Intersection Control Research Articles

Urban Intersection Management Strategies for Autonomous/Connected/Conventional Vehicle Fleet Mixtures

Connected Vehicles and Autonomous Vehicles (CAVs) provide various sources of vehicular related information to intersection infrastructure by integrating on-board sensors processing, wireless communication and other Vehicle-to-Infrastructure (V2I) technologies. Thus connected vehicle technologies can potentially remedy data collection limitations of existing urban intersection managements, enhancing the performances of intersection controls such as reducing vehicle delay, reducing vehicle number of stops and improving energy efficiency. This paper reviews optimization-based signal controls for different penetrations of connected vehicles and conventional vehicles environments, autonomous intersection management specific to completely 100% AVs road states, as well as signal-trajectory joint control for different adoptions of conventional vehicles, CVs and AVs mixture environments. Real time data processing, signal timing optimizations, vehicle trajectory motion planning and evaluation frameworks are summarized to highlight the advantages and limitations of respective intersection control paradigms. It is important to recognize that realistic scenarios in comparative assessments for proposed methods need to be achieved in future works. The effectiveness of different approaches is challenging to be compared without complete evaluation frameworks, and sensitivity analysis and hypothesis tests involving variety penetration rates and flow demands should be performed in order to test the stability of methods in different scenarios.

Research on signal control method of deep reinforcement learning based on value distribution

In the traditional DQN (Deep Q network)-based signalized intersection control strategy, this research introduces an improved Distributional DQN to establish signal optimization decision-making model utilizing reinforcement learning based on value distribution. Different from the DQN model based on expected values, proposed model makes full use of the intersection environment information in each phase action for the distribution of the future total return. At the same time, proposed model constructs an optimization through minimizing the KL divergence between the estimated distribution and the true distribution, which makes it easier minimize the loss and accelerate the convergence speed of the model. In addition, a fixed boundary is reasonably added to the discrete distribution of the reward of the phase action, which effectively suppresses the traffic flow. The reward shock caused by large randomness reduces the instability of the algorithm. The simulation results demonstrate that the Distributional DQN proposed in this paper has a faster convergence rate than the original DQN, and the cumulative delay at the intersection is reduced by about 13.1%, and the average driving speed is increased by 7.1%, which further improves the control efficiency of signalized intersections.

Privacy and Trust in the Internet of Vehicles

The Internet of Vehicles aims to fundamentally improve transportation by connecting vehicles, drivers, passengers, and service providers together. Several new services such as parking space identification, platooning and intersection control—to name just a few—are expected to improve traffic congestion, reduce pollution, and improve the efficiency, safety and logistics of transportation. Proposed end-user services, however, make extensive use of private information with little consideration for the impact on users and third parties (those individuals whose information is indirectly involved). This article provides the first comprehensive overview of privacy and trust issues in the Internet of Vehicles at the service level. Various concerns over privacy are formalised into four basic categories: personal information privacy, multi-party privacy, trust, and consent to share information. To help analyse services and to facilitate future research, the main relevant end-user services are taxonomised according to voluntary and involuntary information they require and produce. Finally, this work identifies several open research problems and highlights general approaches to address them. These especially relate to measuring the trade-off between privacy and service functionality, automated consent negotiation, trust towards the IoV and its individual services, and identifying and resolving multi-party privacy conflicts.

Intersection control with connected and automated vehicles: a review

Purpose This paper aims to review the studies on intersection control with connected and automated vehicles (CAVs). Design/methodology/approach The most seminal and recent research in this area is reviewed. This study specifically focuses on two categories: CAV trajectory planning and joint intersection and CAV control. Findings It is found that there is a lack of widely recognized benchmarks in this area, which hinders the validation and demonstration of new studies. Originality/value In this review, the authors focus on the methodological approaches taken to empower intersection control with CAVs. The authors hope the present review could shed light on the state-of-the-art methods, research gaps and future research directions.

