Multimodal transport hubs are pivotal nodes for improving urban transportation efficiency, and accurate passenger flow prediction constitutes the core of their operational management. Although massive volumes of data can be collected via Internet of Things (IoT) sensing systems, data missing frequently occurs due to equipment malfunctions and communication interruptions. Coupled with the inherently complex spatio-temporal dependencies of passenger flow, traditional methods prove ineffective in such scenarios. Existing studies mostly adopt the paradigm of imputation first, then prediction, which easily induces error propagation and lacks robustness under incomplete data conditions. To address this challenge, a novel Structured Decomposition and Integration (SDI) framework is proposed for robust passenger flow prediction with incomplete data. First, a Spectral-Guided Hierarchical Variational Mode Decomposition (SGH-VMD) method is designed to decouple the aliased modes of complex passenger flow sequences, yielding highly representative decomposed features. Second, with these decomposed features as inputs, a Dual Generative Adversarial Network with Gradient Penalty (Duel-GAN-GP) is constructed to collaboratively complete missing value generation and future sequence prediction, and aggregate the prediction results to reconstruct an integrated passenger flow structure. In addition, the model integrates an efficient self-attention mechanism with multi-scale positional encoding to capture long-range temporal dependencies and model the complex evolution process of passenger flow. Comprehensive validations are conducted on a real dataset from a large-scale multimodal transport hub. Experimental results show that the SDI framework outperforms mainstream baseline models in both accuracy and stability across various artificially simulated incomplete data scenarios, and can fully meet the requirements of real-time applications. Ablation experiments further verify the independent contributions of each core component, providing an effective theoretical solution for modeling complex spatio-temporal passenger flow under incomplete data conditions.

Vehicular ad hoc networks (VANETs) hold significant potential for enhancing road safety and traffic efficiency. The performance of VANETs heavily relies on the strategic deployment of roadside units (RSUs), which gather and disseminate critical information. A key challenge is that different types of information possess varying timeliness requirements, rendering delayed information ineffective. However, this crucial aspect has not been sufficiently addressed in the existing RSU deployment literature. To bridge this gap, we first classify operational scenarios based on discretized traffic flows and information types, analyzing their corresponding transmission time constraints. We then formulate an RSU deployment model that explicitly incorporates these heterogeneous timeliness requirements. To solve this complex problem, we develop a Branch-and-Benders decomposition (BBD) algorithm, which partitions the problem into a master problem for determining RSU locations and multiple subproblems for allocating vehicle communication demands in each scenario. The master problem is solved using a branch-and-cut procedure. Upon finding an integer feasible solution, the dual subproblems are solved to generate optimality and feasibility cuts that are dynamically added to the master problem. Furthermore, we introduce valid inequalities to accelerate convergence. Numerical experiments demonstrate that the proposed BBD algorithm can efficiently generate provably high-quality solutions.

The potential risks associated with various visual occlusion scenarios (VOS) vary greatly. For autonomous vehicles to make informed collision avoidance decisions, it is crucial to accurately assess the potential risk of each type of visual obstruction. However, this problem remains unresolved. In this paper, we simulate the data and knowledge driven cognitive mechanisms of human drivers and propose a human-like potential risk assessment method for VOS. During the perception phase, we move beyond the traditional image feature-based perception paradigm. Instead, we use natural language processing (NLP) to obtain textual semantic features of the scene as the perception result. Specifically, we utilize NLP techniques to construct a data driven VOS description model that generates textual descriptions of visible information in VOS as the perception result. In the risk assessment phase, inspired by human inductive and analogical reasoning, we develop a knowledge driven risk assessment model. Experimental results show that the proposed method can accurately assess the potential risks associated with different types of VOS, and in some cases, even identify risks up to 0.5 seconds earlier than human drivers.

This paper investigates an optimal operation problem for on-demand bus services within an advanced demand-responsive service platform, where passengers reserve their trip requests online. Each request specifies the passenger’s pickup and dropoff locations, service time window, and number of passengers. To enhance bus utilization, the operator incentivizes passengers within the same request to accept split pickup or delivery services and tolerate limited time window violations by offering specific fare discounts. The problem is formulated as a mixed-integer model that jointly optimizes the route and schedule for each bus, with the objective of minimizing the total system cost. To address this problem, a time-window-backward-induction approach is initially introduced to efficiently formulate the bus schedule while accounting for time window flexibility. Building on this approach, a variable neighborhood search with customized operators is developed to optimize bus routes while adhering to bus capacity and time window constraints, particularly in scenarios involving passenger split pickups and deliveries. Algorithm comparisons across extended benchmark instances demonstrate the superior performance of the proposed algorithm in scenarios characterized by narrow time windows, high request volumes, and limited fleet sizes. Subsequently, large-scale experiments based on real-world ride-hailing data are conducted to provide managerial insights and guide operators in designing a cost-efficient on-demand bus system.

Traffic flow analysis largely depends on accurate predictions of microscopic speed. Due to the complexity and stochastic of real-world driving environments, traditional model-driven methods face significant challenges. In recent years, data-driven methods that combine advanced intelligent algorithms have emerged to address the issue of vehicle speed prediction. However, most existing studies primarily focus on the static spatiotemporal relationships between vehicles, with only a few exploring dynamic spatiotemporal correlations. In this study, a new graph structure, named the vehicle generalized-dynamic graph, is constructed to characterize the vehicle trajectory, emphasizing the spatial and temporal evolution of vehicles. In the spatial dimension, we employ the potential field theory to compute the field strength of vehicles in different motion states, enhancing the description of interdependencies among vehicles. In the temporal dimension, the movements of each vehicle at different time points are interrelated. Furthermore, we propose a novel neural network architecture, named the dynamic edge graph convolutional network (DEGCN), to address the vehicle speed prediction problem. The DEGCN model is evaluated through experiments on three real-world vehicle trajectory datasets. The experimental results demonstrate that the proposed model outperforms other baseline models in terms of prediction performance. Additionally, various ablation studies are conducted to evaluate the effectiveness of different components, the potential field theory, and the vehicle generalized-dynamic graph structure.

Maintaining safety and efficiency for mixed traffic consisting of Connected Automated Vehicles (CAVs) and Human-driven Vehicles (HDVs) is an arduous task due to the inherent HDVs’ stochasticity. Especially for longitudinal control, which is the basic function of vehicle automation, prevailing research primarily considers CAV’s car-following control merely the acceleration and deceleration of leading vehicles. However, this approach overlooks the potential disruptions caused by surrounding vehicles executing lane changes, which can significantly impact the control vehicle’s stability and overall safety. Hence, our study introduces a predictive deep reinforcement learning (DRL) longitudinal CAV controller. This innovative approach leverages prediction from a physics-informed neural network as well as the control capability of DRL to better anticipate and mitigate issues arising from lane-changing, enhancing the safety and efficiency of CAVs in such scenarios. Validated by the numerical simulations embedded with the real-world data, the results indicate that the proposed controller significantly enhances the safety and efficiency of CAVs in situations involving lane changes by other vehicles, showcasing its potential as a valuable tool in advancing CAV technology in mixed traffic.

