Abstract: A method for training a machine learning model to recognize an object topology of an object from an image of the object. The method includes: obtaining a 3D model of the object; determining a descriptor component value for each vertex of the grid; generating training data image pairs each having a training input image and a target image. The target image is generated by determining the vertex positions in the training input image; assigning the descriptor component value determined for the vertex at the vertex position to the position in the target image; and adapting at least some of the descriptor component values assigned to the positions in the target image or adding descriptor component values to the positions of the target image.

Abstract: A method for controlling a robot to pick up an object in various positions. The method includes: defining a plurality of reference points on the object; mapping a first camera image of the object in a known position onto a first descriptor image; identifying the descriptors of the reference points from the first descriptor image; mapping a second camera image of the object in an unknown position onto a second descriptor image; searching the identified descriptors of the reference points in the second descriptor image; ascertaining the positions of the reference points in the three-dimensional space in the unknown position from the found positions; and ascertaining a pickup pose of the object for the unknown position from the ascertained positions of the reference points.

Abstract: The disclosure relates to a method for calibrating a sensor component with a calibration model, said method comprising: applying an acting physical variable and at least one disturbance variable to the sensor component; and acquiring training data sets at a plurality of evaluation times, wherein a training data set at each evaluation time is acquired by: providing a value for the physical variable acting on the sensor component and a corresponding desired sensor variable, which is intended to represent the value of the physical variable acting on the component; acquiring an electrical measured variable representing the physical variable; acquiring the at least one disturbance variable; and training the calibration model with the training data sets so that said model maps the at least one disturbance variable to calibration parameters, wherein a difference between the desired sensor variable and the sensor variable is used as a loss function.

Abstract: A method for planning a manipulation task of an agent, particularly a robot. The method includes: learning a number of manipulation skills wherein a symbolic abstraction of the respective manipulation skill is generated; determining a concatenated sequence of manipulation skills selected from the number of learned manipulation skills based on their symbolic abstraction so that a given goal specification indicating a given complex manipulation task is satisfied; and executing the sequence of manipulation skills.

Abstract: A method for training an artificial neural network, ANN, which comprises a multiplicity of processing units. Parameters that characterize the behavior of the ANN are optimized according to a cost function. Depending on outputs determined from learning input quantity values and on learning output quantity values, an output of at least one selected processing unit is deactivated. Selection of the selected processing unit is achieved with the aid of a sequence of quasi-random numbers.

Abstract: A device and a method for training an image generator. The method includes: providing an image sequence that includes an image for each time of a plurality of times; training a first encoder, a second encoder, and a decoder by: for each of a number of times of the plurality of times: for the image assigned to the time, producing a multiplicity of feature maps for the image by a neural network and grouping them into first and second subsets; supplying the first subset to the first encoder to produce first feature vector; supplying the second subset to the second encoder to produce a second feature vector; supplying the first feature vector and the second feature vector to the decoder to produce a predicted target image; producing an error value; and adapting the first encoder, the second encoder, and the decoder to reduce the error value.

Abstract: A method for controlling a robot to pick up an object in various positions. The method includes: defining a plurality of reference points on the object; mapping a first camera image of the object in a known position onto a first descriptor image; identifying the descriptors of the reference points from the first descriptor image; mapping a second camera image of the object in an unknown position onto a second descriptor image; searching the identified descriptors of the reference points in the second descriptor image; ascertaining the positions of the reference points in the three-dimensional space in the unknown position from the found positions; and ascertaining a pickup pose of the object for the unknown position from the ascertained positions of the reference points.

Abstract: A method for training a machine learning model to recognize an object topology of an object from an image of the object. The method includes: obtaining a 3D model of the object; determining a descriptor component value for each vertex of the grid; generating training data image pairs each having a training input image and a target image. The target image is generated by determining the vertex positions in the training input image; assigning the descriptor component value determined for the vertex at the vertex position to the position in the target image; and adapting at least some of the descriptor component values assigned to the positions in the target image or adding descriptor component values to the positions of the target image.

Abstract: A method for planning a manipulation task of an agent, particularly a robot. The method includes: learning a number of manipulation skills wherein a symbolic abstraction of the respective manipulation skill is generated; determining a concatenated sequence of manipulation skills selected from the number of learned manipulation skills based on their symbolic abstraction so that a given goal specification indicating a given complex manipulation task is satisfied; and executing the sequence of manipulation skills.