Modern safety and comfort features must behave country specific to the local environment and traffic conditions in order to gain end consumers’ trust and strengthening OEMs market success respectively. In order to achieve this, a new methodology was developed. In this paper, the approach for designing advanced driving assistance systems (ADAS) with a tailored controller behavior optimized for country specific market expectations like in India is described. Furthermore, the definition of objective performance and calibration targets with automated evaluation of target fulfillment will be deeply discussed. The method is focused on saving time at calibration and validation without compromising the quality of ADAS features. Local market specific driving behavior is investigated and measurement data from real-world driving collected. Data clustering via maneuver detection is performed automatically, which is saving time and effort. The target values for the performance KPIs are extracted from scenarios detected in the measurements by using techniques of design of experiments and empirical modelling. Based on the calculated performance KPIs, multidimensional models representing the ideal driving behavior are created and target values as well as upper and lower limits are set. The methodology will be described on the example of an adaptive cruise control (ACC) designed for the Indian market where ADAS performance targets for the whole operation range of the feature were defined. Since the whole process of data collection, clustering and KPI calculation is mainly automated, the potential for saving time in verification and validation on proving ground as well as in real-world testing of fleets is enormous. The strengths of the current approach as well as future challenges will be shown.
