Robert Boschgmbh

Robert Bosch Gmbh

Thyssen Krupp Ag

Atlas Elektronik Gmbh

Zeus Systems Gmbh

Christoph Zimmer

The Duy Nguyen-Tuong

Matthias Kuehnel

Philipp Nolte

Michael Herman

Jochen Braun

Volker Imhof

Adrian Trachte

Mona Meister

Sebastian Gerwinn

Wenqing Liu

Markus Ulrich

Steven Dietrich

Barbara Rakitsch

Dusan Radovic

Cen-You Li

Dingling Yao

Sriganesh Sriram

Henrik Klessig

Eric Sebastian Schmidt

Jan Martin Lubisch

Hon Sum Alec Yu

Nils Theuerkauf

Uwe Plank-Wiedenbeck

Bernd Fritz Geppert

Jörg Pfister

A method is for ascertaining control model parameters of a control model of an axial piston pump. The method models at least one control variable of an adjustment unit of the axial piston pump as a function of operating variables. Operating points of the axial piston pump each are characterized by operating values of the operating variables. The method includes (i) providing initial control model parameters of the control model and an operating state set including a plurality of initial first operating points, (ii) providing initial safety model parameters of a safety model based on a safety set including a plurality of initial second operating points and associated safety values, and (iii) determining a further operating point which is not yet included in the operating state set. The further operating point is determined such that a variance of the control model is maximized.

Method for determining control model parameters of a control model of an axial piston pump

Active learning for operating a physical system. The method includes: providing a data set that comprises data points each comprising an input for operating the physical system, and a first and second observation of the physical system; training a multi-output Gaussian process for predicting the first observation for a given input with the data set; training a Gaussian process for predicting the second observation for a given input with the data set; determining with the data set an input for operating the physical system; determining the first and second observations that result from operating the physical system with the determined input; and adding a data point to the data set that comprises the determined input and the determined first and second observations.

Device, computer-implemented method of active learning for operating a physical system

Training a Gaussian process state space model, which describes a correlation between selected control parameters of a plurality of control parameters for controlling a robotic device and output variables of the robotic device assigned in each case. The method includes: for each control parameter: ascertaining a transitional normal distribution and an output variable normal distribution assigned to a respective predicted output state, ascertaining a respective value of a piece of mutual information between the ascertained output variable normal distribution and the ascertained transitional normal distribution; selecting the control parameter having the highest value of the mutual information as the new control parameter; controlling the robotic device using the new control parameter and measuring an output variable of the robotic device assigned to the new control parameter; and training the Gaussian process state space model using the new control parameter and the assigned measured output variable of the robotic device.

Device and method for training a gaussian process state space model

A device and method are disclosed for operating a fuel cell system having a fuel cell stack. Data are provided that map input variables of the fuel cell system and a position of a cell of the fuel cell stack on a voltage of the cell. A model is trained to map the input variables of the fuel cell system and the position of a cell of the fuel cell stack on a probability distribution for a prediction of a voltage of the cell. Instantaneous input variables of the fuel cell system are determined. A probability for the voltage of the cell or for a total voltage of the fuel cell stack is determined for a cell of the fuel cell stack based on the input variables using the model based on the probability distribution. A state of the fuel cell system is determined based on the probability.

Device and computer-implemented method for determining a state of a fuel cell system

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.

Method for training a machine learning algorithm

A method for evaluating signals of a sensor unit including at least two sensors. The method includes reading in a first sensor value of a first of the sensors and a second sensor value of a second sensor, the first and second sensor value each representing one parameter of a substance to be measured by the sensors or a linking of the parameters. A threshold value range is read in, which maps a range of combinations of at least the first and second sensor values, which represents the presence or a value of the substance to be measured in surroundings of the first and second sensors. A combination of the read-in first and second sensor values is recognized as being outside the threshold value range. The threshold value range is changed into a changed threshold value range so that the combination is situated within the changed threshold value range.

Method and device for evaluating signals of a sensor unit including at least two sensors

A method for assessing a state of a radio channel. The method includes: ascertaining or providing a piece of state information, which characterizes a simulated state of a spatial arrangement of components of the surroundings of the wireless communication network; ascertaining at least one prediction based on a machine-trained model, the state information being provided as an input parameter in an input section of a machine-trained model, the state information being propagated by the machine-trained model, and the at least one prediction of a piece of channel state information based on the machine-trained model, which characterizes a state of at least one radio channel between two communication modules, being provided in an output section of the machine-trained model.

Device and method for assessing a state of a radio channel

A computer-implemented method for the safe, active training of a computer-aided model for modeling time series of a physical system using Gaussian processes, including the steps of establishing a safety threshold value &#x3b1;; initializing by implementing safe initial curves as input values on the system, creating an initial regression model and an initial safety model; repeatedly carrying out the steps of updating the regression model; updating the safety model; determining a new curve section; implementing the determined new curve section on the physical system and measuring output variables; incorporating the new output values in the regression model and the safety model until N passes have been carried out; and outputting the regression model and the safety model.

Method for the safe training of a dynamic model

A computer-implemented method for inferring a device feature of a device produced on a wafer. The method includes: providing a wafer feature model associating a wafer position indicating a position of a produced device on the wafer to a device feature, wherein the wafer feature model is configured to be trained by one or more wafer feature maps and particularly configured as a Gaussian process model, providing a sample device feature of at least one device at a sample wafer position, and inferring the device feature of at least one other device of the wafer depending on the provided wafer feature model.

Method and device for determining a feature for devices produced on a wafer

Growing community of inventors

Korntal, Germany

Christoph Zimmer