Modeling of Driver’s Steering Behavior in Large-Curvature Path Following with Back Propagation Neural Network

This paper presents a modeling method to describe the driver's steering behavior in following trajectory with large curvature. A target scene is established with the 6-degree-of-freedom driving simulator platform. For collecting experimental data, three experienced drivers are requested to drive with the driving simulator. Then, the back propagating neural network with Levenverg-Marquard (LM) algorithm is used to model the driver's steering behavior in following large-curvature path. Compared with the transfer function driver model, the proposed BP neural network model has higher precision, and potentially with more benefit for designing the shared steering controller individually in following the large curvature path.