Network-wide Traffic State Estimation (TSE), which aims to infer a complete image of network traffic states with sparsely deployed sensors, plays a vital role in intelligent transportation systems. With the development of data-driven methods, traffic dynamics modeling has advanced significantly. However, TSE poses fundamental challenges for data-driven approaches, since historical patterns cannot be learned locally at sensor-free segments. Although graph representation learning shows promise in estimating states at locations without sensors, existing methods typically handle unobserved locations by filling them with zeros, introducing bias to the sensitive graph message propagation. The recently proposed Dirichlet Energy-based Feature Propagation (DEFP) method achieves State-Of-The-Art (SOTA) performance in unobserved node classification by eliminating the need for zero-filling. However, applying it to TSE faces three key challenges: inability to handle directed traffic networks, strong assumptions in traffic spatial correlation modeling, and overlooking distinct propagation rules of different patterns (e.g., congestion and free flow). We propose DGAE, a novel inductive graph representation model that addresses these challenges through theoretically derived DEFP for Directed graph (DEFP4D), enhanced spatial representation learning via DEFP4D-guided latent space encoding, and physics-guided propagation mechanisms that separately handle congested and free-flow patterns. Experiments on three traffic datasets demonstrate that DGAE outperforms existing SOTA methods and exhibits strong cross-city transferability. Furthermore, DEFP4D can serve as a standalone lightweight solution, showing superior performance under extremely sparse sensor conditions. The code of this work is publicly available at:https://github.com/ZJU-TSELab/DGAE

Vehicle trajectory prediction is crucial for ensuring the safety and reliability of autonomous driving systems. Due to the highly stochastic nature of road participants’ behaviors, it is vital that prediction models accommodate a wide range of possible scenarios to mitigate safety risks. To address this challenge, we propose a novel trajectory prediction model called DiffusionTrajPred, an innovative trajectory prediction model based on the diffusion model. This model uniquely combines forward and reverse processes, manipulating noise levels in trajectory data to forecast future paths. Through the application of a mask-based reverse process, the model can make full use of historical trajectory information and predict trajectories that combine accuracy and multiple possibilities. The model utilizes a Transformer architecture for learning the noise, which enables the model to extract richer temporal information from trajectory data, resulting in improved semantic comprehension. Furthermore, we have effectively encoded high-definition (HD) semantic map information and vehicle interaction dynamics as crucial input features, improving the model ’s predictive power. Extensive experiments on the widely recognized open-source dataset ’Argoverse’ reveal that our method outperformed the most existing state-of-the-art methods in terms of accuracy and multimodality, demonstrating the diffusion model’s unique advantage in addressing the stochastic nature of road scenarios in autonomous driving.

The increasing proliferation of electric vehicles (EVs) and renewable energy sources (RESs) poses challenges to the operation of coupled power and transportation networks due to their uncertainties, where EV users' routing and charging behaviors are subjected to their complex decision-making rationality. To economically manage numerous fast charging stations with onsite RESs, this article focuses on the optimal day-ahead bidding and intraday scheduling strategies of a fast charging station aggregator (FCSA) to maximize its profit in the electricity market. Traffic simulation based on boundedly rational dynamic user equilibrium is presented to model charging demand under bounded rationality of EV users. To efficiently manipulate large-scale EVs, a group charging scheduling framework is proposed to reduce decision variables. Uncertainties in electricity prices, RES generation, traffic demand, and user rationality are addressed by stochastic programming. Case studies have validated the effectiveness of the proposed method in reducing the FCSA's operational costs and RES curtailment.

The urban transportation network is crucial for societal development, but it is prone to failures like congestion caused by accidents or disasters. In particular, often network-wide failure is the result of a series of cascading failures originating from a small set of individual links. To prevent such failures, it is essential to identify these critical links and take early action. However, most existing approaches in the literature for evaluating the importance of each link rely on manually designed metrics (e.g., the Network Robustness Index). These methods are time-consuming and not suitable for large-scale urban networks. Additionally, these metrics fail to accurately capture the dynamic traffic interactions influenced by vehicle movement. In this paper, we present a novel method for identifying critical links by learning effective traffic interaction representation (the spatio-temporal dependencies) among roads. By representing the network as an un-directed graph and abstracting the road links as the nodes, we introduce a temporal graph attention model to capture spatial and temporal dependence between nodes. This model combines a graph attention network and a long short-term memory neural network and produces an attention matrix, which represents traffic interactions among links. Furthermore, we propose a traffic influence propagation model to evaluate the influence of each link for the entire road network based on the traffic interaction representation. We rank the importance of links based on their influence and then identify the critical links. A real-world case study in the city of Hangzhou, China is conducted to test our method and we use the network efficiency ratio to quantify its performance. The results suggest that our method can effectively identify the critical links at different periods.

