserved heterogeneity, the local model outperformed the global model. The empirical results show that EMS response time, speeding, and some pedestrian behaviors are the most important factors that affect pedestrians' survival time in fatal injury crashes. However, the effect of factors on pedestrians' survival time is noticeably varied spatially and temporally. The results and their implications are discussed in detail in the paper.

How effective are pedestrian crash prevention systems in improving pedestrian safety? Harnessing large-scale experimental data.

Over the past few years, the number of fatalities and severe injuries of vulnerable road users, particularly pedestrians, has risen substantially. Clearly, the safe mobility of pedestrians is critical in our transportation system. Technology can help reduce vehicle-pedestrian crashes, fatalities, and injuries. Emerging technologies such as pedestrian crash prevention (PCP) systems utilized in on-road vehicles have the potential to mitigate pedestrian crash severity or prevent crashes. However, the reliability and effectiveness of these technologies have remained uncertain. This study contributes toward understanding the effectiveness of PCP systems utilized in on-road vehicles with a low level of automation by investigating two crossing and one longitudinal scenarios. The Insurance Institute for Highway Safety field test data from 2018 to 2021 is harnessed, where several on-road vehicles and their PCP systems are evaluated in terms of safety. The large-scale experimental dataset is comprised of 3095 tests of 91 vehicles with different sizes, makes, and models. The empirical results indicate that in hazardous pedestrian-vehicle conflict situations, the performance of PCP systems has been improved during recent years. The test data shows that some pedestrians were undetected in some tests, but on average, in 70% of the tests, the PCP systems avoided pedestrian crashes. However, for the occurred crashes, PCP systems, on average, were able to mitigate impact speeds of >50%. In real-life situations, this could translate to substantial reductions in injury and fatality risk. Through rigorous analysis, the associations of key factors in the studied scenarios and the performance of PCP systems are explored and discussed in this paper. The modeling results show that increasing the maximum deceleration rate of the PCP system and lower weight of vehicles can significantly improve the performance of the PCP system by decreasing the speed at impact with pedestrians. The average maximum deceleration utilized in PCP systems has been increased over time from 7.48 m/s2 in 2018 to 9.36 m/s2 in 2021. This can be one of the reasons behind the improvement of PCP systems during recent years.

Toward better measurement of traffic injuries - Comparison of anatomical injury measures in predicting the clinical outcomes in motorcycle crashes.

INTRODUCTION: Little evidence exists in the literature regarding the discrimination power of better anatomical injury measures in differentiating clinical outcomes in motorcycle crashes. Furthermore, multiple injuries to different body parts of the rider are seldom analyzed. This study focuses on comparing anatomical injury measures such as the injury severity score (ISS) and the new injury severity score (NISS) in capturing injuries of multiple injured riders and examining the discriminatory capabilities of the ISS and NISS in predicting clinical outcomes post motorcycle crash. METHODS: The study harnessed unique and comprehensive injury data on 322 riders from the US DOT Federal Highway Administration's Motorcycle Crash Causation Study (MCCS). Detailed exploratory analysis is performed and discrete/ordered statistical models are estimated for three clinical outcomes: mortality risk, trauma risk, and trauma status. RESULTS: Around 9% of the riders died and 45% of the riders had injuries. Around 36% of the riders were hospitalized, disabled, or institutionalized. While a very strong dependence was found between ISS and NISS, ISS underestimated injuries sustained by riders. Statistical models for mortality risk revealed that a unit increase in the ISS and NISS was correlated with a 1.18 and 1.17 times increase in the odds of mortality, respectively. Moreover, a unit increase in ISS and NISS values was correlated with a higher trauma risk by 1.48 and 1.36 times, respectively. Our analysis reveals that the probability of a rider being hospitalized or disabled/institutionalized increases with an increase in the NISS. Conclusions and practical applications: The NISS exhibits significantly better calibration and discriminatory ability in differentiating survivors and non-survivors and in predicting trauma status - underscoring the importance of accounting for microscopic body-part-level injury data in motorcycle crashes. We consider that compared with the KABCO scale, the ISS and NISS are more nuanced scores that can better measure the overall injury intensity and can lead to more targeted countermeasures.

From the past to the future: Modeling the temporal instability of safety performance functions.

