Climate change and the extreme weather have a negative impact on road traffic safety, resulting in severe road traffic accidents. In this study, a negative binomial model and a log-change model are proposed to analyse the impact of various factors on fatal traffic accidents. The dataset used in this study includes the fatal traffic accident frequency, social development indicators and climate indicators in California and Arizona. The results show that both models can provide accurate fitting results. Climate variables (i.e., average temperature and standard precipitation 24) can significantly affect the frequency of fatal traffic accidents. Non-climate variables (i.e., beer consumption, rural Vehicle miles travelled ratio, and vehicle performance) also have a significant impact. The modelling results can provide decision-making guidelines for the transportation management agencies to improve road traffic safety.
7 October 2022 in Transportation Research Part C: Emerging Technologies
In complex lane change (LC) scenarios, semantic interpretation and safety analysis of dynamic interaction pattern are necessary for autonomous vehicles to make appropriate decisions. This study proposes a learning framework that combines primitive-based interaction pattern recognition and risk analysis. The Hidden Markov Model with the Gaussian mixture model (GMM-HMM) approach is developed to decompose the LC scenarios into primitives. Then K-means clustering with Dynamic Time Warping (DTW) is applied to gather the primitives into 13 LC interaction patterns. Finally, this study considers time-to-collision (TTC) of two conflict types involved in the LC process. And the TTC is used to analyze the risk of interaction patterns and extract high-risk LC interaction patterns. The LC events obtained from the Highway Drone Dataset (highD) demonstrate that the identified LC interaction patterns contain interpretable semantic information. This study identifies the dynamic spatiotemporal characteristics and risk formation mechanism of the LC interaction patterns. The findings are useful to comprehensively understand the latent interaction patterns, which can then be used to design and improve the decision-making process during lane changes and enhance the safety of autonomous vehicle.
22 July 2021 in Transportmetrica B: Transport Dynamics
Lane-changing is an important driving behaviour and unreasonable lane changes can potentially result in traffic accidents. Currently, the lane-changing data are often recorded with high resolution, which are not appropriate for some common deep learning approaches. To capture the stochastic time series of high-resolution lane-changing behaviour, this study introduces a temporal convolutional network (TCN) to predict the long-term lane-changing trajectory and behaviour. The lane-changing dataset was collected by the driving simulator at the frequency of 60 Hz. Prediction results show that the TCN can accurately predict the long-term lane-changing trajectory and driving behaviour with shorter computational time compared with two benchmark models including the convolutional neural network (CNN) and long short-term memory neural network (LSTM). The advantages of the TCN are rapid response and accurate long-term prediction, which are important for lane-changing assistance in the advanced driver assistance system.
9 May 2022 in Journal of Intelligent Transportation Systems
Understanding human merging behavior patterns at freeway on-ramps is important for assisting the decisions of autonomous driving. This study develops a primitive-based framework to identify the driving patterns during merging processes and reveal the evolutionary mechanism in congested traffic flow at freeway on-ramps. The Nonhomogeneous Hidden Markov Model is introduced to decompose the merging processes into primitives containing semantic information. Then, the time-series K-means clustering is used to group these primitives with variable-length time series into interpretable merging behavior patterns. Different from traditional state segmentation methods (e.g. Hidden Markov Model), the model proposed in this study considers the dependence of transition probability on exogenous variables, thereby revealing the influence of covariates on the evolution of driving patterns. This approach is evaluated in the merging area at a freeway on-ramp using the INTERACTION dataset. Results demonstrate that the proposed approach can deeply analzye the complicated merging processes and provide interpretable merging behavior patterns as well as the evolutionary mechanism. The findings in this study can be useful for designing and improving the merging decision-making of autonomous vehicles.
22 November 2022 in Journal of Transportation Safety & Security
The freeway on-ramp merging section is often identified as a crash-prone spot due to the high frequency of traffic conflicts. Cars and trucks have different sizes and operation characteristics, but very few traffic conflict analysis studies considered different vehicle types at freeway merging sections. Thus, the main objective of this study is to analyze lane-changing conflicts between different vehicle types at freeway merging sections. Vehicle trajectories are extracted from the Unmanned Aerial Vehicle (UAV) video data which are collected in Shanghai, China. Time-to-collision (TTC) is utilized as the surrogate safety measure (SSM) to analyze lane-changing conflicts. Results show that TTC values of car-car conflicts are the smallest, while truck-truck conflicts have the largest TTC values. Although traffic conflicts frequently occur at the on-ramp and additional rightmost lane, the spatial distribution of lane-changing conflicts is significantly different between different vehicle types. The findings of this study are useful for transportation management agencies to design proper strategies to improve traffic safety at freeway merging sections.