Recent research has shown that some network traffic flow patterns are similar across multiple traffic regions. Identifying and transferring these domain-invariant features can significantly boost model accuracy and robustness, providing new insights into dealing with modeling issues like traffic data insufficiency and dataset shift. However, how to acquire transferable network traffic flow patterns from multiple traffic regions and adapt such knowledge to downstream prediction tasks of target regions remains challenging. To realize domain-invariant traffic flow pattern transfer and provide more robust prediction under insufficient data conditions, we propose a macroscopic fundamental diagram (MFD) guided transfer learning method, namely physics-guided multi-source domain adversarial network (PG-MDAN). First, an MFD similarity measure is proposed to determine what traffic flow patterns are transferable and to what extent they can be transferred. PG-MDAN embeds this physics-informed transferability measure in domain adversarial pre-training for better adaptation ability. Numerical experiments based on two real-world urban network traffic datasets show that PG-MDAN can successfully transfer recurrent and non-recurrent network traffic flow patterns from multiple regions to provide more robust and responsive prediction performance. Finally, extensive sensitivity analysis is conducted, and the results validate that applying such physical regularization can effectively avoid negative transfer and provide a flexible tool to initiate traffic flow pattern transfer in practice.

Deep Reinforcement Learning has shown some promise in dynamic traffic signal control by adapting to real-time traffic conditions. However, multi-intersection control presents challenges, primarily due to the need for efficient information exchange across increasing intersections, and the importance of spatiotemporal dynamics in traffic flows. Traditional methods often focus solely on spatial or temporal aspects, leading to suboptimal control strategies. This paper introduces a novel Multi-Agent Incentive Communication Deep Reinforcement Learning (MICDRL) method, designed for collaborative control across multiple intersections. MICDRL features an incentive communication mechanism, allowing agents to generate customized messages that influence other agents’ policies, thereby enhancing coordination and achieving globally optimal decisions. A key feature of MICDRL is its reliance on local information for message generation, effectively reducing communication overhead while ensuring collaboration. Additionally, MICDRL integrates a teammate module that leverages temporal data for predicting other agents’ actions, crucial for understanding collective dynamics and spatial environment characteristics. Empirical results show that MICDRL outperforms several state-of-the-art methods in metrics like queue length and throughput. Furthermore, we introduce a tailored three-layer Internet-of-Things architecture to enhance data collection and transmission.

This paper proposes a generalized car-following (CF) model to depict the dynamics of traffic flow that includes human-driven vehicles (HDVs), connected vehicles (CVs) and connected and autonomous vehicles (CAVs). Notably, the model integrates human reaction times, information delays, and status data from multiple preceding vehicles endowed with communication capabilities. Then, by utilizing the perturbation method, the Intelligent Driver Model (IDM) as an example is taken in this CF model to determine the stability condition of the mixed traffic based on CAV penetration rate and their spatial distribution. Finally, comprehensive co-simulation using PreScan and MATLAB/Simulink is developed to explore the impact of varying CAV penetration rates across seven distinct spatial distributions on traffic capacity and dynamic performance. The findings underscore the efficacy of our proposed model in analyzing mixed traffic scenarios comprising HDVs, CVs, and CAVs. Increasing CAV penetration rates can lead to improved stability, capacity, and dynamic performance within mixed traffic environments. Notably, at the CAV penetration rate below 60%, the spatial distribution labeled as CAVs-HDVs-CVs (where CAVs lead the traffic flow, followed by HDVs, then CVs) demonstrates superior dynamic performance, whereas the HDVs-CVs-CAVs configuration (with HDVs leading, followed by CVs, then CAVs) performs worst. However, it’s noteworthy that spatial distribution scarcely affects dynamic performance when the CAV penetration rate exceeds 60%.

