Longitudinal vehicle guidance using neural networks

The purpose of this paper is to show a simple ability of using neural networks in longitudinal vehicle guidance. The main motivation is an opportunity of neural networks to learn from acquired real driver data, as well as to reproduce many driver behaviour styles raging from extremely comfort to extremely sportive ones. This possibility is shown with a simulated model based longitudinal trajectory generation. This model has used an adjustable comfort parameter for different sorts of driver behaviour. Experiment results, obtained with Audi test vehicle, are also presented.