Volkswagen Ag

Marvin Schröder

Bernd Lehmann

Marius Spika

Christoph König

Christian Bruns

Tatjana Kruscha

Jan Sonnenberg

Jan Kempa

Fabian Galetzka

Benjamin Groß

Jakob Spiegelberg

Laura Fieback

The present disclosure relates to a method, to a computer program comprising instructions, and to a device for environment sensing in a vehicle. For the environment sensing, environment data are recorded by means of at least one vehicle sensor. A prediction is calculated by means of a trained machine learning model based on the recorded environment data, wherein the prediction includes a measure of uncertainty for the prediction. Equally, a deviation value is determined for the recorded environment data that provides a measure of how significantly the recorded environment data deviate from training data for the machine learning model. At least one conformity score is determined based on the measure of uncertainty and the deviation value and then a prediction set is determined based on the at least one determined conformity score. Then, a control signal is generated depending on the determined prediction set.

Detecting and determining relevant variables of an object by means of ultrasonic sensors

A method for setting up a virtual ad hoc network for transmitting at least one piece of information to a first transportation vehicle as a first network subscriber. The method includes the information being provided based on first data from at least one second network subscriber; and at least one second network subscriber being a second transportation vehicle or an infrastructure component; wherein a motor-vehicle-external, central data processing device receives second data from multiple potential second network subscribers and takes the second data and at least one space-time parameter as a basis for determining the second network subscribers and setting up the virtual ad hoc network with the first transportation vehicle, as the first network subscriber, and the determined second network subscribers, the space-time parameter defining a specific area of relevance that has a predetermined physical and temporal correlation with the current position of the first transportation vehicle.

Method for building an ad hoc virtual network and system

Growing community of inventors

Braunschweig, Germany

Marvin Schröder