Driver attention warning system based on a fuzzy representation of the vehicle model

摘要

In this paper a lane departure detection method is studied and evaluated using the full vehicle dynamics software CarSim. The road curvature is estimated and compared to the vehicle trajectory curvature. The proposed algorithm takes account of the steering dynamics and uses the Time to the Lane Keeping (TLK) as a second risk indicator in order to reduce false alarms and integrate the driver corrections. The used nonlinear model deduced from the vehicle lateral dynamics and a vision system is represented by a T-S fuzzy model. Stability conditions of the fuzzy observer are expressed in terms of linear matrix inequalities (LMI)using unmeasurable premise variables. Simulation results show good efficiency of the method under different driving scenarios.