Search

Transportation administrators and urban planners rely on accurate network-wide traffic state estimation to make well-informed decisions. However, due to insufficient sensor coverage, traffic state estimation at sensor-free locations (TSES) poses significant challenges for downstream network-wide traffic analysis. This is because direct observations are not available at these sensor-free locations. Most existing traffic state estimation (TSE) research focuses on inferring several unknown time points based on observed historical data using deterministic models. In contrast, TSES is to infer the entire unknown traffic time series of a given sensor-free node, thereby presenting high predictive difficulty, as we could not learn any historical traffic patterns locally. In this study, we introduce a novel probabilistic model — the conditional diffusion framework with spatio-temporal estimator (CDSTE) — to tackle the TSES problem. When dealing with TSES, deterministic models can only produce point value estimates, which may substantially deviate from the actual traffic states of sensor-free locations. To mitigate this, the proposed CDSTE integrates the conditional diffusion framework with cutting-edge spatio-temporal networks to extract the underlying dependencies in traffic states between sensor-free and sensor-equipped nodes. This integration enables reliable probabilistic traffic state estimations for sensor-free locations, which can be used to quantify the variability of estimations in TSES to support flexible and robust decision-making processes for traffic management and control. Extensive numerical experiments on real-world datasets demonstrate the superior performance of CDSTE for TSES over five widely-used baseline models. • Probabilistic traffic state estimation at sensor-free locations. • Novel conditional diffusion framework with spatio-temporal estimator. • Exploring traffic dynamics between sensor-free and sensor-equipped locations. • Experiments on real-world datasets compared to competitive baselines. [ABSTRACT FROM AUTHOR]

Max-pressure (MP) is a decentralized adaptive traffic signal control approach that has been shown to maximize throughput for private vehicles. However, MP-based signal control algorithms do not differentiate the movement of transit vehicles from private vehicles or between high and single-occupancy private vehicles. Prioritizing the movement of transit or other high occupancy vehicles (HOVs) is vital to reduce congestion and improve the reliability and efficiency of transit operations. This study proposes OCC-MP: a novel MP-based algorithm that considers both vehicle queues and passenger occupancies in computing the weights of movements. By weighing movements with higher passenger occupancies more heavily, transit and other HOVs are implicitly provided with priority, while accounting for any negative impacts of that priority on single occupancy vehicles. And, unlike rule-based transit signal priority (TSP) strategies, OCC-MP more naturally also accommodates conflicting transit routes at a signalized intersection and facilitates their movement, even in mixed traffic without dedicated lanes. Simulations on a grid network under varying demands and transit configurations demonstrate the effectiveness of OCC-MP at providing TSP while simultaneously reducing the negative impact imparted onto lower occupancy private vehicles. Furthermore, OCC-MP is shown to have a larger stable region for demand compared to rule-based TSP strategies integrated into the MP framework. The performance of OCC-MP is also shown to be robust to errors in passenger occupancy information from transit vehicles and can be applied when passenger occupancies of private vehicles are not available. Finally, OCC-MP can be applied in a partially connected vehicle (CV) environment when a subset of vehicles is able to provide information to the signal controller, outperforming baseline methods at low CV penetration rates. • Integrates passenger occupancy information into max pressure algorithm. • Reduces passenger travel time through prioritizing high occupancy vehicles. • Maintains maximum stability property. • Outperforms benchmark MP algorithms under various traffic conditions. • Performs well under both partial and fully connected vehicle environment. [ABSTRACT FROM AUTHOR]

Decentralized traffic signal control methods, such as max-pressure (MP) control or back-pressure (BP) control, have gained increasing attention in recent years. MP control, in particular, boasts mathematically-proven network throughput properties, enabling it to optimize network throughput and stabilize vehicle queue lengths whenever possible. Urban traffic volume is dynamic and features a non-uniform distribution throughout the network. Specifically, heavier traffic is often observed along arterial corridors or major origin–destination streams, such as those in central business districts (CBD), while less traffic is found on sub-arterial roads. To address these issues, many existing signal plans incorporate coordinated signal timing. Numerous previous studies have formulated signal coordination optimization as mixed-integer programming problems, with most belonging to centralized traffic signal controller categories. However, centralized approaches do not scale well to larger city networks. In this paper, we introduce a novel max-pressure signal control approach called Smoothing-MP, which considers signal coordination in urban networks to achieve both maximum vehicle stability and reduced travel time and delay along specific urban corridors, without altering the original stable region proposed by Varaiya (2013). This study represents a pioneering effort in modifying max-pressure control to incorporate signal coordination. Crucially, this policy retains the decentralized characteristic of the original max-pressure control, relying exclusively on local information sourced from upstream and downstream intersections. To evaluate the proposed Smoothing-MP control, we executed simulation studies on two different types of networks, the Downtown Austin Network and a Grid Network. The results unequivocally show that Smoothing-MP matches the maximum throughput of the original MP control. Moreover, it significantly reduces both travel time and delay along coordinated corridors. This dual accomplishment underscores the efficacy and potential advantages of the Smoothing-MP control approach. • For the first time, this research integrates max-pressure control with signal coordination, marking a significant advancement in traffic management strategies. • It enhances the practical applicability of max-pressure control, making it more viable for real-world traffic systems. • The newly proposed max-pressure signal control modification retains the ability to achieve maximum network throughput while preserving the original max-pressure control's stable region. • Simulations were conducted using the Downtown Austin Network and a Grid Network, focusing on selected corridors to demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

This paper aims to establish a framework of participatory traffic control, wherein connected and automated vehicles (CAVs) subtly influence the day-to-day adjustment process of human drivers, strategically redistributing traffic demand to enhance overall system efficiency. To address this complex challenge, we adopt the mean-field control framework, which enables us to model macroscopic interactions between CAVs and other travelers. After theoretically establishing the existence of the optimal policy, we leverage reinforcement learning algorithms to numerically solve the control problem. Distinct from existing approaches, our proposed method is scalable, model-free, distributed, and does not rely on the convergence properties of the underlying day-to-day traffic dynamics. It helps pave the way for the practical implementation of participatory traffic control. • Participatory traffic control framework leveraging connected and automated vehicles (CAVs). • Propose a scalable, model-free and distributed control approach, facilitating real-world implementation. • Utilize the mean-field control to model interactions between CAVs and human drivers. • Employ reinforcement learning to solve for the optimal control policy. [ABSTRACT FROM AUTHOR]

• A virtual risk computation based on matching degree was introduced. • A universal planning method for pre-merging in mixed traffic and regular car-following has been proposed. • A virtual risk-based longitudinal planning model has been formulated. • Enhanced stability and improvements in safety are characteristics of the proposed planning approach. Ramp-merging zones have perennially served as bottlenecks for both safety and efficiency within road traffic. Addressing the inherent uncertainties and anomalous behaviors potentially exhibited by human-driven vehicles (HDVs) in mixed traffic flow, this study introduced a distributed merging control algorithm based on virtual risk assessment. Initially, we proposed a progressive vehicle projection method based on matching degree, formulated to engender smooth longitudinal accelerations. Building upon this foundation, a virtual risk-based longitudinal planning model named V-RQM was established, furnishing longitudinal accelerations with robust stability and safety to Connected and Autonomous Vehicles (CAVs). Results from four diverse simulation experiments corroborate that V-RQM is aptly versatile, suited for conventional one-dimensional car-following environments as well as pre-merging control in heterogeneous traffic flow. The model not only mitigates oscillatory amplitudes while sustaining high traffic efficiency but also exhibits commendable resilience against uncertainties and anomalies indigenous to mixed traffic flow. This research pioneers a novel model-driven approach to ramp-merging control, setting the stage for the full exploitation of CAV capabilities. [ABSTRACT FROM AUTHOR]

Traffic Signal Control (TSC) plays a crucial role in mitigating congestion. The extensive integration of Deep Reinforcement Learning (DRL) into TSC, fueled by the advancements in artificial intelligence, has yielded remarkable efficacy. Nevertheless, prevailing DRL models are typically developed within homogeneous road networks, characterized by identical intersection types and relatively balanced traffic flow patterns. This predominant approach often results in an oversight of the impact of intersection heterogeneity, encompassing variations in intersection geometric structure, traffic demands, signal timing design, and other pertinent factors, on action selections by researchers. This paper addresses the aforementioned gap by introducing a value-decomposition-based spatiotemporal graph attention multi-agent DRL model (MARL_SGAT) that expressly accommodates intersection heterogeneity. Specifically, a heterogeneous correlation index is designed using road network structural parameters and serves to formulate a heterogeneous reward function, enabling the quantification of action execution improvements in diverse road network environments. To address the intricate spatiotemporal features of traffic flows within the heterogeneous road network, the model strategically selects and incorporates these features during the formulation by leveraging a spatiotemporal graph attention network. On these bases, double dual networks are introduced to convert the individual-global-max constraint of action selection into a value range constraint of the action advantage function, thereby facilitating model learning. Simulation results showcase the superior performance of the MARL_SGAT algorithm when compared to seven baseline algorithms. Specifically, the algorithm manifests in reduced average vehicle delays, decreased number of stops, and elevated travel speeds within the controlled road network. These advantages are particularly conspicuous in heterogeneous road network environments. • MARL method for collaborative control of heterogeneous intersections is proposed. • A correlation index is formulated to quantify intersection topology variations. • A novel reward function is designed to offer more precise evaluation method. • The double dual networks simplify the learning process for Q value function. • Performance of the proposed model is validated using actual data set. [ABSTRACT FROM AUTHOR]

