Development of a Signal-Free Intersection Control System for CAVs and Corridor Level Impact Assessment

Abstract

Assuming a full market penetration rate of connected and autonomous vehicles (CAVs) would provide an opportunity to remove costly and inefficient traffic lights from intersections, this paper presents a signal-free intersection control system relying on CAVs’ communicability. This method deploys a deep reinforcement learning algorithm and pixel reservation logic to avoid potential collisions and minimize the overall delay at the intersection. To facilitate a traffic-oriented assessment of the model, the proposed model’s application is coupled with VISSIM traffic microsimulation software, and its performance is compared with other intersection control systems, including fixed traffic lights, actuated traffic lights, and the Longest Queue First (LQF) control system. The simulation result revealed that the proposed model reduces delay by 50%, 29%, and 23% in moderate, high, and extreme volume regimes, respectively, compared to another signal-free control system. Noticeable improvements are also gained in travel time, fuel consumption, emission, and Surrogate Safety Measures.

Synergistic Effects of Biochar and Phosphorus Fertilization on Wheat Growth, Pollution Reduction, and Soil Enzymatic Behavior

“…50 million metric tons of CO2 through traffic is annually produces just in Iran, making up a significant 5.5%-6% of the country's total greenhouse gas emissions, it is not limited to middle east part, for example in the United States, the environmental and economic toll is evident as well. In 2017, wasted fuel amounted to a staggering 3.3 billion gallons, leading to an economic setback of 179 billion USD [34]. it indicates the urgent need for taking a step to resolve this issue as soon as possible.…”

Enhanced Automated Intersection Control for Platooning AVs: A Fusion Model with Significant Traffic, Safety, and Environmental Improvements

“…One of the main goals of this study is to develop a platooning CAV-based intersection control system, which includes the simultaneous deployment of SMD platooning logic and an automated machine learning-based intersection control system for Avs developed by Mirbakhsh et al [9]. It also requires adjusting the models to be compatible.…”

Artificial Intelligence-Based Real-Time Traffic Management

“…For example, by combining artificial neural networks (ANN) with statistical approaches, one-hour forecasts of urban traffic flow rates have been achieved, with neural assembling models providing the most reliable and accurate estimations [9]. Moreover, connected automated vehicles (CAV)-based intersection control systems, which are based on costly physical traffic lights and based on a pixel reservation will no longer be a necessity in full multi-person vehicles (MPR) of autonomous vehicles (AVs) [10].…”