In roadway safety management, safety performance functions (SPFs) are widely used by state and local agencies to predict crashes for base site conditions. SPFs are developed based on historical traffic safety data and are used to make predictions for anticipated site characteristics in the future. An underlying assumption in SPF development is that the relationships between crash frequency and site conditions are stationary from the past (when the model data were collected) to the future (for which SPFs are applied). The assumption using the past to represent the future could be fundamentally problematic. This study proposes a modeling framework that can relax this assumption. Specifically, this framework integrates temporal modeling with time-series analysis to strengthen the current SPF estimation methods. The temporal modeling approach is Temporally Weighted Negative Binomial Regression (TWNBW), and the time-series analysis is tried by employing the Seasonal Autoregressive Integrated Moving Average (SARIMA) and Artificial Neural Networks (ANN) methods. The temporal modeling is to uncover the temporal variations of SPFs and the time-series analysis explains and predicts the relationship between the SPF's temporal variation and time. The outcome of the framework is a set of Future SPFs that capture the temporal unobserved heterogeneity in safety data and describe the predicted relationships between safety performance and site characteristics in the future. A case study using six-year safety datasets from Georgia was conducted to illustrate the key components of the modeling framework. The temporal modeling results showed significant variations in SPFs across time. The parameters for traffic volume, i.e., Average Annual Daily Traffic (AADT), and segment length are associated with an increasing trend with time, and for access point density there is a descending trend. The SPF parameters are found to have a strong seasonality. Both time-series modeling methods appear to be appropriate to explain the temporal variations of SPF parameters, and the models are able to predict SPF parameters with acceptable errors smaller than 1% on average. Future SPFs can be used to support the roadway safety management that affects future traffic safety performance.

Analyzing drivers' hazard recognition: Precursors to single-vehicle collisions.

Extensive driver behavior and performance information provided by real-world video surveillance and sensor data in the SHRP2 Naturalistic Driving Study has enabled the examination of new layers and pathways leading to crash outcomes. We note that the prominence of hazards and the importance of recognizing them vary systematically across single vs. multi-vehicle crashes, and address a fundamental question about safety: why do around three-quarters of drivers involved in single-vehicle crashes not recognize, perceive, or react to the precipitating event (PE)? Using a path-analytic framework through marginal effects, this study investigates factors correlated to recognition of the PE in single-vehicle events, and how these correlations may act as crash precursors. Logit models, accounting for heterogeneity among events and drivers by estimating both fixed and random parameters, quantified correlations among key variables, given a crash or near-crash event (N = 543). The type of PE, roadway environment factors, and driving maneuvers heavily influenced recognition chances. Drivers had a harder time recognizing less conspicuous hazards (e.g. departing the travel way, decreased recognition chances by 48.29%), but seemed better at recognizing prominent hazards (e.g. vehicle losing control, increased recognition chances by 46.71%). In addition, drivers are less likely to recognize PEs when executing less involved driving maneuvers in more relaxed environments, such as daylight (decreased recognition chances by 16.00%), but are more adept in environments that already demand more attention. Recognition reduced the chances of a crash by 12.23%, so we found similar correlations with crash outcome. Future intelligent transportation systems may focus on increasing driver recognition of potential hazards by bringing attention to less conspicuous hazards and less involved driving environments and actions.

Built environment, driving errors and violations, and crashes in naturalistic driving environment.

Driving errors and violations are highly relevant to the safe systems approach as human errors tend to be a predominant cause of crash occurrence. In this study, we harness highly detailed pre-crash Naturalistic Driving Study (NDS) data 1) to understand errors and violations in crash, near-crash, and baseline (no event) driving situations, and 2) to explore pathways that lead to crashes in diverse built environments by applying rigorous modeling techniques. The "locality" factor in the NDS data provides information on various types of roadway and environmental surroundings that could influence traffic flow when a precipitating event is observed. Coded by the data reductionists, this variable is used to quantify the associations of diverse environments with crash outcomes both directly and indirectly through mediating driving errors and violations. While the most prevalent errors in crashes were recognition errors such as failing to recognize a situation (39 %) and decision errors such as not braking to avoid a hazard (34 %), performance errors such as poor lateral or longitudinal control or weak judgement (8 %) were most strongly correlated with crash occurrence. Path analysis uncovered direct and indirect relationships between key built-environment factors, errors and violations, and crash propensity. Possibly due to their complexity for drivers, urban environments are associated with higher chances of crashes (by 6.44 %). They can also induce more recognition errors which correlate with an even higher chances of crashes (by 2.16 % with the "total effect" amounting to 8.60 %). Similar statistically significant mediating contributions of recognition errors and decision errors near school zones, business or industrial areas, and moderate residential areas were also observed. From practical applications standpoint, multiple vehicle technologies (e.g., collision warning systems, cruise control, and lane tracking system) and built-environment (roadway) changes have the potential to reduce driving errors and violations which are discussed in the paper.

