Search

Traffic light optimization is known to be a cost-effective method for reducing congestion and energy consumption in urban areas without changing physical road infrastructure. However, due to the high installation and maintenance costs of vehicle detectors, most intersections are controlled by fixed-time traffic signals that are not regularly optimized. To alleviate traffic congestion at intersections, we present a large-scale traffic signal re-timing system that uses a small percentage of vehicle trajectories as the only input without reliance on any detectors. We develop the probabilistic time-space diagram, which establishes the connection between a stochastic point-queue model and vehicle trajectories under the proposed Newellian coordinates. This model enables us to reconstruct the recurrent spatial-temporal traffic state by aggregating sufficient historical data. Optimization algorithms are then developed to update traffic signal parameters for intersections with optimality gaps. A real-world citywide test of the system was conducted in Birmingham, Michigan, and demonstrated that it decreased the delay and number of stops at signalized intersections by up to 20% and 30%, respectively. This system provides a scalable, sustainable, and efficient solution to traffic light optimization and can potentially be applied to every fixed-time signalized intersection in the world. Without relying on any infrastructure-based vehicle detectors, the authors present a scalable traffic signal re-timing system that uses a small percentage of connected vehicle trajectories as the only input. Real-world tests demonstrate that the system decreases both delays and number of stops. [ABSTRACT FROM AUTHOR]

Traffic congestion is a major concern in urban centers, as it can affect society, the environment, and the economy. There are many studies on the use of computational intelligence (CI) to improve mobility in urban centers. Some of these researches focus on developing strategies for traffic light programming, since traffic coordination is complex due to its many parameters, variables, and dynamic behavior, and also an inefficient traffic control plan can lead to increased delays and contribute to traffic congestion. Although there are many works in the literature on strategies for traffic control, there are still some contributions and gaps to be filled, especially because some studies do not consider the automatic optimization of traffic signals in real time, that is, according to the demand of vehicles on the roads, considering multiple objectives and the use of a network of intersections in their experiments. In addition, some of the proposed models are not independent of simulation to evaluate the solutions of CI algorithms, resulting in a more complex deployment in real situations. In this context, this paper presents a new method to optimize traffic light plan in a network of intersections and in real time, called Active Control of Traffic Signals (ACTS) associated with the Non-Dominated Sorting Genetic Algorithm, considering multiple objectives in the optimization process (minimizing the average delay time and the number of vehicles stops per cycle). To test the applicability of the model, a real dataset of vehicle demand collected by the Company of Transport and Traffic of Belo Horizonte (BHTrans) is loaded into the AIMSUN simulator, then the method is applied and compared with the current traffic control plan used by BHTrans. The results show that the ACTS method reduces the average vehicle delay by almost half compared to the results obtained with the current solution used by BHTrans. In real life, this means less time spent in traffic, which promotes faster traffic flow, reducing traffic congestions. [ABSTRACT FROM AUTHOR]

Intelligent traffic light control (ITLC) algorithms are very efficient for relieving traffic congestion. Recently, many decentralized multi-agent traffic light control algorithms are proposed. These researches mainly focus on improving reinforcement learning method and coordination method. But, as all the agents need to communicate while coordinating with each other, the communication details should be improved as well. To guarantee communication effectiveness, two aspect should be considered. Firstly, a traffic condition description method need to be designed. By using this method, traffic condition can be described simply and clearly. Secondly, synchronization should be considered. As different intersections have different cycle lengths and message sending event happens at the end of each traffic signal cycle, every agent will receive messages of other agents at different time. So it is hard for an agent to decide which message is the latest one and the most valuable. Apart from communication details, reinforcement learning algorithm used for traffic signal timing should also be improved. In the traditional reinforcement learning based ITLC algorithms, either queue length of congested cars or waiting time of these cars is considered while calculating reward value. But, both of them are very important. So a new reward calculation method is needed. To solve all these problems, in this paper, a new ITLC algorithm is proposed. To improve communication efficiency, this algorithm adopts a new message sending and processing method. Besides, to measure traffic congestion in a more reasonable way, a new reward calculation method is proposed and used. This method takes both waiting time and queue length into consideration. [ABSTRACT FROM AUTHOR]

Cooperation between intersections in large-scale road networks is critical in traffic congestion. Currently, most traffic signals cooperate via pre-defined timing phases, which is extremely inefficient in real-time traffic scenarios. Most existing studies on multi-agent reinforcement learning (MARL) traffic signal control have focused on designing efficient communication methods, but have ignored the importance of how agents interact in cooperative communication. To achieve more efficient cooperation among traffic signals and alleviate urban traffic congestion, this study constructs a Graph Cooperation Q-learning Network Traffic Signal Control (GCQN-TSC) model, which is a graph cooperation network with an embedded self-attention mechanism that enables agents to adjust their attention in real time according to the dynamic traffic flow information, perceive the traffic environment quickly and effectively in a larger range, and help agents achieve more effective collaboration. Moreover, the Deep Graph Q-learning (DGQ) algorithm is proposed in this model to optimize the traffic signal control strategy according to the spatio-temporal characteristics of different traffic scenes and provide the optimal signal phase for each intersection. This study also integrates the ecological traffic concept into MARL traffic signal control, which aims to reduce traffic exhaust emissions. Finally, the proposed GCQN-TSC is experimentally validated both in a synthetic traffic grid and a real-world traffic network using the SUMO simulator. The experimental results show that GCQN-TSC outperforms other traffic signal control methods in almost all performance metrics, including average queue length and waiting time, as it can aggregate information acquired from collaborative agents and make network-level signal optimization decisions. [ABSTRACT FROM AUTHOR]

