A Comparative Study of Data-Driven Human Driver Lateral Control Models

To reduce human driving workload, many advanced driver assist systems (ADAS) have been developed using a single, often simple, driver model to predict human-driver interaction in the immediate future. However, each person drives differently, necessitating personalized driver models based on data obtained from actual driver actions. Yet, traditional control-theoretic and physics-based models have difficulty in accurately predicting driver actions. Being inspired from the recent achievements of machine-learning (ML) methods, this work compares several ML-based algorithms in predicting the lateral control actions of human drivers, evaluates each method using both simulated and real human-driving data sets, and discusses their performance.