Search

As a key area of traffic safety research, crash severity modelling has attracted tremendous attention. Recently, there has been growing interest in applying machine learning (ML) methods in this ar...

Emerging automated vehicle (AV) technologies are increasingly being deployed around the world and it is only a matter of time before the transportation landscape changes dramatically. Unfortunately, those changes cannot be well predicted due to the lack of empirical data. But adaptive cruise control (ACC) vehicles are common in the market and can be used to fill this gap. In this paper, we aim to characterize the empirical car-following behaviors of a commercial ACC system and understand how ACC behaves in different conditions and the underlying impact mechanism. It is found that for a single ACC: (i) the ACC response time is comparable to human drivers but much larger than the ACC controller time gap and it exhibits small variance, (ii) the ACC response can amplify or dampen an oscillation, (iii) after the oscillation, the stabilization process can exhibit overshooting or undershooting, and (iv) these CF behaviors depend largely on the ACC headway setting, speed level, and leader stimulus, which produce the impacts directly and/or indirectly through the mediation of earlier ACC behaviors. For a three-vehicle platoon, our main finding is that the change from one ACC vehicle to the next is progressive for oscillation growth, and regressive for deceleration, acceleration, and overshooting. This implies that in long platoons, oscillation amplitude tends to exacerbate very quickly, which forces ACC vehicles further upstream to apply very strong braking followed by a strong acceleration. This can cause significant overshooting and safety hazards.

Given the aging infrastructure and the anticipated growing number of highway work zones in the United States, it is important to investigate methods to improve work zone mobility and safety. Data s...

Crash severity has been extensively studied and numerous methods have been developed for investigating the relationship between crash outcome and explanatory variables. Crash severity data are ofte...

Given the aging infrastructure and the anticipated growing number of highway work zones in the United States, it is important to investigate work zone merge control, which is critical for improving work zone safety and capacity. This paper proposes and evaluates a novel highway work zone merge control strategy based on cooperative driving behavior enabled by artificial intelligence. The proposed method assumes that all vehicles are fully automated, connected and cooperative. It inserts two metering zones in the open lane to make space for merging vehicles in the closed lane. In addition, each vehicle in the closed lane learns how to optimally adjust its longitudinal position to find a safe gap in the open lane using an off-policy soft actor critic (SAC) reinforcement learning (RL) algorithm, considering the traffic conditions in its surrounding. The learning results are captured in convolutional neural networks and used to control individual vehicles in the testing phase. By adding the metering zones and taking the locations, speeds, and accelerations of surrounding vehicles into account, cooperation among vehicles is implicitly considered. This RL-based model is trained and evaluated using a microscopic traffic simulator. The results show that this cooperative RL-based merge control significantly outperforms popular strategies such as late merge and early merge in terms of both mobility and safety measures., Comment: 17pages, 6 figures, TRB 2020

Machine learning (ML) model interpretability has attracted much attention recently given the promising performance of ML methods in crash frequency studies. Extracting accurate relationship between risk factors and crash frequency is important for understanding the causal effects of risk factors and developing safety countermeasures. However, there is no study that comprehensively summarizes ML model interpretation methods and provides guidance for safety researchers and practitioners. This research aims to fill this gap. Model-based and post-hoc ML interpretation methods are critically evaluated and compared to study their suitability in crash frequency modeling. These methods include classification and regression tree (CART), multivariate adaptive regression splines (MARS), Local Interpretable Model-agnostic Explanations (LIME), Local Sensitivity Analysis (LSA), Partial Dependence Plots (PDP), Global Sensitivity Analysis (GSA), and SHapley Additive exPlanations (SHAP). Model-based interpretation methods cannot reveal the detailed interaction relationships among risk factors. LIME can only be used to analyze the effects of a risk factor at the prediction level. LSA and PDP assume that different risk factors are independently distributed. Both GSA and SHAP can account for the potential correlation among risk factors. However, only SHAP can visualize the detailed relationships between crash outcomes and risk factors. This study also demonstrates the potential and benefits of using ML and SHAP to derive Crash Modification Factors (CMF). Finally, it is emphasized that statistical and ML models may not directly differentiate causation from correlation. Understanding the differences between them is critical for developing reliable safety countermeasures.

