Intelligent Traffic Signal Research Articles

Deep Behavioral Cloning for Traffic Control with Virtual Expert Demonstration Under a Parallel Learning Framework

Intelligent traffic signal control is necessary for improving traffic efficiency. These fast changing and challenging traffic scenarios and demands are generally handled by professional traffic engineers. However, it may take years of time and thousands of practices to train such an engineer. This paper proposes a deep behavioral cloning method to learn how to control the traffic signal effectively and efficiently from virtual expert demonstration. The method imitates promising working behavior of optimized offline solutions, and applies it to solve online traffic signal control problems of the similar scenario. Different traffic demand patterns are generated through a combination of different kinds of components. Then the virtual demonstration is constructed by getting an exclusive and optimized solution for each generated virtual traffic demand pattern through a heuristic random search method. After that, a deep neural network-based behavioral cloning method is employed to learn from the virtual demonstration and finish on-line traffic signal control task. The experimental results show that compared with other methods, the proposed method significantly reduces the waiting time and time loss in different situations. And the average traffic speed of the road network at different saturation levels can be improved by 1.58% to 11.54%.

Research on self-organising control method of urban intelligent traffic signal based on vehicle networking

In order to overcome the problem of poor application of traditional urban intelligent traffic signal self-organisation control, a method of urban intelligent traffic signal self-organisation control based on vehicle network is proposed. A signal self-organising control system based on on-demand distribution is constructed, in which the fixed unit module RSU receives vehicle traffic data through sensors. RDU is used to monitor vehicle data and construct signal adaptive control strategy, which can reduce vehicle waiting time and realise urban intelligent traffic signal self-organising control. Simulation results show that the average number of stops at the intersection at the same time point is less than 0.3. The average stopping time is 8.728s, which is obviously lower than other methods. The average pass rate at the intersection is 98.65%, which is obviously higher than other methods and feasible.

Research on self-organising control method of urban intelligent traffic signal based on vehicle networking

In order to overcome the problem of poor application of traditional urban intelligent traffic signal self-organisation control, a method of urban intelligent traffic signal self-organisation control based on vehicle network is proposed. A signal self-organising control system based on on-demand distribution is constructed, in which the fixed unit module RSU receives vehicle traffic data through sensors. RDU is used to monitor vehicle data and construct signal adaptive control strategy, which can reduce vehicle waiting time and realise urban intelligent traffic signal self-organising control. Simulation results show that the average number of stops at the intersection at the same time point is less than 0.3. The average stopping time is 8.728s, which is obviously lower than other methods. The average pass rate at the intersection is 98.65%, which is obviously higher than other methods and feasible.

PlanLight: Learning to Optimize Traffic Signal Control With Planning and Iterative Policy Improvement

Intelligent traffic signal control (TSC) is essential for transportation efficiency in modern road networks. There is an emerging trend of using deep reinforcement learning techniques to train TSC models in simulators for reducing trial-and-error in real-world scenarios, and recent studies have shown promising results. The target of TSC is to minimize the average travel time of a given area. However, it is impractical to directly optimize the target by setting the average travel time as the reward function due to its nature of feedback latency and difficulty on credit assignment. Existing methods often define the reward function in a heuristic way, which may cause a biased optimization on the real target as they only optimize the accumulative reward. In this work, we propose PlanLight, a novel planning-based TSC algorithm that learns from the demonstration of rollout algorithm, which obtains suboptimal control on the given target, through behavior cloning. We show the effectiveness and efficiency of the rollout algorithm in the multi-intersection control scenario. Moreover, we achieve further policy optimization by improving the base policy in the rollout procedure iteratively. Through comprehensive experiments, we demonstrate that PlanLight outperforms both conventional transportation approaches and existing learning-based methods in various sizes of traffic datasets. Furthermore, we empirically show the potential of PlanLight to be a general algorithm to obtain improvement on future state-of-the-art TSC methods.

Cooperative Traffic Signal Control with Traffic Flow Prediction in Multi-Intersection.