Traffic lights are an important controlling factor in traffic flows, and good policies will facilitate traffic congestion. A car's waiting time is highly related to the period in which the traffic lights are green or red; thus, a proper controlling policy reduces the waiting time and speeds up the car movement. Emergency vehicles always have a higher priority than other cars and need to reach their destination faster. In the last decade, a lot of research has been done to solve the traffic light scheduling issue using artificial intelligence techniques. Reinforcement learning with simulating human learning has the outstanding performance to solve complex problems, such as traffic lights control. In this study, a deep reinforcement learning traffic light control was implemented at a crossroad using real-time traffic information with an emphasis on emergency vehicles. The agent learns to adjust its policies to prioritize the emergency cars over the other cars. The results show less waiting time and speed up the cars' movement. It also indicates the emergency vehicles will cross the intersection with the least delay. With 200 to 600 cars and one emergency vehicle, the average delay decreases 2–16% in total using reinforcement learning. Considering more emergency vehicles, there is a 27–40% decrease in average delay for emergency vehicles. [ABSTRACT FROM AUTHOR]

In recent years, due to the drastic rise in the number of vehicles and the lack of sufficient infrastructure, traffic jams, air pollution, and fuel consumption have increased in cities. The optimization of timing for traffic lights is one of the solutions for the mentioned problems. Many methods have been introduced to deal with these problems, including reinforcement learning. Although a great number of learning-based methods have been used in traffic signal control, they suffer from poor performance and slow learning convergence. In this paper, a transfer learning-based method for traffic signal control has been proposed. Multi-agent system has also been used for modelling the traffic network and transfer learning has been used to make reinforcement learning agents transfer their experience to each other. Furthermore, a classifier has been utilized to classify the transferred experiences. The results show that using the proposed method leads to a significant improvement on average delay time and convergence time of the learning process. [ABSTRACT FROM AUTHOR]

This paper presents a novel method to estimate queue length at signalised intersections using connected vehicle (CV) data. The proposed queue length estimation method does not depend on any conventional information such as arrival flow rate and parameters pertaining to traffic signal controllers. The model is applicable for real-time applications when there are sufficient training data available to train the estimation model. To this end, we propose the idea of "k-leader CVs" to be able to predict the queue which is propagated after the communication range of dedicated short-range communication (the communication platform used in CV system). The idea of k-leader CVs could reduce the risk of communication failure which is a serious concern in CV ecosystems. Furthermore, a linear regression model is applied to weigh the importance of input variables to be used in a neural network model. Vissim traffic simulator is employed to train and evaluate the effectiveness and robustness of the model under different travel demand conditions, a varying number of CVs (i.e. CVs' market penetration rate) as well as various traffic signal control scenarios. As it is expected, when the market penetration rate increases, the accuracy of the model enhances consequently. In a congested traffic condition (saturated flow), the proposed model is more accurate compared to the undersaturated condition with the same market penetration rates. Although the proposed method does not depend on information of the arrival pattern and traffic signal control parameters, the results of the queue length estimation are still comparable with the results of the methods that highly depend on such information. The proposed algorithm is also tested using large size data from a CV test bed (i.e. Australian Integrated Multimodal Ecosystem) currently underway in Melbourne, Australia. The simulation results show that the model can perform well irrespective of the intersection layouts, traffic signal plans and arrival patterns of vehicles. Based on the numerical results, 20% penetration rate of CVs is a critical threshold. For penetration rates below 20%, prediction algorithms fail to produce reliable outcomes. [ABSTRACT FROM AUTHOR]

Background: The intersection traffic signal control problem (ITSCP) has become even more important as traffic congestion has been more intractable. The ITSCP seeks an efficient schedule for traffic signal settings at intersections with the goal of maximizing traffic flow while considering various factors such as real-time strategies, signal timing constraints, rapid developments in traffic systems, and practical implementation. Since the factors constituting the ITSCP exhibit stochastically complicated interactions, it is essential to identify these factors to propose solution methods that can address this complexity and still be practically implemented. Objective: The objective of this review is to provide a survey of problems, methods, and practices in the evaluation of the ITSCP. In this paper, a unified terminology for the ITSCP and a citation network of the current body of relevant research are accordingly presented, and various assumptions, constraints, and solution approaches are summarized. A review across the entire body of knowledge throughout the history of the ITSCP is therefore provided. This review also highlights open issues and challenges that remain to be addressed by future research. [ABSTRACT FROM AUTHOR]