This chapter summarizes the presentations of speakers addressing such issues during the Automated Vehicles Symposium 2020 (AVS20) held virtually on July 27–30, 2020. These speakers participated in the break-out session titled “Artificial Intelligence for Automated Vehicle Control and Traffic Operations: Challenges and Opportunities”. The corresponding discussion and recommendations are presented in terms of the lessons learned and the future research directions to be adopted to benefit from AI in order to develop safer and more efficient connected and automated vehicles (CAV). This session was organized by the Transportation Research Board (TRB) Committee on Traffic Flow Theory and Characteristics (ACP50) and the TRB Committee on Artificial Intelligence and Advanced Computing Applications (AED50).

Stop-and-go traffic poses significant challenges to the efficiency and safety of traffic operations, and its impacts and working mechanism have attracted much attention. Recent studies have shown that Connected and Automated Vehicles (CAVs) with carefully designed longitudinal control have the potential to dampen the stop-and-go wave based on simulated vehicle trajectories. In this study, Deep Reinforcement Learning (DRL) is adopted to control the longitudinal behavior of CAVs and real-world vehicle trajectory data is utilized to train the DRL controller. It considers a Human-Driven (HD) vehicle tailed by a CAV, which are then followed by a platoon of HD vehicles. Such an experimental design is to test how the CAV can help to dampen the stop-and-go wave generated by the lead HD vehicle and contribute to smoothing the following HD vehicles’ speed profiles. The DRL control is trained using real-world vehicle trajectories, and eventually evaluated using SUMO simulation. The results show that the DRL control decreases the speed oscillation of the CAV by 54% and 8%-28% for those following HD vehicles. Significant fuel consumption savings are also observed. Additionally, the results suggest that CAVs may act as a traffic stabilizer if they choose to behave slightly altruistically.

Understanding and quantifying the effects of risk factors on crash frequency is of great importance for developing cost-effective safety countermeasures. In this paper, the effects of key crash contributing factors on total crashes and crashes of different collision types are analyzed separately and compared. A novel Machine Learning (ML) method, Light Gradient Boosting Machine (LightGBM), is introduced to model a Texas dataset consisting of vehicle crashes occurred from 2015 to 2017. Compared with other commonly used ML methods such as eXtreme Gradient Boosting (XGBoost), LightGBM performs significantly better in terms of mean absolute error (MAE) and root mean squared error (RMSE). In addition, the SHapley Additive explanation (SHAP) approach is employed to interpret the LightGBM outputs. Significant risk factors are identified, including speed limits, area type, number of lanes, roadway functional class, shoulder width and shoulder type. With the SHAP method, the importance, total effects, and main and interaction effects of risk factors are quantified. The results suggest that the importance of risk factors vary across collision types. Speed limit is a more important risk factor than right/left shoulder width, lane width, and median width for Rear-End (RE) crashes, while the opposite relationship is found for Run-Off-Road (ROR) crashes. Also, it is found that narrow lanes (8ft to 11ft) increase the risk for all types of crashes (i.e., Total, ROR, and RE) in this study. For road segments with 5 or 6 lanes in both directions combined, a lane width greater than or equal to 12ft may help reduce the risk of all types of crashes. These results have important implications for developing accurate crash modification factors and cost-effective safety countermeasures.

Experimental measurements on commercial adaptive cruise control (ACC) vehicles \RoundTwo{are} becoming increasingly available from around the world, providing an unprecedented opportunity to study the traffic flow characteristics that arise from this technology. This paper adds new experimental evidence to this knowledge base and presents a comprehensive empirical study on the ACC equilibrium behaviors via the resulting fundamental diagrams. We find that like human-driven vehicles, ACC systems display a linear equilibrium spacing-speed relationship (within the range of available data) but the key parameters of these relationships can differ significantly from human-driven traffic depending on input settings: At the minimum headway setting, equilibrium capacities in excess of 3500 vehicles per hour are observed, together with an extremely fast equilibrium wave speed of 100 kilometers per hour on average. These fast waves are unfamiliar to human drivers, and may pose a safety risk. The results also suggest that ACC jam spacing can be much larger than in human traffic, which reduces the network storage capacity.

