Abstract: A method for controlling a technical system. The method includes: ascertaining, as a first probability distribution, a probability distribution for a specification of a first chain of actions to perform based on a first state of the technical system to control the technical system; selecting an action for the first state according to the first probability distribution and controlling the technical system accordingly; ascertaining a second state which the technical system has entered by performing the first action; ascertaining by Bayesian inference, as a second probability distribution, a probability distribution for a specification of a second chain of actions to perform based on the second state; selecting an action for the second state according to the second probability distribution and controlling the technical system according to the selected action for the second state.

Abstract: A method for training a control policy for controlling a technical system. The method includes training a neural network to implement a value function by: adapting the neural network for reducing a loss which, for a plurality of states and, for each state, for at least one action that has been previously carried out in the state, involves a deviation between a prediction for a cumulative reward and an estimation of the cumulative reward that is ascertained from a subsequent state that has been achieved by the action, and a reward that is obtained by the action. In the loss, for each action, the deviation for the action is weighted more strongly the greater the likelihood is that the action is selected by the control policy, in relation to the likelihood that the action is selected by a behavior control policy. The method also includes training the control policy.

Abstract: A computer-implemented method for estimating uncertainties using a neural network, in particular, a neural process, in a model. The model models a technical system and/or a system behavior of the technical system. An architecture of the neural network for estimating uncertainties is also described.

Abstract: A device and computer implemented method of controlling a machine. The method includes determining a state of the machine, determining a policy comprising parameters in particular a gain, for mapping the state of the machine to an input for the machine, mapping the state to the input according to the policy, an controlling the machine according to the input. A cone program is defined by a plurality of parameters of a linear quadratic regulator for the machine. A cost function is defined depending on the plurality of parameters and the policy. A constraint is defined for the parameters and for a solution of the cone program. The determining of the policy comprises determining the solution to the cone program so that the cost function meets a criterion subject to the constraint.

Abstract: A method for controlling a robot device. The method includes: acquiring an image of an environment of the robot device; processing the image using a neural network, which outputs from the image a respective value image with pixel values for multiple pixels for at least one action parameter value, the pixel value for each pixel indicating an evaluation of an action specified by the action parameter value and the position of the pixel in the value image; selecting, from multiple actions, the particular action from among the multiple actions for which the pixel value of the pixel in the value image is at a maximum for the action parameter value at the position that specifies the action together with the action parameter value; and controlling the robot device to carry out the selected action.

Abstract: A computer-implemented method for assessing uncertainties in a model with the aid of a neural network in particular, a neural process. The model models a technical system and/or a system behavior of the technical system. An architecture of the neural network for assessing uncertainties is also described.

Abstract: A method for training a conditional neural process for determining a position of an object from image data. The method includes: providing training data for training the conditional neural process, wherein the training data comprise labeled image data showing a particular object and labeled comparison image data regarding the particular object; and training the conditional neural process based on the provided training data, wherein the training of the conditional neural process comprises applying functional contrastive learning, and wherein the training of the conditional neural process comprises applying an end-to-end learning approach.

Abstract: A method for ascertaining a 6D pose of an object. The method includes the following steps: providing image data, wherein the image data include target image data showing the object and labeled comparison image data relating to the object, and ascertaining the 6D pose of the object based on the provided image data using a meta-learning algorithm.

Abstract: A method of controlling a device includes receiving data from a first sensor, encoding, via parameters of an encoder, the data to obtain a latent observation (wt) for the data and an uncertainty vector (?wt) for the latent observation, processing the latent observation with a recurrent neural network to obtain a switching variable (st) which determines weights (?t) of a locally linear Kalman filter, processing the latent observation and the uncertainty vector with said locally linear Kalman filter to obtain updated mean of latent representation (?zt) and covariance of latent representation (?zt) of the Kalman filter, decoding the latent representation to obtain mean (?xt) and covariance of a reconstruction of the data (?xt) and outputting the reconstruction at a time t.

Abstract: A housing for an electric machine includes a cooling device arranged on the periphery of a support plate, the cooling device contacts a heat-conducting ring connected to the housing, and the support plate as well as components arranged thereon have vibration damping and an electric insulation to provide advantageous structural conditions such that an advantageous cooling effect is achieved, and regions within the cooling device can be provided for fitting elements of the support plate.

