The main form of freeway traffic congestion is the familiar stop-and-go wave, characterized by wide moving jams that propagate indefinitely upstream provided enough traffic demand. They cause severe, long-lasting adverse effects, such as reduced traffic efficiency, increased driving risks, and higher vehicle emissions. This underscores the crucial importance of artificial intervention in the propagation of stop-and-go waves. Over the past two decades, two prominent strategies for stop-and-go wave suppression have emerged: variable speed limit (VSL) and jam-absorption driving (JAD). Although they share similar research motivations, objectives, and theoretical foundations, the development of these strategies has remained relatively disconnected. To synthesize fragmented advances and drive the field forward, this paper first provides a comprehensive review of the achievements in the stop-and-go wave suppression-oriented VSL and JAD, respectively. It then focuses on bridging the two areas and identifying research opportunities from the following perspectives: fundamental diagrams, secondary waves, generalizability, traffic state estimation and prediction, robustness to randomness, simulation scenarios for strategy validation, and field tests and practical deployment. We expect that through this review, one area can effectively address its limitations by identifying and leveraging the strengths of the other, thus promoting the overall research goal of freeway stop-and-go wave suppression.

Vehicle trajectory data serves as a crucial foundation for vehicle-level control in mixed traffic environments incorporating connected and automated vehicles (CAVs). However, due to the limited sensing range of CAVs, perception-blind areas inevitably emerge, resulting in partially unobservable vehicle trajectories. To reconstruct unobservable trajectories between CAVs, this paper proposes a novel physics-informed neural network for platoon trajectory reconstruction under partially observed conditions, termed PINN-PTR. PINN-PTR integrates a physics-uninformed neural network (PUNN) with physics-based computational graphs derived from car-following models, in which each vehicle is assigned a distinct parameter set to capture heterogeneity in driving behavior. The proposed model leverages the advantages of both physics-based models, which are data-efficient and interpretable, and deep learning-based models, which are generalizable. Moreover, a bidirectional Newell computational graph (BNCG) is introduced to comprehensively capture the bidirectional temporal and spatial correlations of the ego vehicle with both its leading and following vehicles, based on the propagation of kinematic waves. Two types of PINN-PTR models are studied: one designed solely for trajectory reconstruction and another that jointly reconstructs trajectories and calibrates parameters within physics-based computational graphs. Experimental results on both real-world and synthetic datasets demonstrate that the proposed approach outperforms baseline methods in terms of trajectory reconstruction accuracy and car-following model calibration. Ablation studies further confirm the contributions of the BNCG and heterogeneous modeling to improving reconstruction performance. Finally, vehicle emission estimation is applied as a practical case study to evaluate the effectiveness of the proposed model in real-world scenarios.

This paper presents a deep reinforcement learning (DRL)-based strategy for coordinated ramp metering. Existing DRL-based strategies often fail to explicitly account for the correlation between on-ramp flows and congestion at different bottlenecks. As a result, RL agents must infer these relationships through extensive interactions with the environment, which can cause the control policy to become stuck in local optima, limiting potential traffic performance improvements. To address this problem, the proposed strategy integrates an attention mechanism into the RL agent’s state function, enabling it to capture the spatial-temporal correlations between the traffic states of on-ramps and mainstream segments. This mechanism allows the agent to evaluate the relative importance of each on-ramp’s contribution to a mainstream bottleneck, resulting in more effective ramp metering actions. The proposed method is validated through microscopic traffic simulation on a real-world road network. Experimental results show that the proposed strategy outperforms state-of-the-art DRL-based approaches in improving traffic performance.

A novel autonomous driving motion planning framework for unsignalized intersections is presented. To achieve an effective balance between safety and efficiency in the decision-making process, a motion planning decision strategy tailored for discrete action spaces is developed based on the discrete soft actor-critic algorithm. In response to the challenges posed by the complexity of feature information in dense intersection environments, a multi-level attention mechanism–integrating both feature-level and vehicle-entity-level information–is introduced to significantly enhance feature extraction and processing capabilities. Furthermore, to mitigate the issues of temporal sample distribution imbalance and low utilization of high-value samples in a single experience pool, a dual experience buffer prioritized replay mechanism is proposed, thereby improving training stability. Experimental results indicate that, compared with alternative methods, the proposed framework not only achieves a superior balance between efficiency and safety but also exhibits enhanced interpretability and generalization performance.

With the advancement of self-driving vehicles, autonomous driving systems depend on multimodal data to achieve a dynamic perception of the surrounding environment. Synthetic aperture radar (SAR) techniques can enhance azimuth resolution by utilizing the relative motion between the vehicle and targets, requiring a precise trajectory of the vehicle, normally without the assistance of automotive-grade navigation systems. In this case, data-driven autofocus-based algorithms are typically used to implement compensation for non-systematic motion errors. Despite demonstrating robust autofocus capabilities in numerous scenarios, their potential for application in automotive scenarios still needs to be exploited. This paper aims to provide a comprehensive automotive SAR imaging with autofocus workflow and to analyze the performance of autofocus algorithms based on phase gradient autofocus (PGA) in typical automotive scenarios. We rigorously derive the Omega-$\boldsymbol {K}$algorithm based on the system-grade waveform of frequency modulated continuous wave (FMCW) signals. Based on the analysis of motion error and phase error characteristics, a sub-aperture contrast-based weighted PGA (SAC-WPGA) method, a contrast-based selection strategy (CBSS), and a contrast-based WPGA kernel are proposed to improve the robustness of autofocus for automotive scenarios. In addition, we theoretically discuss the impact of the selection strategy, the PGA kernel, and the selection threshold in detail, highlighting the validity of the proposed method. Finally, we showcase the superiority of the proposed technique by employing experimental data in two typical automotive scenarios, i.e., a simple scenario with isolated dominant points and a complex scenario with strong clutter.