Surrogate Safety Measures (SSM) are important for safety performance evaluation, since crashes are rare events and historical crash data does not capture near crashes that are also critical for improving safety. This paper focuses on SSM and their applications, particularly in Connected and Automated Vehicles (CAV) safety modeling. It aims to provide a comprehensive and systematic review of significant SSM studies, identify limitations and opportunities for future SSM and CAV research, and assist researchers and practitioners with choosing the most appropriate SSM for safety studies. The behaviors of CAV can be very different from those of Human-Driven Vehicles (HDV). Even among CAV with different automation/connectivity levels, their behaviors are likely to differ. Also, the behaviors of HDV can change in response to the existence of CAV in mixed autonomy traffic. Simulation by far is the most viable solution to model CAV safety. However, it is questionable whether conventional SSM can be applied to modeling CAV safety based on simulation results due to the lack of sophisticated simulation tools that can accurately model CAV behaviors and SSM that can take CAV's powerful sensing and path prediction and planning capabilities into crash risk modeling, although some researchers suggested that proper simulation model calibration can be helpful to address these issues. A number of critical questions related to SSM for CAV safety research are also identified and discussed, including SSM for CAV trajectory optimization, SSM for individual vehicles and vehicle platoon, and CAV as a new data source for developing SSM.

Traditional progression band optimization methods are focused on providing uninterrupted flow along arterial streets. For arterials with significant traffic streams joining and leaving from side streets, these approaches often generate poor traffic signal control performance. To address this deficiency, an origin–destination (OD) information based progression band optimization model, OD-BAND, was formulated to coordinate signals for arterials with major side-street traffic streams. This paper aims to extend the OD-BAND model further to address the OD based traffic signal coordination problem in multi-arterial grid networks. The extended model is able to create separate progression bands for each major OD stream in the network. In this expanded model, individual arterials are connected with loop constraints to ensure that offsets derived via different paths for a particular intersection are equal. The new OD-NETBAND model is formulated as a mixed integer linear program that maximizes the sum of each major OD stream’s progression bandwidth. It can optimize simultaneously cycle length, offsets, and phase sequences for the entire network. Performance of the new model is evaluated with AIMSUN microscopic simulation and is compared with MAXBAND-86 and Synchro results.

Approximately 35,000 fatalities are attributed to accidents on U.S. highways each year and more than half of them occurred in rural areas. With such a high percentage of fatalities, rural areas are in critical need of timely and reliable Emergency Medical Services (EMS). EMS provide important prehospital care to victims before they are transferred to a hospital. After an accident occurs, the time it takes for victims to receive care from EMS is crucial to their survival. Compared with urban EMS, rural EMS face multiple challenges. One of them is how to properly site EMS stations to provide cost-effective services in rural areas. The goals of this paper include analyzing the spatial patterns of EMS station and incident locations, and optimizing rural EMS station locations. The data were collected from South Dakota, a rural state. This dataset was used to perform spatial analysis and to develop and evaluate an EMS location optimization model. The location optimization model aims to maximize the rural EMS coverage while taking service equity into consideration. The model was solved by a genetic algorithm toolbox in R. The proposed model provides an important and practical tool for rural EMS officials to select new EMS stations or relocate existing stations to improve service performance under budget and resource constraints.

In a connected vehicle environment, vehicles are able to communicate and exchange detailed information such as speed, acceleration, and position in real time. Such information exchange is important for improving traffic safety and mobility. This allows vehicles to collaborate with each other, which can significantly improve traffic operations particularly at intersections and freeway ramps. To assess the potential safety and mobility benefits of collaborative driving enabled by connected vehicle technologies, this study developed an optimization-based ramp control strategy and a simulation evaluation platform using VISSIM, MATLAB, and the Car2X module in VISSIM. The ramp control strategy is formulated as a constrained nonlinear optimization problem and solved by the MATLAB optimization toolbox. The optimization model provides individual vehicles with step-by-step control instructions in the ramp merging area. In addition to the optimization-based ramp control strategy, an empirical gradual speed l...