In the last decade, pressure-based schemes such as Back Pressure and Max Weight algorithms have been widely researched and applied for traffic signal control due to their simplicity and proven throughput maximization. In such algorithms, the next chosen signal phase at an intersection in a road network is the one with the highest measured weight, representing the pressure of traffic movements at the intersection, determined based on a single characteristic of the traffic flow or vehicles' state at that intersection. This paper develops a new optimal Max Weight control mechanism to enhance the network throughput and reduce vehicle delays in a network using a concept of platooning enabled by Connected Vehicles (CVs). To this end, we propose a new proven optimal Max Weight control scheme where the weight consists of several features including the platoon delay, as well as the speed and position of vehicles within the platoon. To the best of our knowledge, this work is the first to propose a platoon pressure-based concept considering multiple configurable attributes in formulating the pressure. Furthermore, we provide a rigorous stability proof that ensures the throughput optimality of the proposed control scheme. In addition, we also develop a machine learning procedure in this paper to optimize the weighting parameter of each attribute contributing to the total pressure enabling its seamless deployment in practice. A number of simulation results demonstrate the feasibility of the learning procedure and show that our Max Weight platoon pressure-based scheme outperforms the state-of-the-art and well-known existing pressure-based algorithms. • Develop a novel MaxWeight decentralized signal control scheme considering vehicle platooning. • Propose the weight (or pressure) based on the platoons' features or characteristics. • Develop a cross entropy method as the learning algorithm to optimize the parameters of the control algorithm. • Provide theoretical proof for the stability property of the proposed MaxWeight scheme. • Numerically show significant improvements over other well-known existing pressure-based schemes. [ABSTRACT FROM AUTHOR]

Confronted with growing and fluctuating traffic demands, urban transportation system has been encountering mounting challenges in traffic congestion, especially at intersections. With enhanced traffic control precision enabled by the emerging Connected and Automated Vehicle (CAV) technologies, this study proposes a hybrid control strategy for connected and automated traffic at urban intersections, which enables the integration of diverse control schemes to harness their strengths and mitigate their weaknesses. With rolling horizon strategy, a nonlinear optimization model is developed to determine the optimal traffic control plans considering both current status and forthcoming vehicle arrivals. Vehicle delays are elaborately characterized without relying on any empirical assumptions. The original model is converted to a Mixed Integer Programming with Quadratic Constraints (MIP-QC) by employing appropriate linearization techniques, which could be solved by commercial solvers. For the acquisition of instant and reliable solutions, a multilayer feedforward network-based approximate algorithm is developed, referred as Value Approximation Control (VAC) algorithm. Theoretical derivation is provided to validate the capability of VAC algorithm in the precise approximations of the value function in the traffic plan optimization problem, and ultimately enabling to acquire global optimal solutions via specific network design and training techniques. Numerical experiments on both artificial and researcher-collected datasets demonstrate that our proposed VAC algorithm achieves performance nearly equivalent to the mathematical model. Significantly, it outperforms current state-of-art traffic control methods in terms of both intersection throughput and average vehicle delay. Moreover, sensitivity analysis reveals the robustness of the VAC algorithm against inaccuracy in vehicle arrival information, and the stable performance even in the presence of significant disturbances. • A hybrid intersection control strategy to accommodate fluctuating traffic demands for CAVs. • DRIC model to integrate current control methods and generate optimal traffic control plans. • An approximation algorithm, i.e. VAC, to provide instant and reliable solutions tailored to practical applications. • Theoretical analysis to validate that VAC is capable of attaining global optimal solutions. • Numerical experiments on both artificial dataset and real-world dataset to evaluate the performance of the proposed methods. [ABSTRACT FROM AUTHOR]

A distributed method for concurrent traffic signal and routing control of traffic networks is proposed. The method is based on the multi-commodity store-and-forward model, in which the destinations are the commodities. The system benefits from the communication between vehicles and infrastructure, providing optimal signal timings to intersections and routes to vehicles on a link-by-link basis. Using the augmented Lagrangian to model the constraints into the objective, the baseline centralized problem is decomposed into a set of objective-coupled subproblems, one for each intersection, enabling the solution to be computed by a distributed-gradient projection algorithm. The intersection agents only need to communicate and coordinate with neighboring intersections to ensure convergence to the optimal solution while tolerating suboptimal iterations that offer more flexibility, unlike other distributed approaches. Through microsimulation, we demonstrate the effectiveness of the proposed algorithm in traffic networks with time-varying demand. Computational analysis shows that the distributed problem is suitable for real-time applications. A robustness analysis show that the distributed formulation enables a graceful degradation of the system in case of failure. • A multi-commodity traffic flow model cast into a linear dynamic network. • A distributed algorithm for linear dynamic networks and in particular applicable to multi-commodity urban signal traffic control and routing in a connected vehicle environment. • Demonstration of the real-time applicability and robustness to failure of the proposed algorithm and model. • Comparison through microscopic simulation with the corresponding centralized approach, with a decentralized backpressure algorithm, and with fixed-time. [ABSTRACT FROM AUTHOR]

In urban traffic management, the primary challenge of dynamically and efficiently monitoring traffic conditions is compounded by the insufficient utilization of thousands of surveillance cameras along the intelligent transportation system. This paper introduces the multi-level Traffic-responsive Tilt Camera surveillance system (TTC-X), a novel framework designed for dynamic and efficient monitoring and management of traffic in urban networks. By leveraging widely deployed pan–tilt-cameras (PTCs), TTC-X overcomes the limitations of a fixed field of view in traditional surveillance systems by providing mobilized and 360-degree coverage. The innovation of TTC-X lies in the integration of advanced machine learning modules, including a detector–predictor–controller structure, with a novel Predictive Correlated Online Learning (PiCOL) methodology and the Spatial–Temporal Graph Predictor (STGP) for real-time traffic estimation and PTC control. The TTC-X is tested and evaluated under three experimental scenarios (e.g., maximum traffic flow capture, dynamic route planning, traffic state estimation) based on a simulation environment calibrated using real-world traffic data in Brooklyn, New York. The experimental results showed that TTC-X captured over 60% total number of vehicles at the network level, dynamically adjusted its route recommendation in reaction to unexpected full-lane closure events, and reconstructed link-level traffic states with best MAE less than 1.25 vehicle/hour. Demonstrating scalability, cost-efficiency, and adaptability, TTC-X emerges as a powerful solution for urban traffic management in both cyber–physical and real-world environments. • This study proposes a traffic-responsive tilt camera system to dynamically monitor traffic. • A Predictive Correlated Online Learning for real-time traffic data decisions. • A Spatial-temporal learning system integrates road structure and traffic dynamics. • Three scenarios are tested for max flow capture, route planning, and traffic state estimation. [ABSTRACT FROM AUTHOR]

This paper introduces a novel hybrid car-following strategy for connected automated vehicles (CAVs) to mitigate traffic oscillations while simultaneously improving CAV car-following (CF) distance-maintaining efficiencies. To achieve this, our proposed control framework integrates two controllers: a linear feedback controller and a deep reinforcement learning controller. Firstly, a cutting-edge linear feedback controller is developed by non-linear programming to maximally dampen traffic oscillations in the frequency domain while ensuring both local and string stability. Based on that, deep reinforcement learning (DRL) is employed to complement the linear feedback controller further to handle the unknown traffic disturbance quasi-optimally in the time domain. This unique approach enhances the control stability of the traditional DRL approach and provides an innovative perspective on CF control. Simulation experiments were conducted to validate the efficacy of our control strategy. The results demonstrate superior performance in terms of training convergence, driving comfort, and dampening oscillations compared to existing DRL-based controllers. • A novel hybrid car-following strategy for CAVs to mitigate traffic oscillations. • A novel control framework by integrating linear feedback control and DRL. • Excellent control performance on distance maintaining and smooth driving. • Better capability to handle traffic corner cases. [ABSTRACT FROM AUTHOR]

Human crowds often exhibit collective behaviors through self-organization, such as orderly queueing and disordered congestion at exits. Understanding the dynamic mechanisms behind these behaviors is crucial for pedestrian traffic management and the handling of mass crowds. Although current models and experiments have provided profound insights into ordered and disordered pedestrian groups separately, the transition mechanism from order to disorder within pedestrian crowds in front of exits remains unclear. In this study, a pedestrian queueing evacuation experiment was presented to demonstrate the phase transition process of pedestrian movement states as urgency levels in the environment change. We discovered the migration pattern of the phase transition point under evacuation control and identified different propagation modes of pedestrian velocity waves. Furthermore, a pedestrian motion model based on experimental data and observed phenomena was established. This model not only replicates the observed phenomena and regularities from the experiments but also reveals the quantitative phase transition mechanism of pedestrian movement under the influence of a single factor (i.e., urgency level or queueing ratio). Our findings hold significant implications for various domains, including pedestrian management, traffic control, and pedestrian dynamics. • Found pedestrian order–urgency correlation and critical point migration. • Identified speed wave patterns in varying pedestrian motion states. • Developed vision-driven pedestrian queue model from experimental data. • Elucidated pedestrian order phase transitions in specific scenarios. [ABSTRACT FROM AUTHOR]

Conventional platooning control algorithms that improve traffic flow require complex computations and are not well-suited for real-time operations. Moreover, prior research has primarily concentrated on idealized settings, such as isolated intersections or corridors that solely consist of fully connected automated vehicles (CAVs), making it challenging to be applied to real-world traffic systems. To overcome these challenges, this paper aims to design an innovative learning framework based on arrival timing vectors (ATVs) and traffic signal synchronization for platooning control that can improve traffic throughput and reduce fuel consumption through four basic platoon maneuvers: split, acceleration, deceleration, and no-op. We integrate reinforcement learning (RL) with neural networks (NNs) to model non-linear relationships between inputs and outputs for a complex application. The utilization of ATVs as inputs in our proposed framework furnishes an agent with ample information to facilitate a better comprehension of the actions that need to be taken for particular states. Additionally, our proposed DRL-based platooning control collaborates with traffic signal synchronization across adjacent intersections to optimize traffic efficiency in a further step. Numerical experiments have been conducted on both corridor and network scenarios, demonstrating the positive effects of synchronization and DRL-based platooning control on average delay and fuel consumption. Various DRL-based methods have been compared to demonstrate the fast convergence and improved mobility of our proposed algorithm. Furthermore, our algorithm shows robust performance in mixed-traffic environments of CAV and human-driven vehicles. • A new DRL framework using deep learning to manipulate vehicle platoon behaviors. • The approach integrates platooning control with traffic signal synchronization. • A comparison shows the 2DSARSA algorithm outperforms other popular DRL methods. • Case studies showed DRL-based control reduce delay and fuel use in different networks. [ABSTRACT FROM AUTHOR]

