Abstract ：

Data reconstruction is essential in enhancing the quality of vehicle trajectory data. Previous studies have identified the location of abnormal data inaccurately, resulting in poor trajectory reconstruction results. This study proposed a two-step reconstruction method. The first step detected the locations of obviously abnormal speed data using wavelet transform. Then, the abnormal data were repaired by the cubic spline curve interpolation algorithm. The second stage identified the locations of abnormal acceleration data based on the general acceleration value. And the vehicle trajectory data were reconstructed using Lagrange interpolation and Kalman filter algorithms. The approach was utilized on NGSIM trajectory data. The results show that the acceleration values of the proposed method range from −6.69 m/s2 to 4.96 m/s2, with a standard deviation of 0.87. The reconstructed results are more closely matching drivers' physiological capabilities compared to other methods. These findings verify the reliability of the proposed approach and notably improve the quality of the trajectory data. It provides critical foundational data support for traffic planning, design, and management. © 2024 The Author(s). Engineering Reports published by John Wiley & Sons Ltd.

Keyword ：

vehicle trajectory data reconstruction wavelet analysis NGSIM

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Calibrating microscopic traffic simulation models is a prerequisite for simulation applications. This study proposes three novel methods to improve the accuracy and interpretability of the calibration model. The proposed approach involves selecting the calibration parameter, refining the model parameter system, and optimizing the calibration results. The first method expands the single-point mean into a multi-point distribution. The cumulative distribution curve of delay was selected as the calibration parameter. The second method divides the parameter system into global and local parameters. Global parameters were calibrated using NGSIM measured data, and local parameters were calibrated through intelligent algorithms. The third method proposes a methodology of parameter clustering recursion based on the genetic algorithm results, with information entropy selected as the analysis index. To evaluate the effectiveness of the proposed optimization methods, this study used NGSIM trajectory data as a case study. Eight simulation schemes based on the three optimization methods were designed, and simulation experiments were conducted using the VISSIM platform. The results show that the accuracy of the multi-point distribution calibration and parameter value optimization method is significantly higher than the default method. Additionally, the optimization method with calibration of both global and local parameters was more consistent with actual driving characteristics. This study provides a theoretical foundation for improving the practical application of traffic simulation technology, which has significant implications for transportation planning and management.

Keyword ：

Calibration and validation Micro-simulation model Driver behavior NGSIM trajectory

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Car-following behavior is closely related to the longitudinal control of the vehicle, affecting the safety of the vehicle and traffic flow stability. In order to interact with the preceding vehicle, the target vehicle usually collects the driving data of the preceding vehicle. However, data acquisition devices often face malfunctions caused by various unpredictable disruptions, resulting in missing value problems. This may cause the target vehicle to make wrong control decisions. Given this situation, a new car-following(CF) model considering missing data based on Transformer-Generative Adversarial Networks (TransGAN) is proposed. Firstly, Transformer Network with multi-head attention is used to deeply extract the potential features from incomplete vehicle state data, which can filter important information from the input and focus on these, while capturing long distance dependencies. Secondly, a Generative Adversarial Network is constructed. The Generator generates the future multi-step control states of the target vehicle based on the features extracted by Transformer Network. The Discriminator with a fully connected network is applied to simultaneously ensure the generation accuracy. Finally, our proposed model was trained and tested on a publicly available NGSIM I-80 dataset. Compared with other existing advanced works, our model can fit the actual control states of the target vehicle with higher accuracy under different data missing rates of the preceding vehicle, which demonstrates that the proposed method effectively improves the robustness of vehicle longitudinal car-following control under missing data.