Understanding how relationships between crash frequency and correlates vary for multilane rural highways: Estimating geographically and temporally weighted regression models.

Safety Performance Functions (SPFs) are critical tools in the management of highway safety projects. SPFs are used to predict the average number of crashes per year at a location, such as a road segment or an intersection. The Highway Safety Manual (HSM) provides default safety performance functions (SPFs), but it is recommended that states in the U.S. develop jurisdiction-specific SPFs using local crash data. To do this for the state of Tennessee, crash and road inventory data were integrated for multi-lane rural highway segments for the years 2013-2017. In addition to developing SPFs similar to those contained in the HSM, this study applied a new methodology to capture variation in crashes in both space and time. Specifically, Geographically and Temporally Weighted Regression (GTWR) models for the localization of SPFs were developed. The new methodology incorporates temporal aspects of crashes in the models because the impact of a specific variable on crash frequency may vary over time due to several reasons. Results indicate that GTWR models remarkably outperform the traditional regression models by capturing spatio-temporal heterogeneity. Most parameter estimates were found to vary substantially across space and time. In other words, the association of contributing variables with the number of crashes can vary from one region or period of time to another. This finding weakens the idea of transferring default SPFs to other states and applying a single localized SPF to all regions of a state. Enabled by growing computational power, these results emphasize the importance of accounting for spatial and temporal heterogeneity and developing highly localized SPFs. The methodology of this study can be used by researchers to follow the temporal trend and location of critical factors to identify sites for safety improvements.

Investigating the relation between instantaneous driving decisions and safety critical events in naturalistic driving environment.

The availability of large-scale naturalistic driving data provides enormous opportunities for studying relationships between instantaneous driving decisions prior to involvement in safety critical events (SCEs). This study investigates the role of driving instability prior to involvement in SCEs. While past research has studied crash types and their contributing factors, the role of pre-crash behavior in such events has not been explored as extensively. The research demonstrates how measures and analysis of driving volatility can be leading indicators of crashes and contribute to enhancing safety. Highly detailed microscopic data from naturalistic driving are used to provide the analytic framework to rigorously analyze the behavioral dimensions and driving instability that can lead to different types of SCEs such as roadway departures, rear end collisions, and sideswipes. Modeling results reveal a positive association between volatility and involvement in SCEs. Specifically, increases in both lateral and longitudinal volatilities represented by Bollinger bands and vehicular jerk lead to higher likelihoods of involvement in SCEs. Further, driver behavior related factors such as aggressive driving and lane changing also increases the likelihood of involvement in SCEs. Driver distraction, as represented by the duration of secondary tasks, also increases the risk of SCEs. Likewise, traffic flow parameters play a critical role in safety risk. The risk of involvement in SCEs decreases under free flow traffic conditions and increases under unstable traffic flow. Further, the model shows prediction accuracy of 88.1 % and 85.7 % for training and validation data. These results have implications for proactive safety and providing in-vehicle warnings and alerts to prevent the occurrence of such SCEs.

Integration of automated vehicles in mixed traffic: Evaluating changes in performance of following human-driven vehicles.