Accurately monitoring road traffic state is crucial for various applications, including travel time prediction, traffic control, and traffic safety. However, the lack of sensors often results in incomplete traffic state data, making it challenging to obtain reliable information for decision-making. This paper proposes a novel method for imputing traffic state data using Gaussian processes (GP) to address this issue. We propose a kernel rotation re-parametrization scheme that transforms a standard isotropic GP kernel into an anisotropic kernel, which can better model the congestion propagation in traffic flow data. The model parameters can be estimated by statistical inference using data from sparse probe vehicles or loop detectors. Moreover, the rotated GP method provides statistical uncertainty quantification for the imputed traffic state, making it more reliable. We also extend our approach to a multi-output GP, which allows for simultaneously estimating the traffic state for multiple lanes. We evaluate our method using real-world traffic data from the Next Generation simulation (NGSIM) and HighD programs, along with simulated data representing a traffic bottleneck scenario. Considering current and future mixed traffic of connected vehicles (CVs) and human-driven vehicles (HVs), we experiment with the traffic state estimation (TSE) scheme from 5% to 50% available trajectories, mimicking different CV penetration rates in a mixed traffic environment. We also test the traffic state estimation when traffic flow information is obtained from loop detectors. The results demonstrate the adaptability of our TSE method across different CV penetration rates and types of detectors, achieving state-of-the-art accuracy in scenarios with sparse observations. • Using Gaussian process (GP) for Traffic State Estimation (TSE). • Capturing congestion propagation in traffic wave with a rotation kernel. • Leveraging inter-lane correlation to improve TSE accuracy. • Model works well on small datasets and can quantify the TSE uncertainty. • Experiments on real-world and simulated data show GP-TSE accuracy and robustness. [ABSTRACT FROM AUTHOR]

Traditional traffic signal control is one of the most widely used urban traffic control methods, due to its high efficiency, robustness, and simplicity. However, in the era of connected and automated vehicles (CAVs), it is prospective to enhance traffic control precision and achieve vehicle coordination in a more efficient manner. Focusing on an isolated intersection, this study proposes an innovative concept of Fine-grained Phase (FP) for CAV-enabled traffic control, which realizes more refined right-of-way allocation than traditional signal phases while preserving the simplicity and scalability. The development of FP jointly optimizes traffic control strategy and intersection layout design to fully utilize time-space resources, and multiple forms of FP could be generated in response to various traffic demands; meanwhile, vehicle coordination is achieved in an offline–online manner to balance solution quality and efficiency. Under the FP-based control, each lane is assigned with periodical entry time points using FP design results, then vehicles are supposed to catch up with the appropriate time points to fulfill their trips. Theoretical analyses are conducted under stationary vehicle arrival patterns, where the average delay and the intersection capacity associated with different forms of FP can be analytically acquired. For the implementation of FP-based control, we construct a general offline–online framework, consisting of an offline model that optimizes the geometry of the conflict zone at intersections and the control strategy of vehicles simultaneously, which is formulated as a mixed-integer linear programming problem, and an online FP adoption mechanism that can adapt to varying demand patterns. Under the framework, limited online computation is required, facilitating its practical real-time implementation. Simulation studies under a variety of demand settings show that FP-based control is advantageous over benchmark methods in reducing vehicle delay and also improving intersection capacity in most cases; even for cases with extremely imbalanced demands, FP-based control can admit comparable throughput, while the average delay is much smaller. In addition, results of computation time reveal that FP-based control could realize real-time implementation with negligible computation burden. • An innovative concept called FP for intersection traffic control with CAVs. • Joint optimization of traffic control and intersection layout design. • Offline–online implementation framework to balance solution quality and efficiency. • Theoretical analysis for average vehicle delay and admissible traffic capacity. • Improvement over signalized control and the state-of-art reservation strategy. [ABSTRACT FROM AUTHOR]

The shared autonomous vehicle (SAV), combining shared mobility and vehicle automation, will play a pivotal role in urban transportation. Effectively matching SAVs to stochastic customer demand poses a significant challenge, particularly when addressing microscopic multi-AV coordination to prevent conflicts and congestion within a network. To tackle this issue, we propose a novel traffic control scheme called the Integrated Operation Framework for Order Matching and AV Coordination (I-OFOMAC). This scheme introduces a third-party coordinator responsible for integrating online order matching for the SAV platform and real-time AV coordination for the road manager. Our approach utilizes an offline deep reinforcement learning method to train a state value neural network, which facilitates strategic order matching. Additionally, a neural network approximating bisimulation metrics is trained to enhance exploration and accelerate learning. To achieve scalability in network-level AV coordination, we adopt a scheduled transportation scheme. The coordinator solves the I-OFOMAC during each decision epoch, optimizing order matching and AV coordination. The I-OFOMAC aims to balance the goals of minimizing AV travel delay and maximizing SAV service revenue. We conduct extensive simulation studies in the realistic Wangjing network to evaluate the proposed I-OFOMAC scheme. Compared to two-step benchmark frameworks that implement order matching and AV coordination sequentially, the I-OFOMAC achieves an average increase of 13.28% in platform revenue (ranging from 2% to 22.53%) and a 4.48% reduction in average PAV travel delay (ranging from −6.55% to 20.17%). • Mixed AV zone. • Online operations of joint order matching and AV coordination. • Offline deep reinforcement learning framework. • Bisimulation-guided exploration. • A scalable approximate algorithm. • Numerical studies in realistic Wangjing network. [ABSTRACT FROM AUTHOR]

Object counting has been widely studied because of its practicality. However, most currently published object counting datasets contain only a single class of objects, such as crowd or vehicle, which is challenging to meet the usage needs of tasks, such as traffic control. For practical applications, a multi-class object counting (MCOC) dataset that includes transports is increasingly needed. Therefore, this study collected a large-scale MCOC dataset from the Web and live-viewing, called the Soochow university counting (SCU-Counting) dataset. Images from the Web are licensed for free modification, sharing and using for all creative commons. SCU-Counting consists of 2521 images, where 108 images are empty scenes and others are annotated, in a total of 274,199 annotated instances (195,018 humans, 38,831 cars, 2503 trucks, 6445 buses, 10,964 tricycles, 4600 e-bikes, 9729 e-scooters, 3900 bicycles, 2169 motorcycles). Except for empty scenes, each image contains at least one type of objects. In addition, this study proposes a convolutional neural network-based multi-aware feature aggregation network (MAFA-Net) for MCOC. MAFA-Net first uses a front-end module to extract shallow image features, and then designs a multi-aware module that can aggregate contextual, channel and spatial information of features extracted by the front-end. Additionally, a class adaptive weight assignment (CAWA) loss function is developed based on the focal loss function, which can regulate the sample balance between classes in MCOC tasks. We conducted comparative experiments on five public counting datasets to evaluate the effectiveness of our proposed MAFA-Net. In addition, we conducted extensive experiments on the SCU-Counting dataset to validate the counting and target localization abilities of MAFA-Net. For the counting task, MAFA-Net achieves the best MAE (mean absolute error) of 20.08 and MSE (mean squared error) of 46.11, which is 1.84 and 1.75 lower in MAE and MSE than the second best method, respectively. For the localization task, MAFA-Net reaches 90.3% normalized average precision (nAP) at the level of 0.5 and 67.5% average nAP at the level set of { 0. 05 , 0. 1 , ... , 0. 50 } , which suggests that the localization performance of MAFA-Net can meet the requirement of applications. In summary, experimental results demonstrate the usability of the SCU-Counting dataset and the superiority of MAFA-Net. • Collecting a multi-class object counting (MCOC) dataset named SCU-Counting. • Proposing MAFA-Net for MCOC, which can be adapted to the needs of MCOC tasks. • A class adaptive weight assignment loss function is designed to improve the accuracy of counting. • Conducting extensive experiments demonstrates the usability of SCU-Counting. [ABSTRACT FROM AUTHOR]

• Introduction of a generalizable Bayesian recurrent neural network framework for uncertainty quantification in traffic flow prediction. • Utilization of spectral normalization in hidden layers of neural network to enhance generalizability and improve uncertainty estimates. • Demonstration of how normalization alters the training process, controlling model complexity and reducing overfitting. • Spectral normalization improves generalization performance of deep learning models on out-of-distribution datasets, which is crucial for traffic management applications. • Ability of spectral normalization to localize latent feature space under data perturbations, leading to improved generalizability. • Significant outperformance of spectral normalization over layer normalization and models without normalization in both single and multistep prediction horizons. Deep-learning models for traffic data prediction can have superior performance in modeling complex functions using a multi-layer architecture. However, a major drawback of these approaches is that most of these approaches do not offer forecasts with uncertainty estimates, which are essential for traffic operations and control. Without uncertainty estimates, it is difficult to place any level of confidence in the model predictions, and operational strategies relying on overconfident predictions can lead to worsening traffic conditions. In this study, we propose a Bayesian recurrent neural network framework for uncertainty quantification in traffic prediction with higher generalizability by introducing spectral normalization to its hidden layers. In our paper, we have shown that normalization alters the training process of deep neural networks by controlling the model's complexity and reducing the risk of overfitting the training data. This, in turn, helps improve the generalization performance of the model on out-of-distribution datasets. Results demonstrate that spectral normalization improves uncertainty estimates and significantly outperforms both the layer normalization and model without normalization in both single and multistep prediction horizons. This improved performance can be attributed to the ability of spectral normalization to better localize the latent feature space of the data under perturbations. Our findings are especially relevant to traffic management applications, where predicting traffic conditions across multiple locations is the goal, but the availability of training data from multiple locations is limited. Spectral normalization, therefore, provides a more generalizable approach that can effectively capture the underlying patterns in traffic data without requiring location-specific models. [ABSTRACT FROM AUTHOR]