As traffic congestion in cities becomes serious, intelligent traffic signal control has been actively studied. Deep Q-Network (DQN), a representative deep reinforcement learning algorithm, is applied to various domains from fully-observable game environment to traffic signal control. Due to the effective performance of DQN, deep reinforcement learning has improved speeds and various DQN extensions have been introduced. However, most traffic signal control researches were performed at a single intersection, and because of the use of virtual simulators, there are limitations that do not take into account variables that affect actual traffic conditions. In this paper, we propose a cooperative traffic signal control with traffic flow prediction (TFP-CTSC) for a multi-intersection. A traffic flow prediction model predicts future traffic state and considers the variables that affect actual traffic conditions. In addition, for cooperative traffic signal control in multi-intersection, each intersection is modeled as an agent, and each agent is trained to take best action by receiving traffic states from the road environment. To deal with multi-intersection efficiently, agents share their traffic information with other adjacent intersections. In the experiment, TFP-CTSC is compared with existing traffic signal control algorithms in a 4 × 4 intersection environment. We verify our traffic flow prediction and cooperative method.

The Internet of Nature: How taking nature online can shape urban ecosystems

Many of our cities are going digital. From self-driving cars to smart grids to intelligent traffic signals, these smart cities put data and digital technology to work to drive efficiency and improve the quality of life for citizens. Yet, the natural capital upon which cities rely risks being left behind by the digital revolution. Bringing nature online is the next frontier in ecosystem management and will change our relationship with the natural world in the urban age. In this article, we introduce the ‘Internet of Nature’ to bridge the gap between greener and smarter cities and to explore the future of urban ecosystem management in an age of rapid urbanisation and digitisation. The creation of an Internet of Nature, along with the ecosystem intelligence it provides, is an opportunity to elicit and understand urban ecosystem dynamics, promote self-sufficiency and resilience in ecosystem management and enhance connections between urban social and ecological systems.

Cooperative traffic signal control using Multi-step return and Off-policy Asynchronous Advantage Actor-Critic Graph algorithm

Intelligent traffic signal control helps to reduce traffic congestion and thus has been studied for a few decades. Multi-intersection cooperative traffic signal control (CTSC), which is more practical than single-intersection traffic signal control, has attracted much attention and research in recent years. Existing works on multi-intersection CTSC make responsive policies based on the sequence of agents’ actions. One issue in multi-intersection CTSC is that every agent’s actions are mapped from its own road information and some useful information, e.g., the distance of adjacent agents, is ignored, which may lead to suboptimal traffic signal control policies. To address this issue, in this paper a decentralized coordination graph algorithm, referred to as Multi-step return and Off-policy Asynchronous Advantage Actor-Critic Graph (MOA3CG) algorithm, is proposed. The MOA3CG algorithm is based on an asynchronous method of multiagent deep reinforcement learning and a coordination graph; the proposed algorithm makes traffic signal control policies based on current traffic states, the history of observations and other information. A new reward function and An Adjusting Matrix of Traffic Signal Phase Control (AMTSPC) are proposed, which are used by the MOA3CG algorithm in the policy-making process; the AMTSPC is to alter selection of actions by considering the distance of adjacent agents. Experimental results on real-world road scenarios show that the proposed algorithm outperforms other four state-of-the-art algorithms in terms of average delay, average traveling time of vehicles, and the throughput of vehicles, thus eventually helps to mitigate traffic congestion.

Computer vision-guided intelligent traffic signaling for isolated intersections

Computer vision-guided traffic management is an emerging area of research. Intelligent traffic signal control using computer vision is a less explored area of research. In this paper, we propose a new approach of traffic flow-based intelligent signal timing by temporally clustering optical flow features of moving vehicles using Temporal Unknown Incremental Clustering (TUIC) model. First, we propose a new inference scheme that works approximately 5-times faster as compared to the one originally proposed in TUIC in a dense traffic intersection. The new inference scheme can trace clusters representing moving objects that may be occluded while being tracked. Cluster counts of approach roads have been used for signal timing for traffic intersections. It is done by detecting cluster motion inside the regions-of-interest (ROI) marked at the entry and exit locations of intersection approaches. Departure rates are learned using Gaussian regression to parameterize traffic variations. Using the learned parameters as a function of cluster count, an adaptive signal timing algorithm, namely Throughput and Average Waiting Time Optimization (TAWTO) has been proposed. Experimental results reveal that the proposed method can achieve better average waiting time and throughput as compared to the state-of-the-art signal timing algorithms. We intend to publish two datasets as part of this work for enabling the research community to explore computer vision aided solutions for typical problems such as intelligent traffic controlling, violation detection in chaotic road intersections, etc.

Internet of Vehicles and Cost-Effective Traffic Signal Control.

