Abstract: A method for monitoring surroundings of a first sensor system. The method includes: providing a temporal sequence of data of the first sensor system for monitoring the surroundings; generating an input tensor including the temporal sequence of data of the first sensor system, for a trained neural network; the neural network being configured and trained to identify, on the basis of the input tensor, at least one subregion of the surroundings, in order to improve the monitoring of the surroundings with the aid of a second sensor system; generating a control signal for the second sensor system with the aid of an output signal of the trained neural network, in order to improve the monitoring of the surroundings in the at least one subregion.

Abstract: A computer system for providing a plurality of functions for a device, in particular for a vehicle. The computer system has a plurality of system modules configured to provide functions that are differently critical for the operational security of the device. Each system module or a part of a system module is assigned to one zone of a plurality of zones, a zone being a logically and/or physically delimitable unit in the computer system. A first zone is more trustworthy than a second, less trustworthy zone, the danger of a manipulation of a more trustworthy zone being less than of a less trustworthy zone. A first, more critical function being provided by a system module of the first zone and a less critical function being provided by a system module of the second zone.

Abstract: A test system for characterizing solid oxide cells includes at least one gas control unit, at least one fuel gas mixture line, at least one hydrogen gas line, and at least one oxygen gas line. The at least one gas control unit includes at least three stack layers, and at least one hydration unit to humidify the uniform gas mixture. The hydration unit is disposed in a hydration layer of the at least three stack layers. At least one mixing chamber is directly connected in a gas-conductive manner to the fuel gas mixture line and the hydration unit, and is configured for producing the uniform gas mixture and is disposed in a mixing layer of the at least three stack layers. At least one test station for a solid oxide cell is disposed on a test layer of the at least three stack layers.

Abstract: An optical sensor includes first and second light detectors, an optical path, and an evaluation unit. The first light detector detects light in the infrared wavelength range. A light sensitivity of the CCD sensors of the first and second light detectors differ from one another with regard to a predefined wavelength range. The first and second light detectors include pixels in columns and situated next to one another so that a first longitudinal side of the first light detector adjoins a first longitudinal side of the second light detector, and the first and second light detectors receive light via the optical path. The first and second light detectors generate first and second measuring signals, respectively, from electrical charges. The evaluation unit receives the first measuring signals at a first sampling frequency and the second measuring signals at a second sampling frequency, and combines these to form an output signal.

Abstract: A LIDAR sensor, including a window, at least one first group and one second group of electrical conductors, and a detection circuit. The window is a light exit and entry interface of the LIDAR sensor. Each of the groups includes a first conductor and a second conductor, which are situated on and/or within the window, electrically insulated from one another, form a capacitive sensor, and are electrically connected to the detection circuit. The first and second groups are situated at positions which deviate from one another. The detection circuit generates an electrical field between the respective first conductors and second conductors of the respective groups to detect a change in the electrical field as a result of an object in close range of the window, ascertain a position of the object within the surface of the window, and provide a piece of information about the position of the object.

Abstract: A computer-implemented method for operating a laser material processing machine. Process parameters are varied with the aid of Bayesian optimization until a result of the manufacturing, in particular the laser material processing, is sufficiently good. The Bayesian optimization is carried out with the aid of a data-based process model in a first phase, the data-based process model being trained as a function of estimated results. In a second phase, the data-based process model is trained as a function of the ascertained result resulting upon activation of the laser material processing machine.

Abstract: A method for training a neural network to derive, from an image of a camera mounted on a robot, a movement vector for the robot to insert an object into an insertion. The method includes controlling the robot to hold the object, bringing the robot into a target position in which the object is inserted in the insertion, for a plurality of positions different from the target position controlling the robot to move away from the target position to the position, taking a camera image by the camera and labelling the camera image by a movement vector to move back from the position to the target position and training the neural network using the labelled camera images.

Abstract: The present disclosure relates to an internal combustion engine comprising at least one cylinder, four charge-exchange points per cylinder, wherein a first and a second charge-exchange port are each an inlet port, and wherein a third and a fourth charge-exchange port are each an outlet port, also comprising one spark plug and one prechamber spark plug per each cylinder.

Abstract: A method includes generating, using a machine learning model and at a first time interval, a first current vehicle position prediction and generating, using the machine learning model, at a second time interval, a first historical vehicle trajectory prediction based on at least the first current vehicle position prediction and previous spatial information. The method also includes generating, using the machine learning model, at a third time interval, a first future vehicle position prediction based on the first current vehicle position prediction and the first historical vehicle trajectory predication. The method also includes receiving, at the first time interval, sensor data and a sequence of waypoints, and controlling, at the first time interval, at least one vehicle operation of the vehicle using the first current vehicle position prediction, the first historical vehicle trajectory prediction, the first future vehicle position prediction, the sensor data, and the sequence of waypoints.

Abstract: A radar sensing system includes a transmitter and a receiver. The transmitter is configured for installation and use in a vehicle and configured to transmit radio signals. The receiver is configured for installation and use in the vehicle and configured to receive radio signals that include the transmitted radio signals transmitted by the transmitter and reflected from objects in an environment. The receiver includes a plurality of inputs and a plurality of low noise amplifiers (LNAs). Each input of the plurality of inputs is communicatively coupled to a corresponding LNA of the plurality of LNAs. The plurality of LNAs are co-located, and respective outputs of the plurality of LNAs are all directly coupled together at a connection point.