Keyword ：

traffic flow Mathematical models Data models generative adversarial network Autonomous vehicles Safety Transformers deep learning Behavioral sciences Car-following Feature extraction transformer network

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Traffic energy consumption estimation is significant for the sustainable transportation. However, it is difficult to directly employ macro traffic flow data to accurately estimate the traffic energy consumption due to many traffic energy consumption models need second-by-second vehicle trajectory. To solve this problem, this paper proposes a traffic energy consumption model based on the macro-micro data, which the macro data derived from the fixed-location sensors and sparse micro data derived from the Connected and Automated Vehicles (CAVs). The completed vehicle trajectories are constructed by the nonparametric kernel smoothing algorithm and variational theory. To test the performance of the proposed method, the Next Generation Simulation micro (NGSIM) dataset and Caltrans Performance Measurement System macro dataset obtained from the same road and time are used. The results indicate that the proposed method not only can reflect the characteristics of traffic kinematic waves caused by traffic congestion, but also minimize the errors generated by the macro-micro transformation. In addition, it can significantly improve the accuracy of energy consumption estimation.

Keyword ：

Vehicle trajectory reconstruction CAVs data Macro traffic Energy consumption estimation

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Vehicle trajectory prediction is a challenging problem in the field of autonomous driving, which is of great significance to the safety of autonomous driving and traffic roads. In view of the interaction between surrounding vehicles and target vehicle and its own trajectory, we propose a new graph network model to predict future vehicle trajectory. First, the correlation network of vehicles at each time is constructed based on the complex network method. In order to make up for the lack of real spatial relevance caused by the fixed graph, we propose an adaptive parameter matrix to coordinate and optimize the global spatio-temporal graph. Second, the global spatio-temporal features of vehicle historical trajectory data are extracted by stacked graph convolution module. Finally, the obtained graph features are coded based on seq2seq network, and the trajectory prediction of road vehicles at different times in the future is realized. Our model has been trained and verified on the published NGSIM US-101 and I-80 data sets. Compared with other advanced schemes, our model has more accurate results in the future time of 5 seconds. In predicting the future group trajectory of vehicles on the road, the accuracy of long-term prediction is 16.6% higher than that of the most advanced scheme.

Keyword ：

Correlation Automatic driving spatial topology graph Roads temporal logic network Topology Trajectory Index Terms Data models trajectory prediction intelligent transportation graph convolution neural network Predictive models Feature extraction

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Based on the existing safe distance cellular automata model, an improved cellular automata model based on realistic human reactions is proposed in this paper, which aims to reproduce the characteristics of congested traffic flow. In the proposed model, the stochastic noise parameter is optimised by considering driving behavioural difference. The relative speed, gap and acceleration of the front vehicle are introduced into the optimised stochastic noise parameter oriented to describing the asymmetric acceleration behaviour of drivers in congestion. The simulation results show that an uneven distribution of acceleration trajectories of vehicles experiencing congestion exhibited on the spatial-temporal diagram of the proposed model is reproduced. Based on the analysis of the NGSIM, compared with the model with traditional stochastic noise parameter, the vehicles that move ac-cording to the proposed model can be followed more easily and more realistically. Then the actual gap of vehicles can be better reflected by the proposed model and the change of vehicle speed is more stable. Additionally, the traffic efficiency from two aspects of flow and speed shows that the proposed model can significantly improve the traffic efficiency in the medium high density region.

Keyword ：

stochastic noise parameter car-following behaviour heterogeneous traffic flow cellular automata

Cite：

Copy from the list or Export to your reference management。

Abstract ：

A Time Space Diagram (TSD) plays an important role in transportation research and practice due to its capability to exhibit traffic dynamics in time and space. Based on TSDs, this paper aims to reconstruct the traffic spatio-temporal state with the aid of Generative Adversarial Networks (GANs). By mining traffic state correlations and traffic pattern similarities between lanes with or without sufficient observations, the proposed Traffic State Reconstruction GAN (TSR-GAN) model can well estimate the traffic states for road segments with a strong learning capability. Specifically, the traffic states of lanes are converted to TSDs, in which the color represents the values of traffic variables (e.g., speed or density). The TSDs of lanes with or without sufficient data are utilized to train the proposed TSR-GAN model. The fine-tuned TSR-GAN model reconstructs traffic states for road segments with deficient sensor coverage by restoring the high-resolution TSD from its low-resolution observation. With trajectory datasets from Next Generation Simulation (NGSIM), this paper verifies the performance of the TSR-GAN model by estimating travel time via the reconstructed TSDs. Numerical results demonstrate that the proposed model possesses a desirable generalization and transferability, demonstrating the promise of reconstructing traffic states under various conditions. (c) 2021 Elsevier B.V. All rights reserved.

