Search

Intelligent traffic light control (ITLC) aims to relieve traffic congestion. Some multi-agent deep reinforcement learning (MADRL) algorithms have been proposed for ITLC, and most of them use deep neural networks to make decisions. However, the abundant parameters of deep structure lead to the time-consuming training process of MADRL. Recently, a broad reinforcement learning (BRL) approach has been proposed to improve the efficiency of training for an agent. Unlike MADRL algorithms that use deep architecture, BRL utilizes a broad architecture. In this paper, we propose a multi-agent broad reinforcement learning (MABRL) algorithm for ITLC. The MABRL algorithm adopts the broad network to process the joint information and updates the parameters using ridge regression. To increase the effectiveness of interaction among agents, we design a dynamic interaction mechanism (DIM) based on the attention mechanism. The DIM enables agents to aggregate information on particular intersections at appropriate moments. We conduct experiments on three different datasets. The results demonstrate that the effectiveness of MABRL outperforms several state-of-the-art algorithms in alleviating traffic congestion with shorter training time. [ABSTRACT FROM AUTHOR]

Urban traffic congestion is not only an important cause of traffic accidents, but also a major hinder to urban development. By learning the historical traffic flow data, we can forecast the traffic flow of some regions in the future, which is of great significance to urban road planning, traffic management, traffic control and many more. However, due to the complex topology of traffic network and the diversity of influencing factors to traffic flow, the traffic modes are usually complicated and volatile, which makes traffic flow prediction very difficult. In this paper, we propose a new graph convolution neural network, namely Multi-mode Dynamic Residual Graph Convolution Network (MDRGCN), to capture the dynamic impact of different factors on traffic flow in a road network simultaneously. Firstly, we design a multi-mode dynamic graph convolution module (MDGCN), which is employed to capture the impact of different traffic modes by learning two types of relationship matrices. Then, we design a multi-mode dynamic graph convolution gated recurrent unit (MDGRU) to realize the combination of spatial and temporal dependences. Finally, we use a dynamic residual module (DRM) to integrate the orginal traffic data and the spatio-temporal features extracted by the MDGRU module to forecast the future traffic flow. Experimental reulsts conducted on the NYCTaxi and NYCBike datasets validate that the MDRGCN model performs better than the other eight baselines. [ABSTRACT FROM AUTHOR]

• This paper proposes the traffic system with mixed autonomous vehicles and human-driven vehicles. • This paper is the first to study the mixed traffic system from a micro perspective based on the cellular automation model. • An AV only need to gather the information for 5 vehicles in front of it. • Within a certain range of vehicle density, there is an optimal ratio of AVs at which the traffic system has the maximum average flow. • We obtain theoretical solutions of mixed critical vehicle density which are crucial to control the traffic networks. Autonomous vehicles (AVs) being an essential component of the future smart city traffic system is a hot topic in recent years, even though it is still in its development stage. It is conceivable that in the near future, AVs and human-driven vehicles (HVs) will have to co-exist in traffic systems. This is the first paper to study a mixed traffic system from a micro perspective based on the cellular automation model. In this system, by the use of sensors or mutual information exchange, each AV will have a 'foresight' and will be able to know the speeds and positions of vehicles in front of it. In the circular road scenario, we studied how the traffic capacity is influenced by the degree of foresight, the ratio of AVs to HVs, vehicle density, and the probability of random deceleration of HVs. Then we came up with the below conclusions: (a) The optimal foresight is k = 5. An AV only needs to gather the information of the 5 vehicles in front of it. (b) The two critical factors to measure the capacity of a traffic network are the critical vehicle density and the maximum average flow. When the ratio of AVs to HVs is increased, these two critical factors increase at an accelerating rate. (c) Even if a low ratio of HVs is running in the system, it will have an appreciable negative impact. An increased probability of random deceleration can expand the hysteresis loop range and reduce average flow. (d) Within a specific range of vehicle density, there is an optimal ratio of AVs at which the traffic system has the maximum average flow. This has implications in controlling the ratio of AVs. Finally, theoretical solutions of critical vehicle density are obtained by using the mean-field theory in physics. If the vehicle density is larger than these critical values, the traffic system will be in a deadlock state, and all vehicles cannot move. These formulas are crucial to controlling the density and the ratio of AVs and HVs in future intelligent traffic systems and will help to avoid large-scale traffic congestion. The above findings will have practical ramifications for precise traffic management and traffic control in a mixed AV and HVs system. [ABSTRACT FROM AUTHOR]

For the multi-agent traffic signal controls, the traffic signal at each intersection is controlled by an independent agent. Since the control policy for each agent is dynamic, when the traffic scale is large, the adjustment of the agent's policy brings non-stationary effects over surrounding intersections, leading to the instability of the overall system. Therefore, there is the necessity to eliminate this non-stationarity effect to stabilize the multi-agent system. A collaborative multi-agent reinforcement learning method is proposed in this work to enable the system to overcome the instability problem through a collaborative mechanism. Decentralized learning with limited communication is used to reduce the communication latency between agents. The Shapley value reward function is applied to comprehensively calculate the contribution of each agent to avoid the influence of reward function coefficient variation, thereby reducing unstable factors. The Kullback-Leibler divergence is then used to distinguish the current and historical policies, and the loss function is optimized to eliminate the environmental non-stationarity. Experimental results demonstrate that the average travel time and its standard deviation are reduced by using the Shapley value reward function and optimized loss function, respectively, and this work provides an alternative for traffic signal controls on multiple intersections. • A Shapley value reward function is used to encourage collaboration between agents. • Kullback-Leibler divergence eliminates the negative effects of previous experience. • The traffic congestion is reduced by a cooperative reinforcement learning method. [ABSTRACT FROM AUTHOR]

Abstract Modern cities experience heavy traffic flows and congestions regularly across space and time. Monitoring traffic situations becomes an important challenge for the Traffic Control and Surveillance Systems (TCSS). In advanced TCSS, it is helpful to automatically detect and classify different traffic incidents such as severity of congestion, abnormal driving pattern, abrupt or illegal stop on road, etc. Although most TCSS are equipped with basic incident detection algorithms, they are however crude to be really useful as an automated tool for further classification. In literature, there is a lack of research for Automated Incident Classification (AIC). Therefore, a novel AIC method is proposed in this paper to tackle such challenges. In the proposed method, traffic signals are firstly extracted from captured videos and converted as spatial-temporal (ST) signals. Based on the characteristics of the ST signals, a set of realistic simulation data are generated to construct an extended large-scale traffic database to cover a variety of traffic situations. Next, a local mean filter is introduced to suppress the effect of noise and extract significant features from the ST signals. The extracted features are then associated with various types of traffic data: one normal type (inliers) and multiple abnormal types (outliers). For the classification, an adaptive boosting classifier is trained to detect outliers in traffic data automatically. Further, a Support Vector Machine (SVM) based method is adopted to train the model for identifying the categories of outliers. In short, this hybrid approach is called an Adaptive Boosting Support Vector Machines (AB-SVM) method. Experimental results show that the proposed AB-SVM method achieves a satisfied result with more than 92% classification accuracy on average. [ABSTRACT FROM AUTHOR]