With ADAS.ai, ZF aims to accelerate the development and validation of driver assistance systems. The solution uses real driving data that is transformed virtually.
The real-to-real transformation reduces costs and time for validating ADAS systems
ZF
With a suite of data and Artificial Intelligence (AI), ZF ADAS.ai aims to reduce costs and time to market for ADAS systems at SAE level 2+. To achieve this, complete L2+ scenarios are fed into the development and validation phases at several points. The scenarios have been derived from real driving operations and can be read in either in “virtual” or “full sensor” mode. The transfer of the real driving data and its subsequent validation in the virtual space is made possible by algorithms from the Israeli technology company Cognata.
The real-to-real transformation is expected to enable fully virtual engineering for ADAS from all tier-1 suppliers in the future, saving up to 20 % in time and costs. “With our approach, an OEM does not need a large number of test drivers or a multi-million budget to develop and validate in a safe framework. We bring the real and virtual worlds together because we use real data to drive both modalities,” says Christophe Marnat, Executive Vice President of ZF’s Electronics and Advanced Driver Assist Systems Division.