Keyword ：

Generative Adversarial Networks Traffic State Reconstruction Data Imputation Time Space Diagram

Cite：

Copy from the list or Export to your reference management。

Abstract ：

To date, commercial fully autonomous driving is not realized, while level 3 is the next step in the development of autonomous driving. At level 3, the vehicle is driving under the control of the machine, but when feature requests, human driver must take over control. Therefore, autonomous driving control should consider not only efficiency and safety but also human driver's acceptance. This paper develops a car-following (CF) model as a longitudinal control strategy for level 3 autonomous driving based on the automating entropy adjustment on Tsallis actor-critic (ATAC) algorithm. 1641 pairs of CF trajectories extracted from the Next Generation Simulation (NGSIM) data are applied to train the reinforcement learning (RL) agent. Based on the empirical data distributions, we use time margin, time gap, and jerk to construct the reward function and testify the proposed CF model's merits. Simulation results show that the proposed model can enable vehicles to drive safely, efficiently, and comfortably. The proposed model has good stability, and the generated driving behaviors are more acceptable for drivers. This work sheds light on developing a better autonomous driving system from the perspective of human factors.

Keyword ：

Trajectory Data models car-following reinforcement learning Autonomous driving Entropy Vehicles Autonomous vehicles driver's acceptance Reinforcement learning Safety

Cite：

Copy from the list or Export to your reference management。

Abstract ：

State estimate of traffic flow of a freeway segment is considered by using the method of boundary observer design. The observer control and measurements are all located at the boundaries. The nonequilibrium traffic flow dynamics are modeled as a Markov jump linear hyperbolic system with phase transitions. Based on the Lyapunov techniques, the sufficient conditions of matrix inequalities are derived for the exponentially mean-square static as well as the dynamic boundary observer design. Using real traffic data of vehicle trajectories from the Next Generation Simulation (NGSIM) project, the developed stochastic phase transition model of the nonequilibrium traffic flow is calibrated. Moreover, the simulation results illustrate the effectiveness of the boundary observer design for traffic estimation.

Keyword ：

Data models Observers Next Generation Simulation (NGSIM) Traffic control Markov processes Trajectory Boundary observers Markov jump linear hyperbolic systems Mathematical model Vehicle dynamics nonequilibrium traffic flow exponentially mean-square stability

Cite：

Copy from the list or Export to your reference management。

Abstract ：

车辆跟驰模型是被交通科学与交通工程领域广泛认可的微观交通流模型,是交通流理论的基础.近年来,信息感知与获取、大数据、人工智能等技术快速发展,推动了数据驱动跟驰模型的快速发展.数据驱动跟驰模型,是以真实的车辆行驶数据为基础,利用数据科学与机器学习等理论和方法,通过样本数据的训练、学习、迭代、进化,挖掘车辆跟驰行为的内在规律.本文系统回顾了数据驱动跟驰模型在过去20余年的发展历程以及由神经网络和深度学习带动的两次研究热潮,归纳了基于传统机器学习理论的跟驰模型、基于深度学习的跟驰模型、模型与数据混合驱动的跟驰模型3类数据驱动跟驰模型,并分别介绍了其中的典型代表.分析数据源发现,尽管各种高精度轨迹数据不断涌现,目前研究仍多使用美国于2006年发布的Next Generation Simulation(NGSIM)高精度车辆轨迹数据,模型的可移植性和泛化能力值得思考与研究.提出关于模型输入、输出的3个问题:如何考虑更多驾驶行为变量,是否有必要考虑更多行为变量,现有输入、输出是否可替换.在模型测试与验证方面,发现并讨论了目前测试不充分、对比不完整、缺少统一测试集与测试标准等问题.最后,探讨了数据驱动跟驰模型原创性与成功的关键因素等问题.期望通过本文的梳理,帮助研究者更好地了解数据驱动跟驰模型的过去与现状,促进相关研究的快速发展.

Keyword ：

跟驰模型 大数据 深度学习 交通流理论 交通工程 机器学习

Cite：

Copy from the list or Export to your reference management。