The development of Advanced Driver Assistance Systems (ADASs) has reached a stage where, in addition to the traditional challenges of path planning and control, there is an increasing focus on the behavior of these systems. Assistance functions shall be personalized to deliver a full user experience. Therefore, driver modeling is a key area of research for next-generation ADASs. One of the most common tasks in everyday driving is lane keeping. Drivers are assisted by lane-keeping systems to keep their vehicle in the center of the lane. However, human drivers often deviate from the center line. It has been shown that the driver’s choice to deviate from the center line can be modeled by a linear combination of preview curvature information. This model is called the Linear Driver Model. In this paper, we fit the LDM parameters to real driving data. The drivers are then clustered based on the individual parameters. It is shown that clusters are not only formed by the numerical similarity of the driver parameters, but the drivers in a cluster actually have similar behavior in terms of path selection. Finally, an Extended Kalman Filter (EKF) is proposed to learn the model parameters at run-time. Any new driver can be classified into one of the driver type groups. This information can be used to modify the behavior of the lane-keeping system to mimic human driving, resulting in a more personalized driving experience.

The rapid development of automated driving systems in recent years has led to improvements in road safety and travel comfort. One typical function of these systems is Lane Keep Assist, which generally does not take human driving preferences into account. In our previous work, we have demonstrated that it is possible to implement a Lane Keep Assist function that is appropriate to human preferences using a trajectory planning algorithm based on a linear driving model. In our current work, we investigated how to separate the driving styles of individual drivers. We assumed that there are three driving styles: sporty, neutral and defensive. To prove these relations, clustering methods were applied to previously recorded measurements . Simulations with parameters describing the average behaviour of the classes (re-simulated with clustered types) showed that the resulting paths successfully classified drivers, that the 3 classes are distinct in their behaviour and that our model reproduces these behaviours.