Single occupancy vehicles are the most attractive transportation alternative for many commuters, leading to increased traffic congestion and air pollution. Advancements in information technologies create opportunities for smart solutions that incentivize ridesharing and mode shift to higher occupancy vehicles (HOVs) to achieve the car lighter vision of cities. In this study, we present HumanLight, a novel decentralized adaptive traffic signal control algorithm designed to optimize people throughput at intersections. Our proposed controller is founded on reinforcement learning with the reward function embedding the transportation-inspired concept of pressure at the person-level. By rewarding HOV commuters with travel time savings for their efforts to merge into a single ride, HumanLight achieves equitable allocation of green times. Apart from adopting FRAP, a state-of-the-art (SOTA) base model, HumanLight introduces the concept of active vehicles, loosely defined as vehicles in proximity to the intersection within the action interval window. The proposed algorithm showcases significant headroom and scalability in different network configurations considering multimodal vehicle splits at various scenarios of HOV adoption. Improvements in person delays and queues range from 15% to over 55% compared to vehicle-level SOTA controllers. We quantify the impact of incorporating active vehicles in the formulation of our RL model for different network structures. HumanLight also enables regulation of the aggressiveness of the HOV prioritization. The impact of parameter setting on the generated phase profile is investigated as a key component of acyclic signal controllers affecting pedestrian waiting times. HumanLight's scalable, decentralized design can reshape the resolution of traffic management to be more human-centric and empower policies that incentivize ridesharing and public transit systems. [Display omitted] • HumanLight is the first scalable human-centric RL-based adaptive signal controller. • Scalability is enabled from the decentralized design and algorithmic formulation. • HumanLight can democratize urban traffic by equitably allocating green times. • Active vehicles are proposed to handle the variance in occupancy of multimodal traffic. • HumanLight offers policymakers control of the aggressiveness in HOV prioritization. [ABSTRACT FROM AUTHOR]

• A Multi-layer Graph Mask Q-Learning algorithm for traffic signals is proposed. • This study constructs a new upper and lower graph structure to extract geometric and spatial features of intersections. • This article introduces an action masking mechanism, enabling the model to be applicable to intersections of arbitrary structures when utilizing any phase as the action. • Model tests were conducted on synthetic road networks with different traffic volumes and two real urban road networks, and the test results showed that the algorithm has strong generalization ability and scalability. Due to its capability in handling complex urban intersection environments, deep reinforcement learning (DRL) has been widely applied in Adaptive Traffic Signal Control (ATSC). However, most existing algorithms are designed for specific road networks or traffic conditions, making it difficult to transfer them to new environments. Moreover, current graph-based algorithms do not fully capture the geometric and spatial features of intersections, leading to incomplete embedding of the agent's environment depiction. Additionally, the actions adopted by these algorithms are inherently based on fixed-cycle phases, limiting the flexibility of traffic signal control. To address the aforementioned issues, this paper proposes a Multi-layer Graph Mask Q-Learning (MGMQ) algorithm for multi-intersection ATSC to optimize traffic and reduce delay. Unlike previous graph-based algorithms, this paper introduces a method for computing multi-layer graphs, dividing the traffic environment into upper-level traffic network-layer graphs and lower-level intersection-layer graphs, and employs the graph attention algorithm and an improved GraphSAGE algorithm for computation. This method not only enables the generation of embedded state for intersections that include geometric and spatial features, but also allows the algorithm to adapt to different traffic conditions and road networks. Additionally, we introduce an action masking mechanism, allowing this algorithm can be adapted to different action spaces. As a result, the algorithm uses arbitrary signal phases as actions to achieve flexible traffic flow control, and can be directly applied to intersections with arbitrary geometry. The final test results demonstrate that a model trained solely on synthetic road networks can be directly transferred to other synthetic network configurations or real-world urban road networks, outperforming current state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Monitoring traffic dynamics at both link and network levels is vital for effective traffic management and control in urban road networks. Traffic monitoring at the network level, though, is an extremely challenging task due to the amount of data (and consequently sensors) needed to represent a good coverage of the network traffic dynamics. This has motivated researchers to investigate where to locate sensors (e.g. loop detectors) within a network to capture the so-called Reduced Network Macroscopic Fundamental Diagram (NMFD). The existing approaches for reduced NMFD estimation have presented limitations, because of the reliance on solely traffic flow characteristics or single topological features. In response, in this paper, a framework has been proposed to take into account the simultaneous impact of topological and traffic flow features for the estimation of reduced NMFD. Contrary to existing works in literature, which have mainly focused on the loading period, this work considers both loading and unloading periods. The presented framework deploys regression models to identify the set of critical links within the network. The efficiency of the presented method has been validated under both single and multi-reservoir settings and has been compared to two methods that solely consider traffic characteristics. Our findings reveal that the proposed method demonstrates superior performance, particularly when dealing with low coverage rates of loop detectors (e.g. 1%). Moreover, results show that during the recovery period, traffic characteristics (e.g. queue distribution) play a more important role in estimating the NMFD. On the other side, a more significant impact has been observed for the topological features (e.g. speed limit distribution) during the loading period. • Critical links identification through historical FCD and network topological info. • Reduced operational network MFD estimation during loading and unloading periods. • Feature importance analysis using Random Forest Regression (RFR). • Investigating the combined impact of topological and traffic characteristics on NMFD. [ABSTRACT FROM AUTHOR]

• The effect of "backpressure" on responsive signal control performance in one simple network is studied. • Only a simple network is considered and travellers are supposed to choose their own best routes. • It is shown that on the simple network having backpressure increases equilibrium delays. • It is shown that on the simple network having backpressure reduces network capacity. Many responsive traffic signal control strategies are "pressure-driven". These strategies move green-time from stages with a lower pressure to stages with a higher pressure, at each junction; often aiming to approximately equalise stage pressures at each junction. In some of these pressure-driven strategies each stage pressure at a junction includes a "backpressure" term, which depends on downstream links. Such backpressure terms reduce the pressure on stages and reduce pressure most for those stages leading toward the most highly congested downstream road links. The expectation is that there will then be a reduction in traffic flow exiting the junction toward already highly congested road links, and that this will reduce queue lengths and network delays. This paper shows that this is not always the case by giving two examples where having backpressure within the control policy on a network with two signal controlled junctions (1) increases both equilibrium delays at one of the junctions for certain demands, and (2) never reduces any of the equilibrium delays at either junction. A simple dynamic evolution with a steady reduction in demand is also shown in which two of the considered policies, one with backpressure, give rise to equilibrium delays and queues which tend to infinity, and reveal a gap; in this gap feasible demands have no equilibrium consistent with the two control policies and in a day-to-day dynamical context delays and queues are unbounded. This paper considers only the simple network shown in figure 1 under certain specified conditions. One main avenue for further research might be to consider whether the results shown here also hold in different networks under different conditions. [ABSTRACT FROM AUTHOR]

• Proposes a macro–micro approach for vehicle motion inference using velocity contour. • Macro: tailors an enhanced traffic state estimation method to address data sparsity. • Micro: infers car-following and lane-changing behaviors using a joint optimization framework. • Achieves higher accuracy and smoothness compared to two SOTA methods. Vehicle trajectories can offer the most precise and detailed depiction of traffic flow and serve as a critical component in traffic management and control applications. Various technologies have been applied to reconstruct vehicle trajectories from sparse fixed and mobile detection data. However, existing methods predominantly concentrate on single-lane scenarios and neglect lane-changing (LC) behaviors that occur across multiple lanes, which limit their applicability in practical traffic systems. To address this research gap, we propose a macro–micro approach for reconstructing complete vehicle trajectories on multi-lane freeways, wherein the macro traffic state information and micro driving models are integrated to overcome the restrictions imposed by lane boundary. Particularly, the macroscopic velocity contour maps are established for each lane to regulate the movement of vehicle platoons, meanwhile the velocity difference between adjacent lanes provide valuable criteria for guiding LC behaviors. Simultaneously, the car-following models are extended from micro perspective to supply lane-based candidate trajectories and define the plausible range for LC positions. Later, a two-stage trajectory fusion algorithm is proposed to jointly infer both the car-following and LC behaviors, in which the optimal LC positions is identified and candidate trajectories are adjusted according to their weights. The proposed framework was evaluated using NGSIM and HighD datasets, and the results indicated a remarkable enhancement in both the accuracy and smoothness of reconstructed trajectories, with performance indicators reduced by over 30% compared to two representative reconstruction methods. Furthermore, the reconstruction process effectively reproduced LC behaviors across contiguous lanes, adding to the framework's comprehensiveness and realism. [ABSTRACT FROM AUTHOR]

Signal control has been effective to alleviate urban traffic congestion. Massive related works about signal timing optimization have been proposed and led to many signal control methods and systems. In recent years, reinforcement learning (RL) algorithms have attracted the increasing attention of researchers in the area of signal control optimization, since they can learn the optimal timing policy themselves by analyzing changing patterns between the traffic condition and signal timing plans. Multi-intersection traffic signal control problems face more challenges than classical single intersection problems such as the dimensionality issue as the joint action space of multiple agents grows exponentially with the number of intersections. The existing state-of-art multi-agent reinforcement learning algorithms developed for other areas may not suit well with traffic signal control given the complex spatial–temporal nature of traffic flows. In this paper, we propose a novel multi-agent counterfactual actor–critic with scheduler (MACS) framework for multiple interactions. In this method, decentralized actors control the traffic signals and the centralized critic combines recurrent policies with feed-forward critics. Additionally, a scheduler module that exchanges information among agents helps the individual agent better understand the entire environment. The proposed method was evaluated using simulation experiments based on a real-world urban street network in Shenzhen, China. Results showed that the proposed method outperforms the classic model-based method and several existing RL-based methods according to different measures such as queue length, average travel time delay, and throughput. • Develop an AI-based signal control framework to collaborate multiple intersections. • The counterfactual baseline can well assign the credit among multiple intersections. • The scheduler module helps agents better understand the entire environment. [ABSTRACT FROM AUTHOR]