The Internet of Vehicles (IoV) is attracting many researchers with the emergence of autonomous or smart vehicles. Vehicles on the road are becoming smart objects equipped with lots of sensors and powerful computing and communication capabilities. In the IoV environment, the efficiency of road transportation can be enhanced with the help of cost-effective traffic signal control. Traffic signal controllers control traffic lights based on the number of vehicles waiting for the green light (in short, vehicle queue length). So far, the utilization of video cameras or sensors has been extensively studied as the intelligent means of the vehicle queue length estimation. However, it has the deficiencies like high computing overhead, high installation and maintenance cost, high susceptibility to the surrounding environment, etc. Therefore, in this paper, we propose the vehicular communication-based approach for intelligent traffic signal control in a cost-effective way with low computing overhead and high resilience to environmental obstacles. In the vehicular communication-based approach, traffic signals are efficiently controlled at no extra cost by using the pre-equipped vehicular communication capabilities of IoV. Vehicular communications allow vehicles to send messages to traffic signal controllers (i.e., vehicle-to-infrastructure (V2I) communications) so that they can estimate vehicle queue length based on the collected messages. In our previous work, we have proposed a mechanism that can accomplish the efficiency of vehicular communications without losing the accuracy of traffic signal control. This mechanism gives transmission preference to the vehicles farther away from the traffic signal controller, so that the other vehicles closer to the stop line give up transmissions. In this paper, we propose a new mechanism enhancing the previous mechanism by selecting the vehicles performing V2I communications based on the concept of road sectorization. In the mechanism, only the vehicles within specific areas, called sectors, perform V2I communications to reduce the message transmission overhead. For the performance comparison of our mechanisms, we carry out simulations by using the Veins vehicular network simulation framework and measure the message transmission overhead and the accuracy of the estimated vehicle queue length. Simulation results verify that our vehicular communication-based approach significantly reduces the message transmission overhead without losing the accuracy of the vehicle queue length estimation.

Video-Based Vehicle Counting Framework

The continuous development in the construction of transportation infrastructure has brought enormous pressure to traffic control. Accurate and detailed traffic flow information is valuable for an effective traffic control strategy. This paper proposes a video-based vehicle counting framework using a three-component process of object detection, object tracking, and trajectory processing to obtain the traffic flow information. First, a dataset for vehicle object detection (VDD) and a standard dataset for verifying the vehicle counting results (VCD) were established. The object detection was then completed by deep learning with VDD. Using this detection, a matching algorithm was designed to perform multi-object tracking in combination with a traditional tracking method. Trajectories of the moving objects were obtained using this approach. Finally, a trajectory counting algorithm based on encoding is proposed. The vehicles were counted according to the vehicle categories and their moving route to obtain detailed traffic flow information. The results demonstrated that the overall accuracy of our method for vehicle counting can reach more than 90%. The running rate of the proposed framework is 20.7 frames/s on the VCD. Therefore, the proposed vehicle counting framework is capable of acquiring reliable traffic flow information, which is likely applicable to intelligent traffic control and dynamic signal timing.

Development and Application of Dynamic Timing Optimization Platform for Big Data Intelligent Traffic Signals

As the number of car ownership increases, road traffic flow continues to increase. At the same time, traffic pressure at intersections is increasing as well. At present, most of the traffic lights in China are fixed cycle control. This timing control algorithm obviously cannot make timely adjustments according to changes in traffic flow. In this case, a large number of transportation resources would be wasted. It is very necessary to establish a dynamic timing system for Big data intelligent traffic signals. In this research, the video recognition method was used to acquire the number of vehicles at the intersection in real time, and the obtained data was processed by the optimization algorithm to make a reasonable dynamic timing of the traffic signals. The test results show that after using the big data intelligent traffic signal dynamic timing optimization control platform, in the experimental area, the overall total delay time was reduced by 23%, and the travel time was reduced by 15%. During the off-peak period, the overall total delay time in the experimental region was reduced by 17% and travel time was reduced by 10%. The big data intelligent traffic signal dynamic timing optimization platform would improve the operational efficiency and traffic supply capacity of the existing transportation infrastructure, and could provide real convenience for citizens.

A Multi-Objective Agent-Based Control Approach With Application in Intelligent Traffic Signal System

Agent-based approaches have gained popularity in engineering applications, but its potential for advanced traffic controls has not been sufficiently explored. This paper presents a multi-agent framework that models traffic control instruments and their interactions with road traffic. A constrained Markov decision process (CMDP) model is used to represent agent decision making in the context of multi-objective policy goals, where the policy goal with the highest priority becomes the single optimization objective and the other goals are transformed as constraints. A reinforcement learning-based computational framework is developed for control applications. To implement the multi-objective decision model, a threshold lexicographic ordering method is introduced and integrated with the learning-based algorithm. Moreover, a two-stage hybrid framework is established to improve the learning efficiency of the model. While the proposed approach is potentially applicable for different road traffic operations, this paper applies the framework for traffic signal control in a network of Stockholm based on traffic simulation. The computational results show that the proposed control approach can handle a complex case of multiple policy requirements. Meanwhile, the agent-based intelligent control has shown superior performance when compared to other optimized signal control methods.

