Intelligent Traffic Signal Phase Distribution System Using Deep Q-Network

Traffic congestion is a worsening problem owing to an increase in traffic volume. Traffic congestion increases the driving time and wastes fuel, generating large amounts of fumes and accelerating environmental pollution. Therefore, traffic congestion is an important problem that needs to be addressed. Smart transportation systems manage various traffic problems by utilizing the infrastructure and networks available in smart cities. The traffic signal control system used in smart transportation analyzes and controls traffic flow in real time. Thus, traffic congestion can be effectively alleviated. We conducted preliminary experiments to analyze the effects of throughput, queue length, and waiting time on the system performance according to the signal allocation techniques. Based on the results of the preliminary experiment, the standard deviation of the queue length is interpreted as an important factor in an order allocation technique. A smart traffic signal control system using a deep Q-network , which is a type of reinforcement learning, is proposed. The proposed algorithm determines the optimal order of a green signal. The goal of the proposed algorithm is to maximize the throughput and efficiently distribute the signals by considering the throughput and standard deviation of the queue length as reward parameters.

A Comparative Analysis of Machine Learning Algorithms in Design Process of Adaptive Traffic Signal Control System

In recent decades machine learning technology has proved its efficiency in most sectors by making human life easier. With this popularity and efficiency, it is applied to design traffic signal control systems to mitigate traffic congestion and distribute waiting delays. Hence, many researchers around the world are working to address this issue. As a part of the solution, this article presents a comparative analysis of various machine learning models to come up with a suitable model for an isolated intersection. In this context, eight machine learning models including Linear Regression, Ridge, Lasso, Support Vector Regression, k-Nearest Neighbour, Decision Tree, Random Forest, and Gradient Boosting Regression Tree are selected. Shivakumara Swamiji Circle (SSC), one of the intersections in Tumakuru, Karnataka, India is selected as a case study area. Essential data is collected from SSC through videography. The selected models are developed to predict green time based on traffic classification and volume in Passenger Car Units (PCU) for each phase on the PyCharm platform. The models are evaluated based on various performance metrics. Results revealed that all the selected models predict green splits with 91% accuracy using traffic classification as input, whereas, models showed 85% accuracy with PCU as input. And also, Gradient Boosting Regression Tree is the best suitable model for the selected intersection, whereas, Decision Tree is not referred model for this application.

Real-Time Crash-Risk Optimization at Signalized Intersections

Over the past few decades, numerous adaptive traffic signal control (ATSC) algorithms have been proposed to alleviate traffic congestion and optimize traffic mobility using real-time traffic data, such as data from connected vehicles (CVs). However, most of the existing ATSC algorithms do not consider optimizing traffic safety, likely because of the lack of tools to evaluate safety in real time. In this paper, we propose a novel ATSC algorithm for real-time safety optimization. The algorithm utilizes a traditional Reinforcement Learning approach (i.e., Q-learning) as well as recently developed extreme value theory (EVT) real-time crash prediction models. The algorithm was validated using real-world traffic video data collected from two signalized intersections in British Columbia. The results indicated that, compared with an existing fully actuated signal controller, the developed algorithm can significantly reduce the real-time crash risk by 43% to 45% at the intersection’s approaches even at low CVs market penetration rates.

Application of Multi-Agent Deep Reinforcement Learning to Optimize Real-World Traffic Signal Controls

Increasing traffic congestion leads to significant costs associated by additional travel delays, whereby poorly configured signaled intersections are a common bottleneck and root cause. Traditional traffic signal control (TSC) systems employ rule-based or heuristic methods to decide signal timings, while adaptive TSC solutions utilize a traffic-actuated control logic to increase their adaptability to real-time traffic changes. However, such systems are expensive to deploy and are often not flexible enough to adequately adapt to the volatility of today's traffic dynamics. More recently, this problem became a frontier topic in the domain of deep reinforcement learning (DRL) and enabled the development of multi-agent DRL approaches that could operate in environments with several agents present, such as traffic systems with multiple signaled intersections. However, most of these proposed approaches were validated using artificial traffic grids. This paper therefore presents a case study, where real-world traffic data from the town of Lemgo in Germany is used to create a realistic road model within VISSIM. A multi-agent DRL setup, comprising multiple independent deep Q-networks, is applied to the simulated traffic network. Traditional rule-based signal controls, currently employed in the real world at the studied intersections, are integrated in the traffic model with LISA+ and serve as a performance baseline. Our performance evaluation indicates a significant reduction of traffic congestion when using the RL-based signal control policy over the conventional TSC approach in LISA+. Consequently, this paper reinforces the applicability of RL concepts in the domain of TSC engineering by employing a highly realistic traffic model.

Application of Multi-Agent Deep Reinforcement Learning to Optimize Real-World Traffic Signal Controls

Increasing traffic congestion leads to significant costs associated by additional travel delays, whereby poorly configured signaled intersections are a common bottleneck and root cause. Traditional traffic signal control (TSC) systems employ rule-based or heuristic methods to decide signal timings, while adaptive TSC solutions utilize a traffic-actuated control logic to increase their adaptability to real-time traffic changes. However, such systems are expensive to deploy and are often not flexible enough to adequately adapt to the volatility of today's traffic dynamics. More recently, this problem became a frontier topic in the domain of deep reinforcement learning (DRL) and enabled the development of multi-agent DRL approaches that could operate in environments with several agents present, such as traffic systems with multiple signaled intersections. However, most of these proposed approaches were validated using artificial traffic grids. This paper therefore presents a case study, where real-world traffic data from the town of Lemgo in Germany is used to create a realistic road model within VISSIM. A multi-agent DRL setup, comprising multiple independent deep Q-networks, is applied to the simulated traffic network. Traditional rule-based signal controls, currently employed in the real world at the studied intersections, are integrated in the traffic model with LISA+ and serve as a performance baseline. Our performance evaluation indicates a significant reduction of traffic congestion when using the RL-based signal control policy over the conventional TSC approach in LISA+. Consequently, this paper reinforces the applicability of RL concepts in the domain of TSC engineering by employing a highly realistic traffic model.