The introduction of Automated Vehicles (AVs) into the transportation network is expected to improve system performance, but the impacts of AVs in mixed traffic streams have not been clearly studied. As AV's market penetration increases, the interactions between conventional vehicles and AVs are inevitable but by no means clear. This study aims to create new knowledge by quantifying the behavioral changes caused when conventional human-driven vehicles follow AVs and investigating the impact of these changes (if any) on safety and the environment. This study analyzes data obtained from a field experiment by Texas A&M University to evaluate the effects of AVs on the behavior of a following human-driver. The dataset is comprised of nine drivers that attempted to follow 5 speed-profiles, with two scenarios per profile. In scenario one, a human-driven vehicle follows an AV that implements a human driver speed profile (base). In scenario two, the human-driven vehicle follows an AV that executes an AV speed profile. In order to evaluate safety, these scenarios are compared using time-to-collision (TTC) and several other driving volatility measures. Likewise, fuel consumption and emissions are used to investigate environmental impacts. Overall, the results show that AVs in mixed traffic streams can induce behavioral changes in conventional vehicle drivers, with some beneficial effects on safety and the environment. On average, a driver that follows an AV exhibits lower driving volatility in terms of speed and acceleration, which represents more stable traffic flow behavior and lower crash risk. The analysis showed a remarkable improvement in TTC as a result of the notably better speed adjustments of the following vehicle (i.e., lower differences in speeds between the lead and following vehicles) in the second scenario. Furthermore, human-driven vehicles were found to consume less fuel and produce fewer emissions on average when following an AV.

Safety critical event prediction through unified analysis of driver and vehicle volatilities: Application of deep learning methods.

Transportation safety is highly correlated with driving behavior, especially human error playing a key role in a large portion of crashes. Modern instrumentation and computational resources allow for the monitorization of driver, vehicle, and roadway/environment to extract leading indicators of crashes from multi-dimensional data streams. To quantify variations that are beyond normal in driver behavior and vehicle kinematics, the concept of volatility is applied. The study measures driver-vehicle volatilities using the naturalistic driving data. By integrating and fusing multiple real-time streams of data, i.e., driver distraction, vehicular movements and kinematics, and instability in driving, this study aims to predict occurrence of safety critical events and generate appropriate feedback to drivers and surrounding vehicles. The naturalistic driving data is used which contains 7566 normal driving events, and 1315 severe events (i.e., crash and near-crash), vehicle kinematics, and driver behavior collected from more than 3500 drivers. In order to capture the local dependency and volatility in time-series data 1D-Convolutional Neural Network (1D-CNN), Long Short-Term Memory (LSTM), and 1DCNN-LSTM are applied. Vehicle kinematics, driving volatility, and impaired driving (in terms of distraction) are used as the input parameters. The results reveal that the 1DCNN-LSTM model provides the best performance, with 95.45% accuracy and prediction of 73.4% of crashes with a precision of 95.67%. Additional features are extracted with the CNN layers and temporal dependency between observations is addressed, which helps the network learn driving patterns and volatile behavior. The model can be used to monitor driving behavior in real-time and provide warnings and alerts to drivers in low-level automated vehicles, reducing their crash risk.

A taxonomy of driving errors and violations: Evidence from the naturalistic driving study.

Driving errors and violations are identified as contributing factors in most crash events. To examine the role of human factors and improve crash investigations, a systematic taxonomy of driver errors and violations (TDEV) is developed. The TDEV classifies driver errors and violations based on their occurrence during the theoretically based perception-reaction process and analyzes their contributions in safety critical events. To empirically explore errors and violations, made by drivers of instrumented vehicles, in diverse built environments, this study harnesses unique and highly detailed pre-crash sensor data collected in the Naturalistic Driving Study (NDS), containing 673 crashes, 1,331 near-crashes and 7,589 baselines (no-event). Human factors are categorized into recognition errors, decision errors, performance errors, and errors due to the drivers' physical condition or their lack of contextual experience/familiarity, and intentional violations. In the NDS data, built environments (measured by roadway localities) are classified based on roadway functional classification and land uses, e.g., residential areas, school zones, and church zones. Based on the crash percentage to baseline percentage in a specific locality, interstates and open country/open residential (rural and semi-rural settings) may pose lower risks, while urban, business/industrial, and school zone locations showed higher crash risk. Human errors and violations by instrumented vehicle drivers contributed to 93% of the observed crashes, while roadway factors contributed to 17%, vehicle factors contributed in 1%, and 4% of crashes contained unknown factors. The most common human errors were recognition and decision errors, which occurred in 39% and 34% of crashes, respectively. These two error types occurred more frequently (each contributing to nearly 39% of crashes) in business or industrial land use environments (but not in dense urban localities). The findings of this study reveal continued prevalence of human factors in crashes. The distribution of driving errors and violations across different roadway environments can aid in the implementation of driver assistance systems and place-based interventions that can potentially reduce these driving errors and violations.