Robert Boschgmbh

Yxlon International Gmbh

Thomas Wenzel

Tamas Kapelner

Jeremy Simon

Matthias Kirschner

Andre Wagner

Thorben Funke

Hans-Georg Raumer

Max Kirstein

A method for generating training datasets for training an evaluation algorithm using which an alignment of two map datasets can be evaluated to determine navigation information for a mobile device that is moving or is to move in an environment. The method includes, for each of a plurality of training datasets: providing two input feature datasets, wherein underlying map datasets each contain environmental information that has been acquired using a sensor of the mobile device; providing a transformation dataset generated during an alignment of the two input feature datasets; providing a reference transformation dataset as ground truth; determining a correlation dataset based on the two input feature datasets and/or the transformation dataset; determining a quality measure depending on an accuracy of a match between the transformation dataset and the reference transformation dataset; and providing the training dataset which includes the correlation dataset and the quality measure.

Method for generating training datasets for training an evaluation algorithm, method for training an evaluation algorithm and method for evaluating an alignment of two map datasets

A method for recognizing an object from input data is disclosed. Raw detections are carried out in which at least one attribute in the form of a detection quality is determined for each raw detection. At least one further attribute for each raw detection is determined. A temporally or spatially resolved distance measure is determined for at least one attribute of the raw detections. Raw detections of a defined distance measure are combined to form a group of raw detections. The object is recognized from a group with at least one raw detection with the smallest distance measure of the at least one attribute in comparison with another raw detection, or from a group with at least one raw detection which were combined by combining at least two raw detections with the smallest distance measure of the at least one attribute to form said one raw detection.

Method and apparatus for recognizing an object from input data

Method for obtaining at least one significant feature in a series of components of the same type on the basis of data sets by non-destructive testing. The method includes examining a classified random sample of components which have a known production sequence, by a non-destructive testing. A three-dimensional data set for each component is obtained, and components of the sample are divided by good and rejected parts. Defect-free component regions from all of the components of the random sample are extracted. At least one feature which is characteristic of the type of component and production process which, over a predetermined time of component production, exhibits considerable characteristic differences between the good and rejected parts is determined. The determination can be accomplished using neural networks, machine learning approaches, or statistics from the field of data analytics. The at least one feature and its characteristic is defined as a trained classifier.

Method for obtaining at least one significant feature in a series of components of the same type and method for the classification of a component of such a series

Method for obtaining information from short-fibre-reinforced plastic components sequentially produced by an X-ray computed tomography. A learning phase includes: generating CT data sets for a random sample of plastic components from a production process; extracting at least one defect-free region of the plastic components; determining characteristic feature(s) in the extracted regions, relevance of individual features, and regions which are characteristic of the plastic component type and production process thereof, over a predetermined period of the plastic components productions, which exhibit considerable characteristic differences between good parts and reject parts; and defining the feature(s) with its characteristic as trained classifier. An application phase includes: generating a CT data set of the plastic component for inspection; classifying the inspection part based on the trained classifier; examining the characteristic of the feature(s) for a negative trend; and automatically provide a negative trend alert and/or change process parameters to counteract the negative trend.

Method for obtaining information from X-ray computed tomography data for optimizing the injection-moulding process of short-fibre-reinforced plastic parts

Growing community of inventors

Hamburg, Germany

Thomas Wenzel