A New Lane-Changing Model with Consideration of Driving Style

The lane-changing model is a hot spot in the field of traffic research, and there are already a lot of free lane-changing model established mathematical statistical methods or machine learning algorithm. However, these models don’t consider the driver’s driving style to the free lane-changing, and the accuracy of these models is low. This paper considers the driver’s driving style and proposes a new free lane-changing model based on machine learning. The new model splits the sample data into three driving styles: cautious, stable and radical. This paper selects the most effective multilayer perceptron model by comparing different machine learning methods based on the NGSIM trajectory data. In the analysis of the final accuracy of this paper, it can be seen that the new model has a great improvement in accuracy.