In an Autonomous Vehicle-Mixed Traffic Flow (AV-MTF) environment, accurately predicting vehicle speeds is essential for vehicle and traffic operation and management. However, existing research has not achieved high-precision vehicle speed prediction in mixed autonomous traffic environments. To address this, we proposed a car-following speed prediction and anomaly detection method based on the Attention-LSTM-Transformer model. We first employ a multihead attention enhanced LSTM network to dynamically classify vehicle categories in the AV-MTF environment based on vehicle motion states. We propose a novel Transformer-based model that embeds classification labels and car-following state information, enabling precise speed prediction in AV-MTF environments. Additionally, the anomaly detection algorithm is proposed to identify abnormal speeds in car-following situations, covering both constant and instant offsets. The proposed models were trained and tested using the OpenACC dataset, and the effectiveness of the Attention-LSTM-Transformer-based speed prediction model and anomaly detection algorithm is validated. Results show that the classification model achieves an accuracy of 95.57%. Compared to baseline models, the speed prediction model considering vehicle category labels effectively reduces the prediction errors by more than 6.8% in all horizons. This car-following speed anomaly detector achieves over 99% accuracy for constant speed offsets and nearly 90% detection rate for small instant speed anomalies. The findings of this study provide valuable insights for vehicle and traffic operation and management in future AV-MTF environments.

To ensure the track-keeping performance of superhighway driving and improve driving safety, a virtual track-keeping control algorithm is proposed for the vehicle yaw dynamics model based on the discrete effect of Variable Step-length Model Predictive Control (VSMPC). The transverse swing angular velocity-lateral velocity phase plane is employed as the stability criterion for the virtual track environment and front wheel deflection angle constraints. This paper verifies the applicability of the vehicle traveling on superhighway straight lines, circular curves, and combined road sections from the aspects of real-time and accuracy, which demonstrates the effect and stability of the virtual track-keeping control algorithm under the conditions of different vehicle speeds. The results show that the virtual track-keeping control algorithm based on VSMPC can restrict the vehicle with a speed up to 180km/h to the virtual track and a lateral offset within 4cm, thereby maintaining well-driving stability. The VSMPC control strategy effectively avoids the problem of poor model fidelity caused by high vehicle speed and effectively balances the computational efficiency and accuracy of the vehicle under the state of super-high-speed driving.

Truck parking on freight corridors faces the major challenge of insufficient parking spaces. This is exacerbated by the Hour-of-Service (HOS) regulations, which often result in unauthorized parking practices, causing safety concerns. It has been shown that providing accurate parking usage prediction can be a cost-effective solution to reduce unsafe parking practices. In light of this, existing studies have developed various methods to predict the usage of a truck parking site and have demonstrated satisfactory accuracy. However, these studies focused on a single parking site, and few approaches have been proposed to predict the usage of multiple truck parking sites considering spatio-temporal dependencies, due to the lack of data. This paper aims to fill this gap and presents the Regional Temporal Graph Convolutional Network (RegT-GCN) to predict parking usage across the entire state to provide more comprehensive truck parking information. The framework leverages the topological structures of truck parking site locations and historical parking data to predict the occupancy rate considering spatio-temporal dependencies across a state. To achieve this, we introduce a Regional Decomposition approach, which effectively captures the geographical characteristics of the truck parking locations and their spatial correlations. Evaluation results demonstrate that the proposed model outperforms other baseline models, showing the effectiveness of our regional decomposition. The code is available at https://github.com/raynbowy23/RegT-GCN.

Transportation Cyber-Physical Systems (T-CPS) enhance safety and mobility by integrating cyber and physical transportation systems. A key component of T-CPS is the Digital Twin (DT), a virtual representation that enables simulation, analysis, and optimization through real-time data exchange and communication. Although existing studies have explored DTs for vehicles, communications, pedestrians, and traffic, real-world validations and implementations of DTs that encompass infrastructure, vehicles, signals, and communications remain limited due to several challenges. These include accessing real-world connected infrastructure, integrating heterogeneous, multi-sourced data, ensuring real-time data processing, and synchronizing the digital and physical systems. To address these challenges, this study develops a traffic DT based on a real-world connected vehicle corridor. Leveraging the Cellular Vehicle-to-Everything (C-V2X) infrastructure in the corridor, along with communication, computing, and simulation technologies, the DT accurately replicates physical vehicle behaviors, signal timing, communications, and traffic patterns within the virtual environment. Building upon the previous data pipeline, the digital system ensures robust synchronization with the physical environment. Moreover, the DT’s scalable and redundant architecture enhances data integrity, making it capable of supporting future large-scale C-V2X deployments. Lastly, the DT’s ability to provide feedback to the physical system is demonstrated through applications such as signal timing adjustments, vehicle advisory messages, and incident notifications. The proposed DT is a vital tool in T-CPS, enabling real-time traffic monitoring, prediction, and optimization to enhance the safety and mobility of transportation systems.

Efficient identification of key nodes is crucial to optimizing detector deployment and enhancing traffic monitoring in intelligent transportation systems. However, existing approaches often struggle to adapt to dynamic traffic variations, leading to suboptimal coverage and increased deployment costs. We propose bidirectional temporal convolutional graph attention networks (BTC-GATs) to address these limitations. This novel framework integrates bidirectional attention mechanisms to capture upstream and downstream dependencies, temporal convolutional networks for multiscale feature extraction, and graph attention networks for spatial information aggregation. BTC-GATs incorporates adaptive temporal modeling to capture nonlinear traffic dynamics, gradient-based variation analysis to quantify node influence, and a ranking mechanism that fuses attention coefficients with topological attributes to further enhance robustness and interoperability. In addition, a key node coverage study is conducted to examine the trade-off between accuracy and deployment efficiency. Extensive experiments on the California Highway PeMS04 dataset demonstrate that BTC-GATs outperforms benchmark methods in key node identification, offering superior accuracy and stability. Further analysis confirms its robustness under varying traffic conditions and initialization settings, highlighting its potential as a scalable, adaptive, and cost-effective solution for intelligent traffic monitoring. By facilitating efficient sensor placement, BTC-GATs contributes to improved data collection and congestion management in large-scale transportation networks.

