Data-Driven Intersection Management Solutions for Mixed Traffic of Human-Driven and Connected and Automated Vehicles 712 views

According to the U.S. Federal Highway Administration, outdated traffic signal timing currently accounts for more than 10 percent of all traffic delays. On average, adaptive signal control technologies improve travel time at intersections by more than 10 percent in comparison with traditional signal timing methods. In areas with particularly outdated signal timing, improvements can be 50 percent or more. With the emergence of connected and automated vehicles and the recent advancements in Intelligent Transportation Systems, Autonomous Traffic Management has garnered more attention. Cooperative Intersection Management (CIM) is among the more challenging traffic problems that pose important questions related to safety and optimization in terms of vehicular delays, fuel consumption, emissions and reliability. This dissertation proposes two solutions for urban traffic control in the presence of connected and automated vehicles. First a centralized platoon-based controller is proposed for the cooperative intersection management problem that takes advantage of the platooning systems and V2I communication to generate fast and smooth traffic flow at a single intersection. Two cost functions are proposed to minimize total delay and delay variance. Simulated experiments show that the proposed controller produces schedules that minimize travel delay and variance while increasing intersection throughput and reducing fuel consumption, when compared to traffic light policies. The simulations also verify the positive effect of platooning on fuel consumption and intersection throughput. Second, a data-driven approach is proposed for adaptive signal control in the presence of connected vehicles. The proposed system relies on a data-driven method for optimal signal timing and a data-driven heuristic method for estimating routing decisions. It requires no additional sensors to be installed at the intersection, reducing the installation costs compared to typical settings of state-of-the-practice adaptive signal controllers. The proposed traffic controller contains an optimal signal timing module and a traffic state estimator. The signal timing module is a neural network model trained on microscopic simulation data to achieve optimal results according to a given performance metric such as vehicular delay or average queue length. The traffic state estimator relies on connected vehicles' information to estimate the traffic's routing decisions. A heuristic method is proposed to minimize the estimation error. With sufficient parameter tuning, the estimation error decreases as the market penetration rate (MPR) of connected vehicles grows. Estimation error is below 30% for an MPR of 10% and it shrinks below 20% when MPR grows larger than 30%. Simulations showed that the proposed traffic controller outperforms Highway Capacity Manual's methodology and given proper offline parameter tuning, it can decrease average vehicular delay by up to 25%.

PHD (Doctor of Philosophy)

Intelligent Transportation Systems; Cooperative Intersection Management; Deep Neural Networks; Connected and Automated Vehicles; Data Driven Traffic Control; Machine Learning

English

All rights reserved (no additional license for public reuse)

2020-11-30