Abstract: A computer-implemented method for detecting anomalies in a plurality of sensor recordings of a technical system. The method includes: ascertaining a first anomalous value which, with regard to all sensor recordings of the plurality of sensor recordings, characterizes whether or not an anomaly is present; ascertaining a plurality of second anomalous values, each second anomalous value corresponding to a sensor recording of the plurality of sensor recordings, and with regard to the sensor recording characterizing whether or not an anomaly is present in other sensor recordings of the plurality of sensor recordings; detecting an anomaly in a sensor recording if the first anomalous value characterizes the presence of an anomaly, and the second anomalous value corresponding to the sensor recording characterizes no anomaly, and the second anomalous value differs beyond a predefined extent from other second anomalous values of the plurality of second anomalous values.

Abstract: Computer-implemented method for training a machine learning system. The machine learning system is configured to determine an output signal characterizing a likelihood of an input signal. The training includes: obtaining a first training input signal and a second training input signal, wherein the first training input signal characterizes an in-distribution signal and the second training input signal characterizes a contrastive signal; determining, by the machine learning system, a first output signal characterizing a likelihood of the first training input signal and determining, by the machine learning system, a second output signal characterizing a likelihood of the second training input signal; determining a loss value, wherein the loss value characterizes a difference between the first output signal and the second output signal; training the machine learning system based on the loss value.

Abstract: A computer-implemented method for training a machine learning system. The machine learning system is configured to determine a control signal characterizing an action to be executed by a technical system. The method includes obtaining a safe action to be executed by the technical system including: obtaining a state signal; determining, by a parametrized policy module of the machine learning system, a distribution of potentially unsafe actions that could be executed by the technical system; sampling a potentially unsafe action from the distribution; obtaining, by a safety module of the machine learning system, the safe action. The method further includes determining a loss value based on the state signal and the safe action; and training the machine learning system by updating parameters of the policy module according to a gradient of the loss value with respect to the parameters.

Abstract: A method for controlling a robot is described. The method includes acquiring sensor data representing an environment of the robot, identifying one or more objects in the environment of the robot from the sensor data, associating the robot and each of the one or more objects with a respective agent of a multiagent system, determining, for each agent of the multiagent system, a quality measure which includes a reward term for a movement action at a position and a coupling term which depends on the probabilities of the other agents occupying the same position as the agent at a time, determining a movement policy of the robot that selects movement actions with a higher value of the quality measure determined for the robot with higher probability than movement actions with a lower value of the quality measure, and controlling the robot according to the movement policy.

Abstract: A computer-implemented method for ascertaining a fusion of a plurality of predictions, the predictions of the plurality of predictions in each case characterizing a classification and/or a regression result relating to a sensor signal. The fusion is ascertained based on a product of probabilities of the respective classifications and/or regression results and based on an a priori probability of the fusion, the a priori probability for ascertaining the fusion entering into a power, the exponent of the power being the number of elements in the plurality of predictions minus 1.

Abstract: A computer-implemented method for detecting an anomaly in a technical system. The method includes detecting an environment state vector and a system state vector, the environment state vector including at least one first value which characterizes a physical environment condition or a physical operating condition of the technical system, and the system state vector including at least one second value which characterizes a physical condition of the technical system; ascertaining, using an environment anomaly model, an environment value which characterizes a probability or a probability density value with which the environment state vector occurs; ascertaining, using a system anomaly model, a system value which characterizes a conditional probability or a conditional probability density value with which the system state vector occurs if the environment state vector occurs; signaling the presence of an anomaly or signaling the absence of an anomaly based on the environment value and/or the system value.

Abstract: A method for training a control strategy. The method includes providing training data, which demonstrate a control behavior, according to which control actions are to be generated, and training the control strategy with the aid of imitation learning by minimizing a measure of deviation between the distribution of state transitions according to the control strategy and the distribution of state transitions according to the demonstrated control behavior using the training data.

Abstract: A method for detecting anomalies in input image data, in particular from a camera, by detecting to what extent the input image data match at least one predefined distribution of image data or deviate from this predefined distribution. In the method: at least one transformation is provided, which maps input image data to data that have been information-reduced with regard to at least one aspect; at least one neural reconstruction network is provided, which is trained to reconstruct original image data from information-reduced data, which were obtained by applying the transformation to original image data from the predefined distribution; the input image data are mapped to information-reduced data by applying the transformation; the information-reduced data are mapped to reconstructed image data using the neural reconstruction network; the reconstructed image data are used to assess to what extent the input image data match or deviate from the predefined distribution.