This article provides a comprehensive analysis of the effects of connected and automated vehicles (CAVs) market penetration rate, spatial distribution, and V2X communication on the stability of heterogeneous traffic flow. We explore stability variations across different scenarios by developing a car-following model and analyzing stability conditions. Our findings show that increasing CAV market penetration enhances traffic flow stability by expanding the stable speed range and reducing the unstable speed range. Additionally, we investigate the influence of CAV spatial distribution and V2X communication on traffic flow stability. The results reveal that forming CAV platoons reduces intervehicle interference, thus improving stability. Furthermore, V2X communication enhances traffic flow stability by enabling more accurate prediction and control of car-following behaviors. We also examine the impact of cyberattacks on heterogeneous traffic flow, finding that such attacks cause unnecessary accelerations, decelerations, and delays, thereby increasing accident risks. Finally, we acknowledge the study’s limitations and propose future research directions, including nonlinear stability analysis of heterogeneous traffic flow and developing effective control strategies to mitigate the adverse effects of cyberattacks.

High-quality traffic flow data is foundational to the study of traffic issues and practical engineering applications. The development of traffic flow detection methods has greatly facilitated the collection of traffic data; however, anomalies caused by factors such as equipment, networks, and environmental conditions present a common challenge. Traditional data restoration methods, which require extensive complete historical data as prior knowledge, are difficult to implement. In this study, we first analyze and categorize the causes of anomalous data, and introduce strategies for anomaly identification in multi-source freeway data. Based on the unsupervised learning framework of Generative Adversarial Network (GAN), and leveraging their advantages in data generation, we propose an Auxiliary Discrimination Mechanism-based Generative Adversarial Network (ADM-GAN) for the task of traffic flow data restoration. The optimization of the generator and discriminator and the auxiliary discrimination matrix, constructed from the generator’s output and the original data features, enhances the model’s utilization of original data. We tested our model using ETC traffic flow data from the G50 freeway near Suzhou, China. The results demonstrate that ADM-GAN outperforms other state-of-the-art methods in data restoration tasks across various data missing rates. This research offers an efficient and reliable method for freeway traffic data restoration.

The accurate prediction of traffic conditions is essential for effective and efficient traffic management and control. The dynamic and complex nature of traffic data, characterized by intricate temporal and spatial features, presents significant challenges to accurate traffic forecasting. While previous studies have developed various models with advanced algorithms, they often fail to fully capture the holistic spatio-temporal features and the dynamically evolving correlations within traffic networks. Additionally, these studies often overlook the potential of adjacency matrices learned from real-time traffic data to more accurately represent the interconnectivity of nodes within road network. To address these gaps, this study introduces the Generalized Dynamic Spatio-Temporal Graph Convolutional Network (GDSTGCN), a novel prediction model tailored for traffic data. First, this model builds a learning-based generalized dynamic graph structure, which incorporates both spatial and temporal connections and evolves with real-time traffic data. Then, a generalized dynamic graph convolution, integrated with graph diffusion, is crafted to operate on the designed generalized dynamic graph structure. This plays a critical role in holistically capturing local and global spatio-temporal traffic dependencies. Moreover, the generalized dynamic graph convolution is incorporated with Temporal convolution and other essential components, forming a cohesive framework that enables effective and efficient traffic flow predictions. To validate the performance of the GDSTGCN model, we conducted extensive experiments using four real-world road network datasets. The results demonstrate that our model outperforms existing state-of-the-art GCN-based models and traditional baseline methods.

Accurately predicting the probability of crashes is crucial for preventing traffic crashes and mitigating their impacts. However, the imbalance in crash data, irregular road network structures, and heterogeneity in multi-source data pose significant challenges. To address these issues, this study introduces a spatio-temporal graph convolutional network traffic crash prediction model based on Voronoi diagrams that considers geographical spatial distribution. Initially, this study introduces a spatial partitioning method based on Voronoi diagrams, grounded on the geographic spatial distribution characteristics of traffic crashes. It constructs a novel graph structure with spatial units within Voronoi diagrams as nodes and the shared length of different road types between units as edges. This graph structure integrates the spatial distribution characteristics of crashes with the graph structure, substantially contributing to addressing the zero-inflation problem inherent in spatial units constructed on a grid basis. Subsequently, the study employs a GCN (Graph Convolutional Network) and Transformer encoder to build the VSTGCN (Voronoi-Based Spatio-Temporal Graph Convolutional Network) crash prediction model, evaluating its effectiveness using real data from New York City. Comparisons with eight baseline models demonstrate that VSTGCN outperforms them in all evaluation metrics. Moreover, the paper conducts model ablation studies from different perspectives, such as feature modules and graph structure composition, revealing that the chosen spatial, temporal, and spatio-temporal features significantly influence the model’s predictive performance, with spatial features having the most substantial impact. Finally, the novel graph structure based on Voronoi diagrams proposed in this study shows a clear advantage in model effectiveness compared to traditional graph structures. This research can effectively handle complex crash data structures and accurately predict crash probabilities, providing a reliable basis for developing measures to prevent crashes and alleviate their impacts.

This study introduces a novel approach that integrates dynamic Bayesian network with attention based spatio-temporal graph convolutional network to forecast railway train delays, capturing the intricate operation interactions between train events and the dynamic evolution of train delays. Initially, train delay patterns are identified using the K-means clustering algorithm and incorporated as additional variables into the prediction model. To capture dynamic causality in delay propagation, we utilize a dynamic Bayesian network-based dynamic causality graph, incorporating train delay data and domain knowledge to effectively model the train delay propagation. Leveraging these insights on delay dynamic propagation, we propose an attention based spatio-temporal graph convolutional network that effectively models the dynamic spatio-temporal dependency among train events and enhances the accuracy of delay predictions. The proposed method is assessed using operational data from the Wuhan-Guangzhou high-speed railway. Results show that the proposed model outperforms the baseline models, particularly with the expansion of the prediction horizon. The learned dynamic causality of the train delay propagation enhances interpretability and results in a 6.97% reduction in mean absolute error. Furthermore, train delay patterns and weather variables contribute to a respective 12.85% and 4.37% reduction in mean absolute error. The statistical tests further validate the efficacy of the proposed model.

