Kaminski Harmann

The invention pertains to a computer-implemented method (100) for detecting gravitational natural hazards, the method comprising: continuously receiving (110) radar data in real time; continuously monitoring (120) the radar data using a detection algorithm, to detect (130) an indication for a gravitational natural hazard event in the radar data; and, if an indication for a gravitational natural hazard event has been detected, initiating (140) an action in real time, wherein: upon detection of an indication for a gravitational natural hazard event, a trained neural network evaluates (160) radar data that has been accumulated (150) for at least a defined period of time; the trained neural network confirms (170) or refutes the gravitational natural hazard event based on the evaluation; and if the gravitational natural hazard event has been refuted, the initiated action is automatically revised (180).

The invention relates to a system a method for exchanging a swappable battery of a mobile robot (1). The system comprises a swappable battery unit (2) and corresponding battery changing tool (3). The battery changing tool (3) configured to take, hold against the gravity and transfer said battery unit (2) during (i) an insertion of the battery unit (2) into the battery dock (15) of the robot (1) or a charging unit (50), and (ii) a removal of the battery unit (2) from the battery dock (15) of the robot (1) or the charging unit (50). The battery unit (1) comprises at least one holding area (231) configured to be contacted with the battery changing tool (3).

The present invention relates to a cable plug connector 1 configured for providing a mechanically lockable plug connection with a built-in plug connector matched to the cable plug connector 1 as a counterpart. The cable plug connector 1 comprises a plug body 2, wherein the plug body 2 comprises a coupling portion 3, wherein the coupling portion 3 is provided to be inserted into an opening of the built-in plug connector to provide the plug connection, and a receiving cavity 4 extending in an outer wall 5 of the plug body 2, wherein the receiving cavity 4 is configured as a half-shell with a passage 12 to an interior 6 of the plug body 2. The cable plug connector 1 further comprises a mechanical retaining element 7 comprising a locking part 9, an actuating part 10 and a connecting part 11 connecting the locking part 9 with the actuating part 10. The mechanical retaining element 7 is arranged in the receiving cavity 4 such that the actuating part 10 protrudes from the receiving cavity 4 in a direction perpendicular to a center axis 17 of the plug body 2, and the connecting part 11 extends through the passage 12 of the plug body 2, so that the locking part 9 is located in the interior 6 of the plug body 2.

The invention relates to a reality capture device (1) for generating a digital representation of an environment (2). The device comprises a laser scanner (3) configured to carry out a scanning movement of a laser measurement beam (4). The reality capture device comprises an upper portion (8) and a lower portion (9). A laser scanner (3) and an imaging arrangement (7) are comprised by the upper portion (8). The upper portion (8) is fixed on the lower portion (9) such that it is rotatable about a support rotation axis (10). The reality capture device is configured to have two scanning modes. In a stationary scanning mode the upper portion rotates about the support rotation axis relative to the lower portion and the laser scanner is set to move the measurement beam only relative to one of its two rotation axes. In a dynamic scanning mode, the laser scanner is set such that the measurement beam (4) is moved relative to both of the two rotation axes (5, 6), whereas the upper portion (8) is configured to be fixed on the support rotation axis (10) such that it does not rotate about the support rotation axis (10) relative to the lower portion (9).

The invention pertains to a computer-implemented method (100) for characterizing a macrotexture of a ground surface, the method comprising receiving (110) 3D point cloud data of a scene, the scene comprising one or more ground surfaces, the 3D point cloud data comprising a plurality of ground points related to the one or more ground surfaces, selecting (130) a sampling unit of one of the ground surfaces, performing plane fitting (140) for fitting one or more planes, each plane representing a portion of the sampling unit, wherein the plane fitting is based on ground points related to the portion represented by the respective plane, calculating (150) a set of roughness indices, each roughness index characterizing the macrotexture of the sampling unit, wherein the calculation of each roughness index is based on distance values of ground points related to the respective portions, the distance values indicating a distance of the respective ground point relative to the respective plane, generating (160) output based on the set of roughness indices, and providing (170) a graphical representation of the output in a graphical user interface.