Improved reservation-based method with controllable gap strategy for vehicle coordination at non-signalized intersections

Recently, new research has emerged for signal-free intersection control via V2X technologies, and reservation-based intersection control for connected and automated vehicles (CAVs) has great potential to improve travel efficiency and traffic safety. A centralized traffic controller is the key component to coordinate movements of the approaching vehicles considering their priorities. In this paper, we propose a controllable gap strategy for the traffic controller considering the conflict relationship. To reduce the number of timestamp comparisons, we build three conflict modes of different traffic movements and present safe speed-dependent constraints for them. Then, based on the interactive relationship, we design an algorithm to manage the reservations for vehicles, which allows conflict-free vehicles crossing over the intersection synchronously. Furthermore, to ensure absolute safety in all cases, we present a rapid check criterion for conflict-free time slots in the conflict set of the reservation to avoid a potential collision, which removes unnecessary judgments. It is analyzed and proved that the aggregation of these local checks solves the conflicts globally. The strategy relaxes the limits of reservation policy. The proposed method is verified in the SUMO platform compared with the naive reservation-based method. Simulation results within 3000 s show that the proposed method can increase the traffic throughput and avoid vehicle collision for isolated intersections and traffic networks.

Identifying the Adaptability of Different Control Types Based on Delay and Capacity for Isolated Intersection

In urban road networks, intersections are the main bottlenecks. Selecting an appropriate intersection control type can significantly improve the performance of an isolated intersection. Therefore, this paper offers recommendations for selecting the most efficient control type among two-way stop control, signalized intersection (SIG), roundabout (RB), and signalized roundabout (SIGRB) based on capacity and delay. The procedure to calculate delay and capacity is taken from the Highway Capacity Manual 6th edition (2016), or developed separately if needed. Two flow patterns are assumed: fixed and time-varying demand. For fixed demand, the results show that SIGRB outperforms other control types both in capacity and delay at higher demand levels. It was also observed that increase in left-turn ratio increases the delay and decreases the capacity of all control types while its impact on SIGRB was the least. Considering time-varying demand, traffic volume fluctuates over the 5-h period of the analysis. It was found that using both RB and SIGRB together creates significantly less delay compared with the other options. Additionally, using RB provides less variability in delay when there is fluctuation in demand. The major finding of this research is that RB and SIGRB have potential benefits for delay in conditions of (i) high traffic volume, (ii) high left-turn ratio, and (iii) demand fluctuation. Furthermore, it is suggested that SIG should be used if the left-turn ratio is relatively low. The results of this study could help decision-makers to choose the best control type for an isolated intersection under various traffic conditions.

Graphical Animations of the Lim-Jeong-Park-Lee Autonomous Vehicle Intersection Control Protocol

Graphical Animations of the Lim-Jeong-Park-Lee Autonomous Vehicle Intersection Control Protocol

Intersection Management System for Autonomous Vehicles using a Fuzzy Inference System

An intersection management system (IMS) is a critical element in a transport system. Primarily intersection points are controlled with a time-based traffic signal. With the rapid growth in autonomous vehicles (AVs) and intelligent transport systems (ITSs), intersection management is an important area of research and development. The primary direction of this study is designing a management system that can communicate with vehicles, respond to them according to the traffic situation, and significantly reduce and avoid fatal situations like accidents. In this paper, a two-layered fuzzy logic-based controller is proposed to automate a cross-sectional intersection. Vehicles convey their particular information to the intersection unit, and the controller decides the specific action for the vehicles. This intersection controller is an IMS. After that, all roadside information is transferred to a centralized IMS (CIMS). The proposed CIMS reacts to a vehicle by giving an action command to leave the intersection. For prediction in a complex and dynamic environment, especially when many relevant factors overlap, fuzzy logic can be efficient. In this paper, fuzzy logic indicates the action for vehicles. Simulations were performed using MATLAB.

A deep reinforcement learning-based cooperative approach for multi-intersection traffic signal control

Recently, Adaptive Traffic Signal Control (ATSC) in the multi-intersection system is considered as one of the most critical issues in Intelligent Transportation Systems (ITS). Among the proposed AI-based approaches, Deep Reinforcement Learning (DRL) has been largely applied while showing better performances. This paper proposes a new DRL-based cooperative approach for controlling multiple intersections. The problem is modelled as a Multi-Agent Reinforcement Learning (MARL) system, while each agent is trained to select the best action to control an intersection by obtaining information about its local lanes state. The cooperation aspect is manifested in this approach by considering the effect of the state, action and reward of neighbour agents in the process of policy learning. An intersection controller applies a Deep Q-Network (DQN) method, while transferring state, action and reward received from their neighbour agents to its own loss function during the learning process. The experimental results under different scenarios shows that the proposed approach outperforms many state-of-the-art approaches in terms of three metrics: Average Waiting Time (AWT), Average Queue Length (AQL) and Average Emission CO2 (AEC). In addition, the cooperation between the different trained DRL-based controllers allows the system to continuously learn and improve its performance by interacting with the environment, particularly when the traffic is congested.