The connected automated vehicles (CAVs) are envisioned to be implemented most likely on electric vehicles, while traditional fuel-powered manually-driven vehicles (MVs) would probably still dominate the automobile market in the next decade. In this context, this paper addresses urban eco-driving of CAVs in mixed traffic and heterogeneous power conditions. The paper aims to develop a practical and deployable eco-driving strategy for CAVs in mixed traffic flow of CAVs and MVs under realistic and complex traffic conditions. Several typical eco-driving scenarios were studied in detail. In a nutshell, the eco-driving strategy for each CAV was determined by solving a typical two-point boundary value problem with minimum electric energy consumption in urban traffic conditions with small market penetration rates (MPRs) of CAVs. A rolling-horizon scheme was applied to implement the eco-driving strategy to handle uncertain/unpredictable disturbances of preceding MVs and the interference of junction queues to the eco-driving maneuvers of CAVs. The paper also studied how eco-driving for electrified CAVs would affect MVs’ fuel consumptions. Simulation studies were carried out on urban arterial roads of multiple signalized intersections in various scenarios of demand and MPR to verify the energy savings effect of the proposed eco-driving strategy. The results showed that via eco-driving electrified CAVs each had a potential of reducing energy consumption by 40%-61%, meanwhile leading to 5%-34% fuel savings on average for each following MV. Further issues concerning the energy saving mechanism of electrified CAVs, impacts of MVs cut-in from adjacent lanes, and passenger comfort were also examined.

Transportation demand forecasting is a critical precondition of optimal online transportation dispatch, which will greatly reduce drivers’ wasted mileage and customers’ waiting time, contributing to economic and environmental sustainability. Though various methods have been developed, the core spatio-temporal complexity remains challenging from three perspectives: (1) Compound spatial relationships. According to our empirical analysis, these relationships widely exist. Previous studies focus on capturing different spatial relationships using multi-homogeneous graphs. However, the information flow across various spatial relationships is not modeled explicitly. (2) Heterogeneity in spatial relationships. A region’s neighbors under the same spatial relationship may have different weights for this region. Meanwhile, different relationships may also weigh differently. (3) Synchronicity between compound spatial relationships and temporal relationships. Previous research considers synchronous influences from spatial and temporal relationships in a homogeneous fashion while compound spatial relationships are not captured for this synchronicity. To address the aforementioned perspectives, we propose the S patio- T emporal H eterogeneous graph A ttention N etwork (STHAN), where the key intuition is capturing the compound spatial relationships via meta-paths explicitly. We first construct a spatio-temporal heterogeneous graph including multiple spatial relationships and temporal relationships and use meta-paths to depict compound spatial relationships. To capture the heterogeneity, we use hierarchical attention, which contains node level attention and meta-path level attention. The synchronicity between temporal relationships and spatial relationships, including compound ones, is modeled in meta-path-level attention. Our framework outperforms state-of-the-art models by reducing 6.58%, 4.57%, and 4.20% of WMAPE in experiments on three real-world datasets, respectively.

The dynamic spatiotemporal characteristics of queues at urban intersections are crucial to traffic operation tasks such as signal performance measure and signal optimization. This paper addresses the high time-resolution estimation of queue profile at urban signalized intersection using Extended Kalman Filtering (EKF) with data of connected vehicles (CVs). The main features of this work are as follows: (i) a machine learning method was applied to construct a dynamic shockwave propagation model based on shockwave theory and historical data of CVs; (ii) a heuristic approach was proposed to measure the shockwave speed for use in EKF; (iii) an urban queue estimator was designed to combine the dynamic shockwave propagation model and real-time shockwave information via EKF to deliver second-by-second queue profile estimates. The queue estimator does not require any priori information about vehicle arrival patterns and the market penetration rate (MPR) of CVs. The performance and robustness of the queue estimator were evaluated using both simulation and real-world CV data. The results show that the method can provide satisfactory queue estimation results at various MPR levels of CVs, with the estimation error of 2.5 vehicles at the MPR of 5%, and of 0.5 vehicle at the MPR of 40%.

