A model for exploring the relationship between payment structures,fatigue, crash risk,and regulatory response in a heavy-vehicle transport system

Investigations of heavy vehicle crashes have predominantly taken a reductionist view of accident causation. However, there is growing recognition that broader economic factors play a significant role in producing conditions that exacerbate crash risk, especially in the area of fatigue. The aim of this study was to determine whether agent-based modelling (ABM) may be usefully applied to explore the effect of driver payment methods on driver fatigue, crash-risk, and the response of enforcement agencies to major heavy-vehicle crashes. Simulation results showed that manipulation of payment methods within agent-based models can produce similar patterns of behaviour among simulated drivers as that observed in real world studies. Simulated drivers operating under ‘per-km’ and ‘per-trip’ piece rate incentive systems were significantly more likely to drive while fatigued and subsequently incur all associated issues (loss of license, increased crash risk, increased fines) than those paid under ‘flat-rate’ wage conditions. Further, the pattern of enforcement response required under ‘per-km’ and ‘per-trip’ systems was significantly higher in response to greater numbers of major crashes than in flat-rate regimes. With further refinement and collaborative design, ABMs may prove useful in studying the potential effects of economic policy settings within freight or other transport systems ahead of time.     

Computational methodology to predict injury risk for motor vehicle crash victims: A framework for improving Advanced Automatic Crash Notification systems

Advanced Automatic Crash Notification (AACN) systems, capable of predicting post-crash injury severity and subsequent automatic transfer of injury assessment data to emergency medical services, may significantly improve the timeliness, appropriateness, and efficacy of care provided. The estimation of injury severity based on statistical field data, as incorporated in current AACN systems, lack specificity and accuracy to identify the risk of life-threatening conditions. To enhance the existing AACN framework, the goal of the current study was to develop a computational methodology to predict risk of injury in specific body regions based on specific characteristics of the crash, occupant and vehicle. The computational technique involved multibody models of the vehicle and the occupant to simulate the case-specific occupant dynamics and subsequently predict the injury risk using established physical metrics. To demonstrate the computational-based injury prediction methodology, three frontal crash cases involving adult drivers in passenger cars were extracted from the US National Automotive Sampling System Crashworthiness Data System. The representative vehicle model, anthropometrically scaled model of the occupant and kinematic information related to the crash cases, selected at different severities, were used for the blinded verification of injury risk estimations in five different body regions. When compared to existing statistical algorithms, the current computational methodology is a significant improvement toward post-crash injury prediction specifically tailored to individual attributes of the crash. Variations in the initial posture of the driver, analyzed as a pre-crash variable, were shown to have a significant effect on the injury risk.     

Effects of crash warning systems on rear-end crash avoidance behavior under fog conditions

Reduced visibility conditions increase both the probability of rear-end crash occurrences and their severity. Crash warning systems that employ data from connected vehicles have potential to improve vehicle safety by assisting drivers to be aware of the imminent situations ahead in advance and then taking timely crash avoidance action(s). This study provides a driving simulator study to evaluate the effectiveness of the Head-up Display warning system and the audio warning system on drivers’ crash avoidance performance when the leading vehicle makes an emergency stop under fog conditions. Drivers’ throttle release time, brake transition time, perception response time, brake reaction time, minimum modified time-to-collision, and maximum brake pedal pressure are assessed for the analysis. According to the results, the crash warning system can help decrease drivers’ reaction time and reduce the probability of rear-end crashes. In addition, the effects of fog level and drivers’ characteristics including gender and age are also investigated in this study. The findings of this study are helpful to car manufacturers in designing rear-end crash warning systems that enhance the effectiveness of the system’s application under fog conditions.     

Modeling car-following behavior on urban expressways in Shanghai: A naturalistic driving study

Although car-following behavior is the core component of microscopic traffic simulation, intelligent transportation systems, and advanced driver assistance systems, the adequacy of the existing car-following models for Chinese drivers has not been investigated with real-world data yet. To address this gap, five representative car-following models were calibrated and evaluated for Shanghai drivers, using 2100 urban-expressway car-following periods extracted from the 161,055 km of driving data collected in the Shanghai Naturalistic Driving Study (SH-NDS). The models were calibrated for each of the 42 subject drivers, and their capabilities of predicting the drivers’ car-following behavior were evaluated.The results show that the intelligent driver model (IDM) has good transferability to model traffic situations not presented in calibration, and it performs best among the evaluated models. Compared to the Wiedemann 99 model used by VISSIM®, the IDM is easier to calibrate and demonstrates a better and more stable performance. These advantages justify its suitability for microscopic traffic simulation tools in Shanghai and likely in other regions of China. Additionally, considerable behavioral differences among different drivers were found, which demonstrates a need for archetypes of a variety of drivers to build a traffic mix in simulation. By comparing calibrated and observed values of the IDM parameters, this study found that (1) interpretable calibrated model parameters are linked with corresponding observable parameters in real world, but they are not necessarily numerically equivalent; and (2) parameters that can be measured in reality also need to be calibrated if better trajectory reproducing capability are to be achieved.     

