Safe semi-autonomous control with enhanced driver modeling

During semi-autonomous driving, threat assessment is used to determine when controller intervention that overwrites or corrects the driver´s input is required. Since today´s semi-autonomous systems perform threat assessment by predicting the vehicle´s future state while treating the driver´s input as a disturbance, controller intervention is limited to just emergency maneuvers. In order to improve vehicle safety and reduce the aggressiveness of maneuvers, threat assessment must occur over longer prediction horizons where driver´s behavior cannot be neglected. We propose a framework that divides the problem of semi-autonomous control into two components. The first component reliably predicts the vehicle´s potential behavior by using empirical observations of the driver´s pose. The second component determines when the semi-autonomous controller should intervene. To quantitatively measure the performance of the proposed approach, we define metrics to evaluate the infor-mativeness of the prediction and the utility of the intervention procedure. A multi-subject driving experiment illustrates the usefulness, with respect to these metrics, of incorporating the driver´s pose while designing a semi-autonomous system.