Vehicular Ad hoc Networks (VANETs) in intelligent transportation systems have been regarded as an effective means to alleviate traffic congestion, reduce traffic accidents and save fuel. A proper roadside unit (RSU) deployment strategy is essential to improve the efficiency and stability of VANETs’ communication. However, the RSU deployment strategy that combines coverage and quality of service is still limited. To provide city planners with decision-making support, a multi-objective optimization model is built to optimize the deployment of RSUs under a limited budget. Two objective functions are proposed to maximize the number of communication tasks served and minimize the total task-weighted delay. Through a simple transformation of the delay matrix, we transform the proposed multi-objective model into a p-median problem. Then, we design a Lagrangian relaxation algorithm in a multi-objective framework to solve the model. Moreover, simulation examples are presented to demonstrate and validate the proposed model and solution algorithm. We analyze the gap between the algorithm result and the optimal solution, and characterize the Pareto front. The simulation results verify the feasibility and effectiveness of the proposed model and algorithm.

With the rapid development of Internet of Things and communication technologies, the connected vehicle technology with vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication is seen as the most promising solution for reducing traffic accidents and alleviating traffic congestion. Roadside Units (RSUs) play a crucial role in enabling V2I communication, as they can gather and broadcast traffic event information in the road network. Implementing a well-thought-out RSU strategy can significantly improve the stability and efficiency of traffic event information transmission in the road network. However, there is a lack of effective strategies for RSU deployment in stochastic scenarios. The presence of unpredictable factors like equipment failures and network attacks may disrupt the normal functioning of the RSUs. To guide the deployment of roadside facilities, we analyze the transmission time of traffic events in the road network and construct a multi-objective RSU deployment model considering the possibility of RSU failures. This model aims to maximize the number of connected vehicles served and minimize the expected transmission time of events. Through fuzzy programming theory and different decision preferences, we transform the two objectives into a single objective function. A random-key genetic algorithm (RKGA) is designed to solve the transformed model. Moreover, several simulation examples are presented to verify the feasibility and effectiveness of the proposed model and algorithm. The results indicate that decentralized deployment is preferred for low RSU failure probabilities, while centralized deployment is preferred for high failure probabilities.

The roadside unit (RSU), which enables vehicle-to-infrastructure communication, is essential for improving the communication performance of vehicular ad hoc networks. However, optimizing the deployment of RSUs while considering their deployment at both fixed locations and on mobile vehicles remains a challenging issue. To bridge this gap, we develop two spatio-temporal networks derived from vehicle trajectories. Subsequently, the joint deployment challenge of static and mobile RSUs is articulated as a mixed-integer programming model. After linearization, the model can be directly solved by CPLEX. Additionally, the integrated optimization problem can also be formulated as a route-based model. Due to the exponential growth of route numbers, a branch-and-price (BAP) algorithm is designed to solve the route-based model. Within the framework of the BAP, we develop a heuristic technique for generating effective initial solutions. Based on the characteristics of the spatio-temporal network, a directed acyclic graph shortest path algorithm is utilized to accelerate the solution of column generation pricing problem at each node. Simulation examples are presented to demonstrate the proposed algorithm. The results indicate that the BAP can generate verifiable high-quality solutions and has a significant speed advantage over CPLEX for large-scale problems. Furthermore, a series of sensitivity analyses are conducted to assess the system’s responses to various influencing factors.

Aiming at improving the operation of the bottleneck area of the highway in the environment of a connected and automated vehicle, this paper proposes an integrated lane-level control (ILC) method by combining the variable speed limit control method and lane selection method into a comprehensive framework. A lane-level variable speed limit (LVSL) control method is proposed for the mixed traffic flow based on a deep deterministic policy gradient algorithm. Then, a lane-level short-term traffic prediction (LSTP) model based on hybrid deep learning is built to forecast the traffic state in a next control horizon. Finally, a lane selection method using a dynamic programming algorithm is established for the connected automated vehicle (CAV) to look for the optimal lane-level route by considering the estimated traffic speeds and limit speeds from LSTP and LVSL respectively. Comprehensive simulation-based evaluation experiments were conducted in various scenarios e.g., with different traffic demands, penetration rates of CAVs, length of control horizons, and the number of lanes. The evaluation results reveal that the proposed LSTP model outperforms the state-of-the-art traffic prediction models in terms of accuracy and stability. In addition, the proposed ILC method is capable of improving the traffic operation of the bottleneck efficiently by synthetically taking the advantage of the LVSL method and lane selection method. Compared with the no-control strategies, the ILC method can reduce total travel time by more than 30% in various traffic scenarios.

Effective classification of autonomous vehicle (AV) driving behavior emerges as a critical area for diagnosing AV operation faults, enhancing autonomous driving algorithms, and reducing accident rates. This paper presents the Gramian Angular Field Vision Transformer (GAF-ViT) model, specifically designed for analyzing AV driving behavior. The GAF-ViT model is developed upon a novel integration of three key components: GAF Transformation Module, which transforms multivariate driving behavior representative sequences into multi-channel images; Channel Attention Module, which prioritizes relevant behavioral features to enhance classification effectiveness; and Multi-Channel ViT Module, which employs advanced image recognition techniques to accurately classify the resulting multi-channel driving behavior images. This framework not only facilitates detailed analysis of complex multivariate driving behavioral data but also leverages the capabilities of vision-based pattern recognition methods to uncover subtle driving behavior nuances. Experimental evaluation on the Waymo Open Dataset of trajectories demonstrates that the proposed model outperforms baseline models, achieving state-of-the-art performance. Furthermore, an ablation study effectively validates the efficacy of individual modules within the model.

This paper proposes a framework for deep Long Short-Term Memory (D-LSTM) network embedded model predictive control (MPC) for car-following control of connected automated vehicles (CAVs) in traffic mixed with human-driven vehicles (HDVs) and CAVs. The framework consists of: 1) lead HDV trajectory prediction through D-LSTM; and 2) CAV car-following control via MPC based on the predicted vehicle trajectory. For the trajectory prediction, two D-LSTM structures are developed based on the availability of preceding vehicle information: 1) ‘sufficient’ historical information of the position and speed of multiple vehicles ahead; and 2) ‘insufficient’ information where preceding vehicle information is unavailable (e.g., due to failed communication). Based on the prediction, a distributed MPC is designed for each scenario by incorporating the predicted trajectory into state space construction. The proposed D-LSTM models are trained and tested with the NGSIM data for validation. Numerical simulation results for various traffic conditions suggest that the proposed strategies perform better than traditional MPC methods in terms of control objective cost reduction, smoother control, and stabilizing effect. The results also indicate that the sufficient information case outperforms the insufficient information case as expected, which highlights the importance of stable communication.

