From Model T to Waymo: Cars have gotten better – has transportation data science?

Since the early 1900's, automotive safety has been a major societal concern. From the earliest days, data on crashes and fatalities have been used to drive changes that lowered risk. One hundred years later, vehicle automation places us on the brink of an extraordinary change in transportation and especially transportation safety. As a result, data science advances that are enabling automation have to be put to use in measuring crashes and crash mechanisms for public health. In this talk, I will give a brief history of transportation safety data and analytical approaches, followed by more detailed discussion of recent advances in data acquisition and analysis. The talk will wrap up with the specific analytical challenges introduced by self-driving cars and how those challenges present new opportunities for advancements in data science.
Carol A. C. Flannagan is a research associate professor at the University of Michigan Transportation Research Institute (UMTRI), and director of its data group, CMISST. She joined UMTRI in 1991 after completing her Ph.D. in mathematical and experimental psychology at the University of Michigan (U-M). She also holds an M.A. in applied statistics from U-M.
Dr. Flannagan has over 20 years of experience conducting data analysis and research on injury risk related to motor vehicle crashes and was responsible for the development of a model of injury outcome that allows side-by-side comparison of public health, vehicle, roadway and post-crash interventions. She has also applied statistical methods to understanding of the potential benefits of a variety of advanced crash-avoidance technologies. Dr. Flannagan's current work includes several projects focused on development of novel applications of statistics to improve understanding of transportation safety in an environment of fast-changing technology.