Modeling of individual vehicle safety and fuel consumption under comprehensive external conditions

This research intends to explore external factors affecting driving safety and fuel consumption, and build a risk and fuel consumption prediction model for individual drivers based on natural driving data. Based on 120 taxi drivers’ natural driving data during 4 months, driving behavior data under various conditions of the roadway, traffic, weather, and time of day are extracted. The driver's fuel consumption is directly collected by the on-board diagnostics (OBD) unit, and safety index is calculated based on Data Threshold Violations (DTV) and Phase Plane Analysis with Limits (PPAL) considering speed, longitudinal and lateral acceleration. By using a linear mixed model explaining the fixed effect of the external conditions and the random effect of the driver, the influences of various external factors on fuel consumption and safety are analyzed and discussed. The prediction model lays a foundation for drivers' fuel consumption and risk prediction in different external conditions, which could help improve individual driving behavior for the benefit of both fuel consumption and safety.     

Modelling supported driving as an optimal control cycle: Framework and model characteristics

Driver assistance systems support drivers in operating vehicles in a safe, comfortable and efficient way, and thus may induce changes in traffic flow characteristics. This paper puts forward a receding horizon control framework to model driver assistance and cooperative systems. The accelerations of automated vehicles are controlled to optimise a cost function, assuming other vehicles driving at stationary conditions over a prediction horizon. The flexibility of the framework is demonstrated with controller design of Adaptive Cruise Control (ACC) and Cooperative ACC (C-ACC) systems. The proposed ACC and C-ACC model characteristics are investigated analytically, with focus on equilibrium solutions and stability properties. The proposed ACC model produces plausible human car-following behaviour and is unconditionally locally stable. By careful tuning of parameters, the ACC model generates similar stability characteristics as human driver models. The proposed C-ACC model results in convective downstream and absolute string instability, but not convective upstream string instability observed in human-driven traffic and in the ACC model. The control framework and analytical results provide insights into the influences of ACC and C-ACC systems on traffic flow operations.     

A gradient boosting logit model to investigate driver’s stop-or-run behavior at signalized intersections using high-resolution traffic data

Driver’s stop-or-run behavior at signalized intersection has become a major concern for the intersection safety. While many studies were undertaken to model and predict drivers’ stop-or-run (SoR) behaviors including Yellow-Light-Running (YLR) and Red-Light-Running (RLR) using traditional statistical regression models, a critical problem for these models is that the relative influences of predictor variables on driver’s SoR behavior could not be evaluated. To address this challenge, this research proposes a new approach which applies a recently developed data mining approach called gradient boosting logit model to handle different types of predictor variables, fit complex nonlinear relationships among variables, and automatically disentangle interaction effects between influential factors using high-resolution traffic and signal event data collected from loop detectors. Particularly, this research will first identify a series of related influential factors including signal timing information, surrounding traffic information, and surrounding drivers’ behaviors using thousands drivers’ decision events including YLR, RLR, and first-to-stop (FSTP) extracted from high-resolution loop detector data from three intersections. Then the research applies the proposed data mining approach to search for the optimal prediction model for each intersection. Furthermore, a comparison was conducted to compare the proposed new method with the traditional statistical regression model. The results show that the gradient boosting logit model has superior performance in terms of prediction accuracy. In contrast to other machine learning methods which usually apply ‘black-box’ procedures, the gradient boosting logit model can identify and rank the relative importance of influential factors on driver’s stop-or-run behavior prediction. This study brings great potential for future practical applications since loops have been widely implemented in many intersections and can collect data in real time. This research is expected to contribute to the improvement of intersection safety significantly.     