Vehicle trajectory prediction is crucial and indispensable for ensuring the safe and efficient operation of autonomous vehicles in complex traffic environments. The application of Internet of Things technology in the collaborative automated driving system (CADS) has established a robust data foundation for vehicle trajectory prediction. Accurate prediction requires not only a substantial amount of high-quality data but also a deep understanding of the vehicle’s driving characteristics and interactions between neighboring vehicles. To enhance the study of vehicle trajectory prediction, this article proposes a novel Social Force-constrained Gated Recurrent Unit (SF-GRU) model, which integrates data-driven and physics-driven models. Specifically, the SF-GRU model is based on the gated recurrent unit encoder–decoder framework and incorporates social force constraints to enhance and supplement the model input based on vehicle time-series trajectory data, which describes the driving and interactive behaviors of vehicles during driving, as well as the interactions between neighboring vehicles and the surrounding environment. The model is trained and validated using the next generation simulation data set. Experimental results demonstrate that the SF-GRU model outperforms existing state-of-the-art models in both longitudinal and lateral motion, and that social force constraints are more effective than spatial variables in improving prediction accuracy. Furthermore, the SF-GRU model can intuitively and accurately consider the interactions between vehicles, and precisely describe the changes of relevant variables in the prediction process, thus enhancing the interpretability of the data-driven model. The SF-GRU model has great potential in vehicle trajectory prediction and can provide important support for the practical implementation of autonomous driving vehicles.

Oversaturation has become a serious issue for urban intersections worldwide due to the rapid increase in population and traffic demands. The emergence of connected and automated vehicle (CAV) technologies demonstrates the potential to improve oversaturated arterial traffic. Integrating vehicular control and intersection controller optimization into a single process based on CAV technologies can optimize the performance of mixed traffic flow scenarios with various levels of CAV market penetration. This paper proposes an efficient reservation-based cooperative ecodriving model (RCEM) for an isolated intersection under partial and complete CAV market penetration, which can simultaneously optimize the CAV trajectories and intersection controller. CAVs are utilized to precluster manual vehicles into a platoon to improve vehicle passage efficiency. Then, a heuristic-based algorithm is developed to effectively obtain an optimal solution. The proposed RCEM scheme is compared with fixed signal control and actuated signal control in a Simulation of Urban MObility (SUMO)-based platform. Experimental results prove that the RCEM scheme outperforms the fixed signal control and actuated signal control in terms of stop delay, fuel consumption, and emissions under the condition of low levels of CAV penetration. Sensitivity analysis indicates that the system performance further improves as the CAV penetration rate increases, and the stop delay is almost eliminated when the CAV market penetration reaches 100%. Furthermore, the vehicle delay fluctuation under left-turning rates ranging from 5%-75% is 4.4 sec, which is far better than the vehicle delay fluctuation of the fixed signal control (176 sec) and actuated control (65.6 sec).

Autonomous intersection management has become a state-of-the-art control strategy customized for connected and autonomous vehicles. Combining the advantages of tile-based and conflict point-based approaches, this paper proposes a two-stage optimization method based on a developed intersection modeling approach. The first stage is a timing schedule optimization model, assigning vehicle arrival times at an intersection. Based on the output of the first stage, the second stage is a trajectory optimization model, which gives the eco-driving strategies. Moreover, a rolling optimization with a variable cycle length is adopted to run the method continuously. Simulation results show that the proposed method outperforms the genetic algorithm-based method in terms of computation time, and can reduce vehicle delay and fuel consumption by 89.48% and 46.84%, respectively, under different traffic demands compared to the first-come-first-serve method. Furthermore, the performance of the proposed method under asymmetric traffic demand is discussed. Sensitivity analyses suggest that (1) a long cycle length benefits the proposed method within certain limits and (2) a proper deceleration within the intersection can balance traffic delay with fuel consumption. In addition, an additional model with a heuristic rule is compared with the original timing schedule optimization model. It is found that reducing binaries in the first stage can make a tradeoff between the quality of the solution and efficiency, which can be used in conjunction with long cycles.

To solve the problems of when to set up connected automated vehicles (CAVs) dedicated lanes and how many CAVs dedicated lanes to set up under different penetration rates of CAVs, this work focuses on modeling the fundamental diagram of mixed traffic flow with dedicated lanes for CAVs. Firstly, the car-following modes and their proportion of mixed traffic flow without and with CAVs dedicated lanes are analyzed. Secondly, the fundamental diagram of mixed traffic flow is derived based on car-following models to analyze the traffic capacity with and without CAVs dedicated lanes. Then, the relevant properties of the fundamental diagram with CAVs dedicated lanes are proposed and proved. Finally, the sensitivity of related parameters (e.g., CAVs penetration rate, time headway, and free-flow speed) in the fundamental diagram is discussed. Results show that (1) the increase of CAVs penetration rate and free-flow speed can improve the traffic capacity; (2) the design of smaller CAVs time headway benefits traffic capacity. Moreover, one and two CAVs dedicated lanes of three manual lanes are set to improve the traffic capacity to the greatest extent when the penetration rate of CAVs reaches 0.6 and 0.86, respectively. It is noteworthy that developing CAVs dedicated lanes under a reasonable CAVs penetration rate does not waste resources and increases traffic congestion while improving traffic capacity.

Most existing cellular probe-based freeway congestion detection methods rely on on-call WLT (Wireless Location Technologies) signal transition data. However, these techniques facing difficulties such as small sample size, frequent road tests, safety, and privacy issues. This article presents a novel approach using the FCA data for traffic congestion detection on freeways. Two cellular activity features, the link pseudo speed and link probe activity, are defined and calculated. A rule-based algorithm is then developed to determine the traffic congestion state. The proposed method has been implemented and a prototype system has been deployed for a major freeway corridor in China. Validated by fixed-point detector data and incident records, the proposed method is able to identify real-time freeway traffic congestion accurately.

This paper proposes a new dynamic driving risk potential field model under the connected and automated vehicles environment that fully considers the dynamic effect of the vehicle’s acceleration and steering angle. The statistical analysis of the model’s parameter reveals that acceleration and steering angle will directly affect the distribution of the driving risk potential field and that this strong correlation should not be ignored if one is interested in the vehicle’s microscopic motion behavior. We further develop a driving risk potential field-based car-following model (DRPFM) to remedy the failure of acceleration consideration under the conventional environment, whose parameters are calibrated by filtered I-80 NGSIM data with frequent traf?c oscillations. Simulation results indicate that our proposed DRPFM model is proved to be a good description of car-following behavior and outperforms two classical car-following models (Optimal Velocity Model and Intelligent Driver Model) in frequent oscillation phases due to our consideration of potential acceleration data acquisition in real-time under the CAVs environment. In addition, this DRPFM model is applied to deduce the safety conditions for vehicle lane-changing. The analysis results prove that this model can reasonably explain the influencing factors between driver types and lane-changing safety conditions in practice.