The present invention relates to a computer-implemented method 1 for generating a parametric model 13 of a physical structure 36 based on point cloud data, the point cloud data describing a point cloud comprising points 14 acquired in an environment 34 in which the physical structure 36 is located, wherein the physical structure 36 comprises a plurality of parts, wherein the plurality of parts are arranged as an interconnected chain of parts that are physically connected, the method 1 comprising: acquiring the point cloud data 100, the point cloud data comprising geometry information of the environment 34; acquiring geometry information of a set of predefined geometric shapes related to the plurality of parts 200; performing a classification on the point cloud data 300 to detect parts of the plurality of parts in the point cloud data 301 based on the geometry information; assign to each detected part of the plurality of parts a set of points of the point cloud 302; and detect physical connections 5 of two or more detected parts 2, 3 of the plurality of parts 303; and generating 400 a parametric model 13 of the physical structure 36 based on the detected physical connections 5 of the two or more detected parts 2, 3 of the plurality of parts and the geometry information of the set of predefined geometric shapes, wherein the method 1 further comprises deriving geometric parameters 23, 24, 29 for each detected part 2, 3 of the plurality of parts from the geometry information of the set of predefined geometric shapes, wherein generating 400 the parametric model 13 of the physical structure 36 is further based on the derived geometric parameters 23, 24, 29 for each detected part 2, 3 of the plurality of parts, wherein at least one of the derived geometric parameters 23, 24, 29 of a preceding part 2 is used as a constraint for at least one of the geometric parameters 23, 24, 29 of a subsequent part 3 physically connected to the preceding part 2.

The invention pertains to a method of reducing noise in 3D data. The method comprises receiving 3D data that has been captured by a first laser scanner with a first resolution in a first environment. The method further comprises reducing noise in the 3D data by utilizing a noise reduction filter, wherein the noise reduction filter has filtering settings. The invention is characterized in that a trained machine learning model uses the filtering settings, wherein the filtering settings are learned by the machine learning model in a training process. The training process comprises multiple steps. Firstly, it comprises receiving training data from at least two laser scanners, the training data comprising a first set and a second set of 3D data that are structured as point-clouds. Secondly, it the training process comprises clustering the second set of 3D data to produce clustered data. Furthermore, the training process comprises training the machine learning model using the clustered data.

Techniques are provided for generating pre-correlation phase coherent samples that can be used with coherent integration. Samples received over a buffer duration are equally divided into sub-buffers. A pre-correlation accumulation (PCA) output is generated, for each of a plurality of different test Doppler remainders of an unknown Doppler shift, using different multiples of the Doppler remainder being tested. A differential operation, to mitigate the Doppler shift, is executed on the PCA output for a test Doppler remainder, and the PCA output is mixed with a delayed version of itself to generate a PCA differential result. Signal despreading is executed by mixing the PCA differential result with a code matching differential result to generate a despreading result. Coherent integration is executed by accumulating the despreading result to generate a correlation output. If the correlation output meets a predefined threshold, signal detection is confirmed.

The present invention relates to a cable plug connector 1 configured for providing a mechanically lockable plug connection with a built-in plug connector matched to the cable plug connector 1 as a counterpart, wherein the cable plug connector 1 comprises a plug body 2, wherein the plug body 2 comprises a coupling portion 3, an insertion opening 4, and a thread 5. The cable plug connector 1 further comprises a clamping collet 6 comprising at least two clamping teeth 7, wherein the clamping collet 6 is arranged in the insertion opening 4 of the plug body 2, a seal 8 arranged within a cavity 9 of the clamping collet 6, wherein the seal 8 comprises a seal cavity 10, and a bushing 11, wherein the bushing 11 is configured such that - in a state screwed onto the thread 5 of the plug body 2 - the bushing 11 presses on the at least two clamping teeth 7 of the clamping collet 6. Each of the at least two clamping teeth 7 of the clamping collet 6 comprises a cable contact portion 12 and a seal contact portion 13.

The present invention relates to an adaptable damping unit (2, 2a-d) designed for integration into a kinematic chain of a machine (1) designed for coordinative measuring and/or coordinative manipulation of a workpiece (O). The adaptable damping unit (2, 2a-d) is configured for local adaptive damping of varying oscillations of a measuring and/or manipulation tool (4) connected to the endpiece (12) of the kinematic chain in course of operation of the machine (1). The adaptable damping unit (2, 2a-d) comprises an adaptable electro-mechanical damping element, characteristics of which are dynamically adjustable dependent on actual motion and/or position sensor data of the kinematic chain. These adjustable characteristics include at least one of the following: elastic, inertial, and/or energy dissipation characteristics.