Human dynamics based driver model for autonomous car

Abstract

This study presents a new driver model based on human behaviour dynamics for autonomous cars, which allows driverless cars to move appropriately in accordance to the behavioural features of driver owners. This model is established through analysing drivers' various properties, e.g. gender, age, driving experience, personality, and emotion. These attributes collectively determine all the actions occurred during the driving process. Through analysing the statistical data gathered during the simulation, the authors find that the proposed model can reflect the power-law distribution with respect to the concerned human behaviours. Finally, the proposed model is validated by the hardware-in-loop simulator and real driving experiment.