The intersection is a critical traffic problem from the perspective of safety and traffic efficiency. As wireless communication technology advances, vehicle infrastructure cooperative approaches have received increased attention. In this paper, we propose a cooperative critical turning point method to help the cooperation between vehicles and infrastructures to improve the traffic efficiencies. The idea of cooperative critical turning point improves the cooperation between connected automated vehicles, the surrounding traffic and roadside infrastructures in order to provide high efficiencies of the intersection. An intersection management system using such a method is implemented based on the framework of the connected automated vehicle highway system. Such system can efficiently allow a roadside infrastructure receives state information from vehicles, reserve the associated intersection time-space occupancy, and then provide decision-making and planning feedback to the vehicles. The vehicles covered by the system then adjust their trajectories to meet their assigned time slot. The study validates the proposed system that considers the uncertainties of the driving environment by formulating the problem into a POMDP problem and solves it using an online solver. Based on preliminary simulation experiments, the proposed strategy can significantly reduce travel delays, decrease stops and improve the sustainability of the traffic system.

Lane-level traffic state prediction is one of the most essential issues in the connected automated vehicle highway systems. Accurate and timely traffic state prediction of the lane sections can assist the connected automated vehicles in planning the optimal route and making lane selection. In this article, we tackle the problem of forecasting lane-level short-term traffic speed and propose a novel mixed deep learning (MDL) model by coordinating the convolutional long short-term memory (Conv-LSTM) layers, convolutional layers, and a dense layer in an end-to-end structure. The introduction of the Conv-LSTM neural network enables the proposed MDL model to better capture the spatio-temporal characteristics and correlations of the dynamic lane-based traffic flow synchronously. To improve the efficiency of the proposed model, a feature correlation analysis method based on the maximum information coefficient is presented to measure the relevance between the historical traffic flows and the traffic speeds to be forecasted. Validated by the ground-truth traffic flow data collected by the remote traffic microwave sensors installed on the expressways in Beijing, the MDL model is capable of capturing the fluctuation of the lane-level traffic speeds at different types of lanes effectively during the whole day. Furthermore, the results confirm that the MDL model achieves better predictive performance than several state-of-the-art benchmark models in terms of prediction accuracy and space-time distributions. Our code and data are available athttps://github.com/lwqs93/MDL.

In the conventional variable speed limit (VSL) strategy, the control area is fixed under confined conditions. With the facility of the roadside unit, the control area for the VSL will vary in real-time in the connected environment. This study proposed an extended model-based VSL controller to improve traffic efficiency in the connected environment. The controller was designed based on the scheme of model predictive control (MPC). In the controller, an extended cell transmission model (CTM) with variable-length cells was established. The cell length variation was introduced to describe the characteristics of the variable control area. The optimizer in MPC is an improved Genetic Algorithm. A numerical simulation was conducted to show how the method, with the cooperation of variable speed limit and variable control area, alleviates the shock waves. The performance of the method was compared with a conventional VSL without a variable control area. The results show that the extended model-based VSL controller reduces the total travel time by 14.57% compared with the conventional VSL controller. The compared results illustrate that the proposed VSL controller can effectively resolve shock waves produced by the incident.

Recent advances in deep reinforcement learning have shown promising results in solving sophisticated control problems with high dimensional states and action space. Inspired by this, we use the latest deep reinforcement learning (DRL) methods to improve freeway traffic mobility and alleviate recurring bottlenecks and congestion. More specifically, this paper proposes a centralized traffic control system that can coordinate multiple ramp metering (RM) and variable speed limit (VSL) traffic controllers on freeways to minimize the total travel time. The system uses a novel double-layer structure to synchronize different traffic controllers and introduces the actor-critic-based DRL methods to learn joint actions in a high-dimensional traffic environment. The reward function takes into account the waiting time of vehicles, the average speed of different road sections, and the on-ramp queuing limit to improve traffic mobility. We also proposed an integrated feedback controller as a benchmark. The simulation results show that the actor-critic-based methods are superior to other methods and can save more than 20% of the total travel time. We also analyzed the curse of dimensionality problem by comparing the performance of two scenarios in the simulation: one is a single-ramp interweaving area scenario; the other is a large freeway corridor with multiple on-ramps and off-ramps. The results show that our system can effectively handle these two situations without significant performance degradation, which means that the centralized control system can effectively control freeway corridors by directly guiding various traffic controllers. This also leads to the conclusion that we can use a centralized actor-critic-based control unit to manage medium-scale freeway traffic to save computing resources instead of using complex collaboration strategies.

The large-scale application of connected automated vehicles (CAVs) provides new opportunities and challenges for the optimization and management of traffic conflict zones. To improve the traffic efficiency of conflict zones and reduce the travel delay and fuel consumption of CAVs, this paper presents a two-level optimization method of scheduling and trajectory planning for CAVs. At the first level, a 0–1 mixed-integer linear program (MILP) is proposed for vehicles entering scheduling. At the second level, a multi-vehicle optimal trajectory control model is developed based on the optimal vehicle schedule from the first level. Then, to reduce the complexity of solving the multi-vehicle optimal trajectory control model, we transform this model into non-linear programming (NLP) based on the infinitesimal method. Moreover, a rolling optimization strategy is developed to facilitate field application. Numerical simulation experiments of different traffic scenarios are conducted, and the results show that the proposed method can effectively reduce vehicle delays and fuel consumption, compared with the first-in-first-out (FIFO) method. The numerical results show that the vehicle delay can be reduced by up to 54% and fuel consumption by up to 34% under different traffic demands. Sensitivity analysis indicates that the performance of the proposed method is mainly determined by the minimum safety time interval of vehicles entering the conflict zone.

Sensing and communication are the two major concerns in vehicle-road collaboration system, whose function realization needs the support of RSE (roadside equipment). A misleading deployment incurs in waste of valuable resources and degradation of the network performance. Based on the combination strategy, this study proposed a hybrid allocation method to deploy RSE on a highway by considering the sensing capability of traditional ITS sensors and the communication feature of popular networking devices. Two sorts of RSE, the one integrated ITS sensor and networking device, named sensing & communication-RSE (scRSE), and the other belongs to networking devices, named communication-RSE (cRSE), were involved. A hybrid RSE allocation framework was proposed, in which an optimal method was adopted to deploy scRSE on key points for data acquisition and a connectivity probability-based uniform method was used to deploy cRSE for communication. The effectiveness of these methods was verified by case analysis. The results indicated that the proposed hybrid method was very effective and outperformed the conventional uniform deployment method. The key parameters, including the coverage range, RSE spacing, and vehicle density, had an important impact on network connectivity probability. To obtain high connectivity probability, a lower density of connected vehicles (CVs) needs the support of wide coverage of RSE, and vice versa. When the density of CVs reaches to a certain value, vehicular networks could be realized without the help of RSE. Benefitting from the mobility of CVs, increasing their transmission range was better than increasing RSE coverage radius in improving connectivity probability.