Vehicle trajectory data is essential for analyzing and modeling complex traffic behaviors. Although extraction of vehicle trajectory from aerial video data is not a new problem, obtaining trajectories with heading information across various road types, such as intersections or long road segments, requires further research. In this paper, we propose OpenVTER, a generalized Open-source Vehicle Trajectory Extraction framework based on Rotated bounding boxes (RBBs). This framework includes several key components: video stabilization, image division, vehicle detection, vehicle tracking, and data post-processing. Specifically, the rotated vehicle detection model, named YOLOX-R, is applied to detect the small and rotated vehicles using RBBs that provide vehicle heading information. A base-frame video stabilization method is proposed to reduce error accumulation in the transformation matrix and improve the computational efficiency. The rotated vehicle tracking model, named SORT-R, is proposed to enable real-time tracking of RBBs. The performance of YOLOX-R is evaluated on two datasets, showing that vehicle detection challenges are well addressed. Ablation experiments were also conducted to analyze the effectiveness of different modules. Subsequently, we evaluate the completeness of the extracted trajectories under various road types and lighting conditions. The extracted trajectories are also compared with the NGSIM dataset, focusing on internal and platoon consistency. These evaluations demonstrate both the effectiveness and practicality of the proposed framework. Additionally, the visualization analyses of different road types demonstrate the advantages of the trajectories extracted by OpenVTER in various road scenarios for traffic research. The code and dataset are available online for non-commercial research purposes.

This paper proposes an adversarial reinforcement learning (RL)-based traffic control strategy to improve the traffic efficiency of an integrated network with expressway and adjacent surface streets. The proposed adversarial RL integrates adversarial learning into a multi-agent RL model, namely the multi-agent advantage actor-critic (MA2C), so as to enhance the generalization of the control strategy against the mismatch between an offline-training environment and the real traffic process. In the adversarial RL, the RL model is trained to maximize the network throughput, while the adversarial network, which produces disturbances to observed traffic states, is trained based on the opposite reward of the RL model. The proposed control strategy is tested using the microscopic traffic simulation software, SUMO. To reproduce the difference between an offline-training environment and the real traffic process, two different traffic models in SUMO are used for offline-training and online-testing purposes, respectively. Simulation results demonstrate that the proposed approach performs better in reducing total time spent than the original MA2C approach, as well as a conventional feedback based controller.

In order to play the key role of automotive millimeter wave radar in intelligent vehicle systems, direction-of-arrival (DOA) estimation is an essential problem to be solved. For practical intelligent driving applications, DOA estimation requires both real-time performance and high accuracy. Due to unique advantages, deep learning (DL) based methods have attracted more attention. Most of the existing DL-based methods require a large number of snapshots, but only a few snapshots can be guaranteed in practical applications. Moreover, they usually model DOA estimation as a multi-label classification task. The output represents the position of signal DOA on the discrete grid, and the resolution will be limited by the grid. In this paper, a new space-time Network (STNet) is proposed, which models DOA estimation as a regression task to achieve the effect of gridless estimation. We design a space correlation extraction module (SCEM) and a time correlation extraction module (TCEM), using the covariance matrix of the received signal and the original received signal as inputs respectively, treat them as different types of data. In these two modules, skip connection dense blocks (SCDBs) and long short-term memory (LSTM) networks are adopted to process two different forms of data. Through such processing, we retain sufficient information, obtain more features for the regression task, and ensure the estimation effect of using a small number of snapshots. The experimental results indicate that the STNet shows obvious performance gain in the case of small snapshots, achieves gridless estimation effect, and demonstrates excellent adaptability in situations where target DOAs are closely positioned.

This paper extends an existing linear quadratic model predictive control (LQMPC) approach to multi-destination traffic networks, where the correct origin-destination (OD) relations are preserved. In the literature, the LQMPC approach has been presented for efficient routing and intersection signal control. The optimization problem in the LQMPC has a linear quadratic formulation that can be solved quickly, which is beneficial for a real-time application. However, the existing LQMPC approach does not preserve OD relations and thus may send traffic to wrong destinations. This problem is tackled by a heuristic method presented is this paper. We present two macroscopic models: 1) a non-linear route-specific model which keeps track of traffic dynamics for each OD pair and 2) a linear model that aggregates all route traffic states, which can be embedded into the LQMPC framework. The route-specific model predicts traffic dynamics and provides information to the LQMPC before the optimization and evaluates the optimal solutions after the optimization. The information obtained from the route-specific model is formulated as constraints in the LQMPC to narrow the solution space and exclude unrealistic solutions that would lead to flows that are inconsistent with the OD relations. The extended LQMPC approach is tested in a synthetic network with multiple bottlenecks. The simulation of the LQMPC approach achieves a total time spent close to the system optimum, and the computation time remains tractable.