A Bayesian Network model for contextual versus non-contextual driving behavior assessment

Driving behavior is generally considered to be one of the most important factors in crash occurrence. This paper aims to evaluate the benefits of utilizing context-relevant information in the driving behavior assessment process (i.e. contextual driving behavior assessment approach). We use a Bayesian Network (BN) model that investigates the relationships between GPS driving observations, individual driving behavior, individual driving risks, and individual crash frequency. In contrast to prior studies without context information (i.e. non-contextual approach), the data used in the BN approach is a combination of contextual features in the surrounding environment that may contribute to crash risk, such as road conditions surrounding the vehicle of interest and dynamic traffic flow information, as well as the non-contextual data such as instantaneous driving speed and the acceleration/deceleration of a vehicle. An information-aggregation mechanism is developed to aggregates massive amounts of vehicle GPS data points, kinematic events and context information into drivel-level data. With the proposed model, driving behavior risks for drivers is assessed and the relationship between contextual driving behavior and crash occurrence is established. The analysis results in the case study section show that the contextual model has significantly better performance than the non-contextual model, and that drivers who drive at a speed faster than others or much slower than the speed limit at the ramp, and with more rapid acceleration or deceleration on freeways are more likely to be involved in crash events. In addition, younger drivers, and female drivers with higher VMT are found to have higher crash risk.     

北京驾驶员培训行业需求预测和发展研究

机动车驾驶员的素质能够对城市交通运行产生重大影响,良好的技术水平和高尚道德素质的驾驶员,对于保证城市交通安全运行和人民生命财产的安全至关重要。通过开展驾驶员培训市场需求总量的预测研究,能够有效引导培训市场的合理竞争,提升驾驶员培训行业的高质量发展。本文系统分析了驾驶员培训市场需求预测的方法,以北京驾培市场为实例,基于城市新总规,综合考虑经济社会发展、城市人口变化、城市机动车调控和驾驶证饱和率等多种因素,预测未来培训市场需求情况。根据预测结果和市场培训能力对比,提出了针对行业总量发展的对策建议,也能为国内城市进行驾培需求预测研究和行业发展提供参考。     

The heterogeneous effects of guardian supervision on adolescent driver-injury severities: A finite-mixture random-parameters approach

One of the key aspects of graduated driver licensing programs is the new-driver experience gained in the presence of a guardian (a person providing mandatory supervision from the passenger seat). However, the effect that this guardian-supervising practice has on adolescent drivers’ crash-injury severity (should a crash occur) is not well understood. This paper seeks to provide insights into the injury-prevention effectiveness of guardian supervision by developing an appropriate econometric structure to account for the complex interactions that are likely to occur in the study of the heterogeneous effects of guardian supervision on crash-injury severities. As opposed to conventional heterogeneity models with standard distributional assumptions, this paper deals with the heterogeneous effects by accounting for the possible multivariate characteristics of parameter distributions in addition to allowing for multimodality, skewness and kurtosis. A Markov Chain Monte Carlo (MCMC) algorithm is developed for estimation and the permutation sampler proposed by Frühwirth-Schnatter (2001) is extended for model identification. The econometric analysis shows the presence of two distinct driving environments (defined by roadway geometric and traffic conditions). Model estimation results show that, in both of these driving environments, the presence of guardian supervision reduces the crash-injury severity, but in interestingly different ways. Based on the findings of this research, a case could easily be made for extending the time-requirement for guardian supervision in current graduated driver license programs.     

Evaluation of the effect of cooperative infrastructure-to-vehicle systems on driver behavior

In-vehicle technologies and co-operative services have potential to ease congestion problems and improve traffic safety. This paper investigates the impact of infrastructure-to-vehicle co-operative systems, case of CO-OPerative SystEms for Intelligent Road Safety (COOPERS), on driver behavior. Thirty-five test drivers drove an instrumented vehicle, twice, with and without the system. Data related to driving behavior, physiological measurements, and user acceptance was collected. A macro-level approach was used to evaluate the potential impact of such systems on driver behavior and traffic safety. The results in terms of speeds, following gaps, and physiological measurements indicate a positive impact. Furthermore, drivers’ opinions show that the system is in general acceptable and useful.     

Drivers’ ability to learn eco-driving skills; effects on fuel efficient and safe driving behaviour

Whilst driving is inherently a safety–critical task, awareness of fuel-efficient driving techniques has gained popularity in both the public and commercial domains. Green driving, whether motivated by financial or environmental savings, has the potential to reduce the production of greenhouse gases by a significant amount. This paper focusses on the interaction between the driver and their vehicle – what type of eco-driving information is easy to use and learn whilst not compromising safety. A simulator study evaluated both visual and haptic eco-driving feedback systems in the context of hill driving. The ability of drivers to accurately follow the advice, as well as their propensity to prioritise it over safe driving was investigated. We found that any type of eco-driving advice improved performance and whilst continuous real-time visual feedback proved to be the most effective, this modality obviously reduces attention to the forward view and increases subjective workload. On the other hand, the haptic force system had little effect on reported workload, but was less effective that the visual system. A compromise may be a hybrid system that adapts to drivers’ performance on an on-going basis.     

