Computer-implemented method for machine learning of lane markings by means of audio signals, control device for automated driving functions, method and computer program for recognizing lane markings

摘要

Computer-implemented method for machine learning of road markings (M) by means of audio signals, comprising the following process steps • Recording of tire-road noises that arise when at least one tire of a vehicle (1) rolls on a road marking (M) with at least one on the vehicle ( 1) sound sensor (S) that can be arranged and audio signals (T1) are received, • providing the audio signals as actual training data (T2), • identifying the lane marking (M) in the audio signals and providing this marking as the target lane marking (M) (T3 ), • inputting the actual training data into a classifier (K) which is designed to classify the lane marking (M) as a function of the tire / lane noise and obtain an actual lane marking (M) as a classification result (T4), and • Determining a deviation of the actual lane marking (M) from the target lane marking (M) and adapting the classifier (K) to minimize it ung the deviation in order to obtain the lane marking (M) from the audio signal (T5), where the classifier (K) is an artificial neural network comprising several layers, the layers comprising completely connected and / or convolutional layers, and • the deviation between the actual lane marking (M) and the target lane marking (M) is calculated in a reverse feed, • in the reverse feed, the deviation is minimized by changing the weights of connections of the artificial neural network, • the process steps are repeated several times and • All weights are saved after the learning phase.