Understanding the underlying patterns of the urban mobility dynamics is essential for both the traffic state estimation and management of urban facilities and services. Due to the coupling relationship of generative factors in spatial-temporal domain, it is challenging to model the citywide traffic dynamics under a structural pattern of critical features such as hours of days, days of weeks and weather conditions. To address this challenge, this article develops a disentangled representation learning framework to learn an interpretable factorized representation of the independent data generative factors. In order to make full use of the knowledge on generative factors, this article proposes spatial-temporal generative adversarial network (ST-GAN) to assign the generative factors of traffic flow to the feature vector in latent space and reconstructs the high-dimensional citywide traffic flow from the given factors. With the help of the disentangled representations, the decomposed feature vector in latent space discloses the relationship between underlying patterns and citywide traffic dynamics. Several comprehensively experiments show that ST-GAN not only effectively improves the prediction accuracy but also promisingly characterize structural properties of the traffic evolution process.

Urban customized bus companies are increasingly motivated by design efforts that entail more efficient route scenarios to incorporate adaptation to temporal and spatial heterogeneity in travel demand. However, such motivations are usually hindered by ubiquitous arrival unpunctuality resulting from traffic congestion. To resolve this problem, we suggest a time-dependent bus route planning methodology that explicitly considers path flexibility between nodes to be visited. First, we establish a mixed-integer programming model to formulate the problem, where decision-making considerations in bus route planning, path choice between nodes, and passenger assignment are concurrently integrated. Then, we develop a hybrid metaheuristic (combining tabu search and variable neighborhood search) to solve the model, in which satisfactory performance is observed from the numerical test in a small-sized example. Finally, the problem and methodology are addressed in a city-scale instance, where the effects of time-window features and traffic congestion, as well as the benefits from path flexibility inclusion in terms of cost, travel time, and distance are investigated.

The study proposes a cooperative lane changing strategy to improve traffic operation and safety at a diverging area nearby a highway off-ramp in an environment with connected and automated vehicles (CAVs). The cooperative strategy was implemented by the coordination of behaviors between the diverging vehicle and its cooperative vehicle on the target lane. The Minimizing Overall Braking Induced by Lane Changes Model (MOBIL) and Intelligent Driver Model (IDM) were modified to develop a simulation platform for a CAV environment. The optimal cooperative lane changing zones were firstly calculated by a heuristic algorithm, and then were applied in the simulation platform to implement the cooperative strategy. Various metrics were considered to evaluate the proposed strategy, including: total travel time, surrogate safety measures and traffic waves in the system. The experimental results showed that the length of the optimal cooperative zones obtained in our strategy were smaller than the fixed zone required in modified MOBIL strategy. Moreover, the results indicated that the cooperative strategy with the optimal zones, could improve traffic operation, traffic safety and traffic oscillation as compared to the modified MOBIL strategy with the fixed zone. The cooperative strategy can be potentially implemented nearby highway off-ramps by vehicle-based control, with the applications of the aforementioned cooperative zones.

In reality, readings of sensors on highways are usually missing at various unexpected moments due to some sensor or communication errors. These missing values do not only influence the real-time traffic monitoring but also prevent further traffic data mining. In this paper, we propose a multi-view learning method to estimate the missing values for traffic-related time series data. The model combines data-driven algorithms (long-short term memory and support vector regression) and collaborative filtering techniques. It can consider the local and global variation in temporal and spatial views to capture more information from the existing data. The estimations of missing values from four views are aggregated to obtain a final value with a kernel function. Data from a highway network are used to evaluate the performance of the proposed model in terms of accuracy, precision, and agreement. The results indicate that our proposed model outperforms other baselines, especially for block missing pattern with a high missing ratio. Furthermore, the sensitivity of the parameters is analyzed. We can conclude that combining different views can improve the performance of the imputation.

The machine learning-based car-following models are widely adopted to control the longitudinal movements of automated vehicles, such as Google Car and Apple Car, by mimicking the human drivers' car-following maneuver. However, like human drivers, the models easily produce unsafe maneuvers for automated vehicles and has low robustness, especially in uncommon situations. To improve the machine learning-based car-following models, this paper proposes to combine the machine learning models with the kinematics-based car-following models that can overcome the shortcomings of machine learning models, using an optimal combination prediction method, which is called the combination car-following model in the paper. The selected kinematics-based car-following model is the Gipps model that has an intrinsic crash-avoidance mechanism, and the used machine learning-based models are the Back-Propagation Neural Networks (BPNN) model and Random Forest (RF) model, producing the two CCF models, the Gipps-RF model and Gipps-BPNN model. The real vehicle trajectory data sets are applied to calibrate and validate the proposed models, and simulations are conducted to evaluate the model performances. The results display that the proposed CCF models can enhance safety level and robustness of the car-following control of automated vehicles. Both the two CCF models have better performance than the BPNN and RF car-following models in reducing congestion, stabilizing traffic, and avoiding crashes, especially the Gipps-BPNN model.

Variable techniques have been used to collect traffic data and estimate traffic conditions. In most cases, more than one technology is available. A legitimate need for research and application is how to use the heterogeneous data from multiple sources and provide reliable and consistent results. This paper aims to integrate the traffic features extracted from the wireless communication records and the measurements from the microwave sensors for the state estimation. A state‐space model and a Progressive Extended Kalman Filter (PEKF) method are proposed. The results from the field test exhibit that the proposed method efficiently fuses the heterogeneous multisource data and adaptively tracks the variation of traffic conditions. The proposed method is satisfactory and promising for future development and implementation.

Vehicle behavior learning can be used in video surveillance systems to identify normal and abnormal vehicle motion patterns for the management of traffic operations, public services, and law enforcement. The purpose of this paper is to develop a novel adaptive sparse reconstruction method for vehicle behavior learning based on video surveillance systems. First, the ℓ0 minimization problem of sparse reconstruction is relaxed to the ℓp minimization problem (0 <; p <; 1). A hybrid algorithm orthogonal matching pursuit-quasi-Newton is proposed to effectively find the sparse solutions. Then, a sparse reconstruction and similarity-based trajectory classifier is developed to learn vehicle behavior based on the sparse solutions and the trajectory similarity. In order to validate the performance and the effectiveness of the proposed method, four datasets, including CROSS, i-LIDA, Stop Sign, and I5 are used in the experiments. The results show that the classification and the anomaly detection accuracies of the proposed method are superior to the representative methods, including the Naïve Bayes classifier, k nearest neighbor, support vector machine, and traditional sparse reconstruction-based trajectory learning methods.