This paper proposes a new car-following (CF) model to capture the realistic behaviors of connected and automated vehicles (CAVs), whose communication topology (CT) among vehicles is characterized by graph theory in the V2V communication environment. By considering the heterogeneous time delays under the fixed and switching CTs, a generalized CF model is proposed. Based on the Lyapunov–Krasovskii method, a convergence analysis has been implemented for this new CF model with multiple time delays to obtain the convergence condition. Meanwhile, provides an estimate of the time delay bound. Finally, numerical experiments are performed under three typical fixed CTs (i.e., PF topology, BDLF topology, and TPLF topology) and the corresponding switching topology. Results support that the proposed CF model is capable of accurately reproducing the velocity, acceleration, position, and space headway profiles of CAVs traffic flow.

This article develops a new platoon control strategy for heterogeneous connected vehicles (CVs) subject to time delays and external disturbances. Specifically, based on the third-order vehicle model, a novel platoon controller is developed by embedding the variable time headway (VTH) spacing policy and the nonlinear motion coupling interactions between CVs. Simultaneously, an integral sliding mode (ISM) controller is developed to resist the disturbances. Then, the condition of asymptotic stability for the CV platoon and the upper bound of communication delay are deduced by using the Lyapunov theorem. Also, the string stability is proved by using the infinity-norm method. Finally, extensive simulations and co-simulations are provided to show the validity of the developed controller. Moreover, experiments with intelligent micro vehicles are conducted further to validate the practical feasibility of the developed controller.

This paper proposes a longitudinal platoon controller for connected vehicles (CVs) by considering the information of multiple preceding vehicles and the car-following interactions between CVs. The stability of the proposed controller is analyzed using the Routh criterion. For the verification, we develop an integrated platoon control framework for CVs in a V2V/V2I communication environment. The proposed framework consists of two main components: simulation platform and experimental platform. In particular, the simulation platform is developed based on the TransModeler software, and the experimental platform is designed using the self-developed V2X devices. Finally, a scenario of platoon forming is taken as an example and is conducted in simulation platform and experimental platform, respectively. Results demonstrate the effectiveness of the proposed controller with respect to the trajectory and velocity profiles.

With the rapid development of urbanization, the problem of urban traffic congestion has become increasingly prominent. Dynamic route guidance promises to improve the capacity of urban traffic management and mitigate traffic congestion in big cities. In the design of simulation-based experiments for most dynamic route guidance methods, the simulation data is generally estimated from a specific traffic scenario in the real-world. However, highly dynamic traffic in the city implies that traffic scenarios in real systems are diverse. Therefore, if a route guidance method cannot adjust its strategy according to the spatial and temporal characteristics of different traffic scenarios, then it cannot guarantee optimal results under all traffic scenarios. Thus, ideal dynamic route guidance methods should have a highly adaptive learning ability under diverse traffic scenarios so as to have extensive improvement capabilities for different traffic scenarios. In this study, an A* trajectory rejection method based on multi-agent reinforcement learning (A*R2) is proposed; the method integrates both system and user perspectives to mitigate traffic congestion and reduce travel time (TT) and travel distance (TD). First, owing to its adaptive learning ability, the A*R2can comprehensively analyze the traffic conditions for different traffic scenarios and intelligently evaluate the road congestion index from a system perspective. Then, the A*R2determines the routes for all vehicles from user perspective according to the road network congestion index. An extensive set of simulation experiments reveal that, under various traffic scenarios, the A*R2can rely on its adaptive learning ability to achieve better traffic efficiency. Moreover, even in cases where many drivers are not fully compliant with the route guidance, the traffic efficiency can still be improved significantly by A*R2.

Capacity drop at congested freeway bottlenecks is well known with a lot of field observations. This paper studies coordinated ramp metering (RM) and mainstream traffic flow control (MTFC) as well as their integration (RM+MTFC) for freeway traffic, with particular attention to effects of capacity drop on the performance of traffic control measures. Via mathematical analysis and comprehensive simulation studies under an optimal control framework, the work has revealed a capacity-drop-related mechanism that MTFC and ramp metering are based on to take effects, and obtained a number of important conclusions: (1) applications of any control measure (RM, MTFC, or RM+MTFC) in freeways are justified by the existence of capacity drop in field; (2) an appropriate usage of the control measures can effectively prevent the activation of potential bottlenecks on freeways and hence avoid capacity drop; (3) any control measure is beneficial for a large majority of the driver population in a freeway network if it can manage to increase the accumulated total network exit flow; (4) it is a common misconception that ramp metering would simply transfer traffic loads from the freeway mainstream to on-ramps. The work has also highlighted the strengths, weaknesses, and applicability of ramp metering and MTFC.