Queuing theory guided intelligent traffic scheduling through video analysis using Dirichlet process mixture model

Intelligent traffic signaling is an important part of city road traffic management systems. In many countries, it is done through supervised/semi-supervised ways. With the advances in computer vision and machine learning, it is now possible to develop expert systems guided intelligent traffic signaling systems that are unsupervised in nature. In order to schedule traffic signals, it is essential to learn the traffic characterization parameters such as the number of vehicles, their arrival and departure rates, etc. In this work, we use unsupervised machine learning with the help of a modified Dirichlet Process Mixture Model (DPMM) to measure the aforementioned traffic parameters. This has been done using a new feature, named temporal clusters or tracklets extracted using DPMM. Detailed analysis on tracklet behavior during signal on/off period has been carried out to derive a queuing theory-based method for signal duration prediction. The queuing behavior at a junction is analyzed using tracklets for understanding their applicability. Queue clearance time at the junction has been used for predicting the signal duration with the help of Gaussian regression of historical data.Two publicly available video datasets, namely QMUL and MIT have been used for verification of the hypothesis. The mean absolute error (MAE) of the proposed method using tracklets has been reduced by a factor of 2.4 and 6.3 when compared with the tracks generated using Kernel Correlation Filters (KCF) and Kanade–Lucas–Tomasi (KLT), respectively. Through experiments, we are also able to establish that KCF and KLT tracks do not consider spatial occupancy of the vehicles on roads, leading to error in the estimation. The results reveal that the proposed queuing theory-based approach predicts the signal duration for the next cycle more accurately as compared to the ground truths. The method can be used for building intelligent traffic control systems for roadway junctions in cities and highways.

Building Intelligence in Automated Traffic Signal Performance Measures with Advanced Data Analytics

Automated traffic signal performance measures (ATSPMs) are designed to equip traffic signal controllers with high-resolution data-logging capabilities which may be used to generate performance measures. These measures allow practitioners to improve operations as well as to maintain and operate their systems in a safe and efficient manner. While they have changed the way that operators manage their systems, several shortcomings of ATSPMs, as identified by signal operators, include a lack of data quality control and the extent of resources required to use the tool properly for system-wide management. To address these shortcomings, intelligent traffic signal performance measurements (ITSPMs) are presented in this paper, using the concepts of machine learning, traffic flow theory, and data visualization to reduce the operator resources needed for overseeing data-driven ATSPMs. In applying these concepts, ITSPMs provide graphical tools to identify and remove logging errors and data from bad sensors, to determine trends in demand intelligently, and to address the question of whether or not coordination may be needed at an intersection. The focus of ATSPMs and ITSPMs on performance measures for multimodal users is identified as a pressing need for future research.

Modeling Cyber Attacks at Intelligent Traffic Signals

Transportation networks are considered one of the critical physical infrastructures for resilient cities (cyber-physical systems). In efforts to minimize adverse effects that come with the advancement of vehicular technologies, various governmental agencies, such as the U.S. Department of Homeland Security and the National Highway Traffic Safety Administration (NHTSA), work together. This paper develops belief-network-based attack modeling at signalized traffic networks under connected vehicle and intelligent signals frameworks. For different types of cyber attacks, defined in the literature, risk areas and impacts of attacks are evaluated. Vulnerability scores, technically based on the selected metrics, are calculated for signal controllers. In addition, the effect of having redundant traffic sensing systems on intersection performance measures is demonstrated in terms of average queue length differences.

Peer-to-Peer Priority Signal Control Strategy in a Connected Vehicle Environment

This paper presents a methodology that enhances the priority signal control model in the multi-modal intelligent traffic signal system (MMITSS). To overcome the range limit of vehicle to infrastructure (V2I) and the intersection geometry message (MAP) distance limits, peer-to-peer intersection communications are utilized to send priority requests from adjacent intersections. Through integrated communication, the peer priority control strategy can create a signal plan for prioritized vehicles that considers longer term (headway) arrival times. Transit vehicles are considered in this study. The longer-term signal plan provides a flexible signal schedule that allows local phase actuation. The peer priority strategy is effective in reducing the number of stops and delay for priority eligible vehicles, while minimizing the negative impact on regular vehicles. To validate the strategy, a simulation experiment was designed to compare fully actuated control, coordination, and MMITSS priority control using two different VISSIM simulation networks (Arizona and Utah). The result shows that the peer-to-peer long term planning strategy can improve transit service reliability while limiting the adverse impact on other traffic.

