Fuzzy uncertain observer with unknown inputs for Lane departure detection

This paper presents a lane departure detection method. The road curvature is estimated and compared to the vehicle trajectory curvature. The proposed algorithm reduces false alarms and integrates the driver corrections by taking account of the steering dynamics. The used nonlinear model deduced from the vehicle lateral dynamics and a vision system is represented by a T-S fuzzy uncertain model with unknown inputs. Stability conditions of such observers are expressed in terms of linear matrix inequalities (LMI). Simulation results obtained in two various driving scenarios show the efficiency of the proposed method.