Abstract: A method for detecting an environment using images from at least two image sensors. The method includes: providing a first image of the environment from a first image sensor; providing a second image of the environment from a second image sensor; wherein the first image sensor and the second image sensor are configured to detect the environment with different detection ranges; defining a virtual surface, which is arranged between the environment and the at least two image sensors; generating a virtual overall image on the virtual surface based on a projection transformation of respective pixels of the first image and a projection transformation of respective pixels of the second image from a relevant image plane of the relevant image sensor onto the virtual surface; and representing the environment based on the virtual overall image and on a neural network trained to represent the environment, to detect the environment.

Abstract: A computer-implemented method for assessing a robustness of a smoothed classifier for classifying sensor signals received from a sensor. The method includes: providing an input signal depending on the sensor signal, determining, by the smoothed classifier, a first value which characterizes a probability that the input signal, when subjected to noise will be classified as belonging to a first class, wherein the first class is a most probable class, determining, by the smoothed classifier, a second value which characterizes a probability that the input signal, when subjected to the noise, will be classified as belonging to a second class, wherein the second class is a second-most probable class, determining a robustness value on a first inverse value of a standard Gaussian cumulative distribution function at the first value and/or depending on a second inverse value of the standard Gaussian cumulative distribution function at the second value.

Abstract: A method for operating a hardware platform for the inference calculation of a layered neural network. In the method: a first portion of input data which are required for the inference calculation of a first layer of the neural network and redundancy information relating to the input data are read in from an external working memory into an internal working memory of the computing unit; the integrity of the input data is checked based on the redundancy information; in response to the input data here being identified as error-free, the computing unit carries out at least part of the first-layer inference calculation for the input data to obtain a work result; redundancy information for the work result is determined, based which the integrity of the work result can be verified; the work result and the redundancy information are written to the external working memory.

Abstract: A method for operating a driver assistance system of a vehicle in an assistance mode. A driver input instantaneously expressed by a driver of the vehicle by an angular position of a gas pedal of the vehicle is converted into a power setpoint value of the vehicle influencing a vehicle acceleration of the vehicle, as a function of an instantaneous vehicle acceleration value of the vehicle and a target acceleration value of a target vehicle, to assist the driver with imitating a driving behavior of the target vehicle.

Abstract: A computer-implemented method for determining an appropriate control strategy for a mobile agent for an environment with one or more dynamic objects. The method includes: providing a number of different scenarios wherein to each of the scenarios a number of dynamic objects is associated, wherein for each of the scenarios, each of the dynamic objects is associated with a start, a goal and a behavior specification; providing a number of control strategy candidates for the mobile agent; benchmarking each of the control strategy candidates in any of the scenarios; selecting the control strategy for the mobile agent depending on the result of the benchmarking of the control strategy candidates.

Abstract: A method for monitoring and identifying sensor faults in an electric drive system of a vehicle includes collecting corresponding data using sensors in the electric drive system, inputting the collected data to an already-established sensor fault mode identification model, and determining whether a fault mode exists and a fault mode type based on the collected data using the sensor fault mode identification model. The method quickly determines the fault mode caused by a sensor fault in the electric drive system, and the fault mode type of the sensor fault.

Abstract: A method for provision image recordings in a vehicle. The method include: ascertaining a first image recording of a first image sensor of the vehicle and at least one further image recording of at least one further image sensor of the vehicle; carrying out a merging of the first image recording and the at least one further image recording for a reduction of an amount of data for providing the relevant information, the merging taking place based on a selection from the surrounding regions, whereby at least one merged image recording is obtained; initiating at least one transmission of the merged image recording within the vehicle and at least to a central control device of the vehicle, whereby the merged image recording is supplied to a processing for performing the vehicle function.

Abstract: A vertical field effect transistor, including a drift region having a first conductivity type, a trench structure on or above the drift region, a shielding structure, and a source/drain electrode. The trench structure includes at least one side wall at which a field effect transistor (FET) channel region is formed. The FET channel region includes a III-V heterostructure for forming a two-dimensional electron gas at a boundary surface of the III-V heterostructure. The shielding structure is situated laterally adjacent to the at least one side wall of the trench structure and extends vertically into the drift region or vertically further in the direction of the drift region than the trench structure. The shielding structure has a second conductivity type that differs from the first conductivity type. The source/drain electrode is electroconductively connected to the III-V heterostructure of the trench structure and to the shielding structure.

Abstract: The invention relates to a method for determining an effective prevailing uncertainty value (304, 305) for an emission value (301, 302) for a given time point when operating a drivetrain (100) of a motor vehicle with an internal-combustion engine (110), wherein, at different times (n), one prevailing emission value (301) and one prevailing uncertainty value (303) are determined for the emission value, wherein the effective prevailing uncertainty value (304, 305) for the given time point is determined from prevailing uncertainty values (303) and prevailing emission values (301) prior to the given time point.

Abstract: A method for operating a contactor (10) is described, wherein the contactor (10) comprises at least two contacts (18, 20, 22) electrically conductively connected to one another in a closed state of the contactor (10), having the method steps of partially charging an DC link capacitance (103) in electrical contact with the contactor (10) and closing the contactor (10).

Abstract: A method for determining a state of health of at least one electrochemical energy store includes bringing the electrochemical energy store to a predefined voltage state, after which the electrochemical energy store is discharged for a predefined time period and using predefined electric currents, and determining a rate of voltage change during the discharge, on the basis of which the state of health is determined.

