The emergence and application of connected and automated vehicles (CAVs) have played a positive role in improving the efficiency of urban transportation and achieving sustainable development. To improve the traffic efficiency at signalized intersections in a connected environment while simultaneously reducing energy consumption and ensuring a more comfortable driving experience, this study investigates a flexible and real-time control method to navigate the CAVs at signalized intersections utilizing reinforcement learning (RL). Initially, control of CAVs at intersections is formulated as a Markov Decision Process (MDP) based on the vehicles’ motion state and the intersection environment. Subsequently, a comprehensive reward function is formulated considering energy consumption, efficiency, comfort, and safety. Then, based on the established environment and the twin delayed deep deterministic policy gradient (TD3) algorithm, a control algorithm for CAVs is designed. Finally, a simulation study is conducted using SUMO, with Lankershim Boulevard as the research scenario. Results indicate that the proposed methods yield a 13.77% reduction in energy consumption and a notable 18.26% decrease in travel time. Vehicles controlled by the proposed method also exhibit smoother driving trajectories.

With the development of vehicle-road network technologies, the future traffic flow will appear in the form of hybrid network traffic flow for a long time. Due to the change in traffic characteristics, the current hard shoulder running strategy based on traditional traffic characteristics cannot effectively serve the hybrid network traffic flow scenario, and will even lead to the further deterioration of traffic congestion. In order to propose a hard shoulder running strategy suitable for a hybrid network environment, a traffic breakdown prediction method based on a hidden Markov model was established. Secondly, the characteristics of traffic breakdown in a hybrid network environment were analyzed. Finally, based on the traffic breakdown characteristics in a hybrid network environment, a dynamic hard shoulder running method based on the hidden Markov model was proposed. The effectiveness of HMMD-HSR was verified by simulation and comparison with HMM-HSR, LMD-HSR, and N-HSR. The simulation results show that the HMMD-HSR proposed in this paper can improve operation efficiency and reduce travel time in a congested expressway.

Generative Adversarial Networks (GAN) have been widely used in traffic data imputation to improve the accuracy of data imputation. However, existing GAN-based models often suffer from mode collapse and cannot fully reflect the complex characteristics of real-world traffic, which affects the quality of data imputation. To address these challenges, we incorporate the Diffusion Model (DM) into the GAN framework, integrating the traffic dynamics modeling process within the Diffusion-GAN network. Based on this, we propose a Diffusion-TGAN speed data imputation model to generate individual vehicle speeds. Combined with the generated vehicle speed, the group trajectory reconstruction result is further given. The model uses the forward process of DM to generate condition vectors to guide the training of GAN generator. Subsequently, the discriminator of GAN takes the traffic dynamics constraints into account during adversarial training. Traffic dynamics modeling aims to make the generated speed data consistent with the real traffic characteristics. Experiments on multiple data sets show that the proposed model effectively imputes in the spatio-temporal speed data, and reduces the RMSE of the speed considering the position by 23.4% compared with the common GAN model, and reduces the RMSE by 39.7% in the trajectory reconstruction respectively. The code and our model are available at GitHub.

Vehicle trajectory prediction (VTP) poses unique spatial-temporal modeling challenges, as a human-like prediction requires considering fine-grained interactions. Prior models have often used various attention mechanisms to extract key spatial-temporal interactions from the foreground, thus missing background information processing. However, this may result in the model’s insufficient generalization ability in a specific modality. Here this paper presents VCIFormer, a velocity-aware complementary interaction Transformer designed to enhance vehicle trajectory prediction by capturing complex spatial-temporal interactions between foreground and background with context awareness. VCIFormer combines inverse attention with traditional spatial-temporal attention as a complementary mechanism, applying bidirectional optimization to capture foreground and background attention flows. An adaptive visual mask is also developed to align attention allocation with human visual patterns at varying velocities. It enables the model to prioritize critical regions analogous to human driving behavior. Moreover, a context-aware encoder, consisting of a surround-aware module and a motion-enhancement module, is incorporated to provide additional interaction cues and spatial information. VCIFormer is evaluated on six real-world datasets (NGSIM, HighD, RounD, ExiD, Argoverse, and nuScenes) and attains state-of-the-art performance in critical metrics. For example, in comparison to baseline models, there are significant improvements in ADE and FDE by 2.84-18.18% and 9.88-13.33% on the NGSIM, HighD, RounD, and ExiD datasets, respectively. In sum, compared with previous architectures, VCIFormer presents a more effective combination of spatial-temporal interaction layers and context awareness for VTP.

Accurate traffic congestion prediction is crucial for intelligent transportation systems (ITS), especially when accounting for the impact of random traffic events. Such events can lead to lane closures and variable road capacity, further complicating congestion prediction for traditional models. This paper proposes a novel multi-task iTransformer model designed specifically for short-term highway congestion prediction with consideration for random event impacts. Integrating an inverted embedding structure and multi-channel attention mechanism within a multi-task learning framework, the model simultaneously predicts traffic flow and capacity changes induced by events. Within a unified architecture, iTransformer captures the complex interactions among traffic flow, lane occupancy, and incident disturbances, enabling precise responses to dynamic traffic conditions. Empirical analyses based on the real-world data collected from highways in Zhejiang Province are conducted to validate the proposed model. It is shown that the proposed Multi-task iTransformer model performs well in traffic congestion prediction, achieving a 35.2% improvement in accuracy compared to single-task congestion prediction models.