Abstract: A computer-implemented method for detecting anomalies in sensor recordings of a technical system. The method including: ascertaining a first anomalous value which, with regard to all sensor recordings, characterizes whether or not an anomaly is present; ascertaining a plurality of second anomalous values, a second anomalous value from the second anomalous values corresponding to a sensor recording, and the second anomalous value, with regard to the sensor recording and under the condition of the occurrence of the other sensor recordings, characterizing whether or not an anomaly is present in the sensor recording; detecting an anomaly in a sensor recording of the sensor recordings if the first anomalous value characterizes the presence of an anomaly, and the second anomalous value corresponding to the sensor recording characterizes an anomaly, and the second anomalous value differs beyond a predefined extent from other second anomalous values of the second anomalous values.

Abstract: A computer-implemented method for ascertaining a classification and/or a regression result based on the plurality of sensor values. The method includes: ascertaining a plurality of hypotheses regarding a missing sensor value using a machine learning system; ascertaining a plurality of outputs, an output being based in each case on the plurality of sensor values and a hypothesis and the output characterizing a classification and/or a regression result; providing an aggregation of the plurality of outputs as the classification and/or the regression result.

Abstract: A device and method for controlling a hardware agent in a control situation having a plurality of hardware agents. The method includes ascertaining of a potential function by a first neural network; ascertaining of a control scenario for a control situation from a plurality of possible control scenarios by a second neural network; ascertaining a common action sequence for the plurality of hardware agents by seeking an optimum of the ascertained potential function over the possible common action sequences of the ascertained control scenario; and controlling at least one of the plurality of hardware agents in accordance with the ascertained common action sequence.

Abstract: A computer-implemented method for detecting anomalies in a plurality of sensor recordings of a technical system. The method includes: ascertaining a first anomalous value which, with regard to all sensor recordings of the plurality of sensor recordings, characterizes whether or not an anomaly is present; ascertaining a plurality of second anomalous values, each second anomalous value corresponding to a sensor recording of the plurality of sensor recordings, and with regard to the sensor recording characterizing whether or not an anomaly is present in other sensor recordings of the plurality of sensor recordings; detecting an anomaly in a sensor recording if the first anomalous value characterizes the presence of an anomaly, and the second anomalous value corresponding to the sensor recording characterizes no anomaly, and the second anomalous value differs beyond a predefined extent from other second anomalous values of the plurality of second anomalous values.

Abstract: A computer-implemented method for detecting anomalies in sensor recordings of a technical system. The method including: ascertaining a first anomalous value which, with regard to all sensor recordings, characterizes whether or not an anomaly is present; ascertaining a plurality of second anomalous values, a second anomalous value from the second anomalous values corresponding to a sensor recording, and the second anomalous value, with regard to the sensor recording and under the condition of the occurrence of the other sensor recordings, characterizing whether or not an anomaly is present in the sensor recording; detecting an anomaly in a sensor recording of the sensor recordings if the first anomalous value characterizes the presence of an anomaly, and the second anomalous value corresponding to the sensor recording characterizes an anomaly, and the second anomalous value differs beyond a predefined extent from other second anomalous values of the second anomalous values.

Abstract: A computer-implemented method for detecting an anomaly in a technical system. The method includes detecting an environment state vector and a system state vector, the environment state vector including at least one first value which characterizes a physical environment condition or a physical operating condition of the technical system, and the system state vector including at least one second value which characterizes a physical condition of the technical system; ascertaining, using an environment anomaly model, an environment value which characterizes a probability or a probability density value with which the environment state vector occurs; ascertaining, using a system anomaly model, a system value which characterizes a conditional probability or a conditional probability density value with which the system state vector occurs if the environment state vector occurs; signaling the presence of an anomaly or signaling the absence of an anomaly based on the environment value and/or the system value.

Abstract: A method for controlling a robot is described. The method includes acquiring sensor data representing an environment of the robot, identifying one or more objects in the environment of the robot from the sensor data, associating the robot and each of the one or more objects with a respective agent of a multiagent system, determining, for each agent of the multiagent system, a quality measure which includes a reward term for a movement action at a position and a coupling term which depends on the probabilities of the other agents occupying the same position as the agent at a time, determining a movement policy of the robot that selects movement actions with a higher value of the quality measure determined for the robot with higher probability than movement actions with a lower value of the quality measure, and controlling the robot according to the movement policy.

Abstract: A machine learnable system is described. A conditional normalizing flow function maps a latent representation to a base point in a base space conditional on conditioning data. The conditional normalizing flow function is a machine learnable function and trained on a set of training pairs.

Abstract: The learning of probability distributions of data enables various applications, including but not limited to data synthesis and probability inference. A conditional non-linear normalizing flow model, and a system and method for training said model, are provided. The normalizing flow model may be trained to model unknown and complex conditional probability distributions which are at the heart of many real-life applications.