Abstract: A fixing system is disclosed for mounting a camera to a support structure. The fixing system comprises a mounting plate attachable to the support structure and a base detachably connectable to the mounting plate. The mounting plate includes a recess, and the base includes an index plunger with a pressure-loaded pin and a plunger head. When the base is connected to the mounting plate, the pressure-loaded pin of the index plunger is inserted in the recess of the mounting plate. Furthermore, the plunger head of the index plunger is accessible from a side of the base facing away from the mounting plate to pull the pressure-loaded pin out of the recess.

Abstract: Systems and methods for performing vehicle software attestation. One system includes an electronic control unit (ECU) master included in a vehicle and a verifier system. The ECU master receives a digital shadow request generated by the verifier system and generates a digital shadow. The digital shadow is based on a unique, one-way identifier of a program memory space of the ECU master and a unique, one-way identifier of a program memory space of each of a plurality of other ECUs included in the vehicle. The ECU master transmits the digital shadow to the verifier system. The verifier system receives the digital shadow from the ECU master as a first digital shadow, receives a second digital shadow from a digital twin representing software installed in the ECU master and each of the plurality of other ECUs, and determines whether the first digital shadow matches the second digital shadow.

Abstract: A method for controlling an approach of a driving vehicle to at least one preceding reference vehicle using an automated distance setting as a function of a setpoint distance between the vehicle and the reference vehicle. The setpoint distance is calculated as a function of an operating position of an operating element of the vehicle, which is actuatable by the driver of the vehicle and controls a drive of the vehicle. The setpoint distance being reduced directly or indirectly by actuating an actuating element of the vehicle, which has an actuating position, is actuatable by the driver of the vehicle, and controls a braking deceleration of the vehicle. A distance control system, a computer program, and a memory unit, as also described.

Abstract: A method for training a machine learning algorithm including uncertainties. The method includes: pre-training the algorithm based on initially collected data by a control unit in order to obtain an initial model, determining a set of channels, the data originating from channels contained in the set of channels being intended to be used for retraining the initial model, based on an established data level and on the respective influence, which the data originating from one of the channels have on uncertainties instantaneously contained in the initial model, transferring detected data originating from the individual channels of the set of channels to the control unit, and retraining of the initial model by the control unit based on the data transferred to the control unit.

Abstract: The invention relates to a charging device (100), comprising: an input-side first terminal (110_1, 110_2) for connecting to an electrical energy source (200); an output-side second terminal (190_1, 190_2) for connecting to a battery (300) to be charged; and a transformer (150), the primary winding (150_1) of which is electrically connected to the first terminal (110_1, 110_2) by means of a primary circuit (400) and the secondary winding (150_2) of which is electrically connected to the second terminal (190_1, 190_2) by means of a secondary circuit (500).

Abstract: A method for training a neural network. The neural network comprises a first layer which includes a plurality of filters to provide a first layer output comprising a plurality of feature maps. Training of the classifier includes: receiving, by a preceding layer, a first layer input in the first layer, wherein the first layer input is based on the input signal; determining the first layer output based on the first layer input and a plurality of parameters of the first layer; determining a first layer loss value based on the first layer output, wherein the first layer loss value characterizes a degree of dependency between the feature maps, the first layer loss value being obtained in an unsupervised fashion; and training the neural network. The training includes an adaption of the parameters of the first layer, the adaption being based on the first layer loss value.

Abstract: A method for determining an operating state of a vehicle component of a vehicle. The method includes providing a first knowledge graph that contains information concerning a plurality of vehicle components of a vehicle, each vehicle component providing one or more signals. The method includes determining the operating state of a vehicle component from the plurality of vehicle components, the determining including selecting, using the first knowledge graph, a plurality of signals and one or more state parameters that are necessary for determining the operating state of the vehicle component. The determining further includes calculating one or more state parameters of the vehicle component, based on the selected plurality of signals. The determining of the operating state of the vehicle component includes ascertaining the operating state of the vehicle component based on the information contained in the first knowledge graph and based on the calculated one or more state parameters.

Abstract: The invention relates to a method for operating a fuel cell system, in particular a PEM fuel cell system, in which an anode gas is supplied to an anode (1) of a fuel cell via a supply path (2), and is fed back via a recirculation path (3) connected to the anode (1), wherein hydrogen is used as the anode gas. According to the invention, during the start up of the fuel cell system, the anode gas is supplied to a drying device (4), in particular an adsorber, via at least one normally open valve (8, 9, 10), and water is extracted from the anode gas using the drying device (4). The invention also relates to a fuel cell system, in particular a PEM fuel cell system, which is suitable for carrying out the method.

Abstract: A power supply configured for installation in a vehicle is disclosed herein. The vehicle includes a battery, an on-board diagnostics (OBD) port, and a vehicle accessory. In at least one embodiment, the power supply includes a controller area network (CAN) input configured for connection to a CAN pin of the OBD port, a battery input configured for connection to a battery pin of the OBD port, at least one power output configured for connection to a vehicle accessory, and a controller circuit. The controller circuit is configured to (i) monitor a CAN voltage provided via the CAN input, (ii) monitor a battery voltage provided via the battery input, and (iii) selectively deliver power to the at least one power output depending at least in part on the CAN voltage and the battery voltage.