Vehicle Data Collection for Cloud Processing
Kang G. Shin
Kevin and Nancy O’Connor Professor of Computer Science and Professor of Electrical Engineering and Computer Science, College of Engineering
This project built a flexible and extensible vehicular testbed, called CarLab, which (1) collects data from the controller area network bus and installs sensors and smartphones on each car, and (2) transfers data to and processes them in the cloud. CarLab was designed to collect multifaceted sensory data from consumer vehicles, in contrast to existing testbeds, and will therefore lead to unique insights. It was also designed to return value to testbed participants through useful applications, thereby attracting more participants for the testbed. Our approach consisted of an in‐vehicle hub (Raspberry Pi or ARTIK5/10), an on-board diagnostics scanner, and a smartphone app. The cloud components involve a server to collect the data and a visualization website. Additionally, we built several data analytics applications on top of the platform to demonstrate the testbed and provide utility back to the users.
(1) A full system for collecting, uploading, and visualizing data; (2) several hundred participants recruited for users of the testbed; and (3) several projects for returning value to the user and assisting other research and engineering projects.