Abstract: A method for training a control arrangement for a controlled system. The control arrangement includes a regulation device and an actuator that operates according to a control strategy. The method includes the generation of control actions by the regulation device, each control action being generated by detecting measured variables that indicate a state of the controlled system, ascertaining a correction term for the detected measured variables by the actuator according to the control strategy, adapting the detected measured variables using the correction term for the detected measured variables, and generating the control action by supplying the adapted measured variables to the regulation device as the actual value. The method further includes training the control strategy by reinforcement learning for maximizing the gain that is achieved by the generated control actions.

Abstract: A device and computer implemented method of controlling a machine. The method includes determining a state of the machine, determining a policy comprising parameters in particular a gain, for mapping the state of the machine to an input for the machine, mapping the state to the input according to the policy, an controlling the machine according to the input. A cone program is defined by a plurality of parameters of a linear quadratic regulator for the machine. A cost function is defined depending on the plurality of parameters and the policy. A constraint is defined for the parameters and for a solution of the cone program. The determining of the policy comprises determining the solution to the cone program so that the cost function meets a criterion subject to the constraint.

Abstract: A method for generating a computer-implemented machine learning system. The method includes receiving a training data set, which corresponds to a dynamic response of a device, and computing an aggregation of at least one latent variable of the machine learning system, using Bayesian inference, and in view of the training data set. An information item contained in the training data set is transferred directly into a statistical description of the plurality of latent variables. The method further includes generating an a-posteriori predictive distribution for predicting the dynamic response of the device, using the calculated aggregation, and under the condition that the training data set has set in.

Abstract: A computer-implemented method for training a machine learning system in which the machine learning system is configured to ascertain, based on at least a first input signal and a multiplicity of second input signals and second output signals corresponding to the second input signals, a first output signal corresponding to the first input signal, the first output signal characterizing a classification encumbered with an uncertainty and/or a regression encumbered with an uncertainty.

Abstract: A computer-implemented method for ascertaining, using a machine learning system, a first output signal characterizing a classification and/or a regression of a first input signal, and the output signal includes a first representation which characterizes an expected value of the classification or the regression, and a second representation, which characterizes a variance of the classification or regression.

Abstract: A housing for an electric machine includes a cooling device arranged on the periphery of a support plate, the cooling device contacts a heat-conducting ring connected to the housing, and the support plate as well as components arranged thereon have vibration damping and an electric insulation to provide advantageous structural conditions such that an advantageous cooling effect is achieved, and regions within the cooling device can be provided for fitting elements of the support plate.

Abstract: An electronically commutated DC motor has a stator wound with a multi-phase stator winding, a permanent magnet rotor mounted rotatably about a motor axis, a circuit board, a guide plate electrically connected to the winding and a housing component. In one implementation, a DC motor can easily be manufactured with the fewest possible process steps, which exhibits a short axial length and a low weight as well as good heat-dissipation properties. It is also an object of the invention to create a DC motor with integrated electronics, whose motor interior can be filled with oil, and which holds the electronics sealed against this oil. For reasons of logistics, an attempt is also made for partial components, such as the electronics, to be designed such that they are capable of complete prior assembly and testing.

Abstract: An electronically commutated DC motor has a stator wound with a multi-phase stator winding, a permanent magnet rotor mounted rotatably about a motor axis, a circuit board, a guide plate electrically connected to the winding and a housing component. In one implementation, a DC motor can easily be manufactured with the fewest possible process steps, which exhibits a short axial length and a low weight as well as good heat-dissipation properties. It is also an object of the invention to create a DC motor with integrated electronics, whose motor interior can be filled with oil, and which holds the electronics sealed against this oil. For reasons of logistics, an attempt is also made for partial components, such as the electronics, to be designed such that they are capable of complete prior assembly and testing.

Abstract: A lighting device may include a circuit board, at least one light emitting diode fastened to the circuit board, and a housing, wherein the circuit board is a wall segment of the housing.

Abstract: Disclosed is an electrical device, in particular a control unit for a motor vehicle, comprising a plate-shaped circuit support fixed on a metallic base plate of the housing, on which a plastic plug part s fixed on a side facing away from the metallic base plate, characterized in that fixing means which are pivot-shaped and protrude from the base plate, are provided for the common mounting of the plastic plug part, the circuit support and the metallic base plate of the housing, that said fixing means are guided through corresponding recesses in the circuit support and in the plastic plug part, that a deformation is produced at each inserted end and that each deformation is supported y a supporting part on said plastic plug part.