Microsimulation Study Evaluating the Benefits of Cyclic and Non-Cyclic Max-Pressure Control of Signalized Intersections

Max-pressure control is a decentralized method of traffic intersection control, making computations at individual intersections simple. In addition, this method of control has been proven to maximize network throughput if any traffic signal control can stabilize the demand. This paper tests max-pressure controllers in a large-scale microsimulation of the downtown Austin network using the microscopic traffic simulation package SUMO. Nine combinations of weight function and method of defining green time are studied to see how different variations on the max-pressure controller compare. It is shown that the way green time is assigned (cyclic or non-cyclic) has a larger impact on performance than the weight function used by the max-pressure controller. Based on these results a new way of assigning green time is devised. This novel controller mirrors the performance of either the cyclic or the non-cyclic controller depending on the geometry and demand. Large-scale simulation shows that this controller compares favorably with existing controllers using metrics of number of waiting vehicles and average travel time. Common problems with non-cyclic control include the higher likelihood of gridlock and the potential for very long waiting times when demand at a single intersection is asymmetric. On the other hand, the cyclic controller is required to allocate green time to every phase even if the demand is low, increasing the loss time. The novel semi-cyclic controller solves these inherent problems with the cyclic and non-cyclic controllers, making it more likely to be implemented by traffic engineers.

Selection of Intersection Control Type in Urban Areas

Abstract In Egypt, urban planning projects usually do not consider the intersection type. This study developed charts for practitioners that could be used to determine the optimal intersection. The paper studied intersections including; signalized, roundabout, and two-way stop control. It provides a study for the intersection at the targeted level of service D. The traffic patterns were used to calculate the intersection’s capacity and the average control delay. The combinations of turning distribution, percent of heavy vehicles, and type of control were considered. The relationship among capacity, delay and traffic volume has been used to deduce the minimum required lane configuration for each intersection. The results indicated that the roundabout is the best alternative for intersection control with maximum capacity and minimum delays for medium traffic. However, signalized intersection is the best alternative at heavy traffic volumes and a high proportion of left-turning volume.

Intersection traffic deadlock formation and its probability: A petri net‐based modeling approach

Although traffic deadlock at an intersection is a common phenomenon during rush hours, the deadlock formation metrics such as formation probability and duration have not been derived yet. As Petri Net (PN)-based approach can formulate the deadlock formation in analytical form and has been applied in numerous traffic flow studies, the PN is employed to investigate the deadlock formation probability and duration. First, each of the four main components of an intersection is formulated, namely vehicle trajectory, traffic signal, vehicle arrivals, and conflict behaviour, as a Petri Net (or IntersectionPN), and name them CellularPN, TrafficLightPN, DemandPN, and ConflictPN, respectively. Together, the entire intersection becomes an IntersectionPN, on which the system's three classes of states are defined, namely the deadlock state, the trap state, and the live state. The deadlock occurrence is formulated as an integer programming problem, while the formation probability and duration are studied by constructing a reachability graph that leads to the Markov chain of the system. A case study shows that the developed model is able to reproduce an intersection deadlock, and that the focus is on two priority behaviours: “First Enter First Serve” and “Pure Stochastic”. The results show that different behaviours lead to different deadlock formation metrics and that, when the saturation flow rate degrades (due to events such as severe weather conditions), a deadlock will occur more quickly. The research results provide the analysis tool for probabilistic deadlock formation. It can also be applied to the intersection deadlock prevention and control.

A Robust Adaptive Traffic Signal Control Algorithm Using Q-Learning under Mixed Traffic Flow

The operational and safety performance of intersections is the key to ensuring the efficient operation of urban traffic. With the development of automated driving technologies, the ability of adaptive traffic signal control has been improved according to data detected by connected and automated vehicles (CAVs). In this paper, an adaptive traffic signal control was proposed to optimize the operational and safety performance of the intersection. The proposed algorithm based on Q-learning considers the data detected by loop detectors and CAVs. Furthermore, a comprehensive analysis was conducted to verify the performance of the proposed algorithm. The results show that the average delay and conflict rate have been significantly optimized compared with fixed timing and traffic actuated control. In addition, the performance of the proposed algorithm is good in the test of the irregular intersection. The algorithm provides a new idea for the intelligent management of isolated intersections under the condition of mixed traffic flow. It provides a research basis for the collaborative control of multiple intersections.