To improve the performance of systems, optimization has been the prevailing approach in the past. However, the approach faces challenges when multiple goals shall be simultaneously achieved. For illustration, we study a multi-agent system, where agents have a plurality of different, and mutually inconsistent goals. We then allow agents in the system to vote on which traffic signal controllers, which were trained on different goals using deep reinforcement learning, would control the intersection. Taking decisions based on suitable voting procedures turns out to lead to favorable solutions, which perform highly for several goals rather than optimally for one goal and poorly for others. This opens up new opportunities for the management or even self-governance of complex systems that require the consideration and achievement of multiple goals, such as many systems involving humans. Here, we present results for traffic flows in urban street networks, which suggest that "democratizing traffic" would be a promising alternative to centralized control of traffic flows. • We combine voting and traffic signal control. • We use votes of agents as weights for aggregating Q-values of multiple Deep Q-Networks trained on different goals. • Voting allows users to express their preferences and choose how/which algorithm governs them. • We demonstrate the performance of different voting schemes across different voting scenarios. [ABSTRACT FROM AUTHOR]

• An internal model-Kalman filtering-based optimal hybrid feedforward/feedback control strategy is developed. • A practically decoupled platoon regulation around an equilibrium state is established. • String stability of the control system thus obtained is analyzed. • Numerical simulations verified the theoretical analysis in decoupling between successive vehicles. This paper presents an internal model-Kalman filtering-based optimal hybrid feedforward/feedback control strategy for traffic platoon control coordination enabled by SAE Automation Level 2 or Level 3 vehicles, i.e., partially automated vehicles (PAVs). Based on the Helly linear car-following model, a PAV platoon is established. Taking each vehicle's characteristic polynomial as the dominant internal model polynomial, an augmented system state model with filtered inputs is formed, and then both the system states and the external disturbance/internal perturbation from previous vehicle can be estimated by a delicately designed Kalman filter. By using a linear quadratic regulation approach, a distributed hybrid optimal feedforward/feedback controller utilizing the local estimated states is constructed to achieve a practically decoupled platoon regulation around an equilibrium state. String stability of the control system thus obtained is further analyzed. Finally, extensive numerical simulations verified the theoretical analysis in decoupling between successive vehicles, in suppressing the influence of various external disturbances, and in maintaining string stability. [ABSTRACT FROM AUTHOR]

Effective traffic control methods have great potential in alleviating network congestion. Particularly, in an urban network consisting of heterogeneous roads (e.g., freeways and urban roads), how to integrate and coordinate control policies on different roads is a critical issue in large-scale networks. This study addresses this question from two aspects: modeling and control. From the modeling aspect, we formulate the hybrid traffic modeling in heterogeneous networks with the Asymmetric Cell Transmission Model (ACTM) for freeways and the generalized bathtub model for urban roads. For the control aspect, this study considers two representative control approaches: ramp metering for freeways and perimeter control for urban roads, and we aim to develop a deep reinforcement learning (DRL)-based coordinated control framework for large-scale networks. However, there are two significant challenges in the coordinated control in large-scale networks with DRL methods: non-stationary environment and large search space. To address both issues, we incorporate the demonstration to guide the DRL method for better convergence by introducing the concept of "teacher" and "student" models. The teacher models are traditional controllers that provide control demonstrations. For instance, ALINEA and Gating are two representative feedback controllers for ramp metering and perimeter control which can be "teacher" models. The student models are DRL methods, which learn from teachers and aim to surpass the teachers' performance. Additionally, we develop a parallel training scheme to accelerate the proposed DRL method. To validate the proposed framework, we conduct two case studies in a small-scale network and a real-world large-scale traffic network in Hong Kong. Numerical results show that the proposed DRL method outperforms demonstrators as well as DRL methods, and the coordinated control is more effective than just controlling ramps or perimeters respectively. The research outcome reveals the great potential of combining traditional controllers with DRL for coordinated control in large-scale networks. • A generalized hybrid traffic model supporting simulation in large-scale networks. • A novel demonstration-guided DRL method for coordinated traffic control. • A parallel training scheme for DRL methods. • The proposed DRL method is examined in real networks in Hong Kong SAR. [ABSTRACT FROM AUTHOR]

• Traffic signal optimization is integrated with a comprehensive and vehicle-level trajectory planning model for mixed traffic conditions. • The low-level vehicle trajectory planning model integrates both car following and lane changing maneuvers. • The high-level model optimizes traffic signal parameters, and arrival time and lane assignment of CAVs. • A customized solution algorithm is designed to solve the complex problem. • The proposed model shows great mobility and energy benefits over fixed-time and adaptive signal control strategies. Infrastructure-assisted cooperative driving, which consists of connected and automated vehicle (CAV) trajectory planning and traffic signal control, can greatly improve the efficiency of signalized intersection operations. In existing studies, the CAV trajectory planning problem is simplified to only modeling longitudinal vehicle behaviors or assuming the lane changing can be executed instantaneously. The generated CAV trajectories are not realistic and can't be implemented at the vehicle level. Instantaneous lane changing process may also lead to safety issues or uncomfortable driving behavior of following vehicles in a mixed traffic environment. To fill this research gap, we propose an optimization framework that integrates a full CAV trajectory planning model with traffic signal control in a cooperative driving environment with both CAVs and human-driven vehicles (HDVs). A two-level optimization model is formulated based on discrete time. The high-level model optimizes traffic signal parameters, CAV arrival time, and lane assignment at the stop bar, to minimize total vehicle delay. Given arrival time and lane assignment, the low-level model generates trajectories with integrated car-following and lane-changing maneuvers to mimic a human driving policy based on imitation learning. Numerical experiments from a real-world intersection show that the proposed model outperforms adaptive and fixed time signal control by as much as 63.06% in terms of reduction of average vehicle delay, due to better utilization of lane capacity and reduced lost time. In addition to mobility benefits, fuel consumption is also significantly reduced under the proposed infrastructure-assisted cooperative driving framework. [ABSTRACT FROM AUTHOR]

Although Connected Vehicles (CVs) have demonstrated tremendous potential to enhance traffic operations, they can impose privacy risks on individual travelers, e.g., leaking sensitive information about their frequently visited places, routing behavior, etc. Despite the large body of literature that devises various algorithms to exploit CV information, research on privacy-preserving traffic control is still in its infancy. In this paper, we aim to fill this research gap and propose a privacy-preserving adaptive traffic signal control method using partially connected vehicle data. Specifically, we proposed a privacy-preserving mechanism to protect CV data against three types of attacks: CV collusion attacks, database attacks, and inference attacks. The mechanism leverages secure Multi-Party Computation and differential privacy to aggregate individual-level CV data to calculate key traffic parameters without compromising the privacy of CV users. For seamless integration with the privacy-preserving mechanism, we develop a traffic signal optimization model and an arrival rate estimator relying only on aggregated CV data, being applied to both undersaturated and oversaturated traffic conditions. The optimization model is further extended to a stochastic programming problem to explicitly handle the noises added by the privacy-preserving mechanism. Evaluation results show that the linear optimization model preserves privacy with a marginal impact on control performance, and the stochastic programming model can significantly reduce residual queues compared to the linear programming model, with almost no increase in vehicle delay. Overall, our methods demonstrate the feasibility of incorporating privacy-preserving mechanisms in CV-based traffic modeling and control, which guarantees both utility and privacy. • Address data privacy issues for CV-based traffic signal control. • Combine SMPC and DP for privacy-preserving mechanism without a trusted third party. • Systematically integrate traffic models with the privacy-preserving mechanism. • Two-stage stochastic model to explicitly handle parameter noises introduced by DP. • Proposed methodology preserves CV privacy with marginal impact on control performance. [ABSTRACT FROM AUTHOR]

• Develop a framework including both stability analysis and implementation constraints for traffic platoon control via sparse autonomous vehicles. • Identify the number of human-driven vehicles that can be stabilized by one single autonomous vehicle. • Establish error dynamics in traffic platoon considering multiple disturbances and error composition. • Propose a novel ring string stability that is flexible and applicable to mixed ring traffic. The emergence of autonomous vehicles (AVs) is expected to revolutionize road transportation and it has been demonstrated that AVs can be employed as mobile actuators to effectively dissipate stop and go waves. This paper proposes a comprehensive theoretical framework including stability and implementation considerations for analyzing traffic platoon control via sparse AVs and discussing the number of HDVs that can be stabilized by one AV. Considering multiple disturbance sources, we first discuss the output error composition and analyze traffic dynamics in a platoon system. Then we discuss the Lyapunov asymptotic stability (LAS) of the system based on eigenvalue analysis and propose a novel ring string stability (RSS), which ensures the boundedness of disturbance error and guarantees that the effect of disturbance will not be amplified over a lap. The proposed RSS is flexible and applicable to mixed traffic, since the string instability for predecessor-follower pairs are allowed, provided they can be compensated by AVs. In addition, the practical constraints including driving safety and vehicle physical limitations are modeled. The worst-case evaluation of constraints is conducted to reproduce the critical scenarios in real life. Finally, we conduct numerical experiments and analyze the traffic platoon control from the aspects of both stability and practical implementations. New findings include: (1) The introduction of AVs is beneficial to dampen the waves and stabilize the HDV flow. (2) Considering the implementation issues, there is an upper bound of HDVs that can be stabilized by one single AV. (3) As the number and amplitudes of exogenous disturbances increase, it will be more challenging for sparse AVs to ensure stability and meanwhile satisfy the practical constraints. [ABSTRACT FROM AUTHOR]

