Abstract: The great promises of automated vehicles will only be achieved if they are designed within human capabilities. Driver models can serve a crucial role in the automated vehicle design process by simulating human responses to driving situations given a set of system parameters. Through this process, system parameters can be calibrated within driver limits, ultimately leading to safer transportation systems. Despite the fact that driver models are frequently used to assess manual driving safety and advanced safety systems, there have been few attempts to extend these models to automated vehicle transitions of control. The goal of this talk is to discuss a model development process to predict driver behavior following unexpected transitions of control from an automated vehicle. The discussion will introduce a model development approach that is grounded in contemporary cognitive theory, empirical findings, and actual on-road observations and show that this process leads to accurate predictions of driver steering and braking behavior. The talk will close with a discussion of future directions and applications.
Dr. Tony McDonald is an Assistant Professor and the Corrie and Jim Furber '64 Faculty Fellow in the WM Michael Barnes Department of Industrial and Systems Engineering at Texas A&M University and the Director of the Human Factors and Machine Learning Lab. His research focuses on integrating human factors methods and models with machine learning algorithms to develop technology that improves transportation safety and health outcomes. Dr. McDonald was a recipient of the 2019 Human Factors Award for Excellence in Human Factors Research and received the 2020 Stephanie Binder Young Professional Award from the Human Factors and Ergonomics Society. He received his M.S and Ph.D. in Industrial Engineering from the University of Wisconsin-Madison in 2012 and 2014, respectively, and his B.S. in Mechanical Engineering from MIT in 2010.