Abstract: Microcracked and crack-free catalyst layers such as for electrodes in electrochemical cells (e.g., fuel cells) and method of making the same are disclosed. The microcracks may improve durability by better tolerating stresses without inducing or propagating into macrocracks. The microcracks also improve efficiency by providing reactant (e.g., oxygen) passages to catalyst in the catalyst layer. The microcracks may be formed in a predetermined pattern to further localize additional reactant passages is conventionally starved or more starved locations.

Abstract: A radar system with on-system calibration includes capabilities for radar detection and correction for system impairments to improve detection performance. The radar system is equipped with pluralities of transmit antennas and pluralities of receive antennas. The radar system uses a series of calibration measurements of a known object to estimate the system impairments. A correction is then applied to the beamforming weights to mitigate the effect of these impairments on radar detection. The estimation and correction requires no external measurement equipment and can be computed on the radar system itself.

Abstract: A computer-implemented system and method relate to gesture recognition. A machine learning system is trained using a training dataset of sensor data that include a set of gestures. The training dataset includes at least a first subset that displays a first gesture. Loss data is generated based on a first loss function that includes a first cross entropy loss and a second cross entropy loss. Parameters of the machine learning system are updated based on the loss data. The machine learning system is outputted and configured for gesture recognition of the set of gestures. The machine learning system includes (i) a first subnetwork to generate feature data based on the sensor data, (ii) a second subnetwork to extract a selected patch of the feature data, and (iii) a third subnetwork to generate gesture data based on a classification of the corresponding feature data of the selected patch. The first cross entropy loss is based on a first performance of the second subnetwork in relation to the training dataset.

Abstract: A computer-implemented method includes converting tabular data to a text representation, generating metadata associated with the text representation of the tabular data, outputting one or more natural language data descriptions indicative of the tabular data in response to utilizing a large language model (LLM) and zero-shot prompting of the metadata and text representation of the tabular data, outputting one or more summaries utilizing the LLM and appending a prompt on the one or more natural language data descriptions, selecting a single summary of the one or more summaries in response to the single summary having a smallest validation rate, receiving a query associated with the tabular data, outputting one or more predictions associated with the query, and in response to meeting a convergence threshold with the one or more predictions generated from the one or more iterations, output a final prediction associated with the query.

Abstract: A method for operating an electrical energy store, which includes at least two electrical energy store modules connected in parallel and a connector. It is initially queried which electrical energy store modules are operational. A first voltage of an operational electrical energy store module is then determined, which is greater than or equal to the voltage of all operational electrical energy store modules. Those operational electrical energy store modules are then selected, whose voltage is within a voltage range below the first voltage. The selected electrical energy store modules are then electroconductively connected to the connector.

Abstract: A method is for influencing and/or operating a steering system, in particular a steer-by-wire steering system. In the method, a setpoint for an operating element actuator is determined independently of a setpoint for a steering gear actuator, and the operating element actuator is actuated depending on the setpoint for the operating element actuator. The setpoint for the steering gear actuator of the steering system is determined independently of the setpoint for the operating element actuator, and the steering gear actuator is actuated depending on the setpoint for the steering gear actuator. The setpoint for the operating element actuator is determined depending on a target value for a behavior of an operating element and depending on a first request value. The setpoint for the steering gear actuator is determined depending on a target value for a behavior of the steering gear actuator and depending on a second request value.

Abstract: A method for training an artificial neural network uses training data that include first image data of a first image and second image data of a second image of an infrastructure. The first image includes a first feature, and the second image includes a second feature corresponding to the first image. The training data include a relative desired translation and a relative desired rotation between the first feature and the second feature. The training includes extracting the first feature from the first image and extracting the second feature from the second image using the artificial neural network. The extracted first feature is represented by first feature data having a first volume of data. The extracted second feature is represented by second feature data having a second volume of data. The training further includes ascertaining a relative translation and a relative rotation between the extracted first feature and the extracted second.

Abstract: An electrode for use in a device configured to remove ions from a solution. The electrode includes an intercalation material including a binary transition metal Prussian blue analogue compound, a ternary transition metal Prussian blue analogue compound, or a combination thereof. The binary compound may have a general formula: AxByCz[Fe(CN)6], where A=Li, Na, or K; B=Mn, Fe, Ni, Cu, or Zn; C=Mn, Fe, Ni, Cu, or Zn; 0?x?1; 0?y?1; and 0?z?1. The ternary compound may have the general formula: AxByCzDw[Fe(CN)6], where A=Li, Na, or K; B=Mn, Fe, Ni, Cu, or Zn; C=Mn, Fe, Ni, Cu, or Zn; D=Mn, Fe, Ni, Cu, or Zn; 0?x?1; 0?y?1; 0?z?1; 0?w?1.

Abstract: A battery pack includes a battery pack housing that is sealed and flooded with a dielectric fluid. In addition, the battery pack includes a battery module that is disposed in the battery pack housing, and a vent block that is disposed on the lid and communicates with an interior space of the battery pack housing. The vent block is configured to permit the battery pack to accommodate volume changes of the dielectric fluid within the battery pack housing.

Abstract: A processing unit for multiplying a first value by a first multiplicand, or for multiplying the first value by, in each instance, a second and third multiplicand. The processing unit receives the multiplicands in a logarithmic number format, so that the multiplicands are each present in the form of at least one exponent at a specifiable base. The processing unit includes a first register, in which either two exponents of the first multiplicand or the exponent of the second and the exponent of the third multiplicand are stored. A set configuration bit indicates whether either the two exponents of the first multiplicand or the exponent of the second and the exponent of the third multiplicand are stored in the first register. The processing unit includes at least two bitshift operators. A method and a computer program for multiplying the value by the multiplicand are also described.