Car-following Model Based on Genetic Algorithm Optimized BP Neural Network

Abstract

Due to the single BP network with the vehicle model is difficult to adapt to the complex traffic environment. Select the subject speed, the relative distance and relative velocity as the model variables. Construct the BP neural network of carfollowing model based on the real vehicle test, and use genetic algorithm to optimize the car-following model. The results show that the model has the highest accuracy, and the accuracy of the model is improved to 94.17% after optimization of the genetic algorithm.