Method and device for collision avoidance during workpiece processing by a multi-axis processing machine

A method for processing a workpiece using a device, the device comprising a processing machine configured for three-dimensionally processing the workpiece and the device further comprising a tool head having a tool, the tool head being movable about at least a first axis and a second axis, the method being carried out by the device, the method comprising

• B) capturing input data concerning a contour of the workpiece, concerning a contour of the tool head, concerning a distance between the tool head and the workpiece, concerning the first axis, and concerning the second axis;
• C) processing the input data to form feature data;
• D) processing the feature data in a machine learning algorithm of the device;
• E) outputting a forecast from the machine learning algorithm regarding a collision of the tool head with the workpiece or some other part of the processing machine,
• wherein, in a case of a collision forecast in the method step E), the following method steps are carried out after the method step E)
• F) varying values of the first axis or of the second axis in the input data, the varying of the values corresponding to a pivoting of the first axis or the second axis;
• G) carrying out the method steps B) to E);
• H) carrying out the method steps F) and G) until no collision is forecast in the method step E) or a predefined number of passes of the method steps F) and G) has been reached, in which case, in an absence of a collision, the values of the input data of the first axis and second axis used in method step B) are output.

A device for processing a workpiece, the device comprising

• a processing machine configured for three-dimensionally processing the workpiece;
• a tool head having a tool, the tool head being movable about at least a first axis and a second axis;
• and
• a controller configured to operate the device to carry out a method, the method comprising
• B) capturing input data concerning a contour of the workpiece, concerning a contour of the tool head, concerning a distance between the tool head and the workpiece, concerning the first axis, and concerning the second axis;
• C) processing the input data to form feature data;
• D) processing the feature data in a machine learning algorithm of the device;
• E) outputting a forecast from the machine learning algorithm regarding a collision of the tool head with the workpiece or some other part of the processing machine,
• wherein, in a case of a collision forecast in the method step E), collision-free input data of the first axis and second axis are output in the method step E), wherein the collision-free input data corresponds to a pivoting of the first axis and the second axis.