Modeling driver behavior during complex maneuvers

This paper focuses on the modeling of driver behaviors during maneuvers that involve tire saturation. Drifting maneuvers are performed by an expert driver on low friction surfaces. Driving data is recorded and used to aid the construction of two different driver models. The first model parallels the driver to a model predictive controller and the second model treats the driver as a switched linear state feedback controller. This paper compares the two approaches and presents a framework where the driver model is integrated into an autonomous controller in the form of an optimization problem.