Intelligent Data Exploration & Analysis for New & Existing Transportation Technology (IDEANETT)
Focus: Integration of CAV fleet data with NCDOT data infrastructures to create a publicly beneficial travel time visualization and information system
PI: Dr. Hyoshin (John) Park, NC A&T University
Project Description: This project will develop data-driven vehicle routing algorithm with a particular class of problem dealing with 1) time-dependent transportation network, 2) spatial-temporal map dependencies, and 3) a priori time-varying least travel time.
The primary objective of this project is to reduce the travel time of the in-vehicle navigation system for the North Carolina highway in a simulation environment. This research will be used to inform more accurate travel information for travelers and a better navigation option with less uncertainty, to help NCDOT Traffic Management Unit and Traffic Systems Operations staff’s ability to understand the data adaptability in North Carolina, and to provide a tool for use in handling existing and new sensor data. NCDOT will be capable of handling an unprecedented amount of data significantly enhancing reliability of travel time information.
The results of this research will be visualization system to estimate and predict short-term and long-term travel time by links and paths levels in North Carolina, through spatiotemporal correlation map.
Research Impact: The results of this project will provide benefits at multiple levels. At the local level, the CAV data will provide up-to-date information on the travel time that can be used by traffic operator and travelers. At the state level, CAV data-driven navigation algorithm directly and instantly benefits traveling citizens by reducing their travel time. A particular measurement of interest will be a travel time reduction by quantifying link and path travel time uncertainty in transportation network.