Trajectory Length Prediction for Intelligent Traffic Signaling: A Data-Driven Approach

Ship trajectory length prediction is vital for intelligent traffic signaling in the controlled waterways of the Yangtze River. In current intelligent traffic signaling systems (ITSSs), ships are supposed to travel exactly along the central line of the Yangtze River, which is often not a valid assumption and has caused a number of problems. Over the past few years, traffic data have been accumulated exponentially, leading to the big data era. This trend allows more accurate prediction of ships’ travel trajectory length based on historical data. In this paper, ships’ historical trajectories are first grouped by using the fuzzy c-means clustering algorithm. The relationship between some known factors (i.e., ship speed, loading capacity, self-weight, maximum power, ship length, ship width, ship type, and water level) and the resultant memberships are then modeled using artificial neural networks. The trajectory length is then estimated by the sum of the predicted probabilities multiplied by the trajectory cluster centers’ length. To the best of our knowledge, this is the first time to predict the overall trajectory length of manually controlled ships. The experimental results show that the proposed method can reduce the probability of generating incorrect traffic control signals by 74.68% over existing ITSSs. This will significantly improve the efficiency of the Yangtze River traffic management system and increase the traffic capacity by reducing the traveling time.

An Approach for Intelligent Traffic Signal Control System for Ambulance Using IoT

Today, many human lives are being expired due to traffic jam and get delayed in reaching the hospital within time. In an emergency condition when a patient is in the ambulance, he/she has to reach the hospital with utmost fast to the nearest hospital should be done in a speedy way to save their lives, hence there is a need to tackle the traffic jam and control the traffic lights accordingly so that ambulance’s lane must be made green and thus providing a stoppage free way for the Ambulance to reach the hospital without delay in time.Normally traffic light systems operate on a timing mechanism that changes the light after a given interval of time. Thus, automated traffic signal releasing system for ambulance will not spend unnecessary time waiting for the traffic lights to change and manage of traffic jam. This proposed project aims to provide facilities and make easier for vehicle in emergency case especially for an ambulance. In an emergency situation, we are using the transmitter and receiver circuit which is using the Radio Frequency (RF) Sensor respectively. The transmitter will send the signal to the receiver that placed at every single traffic light to turn the traffic light from red to green light as the normal traffic is passed through, the traffic light will operate as usual until ambulance vehicle press the button by passing through it. This project aims to design an intelligent traffic light signal which makes the arrival of ambulance free way by halting traffic in case of emergencies. Hence this project will act as a life saver.

Iterative Tuning With Reactive Compensation for Urban Traffic Signal Control

To utilize the utmost capacities of junctions with traffic signals, having preemptive and predictive capabilities with integrated traffic sensors are important elements for an intelligent traffic signal control system. Recently, an efficient and preemptive traffic signal control strategy known as iterative tuning (IT) has been developed by exploring repetitive characteristic of traffic demand on working days, whereas on weekends or days with special events, severe nonrepetitive disturbances limit the performance of IT strategy practically. This paper proposes a preemptive and predictive methodology, i.e., IT strategy with reactive compensation (ITRC), to reduce network delay time and eliminate unnecessary stops for vehicles. With anticipation of repetitive traffic flows based on historical data, nominal traffic signals are tuned by IT controller over repetitions. The reactive compensation, which is junction-based model predictive control strategy (JMPC), makes adjustments on nominal traffic signals and compensates the nonrepetitive elements. Rigorous analysis provides sufficient condition for guaranteeing the convergence of ITRC. Case study of Commonwealth Avenue in Singapore with heavy traffic from morning peak to evening peak hours is presented, and the simulation results show the effectiveness, robustness, and convergence of ITRC over pure IT strategy and pure JMPC strategy for scenarios with various traffic variations, respectively.

INTELLIGENT TRAFFIC SIGNAL CONTROL SYSTEM

Adaptive traffic signal control system is presents an intelligent traffic signal control system using image processing technique. With the help of specialized algorithm, morphology and image needed to avoid traffic congestion. This paper processing technique, the vehicles are detected, recognized and density is calibrated for controlling traffic density. This is the most reliable and upcoming technology in the road transit system