Using epidemiological and simulation data to inform the testing of autonomous vehicles

Johnathon Ehsani1, Tak Igusa2, Hadi Kharrazi3, 1 Center for Injury Research and Policy, Dept. of Health Policy and Management, Dept. of Health, Behavior and Society, Bloomberg School of Public Health, Johns Hopkins University, 2Center for Systems Science and Engineering, Dept. of Civil Engineering, Whiting School of Engineering, Johns Hopkins University, 3Center for Population Health Information Technology, Dept. of Health Policy and Management, School of Public Health, Johns Hopkins University

Autonomous vehicles (AVs) have the potential to transform mobility and reduce the burden of motor vehicle crashes. Before this promising future can become reality, however, there is a need for extensive testing of AVs. As industries aggressively roll out testing plans, they have found that the most challenging questions are on the location and timing of AV testing. While AV engineers are mastering factors such as motion control, path planning, localization, perception and mapping, they have not yet considered in suitable depth the epidemiology of crash risk, particularly within urban settings. This collaboration between public health and systems engineering will develop an epidemiology-based simulation tool, operating within IDIES’ SciServer, that would enable AV R&D to generate high-resolution data of crash risk that can inform the development of AV testing programs in urban centers in the U.S.