coRide: Data-driven Ridesharing Service for Large-Scale Vehicle Networks

Abstract:

Following Smart Cities Initiative from White House, this project was aimed to address urban transportation challenges through ridership sharing in both time and space across different transportation modes. Our research project is uniquely built upon large-scale urban infrastructure systems across different cities in the world, including NYC, Washington D.C., San Francisco, Rome, Beijing, Shanghai and Shenzhen. We have investigated real-time interactions among heterogeneous urban ITS systems including taxis, buses, trucks, subways, bikes, personal vehicles, electric vehicles, along with cellphone and smartcard systems. Specifically, we build urban mobility models using multi-view learning from several types of big urban data, e.g., 10 TB vehicle GPS data from 10,000 vehicles, 1 TB smartcard transaction data from 16 million smartcard users, and 1 TB cellphone CDR data from 16 million cellphone users. Such mobility models enable us to build an efficient carpool service, called coRide, in a large-scale taxicab network intended to reduce total mileage for less gas consumption. We evaluate coRide with a real world dataset of more than 14,000 taxicabs, and the results show that compared with the ground truth, our service reduces 33% of total mileage; with our win-win fare model, we lower passenger fares by 49% and simultaneously increase driver profit by 76%. We will extend our study to other transportation modes such as bike rental networks. We will address a set of challenging issues including (i) imperfect and large volume real-time data feeds, (ii) heterogeneous models with dynamic weights, and (iii) site-specific practical deployment issues.