To explore the potential relationship between the leading vehicle and the following vehicle during car-following, we proposed a novel car-following model combining a convolutional neural network (CNN) with a long short-term memory (LSTM) network. Firstly, 400 car-following periods were extracted from the natural driving database and the OpenACC car-following experiment database. Then, we developed a CNN-LSTM car-following model, and the CNN is employed to analyze the potential relationship between the vehicle’s dynamic parameters and to extract the features of car-following behavior to generate the feature vector. The LSTM network is adopted to save the feature vector and predict the speed of the following vehicle. Finally, the CNN-LSTM model is trained and tested with the extracted car-following trajectories data and compared with the classical car-following models (LSTM model, intelligent driver model). The results show that the accuracy and the ability to learn the heterogeneity of the proposed model are better than the other two. Furthermore, the CNN-LSTM model can accurately reproduce the hysteresis phenomenon of congested traffic flow and apply to heterogeneous traffic flow mixed with adaptive cruise control vehicles on the freeway, which indicates that it has strong generalization ability.

The lateral control of the vehicle is significant for reducing the rollover risk of high-speed cars and improving the stability of the following vehicle. However, the existing car-following (CF) models rarely consider lateral control. Therefore, a CF model with combined longitudinal and lateral control is constructed based on the three degrees of freedom vehicle dynamics model and reinforcement learning method. First, 100 CF segments were selected from the OpenACC database, including 50 straight and 50 curved road trajectories. Afterward, the deep deterministic policy gradient (DDPG) car-following model and multi-agent deep deterministic policy gradient (MADDPG) car-following model were constructed based on the deterministic policy gradient theory. Finally, the models are trained with the extracted trajectory data and verified by comparison with the observed data. The results indicate that the vehicle under the control of the MADDPG model and the vehicle under the control of the DDPG model are both safer and more comfortable than the human-driven vehicle (HDV) on straight roads and curved roads. Under the premise of safety, the vehicle under the control of the MADDPG model has the highest road traffic flow efficiency. The maximum lateral offset of the vehicle under the control of the MADDPG model and the vehicle under the control of the DDPG model in straight road conditions is respectively reduced by 80.86% and 71.92%, compared with the HDV, and the maximum lateral offset in the curved road conditions is lessened by 83.67% and 78.95%. The proposed car following model can provide a reference for developing an adaptive cruise control system considering lateral stability.

There is limited research on the loss and reconstruction of car-following features. To delve into car-following's characteristics, we propose a car-following model based on LSTM-Transformer. By fully leveraging the advantages of long short-term memory (LSTM) and transformer models, this study focuses on reconstructing the input car-following features. Training and testing were conducted using 700 car-following segments extracted from a natural driving dataset and the Next Generation Simulation (NGSIM) dataset, and the proposed model was compared with an LSTM model and an intelligent driver model. The results demonstrate that the model performs exceptionally well in feature reconstruction. Moreover, compared to the other two models, it effectively captures the car-following features and accurately predicts the position and speed of the following car when features are lost. Additionally, the LSTM-Transformer model accurately reproduces traffic phenomena, such as asymmetric driving behavior, traffic oscillations and lag, by reconstructing the lost features. Therefore, the LSTM-Transformer car-following model proposed in this study exhibits advantages in feature reconstruction and reproducing traffic phenomena compared to other models.

Due to imperfect design norms and guidelines for China’s truck escape ramp, previous studies have not been able to reflect the effect of wheel subsidence process on the deceleration of runaway vehicles. A discrete element method was used to establish an aggregate discrete element and a wheel discrete element. The three-dimensional discrete element model for an aggregate-wheel combination was established based on a particle flow code in three dimensions on a software platform using the “FISH” language. The microscopic parameters of the aggregate discrete element particles and wheel discrete element particles were calibrated using a simulated static triaxial compression test and real vehicle test data, respectively. Four sets of numerical simulation tests were designed for analyzing the influence of the aggregate diameter, grade of the arrester bed, truckload, and entry speed on the wheel subsidence depth and stopping distance of runaway vehicles. The results indicate that the smaller the aggregate diameter and entry speed and the greater the truckload and grade of the arrester bed, the more easily the wheel falls into the gravel aggregate, the better the deceleration effect, and the smaller the stopping distance. As the wheel subsidence depth increases, the speed at the unit stopping distance decreases more quickly. The maximum subsidence depth mainly depends on the truckload. The research results can provide a theoretical basis for the design of the arrester bed length and the thickness of the aggregate pavement in a truck escape ramp.

Introduction: Although the fall protection net installed at the end of the truck escape ramp has a protective effect on trucks and drivers, but lacks sufficient theoretical basis and verification method. Objectives: The primary objective of this paper was to design a fall protection net that meets the regulations and research its protection performance. Methods: The finite-element method was used to design the overall size, material, mesh length, mesh type, shape, and supporting structure of the fall protection net installed at the end of truck escape ramp, then dummy and truck models were used to impact the fall protection net to verify the rationality of the design. After the design completed, the truck model was used to impact the fall protection net twice to research the cumulative protection performance. Results: A fall protection net with a width of 6000 mm, a span of 6000 mm, a depth of 5196 mm, a mesh length of 150 mm, a mesh type of diamond mesh, a shape of 60-degree V-shaped, a supporting structure of steel pipe supporting has a better effect on energy absorption and protection. Within the two consecutive impacts, the residual plastic deformation and stress of the fall protection net generated in the first impact severely affect the protection performance in the second impact. Conclusion: It is feasible to use the finite-element method to design and research the fall prevention net installed at the end of the truck escape ramp, and the fall protection net can indeed protect the trucks and drivers, and it should be inspected and maintained after impact to ensure the protective performance in subsequent use.

To address traffic congestion in urban expressways during the transition from wide to narrow sections, this study proposed a car-following strategy based on deep reinforcement learning. Firstly, a car-following strategy was developed based on a twin-delayed deep deterministic policy gradient (TD3) algorithm, and a multi-objective constrained reward function was designed by comprehensively considering safety, traffic efficiency, and ride comfort. Secondly, 214 car-following periods and 13 platoon-following periods were selected from the natural driving database for the strategies training and testing. Finally, the effectiveness of the proposed strategy was verified through simulation experiments of car-following and platoon-following. The results showed that compared to human-driven vehicles (HDV), the TD3 and deep deterministic policy gradient (DDPG)-based strategies enhanced traffic efficiency by over 29% and ride comfort by more than 60%. Furthermore, compared to DDPG, the relative errors between the following distance and desired safety distance using TD3 could be reduced by 1.28% and 1.37% in simulation experiments of car-following and platoon-following, respectively. This study provides a new approach to alleviate traffic congestion for wide-to-narrow road sections in urban expressways.