Personalized Adaptive Cruise Control Based on Online Driving Style Recognition Technology and Model Predictive Control

Abstract

This paper proposes a personalized adaptive cruise control (ACC) system based on driving style recognition and model predictive control (MPC) to meet different driving styles while ensuring car-following, comfort and fuel-economy performances. To obtain the controller parameters corresponding to different driving styles, a set of real vehicle experiments are conducted to collect driving data of 66 randomly recruited drivers, then the experimental data is clustered through unsupervised machine learning method. On the basis of it, a driving style classifier is designed by supervised machine learning method, which can be used to recognize the driving style of drivers online. Then, the control problem of the personalized ACC system is described as a multi-objective optimization problem which is solved by MPC method. The simulation results show that the proposed personalized ACC system can meet the requirements of different driving styles and guarantee various performances.