Search

Side collisions caused by sudden vehicle cut-ins comprise a significant proportion of traffic accidents. Due to the complex and dynamic nature of traffic environments, the warning algorithms in advanced driving assistant systems (ADAS) often misjudge and misdiagnose risk and omit necessary warnings, because they rely solely on the sensing information of the single vehicle equipped with ADAS and have limited insights from and communication with the surrounding vehicles and traffic environment. To improve the effectiveness of ADAS in cut-in scenarios, this study established a collision warning model in a vehicle-to-vehicle (V2V) communication environment. Firstly, based on the support vector machine-recursive feature elimination (SVM-RFE) lane-change intent-recognition model, the lane-change feasibility and the change rate of the lateral offset, the logical ``and'' was used to establish a lane-change behavior prediction model, and a trajectory prediction model was established based on the long short-term memory (LSTM). Then, based on the proposed comprehensive prediction model for lane-change behavior, the driving trajectory prediction model, and the oriented bounding box (OBB) detection algorithm, a collision warning model was established for a V2V environment. Finally, based on a driving simulation platform and a real-world vehicle test, a cut-in experiment in a V2V environment was designed and implemented. By comparing the warning confusion matrix and warning time, it was found that the proposed cut-in collision warning model is superior to the traditional collision warning model. The results of this study can provide new modeling ideas and a theoretical basis for ADAS to further optimize for a cut-in scenario.

China's traffic safety attracts increasing research interest. Official data show that crashes in the western region of China are more severe than those in the eastern region. However, research on crash severity in western China is scarce. This study applied a hierarchical Bayesian logistic model to examine the significant factors related to crash and vehicle/driver levels and their heterogeneous impacts on the severity of drivers' injury. Crash data were collected from Lintao, a rural mountainous county in western China. A variable was proposed to measure the relative difference between the crashworthiness of one vehicle and the aggressivity of the other vehicle in the mixed traffic flow. Results indicated that the majority of the total variance was induced by between-crash variance, showing the suitability of the utilized hierarchical modeling approach. One crash-level variable and six vehicle/driver-level variables, namely, road type, compatibility difference, age, vehicle type, drunk driving, driving unregistered vehicle, and driving years, significantly affected modeling drivers' injury severities. Among these variables, road type (national and provincial), age (young and senior drivers), driving unregistered vehicle, and drunk driving tended to increase the odds of crash-related mortality. Driving years (new drivers with less than six years of driving experience) and vehicle type (heavy vehicle) were likely to decrease the probability of fatal outcomes. Compatibility difference was relatively significant, and the possibilities of mortality in single vehicle crashes were higher than those in multivehicle and pedestrian-involved crashes. The developed methodology and estimation results provided insights into the internal mechanism of rural crashes and effective countermeasures to prevent rural crashes.

We consider an inventory routing problem in which a single vehicle is responsible for the transport of a commodity from a set of supply locations to a set of demand locations. At each location the inventory must be kept within predefined bounds, and the location specific supply and demand rates are constant throughout the time horizon. Each location can be visited several times during the time horizon, and the vehicle can visit the locations in any order as long as the capacity of the vehicle is not exceeded. Two models are presented, each defined on a different extended network. In a location-event model, the nodes are indexed by the location and the number of visits made so far to that location, while in a vehicle-event model the nodes are indexed by the location and the number of visits so far on the vehicle route. Both models are based on continuous time formulations. They are tightened with valid inequalities, and a new branching algorithm is designed to speed up the solution time of the models. Computational tests based on a set of maritime transportation instances are reported to compare both models and the corresponding tightened variants.

Undoubtedly, single-vehicle crashes remain a major concern for roadway users and highway administrators, especially in low- and middle-income developing countries, where accident death rates remain extremely high. This study investigates the temporal instability of contributing factors of driver-injury severities in single-vehicle crashes using data in Thailand, a developing country, from 2011 to 2017. Uncorrelated and correlated random parameters models with possible heterogeneity in means and variances were estimated for individual year model using two levels of driver-injury severities, namely, no/minor injury and severe/fatal injury. The models considered a wide range of factors, such as driver, roadway, vehicle, crash, environmental and temporal, and spatial characteristics. A series of likelihood ratio test and the marginal effect of significant factors were computed to explore the temporal stability of the year models and to investigate the temporal instability of the effect of each parameter estimate on the probability of driver-injury severities within given time periods. The result indicates that a substantial temporal instability exists in the model specifications and estimated parameters (temporally unstable factor included male driver, driving using exceeding speed limit, crashes on asphalt pavement, crashes on weekends, and crashes on weekend during nighttime with present of road lighting) across the time periods under study (despite being insignificant in particular year models, some factors were stable but marginal effects varied across time). The findings may be used to assist and guide decision makers in policy generation for plans to mitigate driver-injury severities. Despite the unclear source of temporal instability, the findings emphasize the importance of the temporal instability of the factors that influence the outcomes of driver-injury severities. Alternatively, ignoring temporal instability in studies on crash severity may lead to high levels of bias and inaccurate conclusions. With regard to methodologies, both random parameters with heterogeneity in means and variances and correlated random parameters with heterogeneity in means approaches are promising methods with ability to offer another layer of insight into unobserved heterogeneity in injury severity research.