• Dynamic feedback control for a class of day-to-day traffic adjustment processes. • Demand management and supply regulations are considered. • Only two adjustment parameters with well-identified physical meanings are involved. • The requirement on adjustment parameters for convergence and stability is mild. • Novel output stability notion. In the literature, networks are usually assumed to operate at their steady states in static traffic assignment models. Given a set of demand management and supply regulation strategies, whether the vehicular traffic on a network would approach or not to a steady state under certain assumptions of behavioral realism is of importance and great interest in practice. Moreover, one primary reason for understanding the long-term traffic evolution dynamics is to control or influence the system trajectory in an efficient manner. To address these problems, we focus on a dynamic feedback control design and its subsequent steady-state analysis for a class of day-to-day (DTD) disequilibrium process so that the network traffic would evolve towards the desired stable traffic equilibrium. We propose an interconnected dynamic system framework for the stability and convergence analysis of DTD traffic adjustment process under the dynamic feedback control. Distinguished from the existing studies, we introduce a notion of output stability as well as the Lyapunov-like conditions to carry out the investigation noting that the steady states of the dynamic tolls that correspond to the Lagrange multipliers of the traffic equilibrium problem can be non-unique. The proposed method gives rise to a new approach to selecting pricing strategy. The proposed method involves only two adjustment parameters with well-identified physical meanings while the requirement on adjustment parameters for convergence and stability is mild. Finally, several numerical examples are presented to illustrate the insightful findings. It is found that, with dynamic feedback control, the network traffic state can converge to the desired equilibrium in a much faster manner than the case without control. The dynamic feedback controller can be implemented as demand management and supply regulation strategies such as road pricing and signal control. [ABSTRACT FROM AUTHOR]

• Development of an adaptive control system to manage railway traffic in real-time. • Application of approximate dynamic programming to railway traffic management. • Application of reinforcement learning to approximate railway traffic states. • A computationally efficient approach to manage the stochastic nature of railways. This study presents an adaptive railway traffic controller for real-time operations based on approximate dynamic programming (ADP). By assessing requirements and opportunities, the controller aims to limit consecutive delays resulting from trains that entered a control area behind schedule by sequencing them at a critical location in a timely manner, thus representing the practical requirements of railway operations. This approach depends on an approximation to the value function of dynamic programming after optimisation from a specified state, which is estimated dynamically from operational experience using reinforcement learning techniques. By using this approximation, the ADP avoids extensive explicit evaluation of performance and so reduces the computational burden substantially. In this investigation, we explore formulations of the approximation function and variants of the learning techniques used to estimate it. Evaluation of the ADP methods in a stochastic simulation environment shows considerable improvements in consecutive delays by comparison with the current industry practice of First-Come-First-Served sequencing. We also found that estimates of parameters of the approximate value function are similar across a range of test scenarios with different mean train entry delays. [ABSTRACT FROM AUTHOR]

• New data driven framework for OD matrix estimation. • No equilibrium assignment nor network loading model needed. • Scalable for large networks using dimensionality reduction techniques. • Supervised learning to estimate production and attraction from 3D supply patterns. • Results on small and large network promising. The fundamental challenge of the origin-destination (OD) matrix estimation problem is that it is severely under-determined. In this paper we propose a new data driven OD estimation method for cases where a supply pattern in the form of speeds and flows is available. We show that with these input data, we do not require an iterative dynamic network loading procedure that results in an equilibrium assignment, nor do we need an assumption on the kind of equilibrium that emerges from this process. The minimal number of ingredients which are needed are (a) a method to estimate/predict production and attraction time series; (b) a method to compute the N shortest paths from each OD zone to the next; and (c) two—possibly OD-specific—assumptions on the magnitude of N ; and on the proportionality of path flows between these origins and destinations, respectively. The latter constitutes the most important behavioral assumption in our method, which relates to how we assume travelers have chosen their routes between OD pairs. We choose a proportionality factor that is inversely proportional to realized travel time, where we incorporate a penalty for path overlap. For large networks, these ingredients may be insufficient to solve the resulting system of equations. We show how additional constraints can be derived directly from the data by using principal component analysis, with which we exploit the fact that temporal patterns of production and attraction are similar across the network. Experimental results on a toy network and a large city network (Santander, Spain) show that our OD estimation method works satisfactorily, given a reasonable choice of N , and the use of so-called 3D supply patterns, which provide a compact representation of the supply dynamics over the entire network. Inclusion of topological information makes the method scalable both in terms of network size and for different topologies. Although we use a neural network to predict production and attraction in our experiments (which implies ground-truth OD data were needed), there are straight-forward paths to improve the method using additional data, such as demographic data, household survey data, social media and or movement traces, which could support estimating such ground-truth baseline production and attraction patterns. The proposed framework would fit very nicely in an online traffic modeling and control framework, and we see many paths to further refine and improve the method. [ABSTRACT FROM AUTHOR]

• Centralised and decentralised algorithms with optimal control formulation. • Sensitivity based decentralised signal optimisation algorithms. • Comparison with distributed backpressure control policy. • Investigation of different network decomposition schemes. • Case study of optimisation algorithms on Central London networks. This study develops and analyses the centralised and decentralised solution procedures for urban network traffic management through an optimal control framework. The optimal control is formulated based upon the Hamilton-Jacobi formulation of kinematic wave model. Following the problem decomposition under the decentralised scheme, we introduce the use of semi-analytical performance derivatives when developing the decentralised solution algorithm. The proposed control strategies are applied to a set of test scenarios constructed from a real road network in Central London in the UK. Specific interests in the investigation include comparison of the performance gain and computational effort of the two strategies under different circumstances. We also investigate effect of network decomposition strategies on the performance of the solution algorithm. This study generates insight on urban traffic management with use of traffic flow theory, decentralised optimisation, and network decomposition techniques. [ABSTRACT FROM AUTHOR]

• Neighborhood MFDs are re-scaled to account for effects of cordon queues. • Simulation experiments reveal that re-scaled MFDs better predict traffic performance. • Cordon-metering plans are found to be more effective as well. Optimal cordon-metering rates are obtained using Macroscopic Fundamental Diagrams in combination with flow conservation laws. A model-predictive control algorithm is also used so that time-varying metering rates are generated based on their forecasted impacts. Our scalable algorithm can do this for an arbitrary number of cordoned neighborhoods within a city. Unlike its predecessors, the proposed model accounts for the time-varying constraining effects that cordon queues impose on a neighborhood's circulating traffic, as those queues expand and recede over time. The model does so at every time step by approximating a neighborhood's street space occupied by cordon queues, and re-scaling the MFD to describe the state of circulating traffic that results. The model also differentiates between saturated and under-saturated cordon-metering operations. Computer simulations of an idealized network show that these enhancements can substantially improve the predictions of both, the trip completion rates in a neighborhood and the rates that vehicles cross metered cordons. Optimal metering policies generated as a result are similarly shown to do a better job in reducing the Vehicle Hours Traveled on the network. The VHT reductions stemming from the proposed model and from its predecessors differed by as much as 14%. [ABSTRACT FROM AUTHOR]

• Propose a state transfer risk decision (STRD) method for a large-scale traffic network. • This method is based on the conditional risk decision model. • This method provides an acceptable traffic flow range at the sub-region boundary by risk interval. • Proposed method improves the state stability compared to PI and NSTRD. Network state degradation probabilities increase with traffic density. Specifically, at critical or congested densities, any over-input traffic flow may cause degradation, local traffic jams, and even hysteresis of the road network. Existing macroscopic traffic control methods usually target the maximum capacity or minimum delay to improve the road network efficiency and do not consider the negative effect of perimeter control on the state transfer of the road network. This study provides a method to prevent the transfer of the network state when implementing boundary control. First, according to the data detected for the road network, the concept of a conditional value at risk is used to establish a risk decision model that considers the influence of the boundary input flow rate on sub-region state degradation. Then, based on the risk decision model, we propose a state transfer risk decision (STRD) perimeter control method for a large-scale traffic network with multiple sub-regions. This perimeter control method predicts the traffic demand of every sub-region, selects an acceptable traffic flow range at the sub-region boundary by risk interval, regards the maximum trip completion flow and the minimum total travel time as the decision-making objectives, and controls multiple sub-region boundaries. The simulation results show that compared with proportional integral (PI) control and no STRD (NSTRD) control, the STRD control scheme can effectively prevent the state transfer of all sub-regions, improve the trip completion flow, and decrease the travel delay of the network. [ABSTRACT FROM AUTHOR]

• We design an optimal lane management strategy for a heterogeneous traffic condition. • We dynamically control the network inflow by optimizing the size of the CAV platoons. • The multiple lane type corridors are modeled as sets of parallel bottlenecks. • The dynamics of the congestion in the network is modeled using the MNFD. • We solve the optimization problem for the city of San Francisco, CA. The advent of autonomous driving technologies has created a crucial need for upgrading conventional traffic control and lane management strategies in large cities. In this research, we design an optimal lane management strategy for corridors with a heterogeneous demand of human-driven, autonomous, and communicant autonomous vehicles (HVs, AVs, and CAVs). In a monocentric city setting, we dynamically control the inflow of the network by optimizing the size of CAV platoons in the corridors based on the instantaneous condition of the integrated system. These corridors can potentially have three types of lanes for vehicles with different levels of automation technology. We model the multiple lane type corridors as sets of parallel bottlenecks with general distributions of multiclass demand. The dynamics of the congestion in the network is also modeled using the macroscopic network fundamental diagram (MNFD). To study the impacts of the rise in the penetration rate of AVs and CAVs on the performance of the system, we derive a closed-form representation of the model. We show that the increase of the delay in the network with the rise in the penetration rate of AVs and CAVs can have a stable, an unstable, or a hybrid pattern. To optimize the system, we minimize a weighted summation of the experienced delay in the corridors and the total travel time in the urban network by optimizing the number of lanes of each type and the dynamic size of the CAV platoons. The results of the San Francisco case study show that implementing an optimal lane management strategy can reduce the experienced delay in the corridors up to 78% with a rise in the AV/CAV penetration rate. By dynamically controlling the size of the CAV platoons in the automated highway of the Bay Bridge, we limit the increase of the travel time in the downtown network as low as 5%. [ABSTRACT FROM AUTHOR]