As the vital node of a passenger transportation network, the transportation hub is the connection between multiple travel modes and the important port for the massive passenger flow to enter into or exit from a city area. Transportation operators need to understand the passenger flow pattern for hub management, transportation planning, and so on. However, it is difficult to use traditional methods, such as video detection, to provide such information. With the increasing number of mobile phone users, mobile phone data have shown remarkable potential in detecting the transportation information with high sampling coverage and low cost. This paper utilizes the mobile phone data to characterize the passenger flow of the Hongqiao transportation hub located in Shanghai, China. First, a temporal-spatial clustering method is proposed to identify the passenger active area of the Hongqiao hub in the wireless communication space. Second, a classification process is presented to extract different types of passengers in this transportation hub. Subsequently, the access characteristics of passengers in the city are studied for various time intervals. The results further verify the potential of using mobile phone data to monitor and characterize passenger flow related to the transportation hubs.

Short-term traffic prediction plays a critical role in many important applications of intelligent transportation systems such as traffic congestion control and smart routing, and numerous methods have been proposed to address this issue in the literature. However, most, if not all, of them suffer from the inability to fully use the rich information in traffic data. In this paper, we present a novel short-term traffic flow prediction approach based on dynamic tensor completion (DTC), in which the traffic data are represented as a dynamic tensor pattern, which is able capture more information of traffic flow than traditional methods, namely, temporal variabilities, spatial characteristics, and multimode periodicity. A DTC algorithm is designed to use the multimode information to forecast traffic flow with a low-rank constraint. The proposed method is evaluated on real-world data sets and compared with other state-of-the-art methods, and the efficacy of the proposed approach is validated on the experiments of traffic flow prediction, particularly when dealing with incomplete traffic data.

Lane changing is a common driving behavior in traffic, and the algorithm of lane-changing maneuver is an indispensable part of the design of autonomous vehicle control and adaptive cruise control. Although extensive research studies focused on modeling drivers' decision mechanism, lane-changing execution (LCE) happening after the lane-changing decision has not attracted much attention, which has a significant impact on driving safety and traffic simulation results. This paper attempts to replicate the real LCE behavior by proposing new LCE models. Depending on whether the lag vehicle on the target lane is considered in an LCE or not, two types of lane-changing execution are defined, namely, the cooperative LCE (CLCE) and the forced LCE (FLCE). The real vehicle trajectory data, i.e., the NGSIM data, are applied to train and test the proposed models. The results illustrate that the proposed models have good performance in replicating the CLCE and FLCE behavior and outperform the first LCE model proposed by Moridpouret al. Furthermore, when drivers decide to conduct a lane-changing execution, their considerations of the vehicles on the target lane have happened, and their considerations of the vehicles on the current lane decrease sharply during the LCE. In addition, the driver generally pays more attention to the preceding vehicle than to the lag vehicle on the target lane in an LCE.

The majority of existing studies in subway train operations focus on timetable optimization and vehicle tracking methods, which may be infeasible with disturbances in actual operations. To deal with uncertain passenger demands and realize real-time train operations (RTOs) satisfying multiobjectives, including overspeed protection, punctuality, riding comfort, and energy consumption, this paper proposes two RTO algorithms via expert knowledge and an online learning approach. The first RTO algorithm is developed by a knowledge-based system to ensure the multiple objectives with a constant timetable. Then, by considering uncertain passenger demand at each station and random running time errors, we convert the train operation problem into a Markov decision process with nondeterministic state transition probabilities in which the aim is to minimize the reward for both the total time delay and energy consumption in a subway line. After designing policy, reward, and transition probability, we develop an integrated train operation (ITO) algorithm based on Q-learning to realize RTOs with online adjusting the timetable. Finally, we present some numerical examples to test the proposed algorithms with real detected data in the Yizhuang Line of Beijing Subway. The results indicate that, taking the multiple objectives into account, the RTO algorithm outperforms both manual driving and automatic train operations. In addition, the ITO algorithm is capable of dealing with uncertain disturbances, keeping the total time delay within 2 s and reducing the energy consumption.

The tensor completion problem is to recover a low-n-rank tensor from a subset of its entries. The main solution strategy has been based on the extensions of trace norm for the minimization of tensor rank via convex optimization. This strategy bears the computational cost required by the singular value decomposition (SVD) which becomes increasingly expensive as the size of the underlying tensor increase. In order to reduce the computational cost, we propose a multi-linear low-n-rank factorization model and apply the nonlinear Gauss–Seidal method that only requires solving a linear least squares problem per iteration to solve this model. Numerical results show that the proposed algorithm can reliably solve a wide range of problems at least several times faster than the trace norm minimization algorithm.

With the development of probe vehicle technologies and the emerging connected vehicle technologies, applications and models using trajectory data for calibration and validation significantly increase. However, the error accumulation issue accompanied by the calibration process has not been fully investigated and addressed. This paper explores the mechanism and countermeasures of the error accumulation problems of car-following models calibrated with microscopic vehicle trajectory data. In this paper, we first derive the error dynamic model based on an acceleration-based generic car-following model formulation. The stability conditions for the error dynamic model are found to be different from the model stability conditions. Therefore, adjusting feasible ranges of model parameters in the car-following model calibration to ensure model stability cannot guarantee the error stability. However, directly enforcing those error stability conditions can be ineffective, particularly when explicit formulations are difficult to obtain. To overcome this issue, we propose several countermeasures that incorporate error accumulation indicators into the error measures used in the calibration. Numerical experiments are conducted to compare the traditional and the proposed error measures through the calibration of five representative car-following models, i.e., General Motors, Bando, Gipps, FREeway SIMulation (FRESIM), and intelligent driver model (IDM) models, using field trajectory data. The results indicate that the weighted location mean absolute error (MAE) and the location MAE with crash rate penalty can achieve the best overall error accumulation performance for all five models. Meanwhile, traditional error measures, velocity MAE, and velocity Theil's U also achieve satisfactory error accumulation performance for FRESIM and IDM models, respectively.

Dynamic demands are the basic inputs of some existing dynamic assignment function. However, current data collection technologies do not directly support all the requirements of Dynamic Traffic Assignment (DTA) models. As a new traffic data collection technology, cell probe data could provide link flow, travel time and dynamic traffic demand at the same time. But these parameters are partial for a network.