A learning-based approach for lane departure warning systems with a personalized driver model

Misunderstanding of driver correction behaviors is the primary reason for false warnings of lane-departure-prediction systems. We proposed a learning-based approach to predict unintended lane-departure behaviors and chances of drivers to bring vehicles back to the lane. First, a personalized driver model for lane-departure and lane-keeping behavior is established by combining the Gaussian mixture model and the hidden Markov model. Second, based on this model, we developed an online model-based prediction algorithm to predict the forthcoming vehicle trajectory and judge whether the driver will act a lane departure behavior or correction behavior. We also develop a warning strategy based on the model-based prediction algorithm that allows the lane-departure warning system to be acceptable for drivers according to the predicted trajectory. In addition, the naturalistic driving data of ten drivers were collected to train the personalized driver model and validate this approach. We compared the proposed method with a basic time-to-lane-crossing (TLC) method and a TLC-directional sequence of piecewise lateral slopes (TLC-DSPLS) method. Experimental results show that the proposed approach can reduce the false-warning rate to 3.13% on average at 1-s prediction time.