The contribution of connected vehicles to network traffic control: A hierarchical approach

Connected vehicles (CVs) can considerably contribute to traffic control in the near future by providing real-time information. Such information can be exploited to identify the current traffic condition. However, challenges resulting from a high volume of data and lack of perfect knowledge in mixed traffic scenarios (consisting of CVs and conventional vehicles) have led to relatively sparse research in network-wide CV-based traffic control. To deal with such challenges, this paper proposes a hierarchical framework integrating three layers: (i) an intersection controller at individual intersections located in the center of the network, (ii) a network controller to regulate traffic coming into the network, and (iii) a phase controller to optimize the sequence of intersections’ signals. This approach permits the inclusion of information of (a limited number of) CVs to estimate and control queue lengths at individual intersections as well as the overall network load. Simulations carried out in VISSIM validate our approach in comparison with alternative control systems such as the application of (1) a traffic-responsive control, (2) a traffic accumulation regulator, or (3) a network signals coordinator. Moreover, comparisons between the proposed framework and a central system equipped with the information of all vehicles (giving rise to the optimal operation with, however, costly computation) under the consideration of different penetration rates of CVs and network layouts confirm that this framework results in competitive performance indicators, which, owing to the hierarchical structure, can be efficiently employed in real-time applications.

Traffic Behavior Recognition from Traffic Videos under Occlusion Condition: A Kalman Filter Approach

Real-time traffic data at intersections is significant for development of adaptive traffic light control systems. Sensors such as infrared radiation and GPS are not capable of providing detailed traffic information. Compared with these sensors, surveillance cameras have the potential to provide real scenes for traffic analysis. In this research, a You Only Look Once (YOLO)-based algorithm is employed to detect and track vehicles from traffic videos, and a predefined road mask is used to determine traffic flow and turning events in different roads. A Kalman filter is used to estimate and predict vehicle speed and location under the condition of background occlusion. The result shows that the proposed algorithm can identify traffic flow and turning events at a root mean square error (RMSE) of 10. The result shows that a Kalman filter with an intersection of union (IOU)-based tracker performs well at the condition of background occlusion. Also, the proposed algorithm can detect and track vehicles at different optical conditions. Bad weather and night-time will influence the detecting and tracking process in areas far from traffic cameras. The traffic flow extracted from traffic videos contains road information, so it can not only help with single intersection control, but also provides information for a road network. The temporal characteristic of observed traffic flow gives the potential to predict traffic flow based on detected traffic flow, which will make the traffic light control more efficient.

Cooperative signal-free intersection control using virtual platooning and traffic flow regulation

The emerging technologies of connectivity and automation enable the potential for signal-free intersection control. In this context, virtual platooning is posited to be an innovative, decentralized control strategy that maps two-dimensional vehicle movements onto a one-dimension virtual platoon to enable intersection operations. However, the effectiveness of virtual platooning-based control can be limited or degraded by parametric inaccuracies and unparameterized disturbances in vehicle dynamics, heavy traffic congestion, and/or uncoordinated platoons in multi-lane intersections. To explicitly address these limitations, this study proposes a hybrid cooperative intersection control framework consisting of microscopic-level virtual platooning control and macroscopic-level traffic flow regulation for traffic environments with connected autonomous vehicles. In virtual platooning control, vehicles approaching an intersection are organized into coordinated independent virtual platoons to avoid potential conflicts triggered by platoon formation changes. Through coordination, vehicles in a platoon are grouped into compatible passing sets to maintain desired safe spacing when proceeding through the intersection. We propose a distributed adaptive sliding mode controller (DASMC) which uses the backstepping control method and model reference adaptive control method to address parametric inaccuracies, and the sliding mode control method to consistently suppress the negative effects of the unparameterized disturbances. Each vehicle approaching the intersection utilizes the kinematic information from neighboring vehicles to implement the DASMC in a distributed manner such that vehicles within the same virtual platoon can achieve consensus safely. However, virtual platooning control cannot preclude excessive traffic from approaching the intersection, which can cause undesired spillbacks and degrade intersection control performance. To address this issue, traffic flow regulation is integrated with the virtual platooning control using an iterative feedback loop mechanism. In each iteration of the iterative feedback loop, a constrained finite-time optimal control (CFTOC) problem is solved to determine the optimal input flow permitted to proceed through the intersection, and the virtual platooning control provides feedback on the queue status to the CFTOC to initiate the next iteration. The effectiveness of the proposed intersection control framework is evaluated through numerical experiments. The results indicate that the proposed virtual platooning DASMC controller can mitigate the effects of parametric inaccuracies and unparameterized disturbances to achieve consensus for approaching vehicles, as well as guarantee string stability. Further, the proposed framework can alleviate traffic spillbacks and travel delays effectively through traffic flow regulation.