The joint analysis of injury severity of drivers in two-vehicle crashes accommodating seat belt use endogeneity

The current study contributes to the existing injury severity modeling literature by developing a multivariate probit model of injury severity and seat belt use decisions of both drivers involved in two-vehicle crashes. The modeling approach enables the joint modeling of the injury severity of multiple individuals involved in a crash, while also recognizing the endogeneity of seat belt use in predicting injury severity levels as well as accommodating unobserved heterogeneity in the effects of variables. The proposed model is applied to analyze the injury severity of drivers involved in two-vehicle road crashes in Denmark.The empirical analysis provides strong support for the notion that people offset the restraint benefits of seat belt use by driving more aggressively. Also, men and those individuals driving heavy vehicles have a lower injury risk than women and those driving lighter vehicles, respectively. At the same time, men and individuals driving heavy vehicles pose more of a danger to other drivers on the roadway when involved in a crash. Other important determinants of injury severity include speed limit on roadways where crash occurs, the presence (or absence) of center dividers (median barriers), and whether the crash involves a head-on collision. These and other results are discussed, along with implications for countermeasures to reduce injury severities in crashes. The analysis also underscores the importance of considering injury severity at a crash level, while accommodating seat belt endogeneity effects and unobserved heterogeneity effects.     

Interface design considerations for an in-vehicle eco-driving assistance system

This high-fidelity driving simulator study used a paired comparison design to investigate the effectiveness of 12 potential eco-driving interfaces. Previous work has demonstrated fuel economy improvements through the provision of in-vehicle eco-driving guidance using a visual or haptic interface. This study uses an eco-driving assistance system that advises the driver of the most fuel efficient accelerator pedal angle, in real time. Assistance was provided to drivers through a visual dashboard display, a multimodal visual dashboard and auditory tone combination, or a haptic accelerator pedal. The style of advice delivery was varied within each modality. The effectiveness of the eco-driving guidance was assessed via subjective feedback, and objectively through the pedal angle error between system-requested and participant-selected accelerator pedal angle. Comparisons amongst the six haptic systems suggest that drivers are guided best by a force feedback system, where a driver experiences a step change in force applied against their foot when they accelerate inefficiently. Subjective impressions also identified this system as more effective than a stiffness feedback system involving a more gradual change in pedal feedback. For interfaces with a visual component, drivers produced smaller pedal errors with an in-vehicle visual display containing second order information on the required rate of change of pedal angle, in addition to current fuel economy information. This was supported by subjective feedback. The presence of complementary audio alerts improved eco-driving performance and reduced visual distraction from the roadway. The results of this study can inform the further development of an in-vehicle assistance system that supports ‘green’ driving.     

Utilizing naturalistic driving data for in-depth analysis of driver lane-keeping behavior in rain: Non-parametric MARS and parametric logistic regression modeling approaches

It is known that adverse weather conditions can affect driver performance due to reduction in visibility and slippery surface conditions. Lane keeping is one of the main factors that might be affected by weather conditions. Most of the previous studies on lane keeping have investigated driver lane-keeping performance from driver inattention perspective. In addition, the majority of previous lane-keeping studies have been conducted in controlled environments such as driving simulators. Therefore, there is a lack of studies that investigate driver lane-keeping ability considering adverse weather conditions in naturalistic settings. In this study, the relationship between weather conditions and driver lane-keeping performance was investigated using the SHRP2 naturalistic driving data for 141 drivers between 19 and 89 years of age. Moreover, a threshold was introduced to differentiate lane keeping and lane changing in naturalistic driving data. Two lane-keeping models were developed using the logistic regression and multivariate adaptive regression splines (MARS) to better understand factors affecting driver lane-keeping ability considering adverse weather conditions. The results revealed that heavy rain can significantly increase the standard deviation of lane position (SDLP), which is a very widely used method for analyzing lane-keeping ability. It was also found that traffic conditions, driver age and experience, and posted speed limits have significant effects on driver lane-keeping ability. An interesting finding of this study is that drivers have a better lane-keeping ability in roadways with higher posted speed limits. The results from this study might provide better insights into understanding the complex effect of adverse weather conditions on driver behavior.     

