Abstract: A method for providing training datasets for training an object classification model for object classification in an ultrasonic sensor system is disclosed.

Abstract: A method for operating an ultrasonic sensor system having an ultrasonic sensor device for determining an object property of an environment object, in which classification models for determining classification results which specify a modeled object property of the environment object are provided for a plurality of detection situations of the environment object, each classification model trained for evaluation with a different subset of signal characteristics extracted from ultrasonic reception signals to provide a classification result of the corresponding classification model and an associated quality specification, includes: detecting the ultrasonic reception signals; determining the quantity of signal characteristics from the ultrasonic reception signals; determining classification results and associated quality specifications by evaluating the classification models with the corresponding subset of the quantity of the signal characteristics on the basis of the detection situation; and determining the object

Abstract: A method for classifying objects in the surroundings of a vehicle using ultrasonic sensors which emit ultrasonic pulses and receive ultrasonic echoes reflected by objects. Distances between the sensors and objects reflecting ultrasonic pulses are ascertained via at least two ultrasonic sensors including overlapping fields of vision, and a position determination of the reflecting objects taking place using lateration and the assignment of the received ultrasonic echoes to object hypotheses for distinguishing between extensive objects and point-like objects.