Adaptive Traffic Signal Control Model on Intersections Based on Deep Reinforcement Learning

Abstract

Controlling traffic signals to alleviate increasing traffic pressure is a concept that has received public attention for a long time. However, existing systems and methodologies for controlling traffic signals are insufficient for addressing the problem. To this end, we build a truly adaptive traffic signal control model in a traffic microsimulator, i.e., “Simulation of Urban Mobility” (SUMO), using the technology of modern deep reinforcement learning. The model is proposed based on a deep Q-network algorithm that precisely represents the elements associated with the problem: agents, environments, and actions. The real-time state of traffic, including the number of vehicles and the average speed, at one or more intersections is used as an input to the model. To reduce the average waiting time, the agents provide an optimal traffic signal phase and duration that should be implemented in both single-intersection cases and multi-intersection cases. The co-operation between agents enables the model to achieve an improvement in overall performance in a large road network. By testing with data sets pertaining to three different traffic conditions, we prove that the proposed model is better than other methods (e.g., Q-learning method, longest queue first method, and Webster fixed timing control method) for all cases. The proposed model reduces both the average waiting time and travel time, and it becomes more advantageous as the traffic environment becomes more complex.

Online Traffic Accident Spatial-Temporal Post-Impact Prediction Model on Highways Based on Spiking Neural Networks

“…With the rapid development of artificial intelligence and computer technology, deep learning has been widely applied in traffic domain, including traffic state prediction [8,9], traffic signal control [1,10], and driving model development [11]. e works mentioned above are all based on artificial neural networks (ANNs), where the neurons use differentiable, nonlinear activation functions.…”

“…A CNN consists of an input and an output layer, multiple convolutional layers, and optional hidden layers such as pooling layers, fully connected layers, and normalization layers. Figure 6 shows the demonstration of how these layers can be combined to build a CNN according to the requirement [1]. Convolutional layers apply a convolution operation to the input and pass the result to the next layer, so as to achieve feature extraction [46].…”

“…People's living standards have increased all over the world, leading to an increase in the ownership of private vehicles [1]. While private vehicles have improved people's traveling experience, they have also contributed to several traffic problems, where traffic safety is one of the main concerns.…”

İdeal Trafi̇k Işik Devre Süresi̇ İçi̇n Kavşak Taşit Geci̇kmesi̇ Opti̇mi̇zasyonu

“…Birinci tip sistemde önceden ayarlanan trafik ışık devir süreleri sabit bir şekilde işlemektedir. İkinci tip sinyal sistemlerinde ise çevreye duyarlı bir şekilde trafik sinyal süreleri değişebilmektedir [2,3]sa. Araç sayısının fazla olduğu yollarda yeşil ışık süreleri artırılır, araç sayısının az olduğu yollarda ise kırmızı ışık süreleri artırılarak [4] ya da kavşak gecikme süreleri optimize edilerek çözüm yolları sunulabilmektir.…”

Multi-Task Fusion Deep Learning Model for Short-Term Intersection Operation Performance Forecasting

“…Noted that the intersection's spatial traffic features are more complex, which is affected by travelers' route choices and management control. In terms of spatial correlations, the convolutional neural networks (CNN) model is a mature method to extract spatial traffic features [17]. Even though the CNN model can extract intersections' spatial features, the CNN model cannot reveal the intersection's topology structure.…”