A rule-based neural network approach to model driver naturalistic behavior in traffic

This paper proposes a rule-based neural network model to simulate driver behavior in terms of longitudinal and lateral actions in two driving situations, namely car-following situation and safety critical events. A fuzzy rule based neural network is constructed to obtain driver individual driving rules from their vehicle trajectory data. A machine learning method reinforcement learning is used to train the neural network such that the neural network can mimic driving behavior of individual drivers. Vehicle actions by neural network are compared to actions from naturalistic data. Furthermore, this paper applies the proposed method to analyze the heterogeneities of driving behavior from different drivers’ data.Driving data in the two driving situations are extracted from Naturalistic Truck Driving Study and Naturalistic Car Driving Study databases provided by the Virginia Tech Transportation Institute according to pre-defined criteria. Driving actions were recorded in instrumented vehicles that have been equipped with specialized sensing, processing, and recording equipment.     

An optimal variable speed limits system to ameliorate traffic safety risk

Active Traffic Management (ATM) systems have been emerging in recent years in the US and Europe. They provide control strategies to improve traffic flow and reduce congestion on freeways. This study investigates the feasibility of utilizing a Variable Speed Limits (VSL) system, one key part of ATM, to improve traffic safety on freeways. A proactive traffic safety improvement VSL control algorithm is proposed. First, an extension of the METANET (METANET: A macroscopic simulation program for motorway networks) traffic flow model is employed to analyze VSL’s impact on traffic flow. Then, a real-time crash risk evaluation model is estimated for the purpose of quantifying crash risk. Finally, optimal VSL control strategies are achieved by employing an optimization technique to minimize the total crash risk along the VSL implementation corridor. Constraints are setup to limit the increase of average travel time and the differences of the posted speed limits temporarily and spatially. This novel VSL control algorithm can proactively reduce crash risk and therefore improve traffic safety. The proposed VSL control algorithm is implemented and tested for a mountainous freeway bottleneck area through the micro-simulation software VISSIM. Safety impacts of the VSL system are quantified as crash risk improvements and speed homogeneity improvements. Moreover, three different driver compliance levels are modeled in VISSIM to monitor the sensitivity of VSL effects on driver compliance. Conclusions demonstrated that the proposed VSL system could improve traffic safety by decreasing crash risk and enhancing speed homogeneity under both the high and moderate compliance levels; while the VSL system fails to significantly enhance traffic safety under the low compliance scenario. Finally, future implementation suggestions of the VSL control strategies and related research topics are also discussed.     

Validation of in-car observations,a method for driver assessment

An in-car observation method with human observers in the car was studied to establish whether observers could be trained to observe safety variables and register driver’s behaviour in a correct and coherent way, and whether the drivers drove in their normal driving style, despite the presence of the observers. The study further discussed the observed variables from a safety perspective. First three observers were trained in the observation method and on-road observations were carried out. Their observations were then compared with a key representing a correct observation. After practising the observation method the observers showed a high correlation with the key. To establish whether the test drivers drove in a normal way during the in-car observations, comparisons of 238 spot-speed measurements were carried out. Driver’s speeds when driving their own private cars were compared with their speeds during the in-car observations. The analysis showed that the drivers drove in the same way when being observed as they did normally. Most of the variables studied in the in-car observations had a well documented relevance to traffic safety. Overall, in-car observation was shown to be a reliable and valid method to observe driver behaviour, and observed changes provide relevant data on traffic safety.     

Human-like autonomous car-following model with deep reinforcement learning

This study proposes a framework for human-like autonomous car-following planning based on deep reinforcement learning (deep RL). Historical driving data are fed into a simulation environment where an RL agent learns from trial and error interactions based on a reward function that signals how much the agent deviates from the empirical data. Through these interactions, an optimal policy, or car-following model that maps in a human-like way from speed, relative speed between a lead and following vehicle, and inter-vehicle spacing to acceleration of a following vehicle is finally obtained. The model can be continuously updated when more data are fed in. Two thousand car-following periods extracted from the 2015 Shanghai Naturalistic Driving Study were used to train the model and compare its performance with that of traditional and recent data-driven car-following models. As shown by this study’s results, a deep deterministic policy gradient car-following model that uses disparity between simulated and observed speed as the reward function and considers a reaction delay of 1 s, denoted as DDPGvRT, can reproduce human-like car-following behavior with higher accuracy than traditional and recent data-driven car-following models. Specifically, the DDPGvRT model has a spacing validation error of 18% and speed validation error of 5%, which are less than those of other models, including the intelligent driver model, models based on locally weighted regression, and conventional neural network-based models. Moreover, the DDPGvRT demonstrates good capability of generalization to various driving situations and can adapt to different drivers by continuously learning. This study demonstrates that reinforcement learning methodology can offer insight into driver behavior and can contribute to the development of human-like autonomous driving algorithms and traffic-flow models.