“Data-Driven Applications for Connected Vehicle Based TrafficSignal Systems”
Massive deployments of connected vehicles (CVs) are now on the horizon, and will undoubtedly introduce paradigm shifts to the transportation system. At signalized intersections, CV can receive real-time information and advise drivers of safer and more fuel-efficient driving, while signal controllers can receive vehicle position and speed information for more effective operation. Considering signalized intersections are often hot-spots of congestion and driving frustration, tremendous opportunities exist with CVs to improve the effectiveness and efficiency of traffic signal operation. However, due to the lack of real-world deployment of CVs, their benefits at signalized intersections have yet been explored. This limitation has now been partially overcome with the safety pilot model deployment (SPMD) project, world’s first large-scale CV deployment project with around 3,000 CVs. Through mining real-world data from the SPMD project, this dissertation develops three innovative applications to explore benefits of CVs with low penetration rates for traffic signal systems. Firstly, to facilitate the deployment of Vehicle-to-Infrastructure (V2I) systems at intersections, an automatic procedure is developed for generating intersection map, a critical element of many CV applications. Using data from roadside equipment 2 (RSE), the proposed procedure can automatically estimate intersection geometry and associated signal phases of traffic lanes, hence serving as a cost-effective alternative to help deploying and maintaining RSEs. Secondly, to pave the way for detector-free signal operation, an approach is developed for estimating traffic volumes with CV or probe vehicle data. This application could help to reduce the dependency of traffic signals on detectors, and hence would be particularly beneficial for assisting signal operation. Lastly, to explore the benefits of V2I communication for driving assistance, a speed advisory system is proposed to help drivers reduce fuel consumption when driving through signalized intersections, based on information received from RSEs. An efficient algorithm is proposed based on Pontryagin’s maximum principle so that it can be implemented on-board in real time. With the three applications for improving CV-based traffic signal system in three different perspectives, the ultimate objective of this dissertation is to facilitate the development and deployment of CV-based traffic signal system in the near future.
Chair: Henry Liu