• Designing a macroscopic modeling framework for perimeter gating control and dynamic user equilibrium. • Designing a routing scheme with instantaneous dynamic user equilibrium and predictive travel time. • Application of Proportional-Integral (PI) controller for traffic control. • Investigating the impact of perimeter gating control on routing inside-and-outside the reservoir. • Analysis of emissions in the traffic network. In recent years, several perimeter control strategies have been proposed for traffic management in cities. The common factor found in these works is the use of Macroscopic Fundamental Diagram (MFD) models to describe the dynamics of the network and optimize traffic inside the perimeter by manipulating perimeter inflows. Perimeter gating control strategies are attractive for traffic management inside the inner city. However, it inevitably creates a negative impact on the traffic outside. Most of the works in this research area have neglected vehicle re-routing outside the controlled perimeter, i.e., they do not consider demand elasticity to the central region resulting from gating and the related queues. In this paper, we propose a global modeling framework capable of assessing the effect of perimeter gating control (in terms of queue, emission, and total time spent) on the full network, considering demand elasticity resulting from Dynamic User Equilibrium (DUE). Classical Proportional-Integral (PI) control scheme is used to control traffic congestion inside a central region (reservoir). The modeling framework is comprised of: (i) an accumulation-based MFD model to reproduce traffic dynamics inside the reservoir, (ii) point-queue model to represent queuing vehicles on inbound links to the gating points, and (iii) a time-dependent travel time profile based on a steady-state approximation of MFD dynamics to characterize the alternative road network (bypass). DUE is then implemented, considering instantaneous predicted travel time. This determines how the demand to the inner region is affected by the gating. The functioning of the global system is assessed by total time spent and NOx and CO 2 emissions inside the reservoir and for the full network. The presented simulation results show that the perimeter gating control helps to maintain congestion at the desired level with significant improvements in the total time spent and the mean speed in the network. However, it shows a slight increase in the queues. As expected, deviation to the bypass alternative is significant and should not be neglected when carrying out a global assessment of gating system performance. [ABSTRACT FROM AUTHOR]

• Developing a max pressure traffic controller based on travel times. • Investigating work-conservative property in the developed max pressure traffic controller. • Comparison analysis with other traffic controllers via microsimulation test study. • Real implementation of the travel time max pressure controller to a signalized intersection. The traffic control of an arbitrary network of signalized intersections is considered. This work presents a new version of the recently proposed max-pressure controller, also known as back-pressure. The most remarkable features of the max-pressure algorithm for traffic signal control are: scalability, stability, and distribution. The modified version presented in this paper improves the practical applicability of the max-pressure controller by considering as input travel times instead of queue lengths. The two main practical advantages of this new version are: (i) travel times are easier to estimate than queue lengths, and (ii) max-pressure controller based on travel times has an inherent capacity-aware property, i.e., it takes into account the finite capacity of each link. Travel time tends to diverge when the queue length is close to its capacity. It should be noted that previous max-pressure algorithms rely exclusively on queue length measurements, which may be difficult to accomplish in practice. Moreover, these previous algorithms generally assume queues with unbounded capacity. This may be problematic because a model with unbounded capacity links is not able to reproduce spillbacks, which are one of the most critical phenomena that a traffic signal controller should avoid. After presenting the new version of the max-pressure controller, it is analyzed and compared with existing control policies in a microscopic traffic simulator. Moreover, results of a real implementation of the developed algorithm to a signalized intersection, located at an urban arterial in Jerusalem, are shown and analyzed. To the best of the authors' knowledge, this experiment is the first real implementation of a max-pressure controller at a signalized intersection. [ABSTRACT FROM AUTHOR]

• Real-time, Connected Vehicle-based traffic signal control algorithm. • Algorithm seeks to balance between efficiency and equity. • Algorithm minimizes average delay while limiting the maximum individual delay. • Equity at intersections can be improved with minimum loss of efficiency. This paper extends a real-time, Connected Vehicle-based traffic signal control algorithm at isolated intersections to balance between two competing intersection objectives: efficiency and equity. In this approach, a central controller is used to collect real-time locations of connected vehicles at regular intervals, which can then be used to also identify the existence of some of the non-connected vehicles. The control algorithm then aims to optimize the discharge sequence of naturally occurring platoons of vehicles based on their proximity. Specifically, the strategy selects the platoon discharge sequence—and associated signal phase and timing plan—that minimizes average vehicle delay (measure of efficiency) while limiting the maximum delay any individual vehicle may experience (measure of equity). The latter objective is only possible with detailed vehicle-level information available from connected vehicles. The results show that without the threshold on maximum individual vehicle delay, average delay is often minimized at the expense of very large delays imposed onto some vehicles. By implementing a threshold, both the maximum vehicle delay and the distribution of individual vehicle delays—as measured by the standard deviation and a common measure of population inequity, the Gini coefficient—can be improved, often with only negligible impacts to intersection efficiency. However, the tradeoff between equity and efficiency becomes more significant as the maximum vehicle delay threshold decreases. Sensitivity tests show that this control algorithm works well for different total traffic demands and different demand patterns. The proposed algorithm is also effective under imperfect connected vehicle penetration rates when the connected vehicles make up more than 40% of the traffic stream. The results suggest that the proposed strategy can help significantly reduce long delays and inequitable treatment of vehicles at an intersection when vehicle-level information is available to a signal controller. [ABSTRACT FROM AUTHOR]

• This paper proposes a network-wide method to identify intersection traffic congestion in a road network. • The proposed method is solely based on low-frequency probe vehicle data, i.e., map-independent. • It is able to rapidly and approximately detect intersection congestion along all turning directions. • It is a computer-aided method in the era of big data can greatly decrease traffic engineers' workload. Locating the bottlenecks in cities where traffic congestion usually occurs is essential prior to solving congestion problems. Therefore, this paper proposes a low-frequency probe vehicle data (PVD)-based method to identify turn-level intersection traffic congestion in an urban road network. This method initially divides an urban area into meter-scale square cells and maps PVD into those cells and then identifies the cells that correspond to road intersections by taking advantage of the fixed-location stop-and-go characteristics of traffic passing through intersections. With those rasterized road intersections, the proposed method recognizes probe vehicles' turning directions and provides preliminary analysis of traffic conditions at all turning directions. The proposed method is map-independent (i.e., no digital map is needed) and computationally efficient and is able to rapidly screen most of the intersections for turn-level congestion in a road network. Thereby, this method is expected to greatly decrease traffic engineers' workloads by providing information regarding where and when to investigate and solve traffic congestion problems. [ABSTRACT FROM AUTHOR]

• This paper presents a data-driven hybrid control (DDHC) framework. • DDHC framework composed of data-driven control module, performance module, and optimization module. • Control strategies including acceleration strategy and deceleration strategy. • The effectiveness of the proposed DDHC framework is evaluated with the data of a transit route in Urumqi, China. This paper presents a data-driven hybrid control (DDHC) framework that can arrange adaptive control strategies for vehicles to effectively improve the transit performance of the public transport system. The framework depicts a powerful combination of a data-driven control method that is used to imitate the control behaviour of dispatchers and a mathematical optimization method. Three components comprise the DDHC framework: a data-driven control module, a performance module, and an optimization module. The data-driven control module contains a random forest model which is adopted to justify whether to intervene in the operation of a bus line, and if so, which vehicles should be controlled and what type of control strategy should be taken – an acceleration strategy or deceleration strategy. The performance module including vehicle operation state models is used to describe the system evolution. The last component optimizes the specific control actions – which type of acceleration or deceleration strategy should be adopted – by minimizing total passenger travel time. The effectiveness of the proposed DDHC framework is evaluated with the data of a transit route in Urumqi, China. The results show that the DDHC framework with reasonable parameters can suit the needs of real-time control in complex traffic environments. [ABSTRACT FROM AUTHOR]

• In 2 simple networks P0 and MP do not maximise throughput if demand exceeds capacity. • In these 2 networks modified P0 and MP maximise throughput if demand exceeds capacity. • In a simple network with route choice, P0 maximises throughput for all demands. • In this simple network MP does not maximise long run throughput for all demands. This paper seeks traffic signal control policies which maximise long-run network throughput when demand is within network capacity and also when demand is beyond network capacity. The paper considers smooth versions of two well-known responsive traffic signal control policies: the P 0 policy (see Smith, 1979b, 1980 or Smith et al., 2015) and the maxpressure or MP policy (see Varaiya, 2013a). The paper gives two simple example networks where both of these smooth responsive traffic control policies give rise to decreasing throughput for increasing demands; when these demands are beyond the network capacity. The paper then suggests a simple modification of the two responsive traffic control policies and shows that the two modified policies do maximise the long run throughput of the two signal-controlled networks; both when a steady input demand D is within network capacity and also when a steady demand exceeds network capacity. The modified version of P 0 is as follows: for a certain positive number K , for D ⩽ K use responsive policy P 0 , and for D > K use the green-times generated by P 0 when D = K. Thus in this modification the green-time proportions generated by responsive P 0 are frozen as demand passes through K ; and remain fixed for all demands D which exceed K. The paper shows that the above modification when applied to a continuous version of MP also maximises throughput in both networks for all values of the steady demand D. Finally the paper considers a signal controlled network with route choice. It is shown that if routes are chosen by travellers in their own best interests then the continuous version of MP does not always maximise throughput, even if the constant input demand D is within the network capacity, but P 0 does always maximise throughput, even when the constant input demand D is beyond the network capacity. [ABSTRACT FROM AUTHOR]