A Scalable Deep Learning Framework for Extracting Model Inventory of Roadway Element Intersection Control Types From Panoramic Images

In the United States, the Model Inventory of Roadway Element (MIRE) provides a comprehensive list of data that are needed to support states’ data-driven safety programs. The intersection control is part of the MIRE Fundamental Data Elements (FDE) for which state Departments of Transportation are required to complete the collection by September 30, 2026. It is essential roadway data that have been used widely in traffic safety studies. This study proposes a scalable and automated deep learning framework for detecting and classifying stop and yield intersection controls using panoramic street view images. The Faster Region-based Convolutional Neural Networks (Faster R-CNN) model architecture was used to detect and classify stop and yield signs from the images. A transfer learning process was deployed using the Inception-ResNet-v2 generic feature extractor to accelerate the training and performance of the deep learning model with less data collection effort. The effectiveness and scalability of the proposed framework were tested on a sample of road intersections in the state of Michigan. The proposed deep learning model achieved a recall value of 97.7% and 98.2% for detecting and classifying stop and yield signs respectively. The evaluation of the model performance at a county level suggests that the model can be scaled to a statewide level without a substantial increase in the demand for computational resources. As demonstrated in this study, state DOTs can leverage the advancement of deep learning techniques and the availability of imagery data to expedite the process of collecting the MIRE data.

Distributed Formation Control for Managing CAV Overtaking and Intersection Maneuvers

While intelligent transport systems are preparing to welcome connected and automated vehicles (CAVs), it is uncertain which algorithms should be employed to manage them. In particular, even though remarkable improvements in telecommunication technologies, such as vehicle-to-everything (V2X), enable communication and computation sharing among different agents, e.g. vehicles and infrastructures, distributed control algorithms are still not fully exploited. However, such methodologies have the potential to perfectly blend with the very nature of CAVs and alleviate traffic management units from the centralized computational burden. In this paper, we propose a formation control algorithm to control vehicle trajectories for two scenarios: 1) overtaking, and 2) intersection control. We include a simulation experiment to show some preliminary results and discuss limitations and future steps.

A Nearly Throughput-Maximum Knotted Intersection Design and Control for Connected and Automated Vehicles

A Nearly Throughput-Maximum Knotted Intersection Design and Control for Connected and Automated Vehicles

Signalized Intersection Control in Mixed Autonomous and Regular Vehicles Traffic Environment—A Critical Review Focusing on Future Control

The recent advancement in industrial technology has offered new opportunities to overcome different problems of stochastic driving behavior of humans through effective implementation of autonomous vehicles (AVs). Optimum utilization of driving behavior and advanced capabilities of the AVs has enabled researchers to propose autonomous cooperative-based methods for signalized intersection control under an AV traffic environment. In the future, AVs will share road networks with regular vehicles (RVs), representing a dynamic mixed traffic environment of two groups of vehicles with different characteristics. Without compromising the safety and level of service, traffic operation and control of such a complex environment is a challenging task. The current study includes a comprehensive review focused on the signalized intersection control methods under a mixed traffic environment. The different proposed methods in the literature are based on certain assumptions, requirements, and constraints mainly associated with traffic composition, connectivity, road infrastructures, intersection, and functional network design. Therefore, these methods should be evaluated with appropriate consideration of the underlying assumptions and limitations. This study concludes that the application of adaptive traffic signal control can effectively optimize traffic signal plans for variations of AV traffic environments. However, artificial intelligence approaches primarily focusing on reinforcement learning should be considered to better utilization of the improved AV characteristics.