A hanging tie is a form of railroad track distress that occurs when voids have developed beneath the ties due to uneven ballast settlement and improper maintenance practices. It will lead to an increase in dynamic impact loading on the top of the ballast thereby further deteriorating the track structure. This paper proposes a fast, nondestructive screening method to identify the hanging tie problem. The method utilizes a dynamic track model to characterize the track’s “moving deflection spectrum” under different tie-supporting scenarios. The model includes a moving dynamic load and ties with discrete supports. The moving deflection spectrum shows dynamic responses of the “track moving deflection” in the frequency domain. The modeling results indicate that a significant discrepancy exists in the moving deflection spectrum depending on whether or not there is a hanging tie condition. To validate this method, preliminary field tests were carried out on both Boston Metro and St. Louis Metro lines. Then the moving deflection spectrum generated by the model is compared with the moving deflection spectrum in the field tests as measured by the accelerometers installed on a high-rail vehicle. Results show that the method is effective in identifying the hanging tie problem and has great potential to be employed by the rail industry in the future.

OD-BAND is a progression optimization model that can provide dedicated progression bands for major origin–destination (O-D) flows in an arterial network. The model is an extension of the well-known MAXBAND model and is solved by advanced mathematical programming optimization software. In this paper, the original OD-BAND model is extended in a number of important ways: ( a) the mathematical formulation is generalized to model all possible O-D flows in an arterial; ( b) phase sequence optimization is included for all intersections along the arterial; and ( c) the bandwidths are weighted by the number of street segments that they traverse and their traffic volumes. It is shown that this formulation can provide suitable progression bands for all major O-D flows, including both through bands and cross bands. Simulation results demonstrated that OD-BAND compared favorably with existing arterial traffic signal coordination models MAXBAND and MULTIBAND and could be used as a valuable tool in signal control software. In particular, this approach is most suitable for integrated traffic signal coordination and route guidance in an environment of connected vehicles in which connected vehicles and crowd-sourced data can be used to derive detailed and accurate O-D information. Progression bands can then be established for each major O-D flow, and route guidance can be provided to vehicles to travel within those bands with minimum delay and fuel consumption.

Commercial large truck crashes are more likely to involve fatalities and significant costs than passenger vehicle crashes are. To reduce fatigue-related crashes of large trucks caused by drivers' irregular work schedules, FMCSA has enforced hours-of-service rules to regulate the activities of drivers of commercial large trucks. The complex influence of drivers' multiday driving activity patterns on crash risk was examined with data collected from two national truckload carriers. A machine learning approach, k-means clustering, was used to classify large truck drivers into 10 clusters according to their 15-min driving activities over multiple days. Then, the crash risk and driving activity pattern were identified for each cluster. Discrete-time logistic regression models were used to quantify the relationships between driving activity patterns and crash risk. Results indicated that the driving pattern with the lowest crash risk could be daytime driving between 4:00 a.m. and noon, with rest breaks in the late afternoon (4:00 to 6:00 p.m.). Drivers with high proportions of afternoon on-duty time after a long off-duty period experienced significantly higher crash risk. A representative day concept is proposed as a complementary method to identify relationships between driving patterns and crash risk. Moreover, on-duty hours can be a useful indicator of crash risk for drivers of large trucks. High proportions of on-duty hours in the early morning and late afternoon often are associated with high crash risk.

Data plays a critical role in the safety of all transportation modes (e.g., air, railroad, and highway). This chapter focuses specifically on highway traffic safety. Studies on highway traffic safety cover a variety of topics, including human factors, crash count/frequency modeling, safety effectiveness evaluation (e.g., before and after study), economic appraisal, hot spot analysis, and injury severity modeling. In this chapter, an overview of existing highway traffic safety research will be provided first. Based on this overview, various methodologies that have been adopted in these studies will be discussed and summarized. Since almost all these safety studies rely heavily on data and data analytics, a detailed discussion of available data for highway traffic safety applications and their limitations is presented. In addition, this chapter discusses potential new data sources enabled by various big data initiatives and recent advancements in Intelligent Transportations Systems (ITS), such as Connected and Autonomous Vehicles (CAVs).