Abstract: A method for validating a software, particularly a driver-assistance software. The method includes receiving of a sensor signal that is to be processed by the software; determining of a reference signal by an adaptive filter based on the sensor signal, the reference signal representing an anticipated sensor signal; determining an error signal based on the sensor signal and the reference signal, the error signal representing a performance of the software; determining an anti-sensor signal by a machine-learning unit based on the sensor signal, the machine-learning unit being trained with sensor signals already evaluated; controlling of the adaptive filter by a control unit based on the determined error signal and the adaptive anti-sensor signal; and validation of the software based on the determined error signal.

Abstract: A method for validating a software, particularly a driver-assistance software. The method includes receiving of a sensor signal that is to be processed by the software; determining of a reference signal by an adaptive filter based on the sensor signal, the reference signal representing an anticipated sensor signal; determining an error signal based on the sensor signal and the reference signal, the error signal representing a performance of the software; determining an anti-sensor signal by a machine-learning unit based on the sensor signal, the machine-learning unit being trained with sensor signals already evaluated; controlling of the adaptive filter by a control unit based on the determined error signal and the adaptive anti-sensor signal; and validation of the software based on the determined error signal.