Prediction of unintended lane departure based on detection of lane boundary

To address the unintended lane departure problem in nowadays´ vehicle safety, a novel method is proposed in this paper, to predict the tendency of lane departure. The method doesn´t need a lane model to describe the center line of the lane, but just the detected lane boundary points, so can overcome the influence of lane recognition problem and reduce the effect of lane model error, which is very difficult to resolve up to now. Another aspect, as the prediction of the future trajectory is based on a defined steering angle zone, but without the measured steering angle, so the novel method can conquer the disturbance of the measure error of the steering angle, especially at high speed situation. Real vehicle experiments based on the method are carried out on the prototype HONGQI Autonomous Land Vehicle on highway. Results show that the method can provide a stable and accurate alarm, when the vehicle is going to be departure from the lane.