A NEW APPROACH FOR STEERING WHEEL ANGLE PREDICTION. IN: HUMAN FACTORS IN DRIVING, SEATING AND VISION

To monitor driver attention, the difference between the predicted degrees of the steering wheel angle and the actual one is generally evaluated. The effectiveness of this solution mainly depends on the quality of the prediction model of the steering wheel angle. This paper introduces a new approach to selecting the information that characterizes the dynamic state of the vehicle in order to integrate it into the prediction model. The proposed method relies on the analysis of a set of specific driver reactions which are assumed to characterize the steering behavior and which mainly depend on the dynamic states of the vehicle. The fundamental issue of this approach is to propose a generic structure of a prediction model taking into account this information. The results obtained by this method when applied to experiments using a driving simulator are discussed. To improve a model of steering wheel angle prediction, these results suggest that it is necessary to explore relationships between the steering behavior and the lateral dynamic components such as orientation and lateral position of the vehicle in the lane, and to study environmental impact such as the position of the crash barrier relative to the vehicle.