Developing an agent-based online adaptive signal control (ASC) framework using connected vehicle (CV) technology
PI: G. Wu, UC Riverside; Co-PI: Matthew Barth, UC Riverside
Abstract: For arterial roadways, most active traffic and demand management (ATDM) strategies have focused on traffic signal timing optimization at signalized intersections. However, conventional traffic signal control strategies rely on the measurements from point detection (e.g., vehicle counts), and estimate traffic states such as vehicle speed and queue length based on very limited information. The introduction of Connected Vehicle (CV) technology can potentially address the limitations of point detection through wireless communications. For example, detailed information of an approaching vehicle (e.g., type, speed and turning movement) can be communicated to the traffic signal controller to assist phase and timing optimization. It is proposed herein to: 1) develop an agent-based adaptive signal control (ASC) framework based on real-time traffic information through CV technology; 2) evaluate the performance of the proposed system in terms of mobility and fuel consumption by using microscopic traffic simulation and vehicle energy/emissions models; and 3) address practical considerations in the possible field deployment of the proposed framework. The proposed ASC framework has significant potential to mitigate multi-modal traffic congestion at signalized intersections, especially in urban areas, thus enhancing the economic competitiveness and improving traffic fuel economy in the U.S.
Quarterly Progress Reports
Click on the links below to download any of the quarterly progress reports already finished.