Development of a Prediction Method for Driver's Propensity☆

The influence of the driver's physiological and psychological characteristics on traffic safety is mainly represented as driver's tendency. Previous research about the driver's tendency mostly focused on the influence on traffic safety and the driver's psychological characteristics from a relative static and macroscopic perspective. In this paper, the Multi-Sensor Real-time Information Gathering Systems and the car-following experiments are designed to collect dynamic information about driver's behavior, vehicle state, traffic environment, etc., to compute driver's tendency. The data is divided into groups and ran through BP Neural Networks to obtain the correct classification rate for estimation. The characteristics of driver's tendency are extracted from a great number of samples through the Discrete Particle Swarm Optimization Method.

Xiao-yuan Wang

Papers

Extraction of the Dynamic Vehicle Driver's Tendency Feature Based on Car-Following