Inferring driver intentions using a driver model based on queuing network

Abstract

Inferring driver intentions plays an important role in developing human-centric intelligent driver assistance systems. In this paper, we propose a method of inferring the lane-changing intention of drivers by using a driver model based on the queuing network (QN) cognitive architecture. Driver behavior data associated with a range of possible driver intentions are simulated by using the QN-based driver model previously validated. The intentions of drivers are deduced by comparing these sets of simulated behavior data with the collected behavior data of drivers. The experimental results in a driving simulator show that the method can infer typical and rapid lane-changing intention of drivers well.