• A series of methods are proposed for queue length and traffic volume estimation. • Only a few assumpitions are imposed and only probe vehicle data are needed. • The methods work well even when the penetration rate of probe vehicles is low. • Test results show the methods are useful for signal control and performance measures. The rapid development of connected vehicle technology and the emergence of ride-hailing services have enabled the collection of a tremendous amount of probe vehicle trajectory data. Due to the large scale, the trajectory data have become a potential substitute for the widely used fixed-location sensors in terms of the performance measures of transportation networks. Specifically, for traffic volume and queue length estimation, most of the trajectory data based methods in the existing literature either require high market penetration of the probe vehicles to identify the shockwave or require the prior information about the queue length distribution and the penetration rate, which may not be feasible in the real world. To overcome the limitations of the existing methods, this paper proposes a series of novel methods based on probability theory. By exploiting the stopping positions of the probe vehicles in the queues, the proposed methods try to establish and solve a single-variable equation for the penetration rate of the probe vehicles. Once the penetration rate is obtained, it can be used to project the total queue length and the total traffic volume. The validation results using both simulation data and real-world data show that the methods would be accurate enough for assistance in performance measures and traffic signal control at intersections, even when the penetration rate of the probe vehicles is very low. [ABSTRACT FROM AUTHOR]

Traffic volume is an indispensable ingredient to provide fine-grained information for traffic management and control. However, due to the limited deployment of traffic sensors, obtaining full-scale volume information is far from easy. Existing work on this topic focuses primarily on improving the overall estimation accuracy of a particular method and ignores the underlying challenges of volume estimation, thereby having inferior performance in some critical tasks. This paper studies two key problems with regard to traffic volume estimation: (1) underdetermined traffic flows caused by fully undetected paths that can allow arbitrary volume values without violating the conservation law, where using local side information is insufficient to tackle, and (2) nonequilibrium traffic flows arise when traffic flows vary in density over space and time due to congestion propagation delay, which produce time-shifted volume readings to varying degrees. Here we demonstrate a graph-based deep learning method that offers a data-driven, equation-free, and correlation-adaptive approach to address the above issues and perform accurate network-wide traffic volume estimation. Particularly, in order to quantify the dynamic and nonlinear speed-volume relationships for the estimation of underdetermined flows, a speed pattern-adaptive adjacency matrix based on graph attention is developed and integrated into the graph convolution process, to capture nonlocal correlations between volumes. To measure the impacts of nonequilibrium flows, a temporal masked and clipped attention combined with a gated temporal convolution layer is customized to capture time-asynchronous correlations between upstream and downstream sensors under varying impacts of congestion delay. We then evaluate our model on a real-world highway traffic volume dataset and compare it with several benchmark models. It is demonstrated that the proposed model achieves high estimation accuracy even under 20% sensor coverage rate and outperforms other baselines significantly, especially on underdetermined and nonequilibrium flow locations. Furthermore, comprehensive quantitative model analysis is also carried out to justify the model designs. The source code and datasets are publicly available at:. • Identifies underdetermined and non-equilibrium problems for network-wide traffic volume estimation. • Tailors a spatiotemporal correlation adaptive graph convolution network (STCAGCN) for volume estimation. • Exploits global speed-volume relationship as a remedy to underdetermined flows. • Captures time-asynchronous correlations in non-equilibrium flows with masked and clipped attention. • STCAGCN achieves state-of-the-art performances on all tasks. [ABSTRACT FROM AUTHOR]

The traffic capacity of signalized intersections can be increased using vehicle to infrastructure (V2I) communication by broadcasting traffic control signals to connected autonomous vehicles (CAVs). However, the potential improvement in traffic capacity with only CAVs can be substantially reduced under mixed traffic environments that include autonomous vehicles (AVs) without V2I communication. The main contribution of this work is to increase the traffic capacity (close to that achieved by CAVs with V2I communication) when there is a substantial number of AVs without V2I communication — by using a delayed-self-reinforcement (DSR) approach for vehicle spacing control with already available history of the AVs own control inputs and sensed information. Moreover, analytical estimates are established to predict the improvements in traffic capacity achieved for AVs with the DSR approach compared to the case without the DSR approach. Simulation results match the analytical predictions and show that AVs using the DSR approach (without V2I communication) are able to recover 88% of intersection capacity achieved with CAVs (with V2I communication) and result in 2.7 times the intersection capacity achieved by AVs without DSR on one way traffic. Moreover, similar improvements with DSR are shown for a real-world intersection using the Simulation of Urban MObility (SUMO) platform. AVs with DSR approach are able to recover 96% of intersection capacity achieved with CAVs (with V2I communication) and result in 1.4 times the intersection capacity achieved by AVs without DSR. Improvements using DSR are also seen with mixed traffic that includes human-driven vehicles (HDVs). [ABSTRACT FROM AUTHOR]

Controlling traffic in large-scale urban road networks is a challenging problem. Aggregated dynamical models, based on the macroscopic fundamental diagram (MFD) of urban traffic, enable model-based control design. As an alternative to perimeter control actuation commonly used in MFD-based control, in this paper, we propose actuation over regional space-mean speeds, which we name average speed control. The method involves manipulation of regional speeds via instrumentation similar to variable speed limits in freeways, or using vehicle-to-infrastructure communication. We develop nonlinear model predictive control schemes considering actuation over average speed and perimeter control. Their performances are compared using simulations on congested scenarios, the results of which suggest potential of the method as an alternative or complementary actuation to perimeter control. • A novel speed control strategy for urban networks. • Manipulation of regional average speeds to optimize traffic conditions in the whole network. • An MPC scheme combining perimeter control and average speed control. [ABSTRACT FROM AUTHOR]

Model predictive control (MPC) has been widely used for traffic management, such as for minimizing the total time spent or the total emissions of vehicles. When long-term green urban mobility is considered including e.g. a constraint on the total yearly emissions, the optimization horizon of the MPC problem is significantly larger than the control sampling time, and thus the number of the variables that should be optimized per control time step becomes very large. For systems with dynamics that involve nonlinear, non-convex, and non-smooth functions, including urban traffic networks, this results in optimization problems that are computationally intractable in real time. In this paper, we propose a novel bi-level temporal distribution of such complex MPC optimization problems, and we develop two mathematically linked short-term and long-term MPC formulations with small and large control sampling times that will be solved together instead of the original complex optimization problem. The resulting bi-level control architecture is used to solve the two MPC formulations online for real-time control of urban traffic networks with the objective of long-term green mobility. In order to assess the performance of the bi-level control architecture, we perform a case study where a rough version of the model of the urban traffic flow, S-model, is used by the long-term MPC level to estimate the states of the urban traffic networks, and a detailed version of the model is used by the short-term MPC level. The results of the simulations prove the effectiveness (with respect to the objective of control, as well as computational efficiency) of the proposed bi-level MPC approach, compared to state-of-the-art control approaches. • A bi-level MPC-based architecture is implemented for green mobility. • The link of the control levels is based on the long and short-term allowed emissions. • This framework can limit the emissions with an affordable online computation time. [ABSTRACT FROM AUTHOR]

• Propose priority-based infrastructure and control aware user heterogeneity, i.e. value-of-time. • Develop a joint optimization framework for traffic signal control and priority-based pricing. • Utilize connected vehicles to inform traffic flow and value-of-time information. • Test the proposed joint framework in real-city settings that resemble Zurich network. • Demonstrate traffic performance can be significantly improved while equitable savings achieved. Real-time control of large-scale urban networks has been attracting significant research attention. This paper, using the information provided by connected vehicles, proposes a novel control approach based on the concept of perimeter control to maximize the social welfare of all vehicles. The contributions of this paper are threefold. First, we consider vehicle heterogeneity (i.e. corresponding to different transportation modes, or with different occupancies, values of time, priority levels, etc.) and integrate a priority scheme into perimeter control to improve both the traffic performance and the social welfare. This is achieved by installing priority lanes at some of the perimeter intersections. Unlike the existing research works that provide priority to certain traffic modes, we dynamically identify the groups of vehicles that we should prioritize, in order to maximize the social welfare. Second, we develop a model predictive control approach to simultaneously optimize the toll for using the priority lanes and the traffic signal timings at the perimeter intersections. This approach can explicitly handle the constraint of the storage capacity of each intersection link. Third, we propose a recursive estimation algorithm to update our knowledge on the distribution of the value of times (VOTs), using the lane choice information of connected vehicles. The proposed approach is tested in a simulated network which resembles the main features of the city center of Zurich, Switzerland. By using the proposed strategy, the traffic accumulation inside the network is still stabilized, and the monetary costs due to delay are significantly reduced at the entire network (up to 25.8%) compared to the strategy without priority. The distribution of the combined cost (including cost due to delay and tolls) is more uniform across VOT groups than that resulting from the strategy without priority. It is also shown that the proposed recursive estimation algorithm quickly converges and further improves the social welfare. [ABSTRACT FROM AUTHOR]

• We propose an integrated simulation framework to assess traffic safety performance. • Evaluating traffic safety of a moving vehicle as a part of traffic flow. • Simultaneous consideration of complex geometric and other environmental conditions. • Introduction of an overall safety performance index of the whole traffic flow. Vehicles are extremely vulnerable to single-vehicle accidents under some hazardous driving conditions (i.e. strong wind, icy or snowy road surface). An integrated framework is proposed to assess single-vehicle traffic safety performance of stochastic traffic flow under hazardous driving conditions. Different from most existing studies focusing on a single vehicle moving at a constant speed, for the first time, the proposed work evaluates individual vehicle safety performance based on the time-dependent simulation results of stochastic traffic flow, including instantaneous speeds and positions of each vehicle as a part of simulated traffic flow. Simultaneously, complex geometric and other environmental conditions of the highway system are also considered realistically, not only during the safety assessment process, but also in quantifying the wind loads applied on the vehicles. Finally, with the safety information of each individual vehicle, an overall safety performance index of the whole traffic flow on the highway system is further introduced, which serves as a potential traffic safety performance measure and resilience indicator of transportation infrastructure systems under various hazards. This study has potential applications to not only regular vehicles, but also advanced traffic management and control algorithms for connected and autonomous vehicles in hazardous driving environments. [ABSTRACT FROM AUTHOR]