Advanced Driver Assistance Systems (ADAS) support drivers in fulﬁlling their driving task by reducing workload and enabling a more safe and comfortable drive. However, the increasing market penetration of ADAS, along with the wide variety of types and models, has led to a need for a cost and time-eﬃcient way to integrate and parametrize new systems. One essential point for the integration process of comfort-oriented ADAS is the question of driver satisfaction with respect to safety, reliability, trust and comfort. The current work oﬀers a method for parametrizing an ADAS controller with the help of test drives with non-professional drivers. The proposed method is validated by the parametrization of an Adaptive Cruise Control (ACC) system, which supports the driver by keeping a desired vehicle speed or deﬁned distance to a proceeding slower moving vehicle, the Object to Follow (OTF). For the selection of the OTF, the prediction of the future path of the own vehicle (ego vehicle) is an essential part of the ACC system. Today, diﬀerent algorithms are implemented for path prediction. To evaluate these algorithms, test drives were carried out with a specially equipped vehicle with non-professional test drivers. Based on the measured data, diﬀerent methods for path prediction were compared. A novel steering prediction algorithm was developed, which is used in combination with a linear Single-Track Model (STM) to predict the ego vehicle’s path. Based on the predicted ego vehicle path, the OTF is selected, which is then used to parametrize a novel ACC controller. The performance of the controller fulﬁls previously deﬁned safety and comfort requirements, as well as string stability. Simulations with the recorded OTF data as input were carried out, which showed that the ACC controller is able to simulate the behaviour of the human driver. Furthermore, the controller cuts acceleration peaks, which leads to a more comfortable feeling than with the measurements obtained when the human drove the vehicle. Finally, a comparison with measurements of a state-of-the-art ACC system showed similar behaviour compared to the production controller in following another vehicle. The results of the present study show that the proposed method is able to identify an appropriate set of parameters for an ACC controller. The idea of parametrizing the controllers with the help of human test driver should lead to a human-like behaviour and increase customer acceptance of the system. Additionally, this optimized parametrization method will help to shorten the development and validation process, which is very important for saving costs.