Optimizing an automated process to select and grip an object via a robot
AssigneeSiemens Aktiengesellschaft
InventorMathias Witt
Life of this patent
Estimating the term…
Abstract
A method for optimizing an automated process to select and grip an object by a robot in an arrangement that includes a plurality of robots with regard to a specifiable optimization criterion, wherein the objects to be potentially gripped irregularly occur with respect to their spatial position and a time of their arrival, where detection of objects to be potentially gripped by robots is performed, detection of a priority characteristic as well as an assignment to one of the robots for the objects to be potentially gripped via an automated learning algorithm, taking the optimization criterion into account, and where selection and gripping depending on the assignment and the priority characteristic is implemented.
Claims19
A method for optimizing an automated process for selecting and gripping an object via a robot in an arrangement consisting of a plurality of robots with respect to a specifiable optimization criterion, the objects to be potentially gripped irregularly occurring with respect to their spatial position and a time of their arrival, the method comprising:
- detecting the objects to be potentially gripped by robots;
- detecting a priority characteristic which controls a priority of objects which were jointly assigned to the robot and detecting whether the objects to be potentially gripped are assigned to one of the robots via an automated learning algorithm, said detections taking into account the specifiable optimization criterion, and the automated learning algorithm taking into account a position of the object with respect to a respective operating range of the plurality of robots, positions of other objects, other objects in the operating range of the plurality of robots and possible gripping processes of the plurality of robots, and the specifiable optimization criterion;
- and
- selecting and gripping the object, depending on the assignment and the priority characteristic.
A non-transitory computer-program product encoded with a computer program which, when executed on a program-controlled device, causes optimization of an automated process for selecting and gripping an object via a robot in an arrangement consisting of a plurality of robots with respect to a specifiable optimization criterion, the objects to be potentially gripped irregularly occurring with respect to their spatial position and a time of their arrival, the computer program comprising:
- program code for detecting the objects to be potentially gripped by robots;
- program code for detecting a priority characteristic which controls a priority of objects which were jointly assigned to the robot and detecting whether the objects to be potentially gripped are assigned to one of the robots via an automated learning algorithm, said detections taking into account the specifiable optimization criterion, and the automated learning algorithm taking into account a position of the object with respect to a respective operating range of the plurality of robots, positions of other objects, other objects in the operating range of the plurality of robots and possible gripping processes of the plurality of robots, and the specifiable optimization criterion;
- and
- program code for selecting and gripping the object, depending on the assignment and the priority characteristic.
A production machine comprising:
- a motion-control system for controlling motion of robots, wherein the motion-control system is configured to:
- detect objects to be potentially gripped by robots;
- detect a priority characteristic which controls a priority of objects which were jointly assigned to the robot and detect whether the objects to be potentially gripped are assigned to a robot via an automated learning algorithm, said detections taking into account a specifiable optimization criterion, and the automated learning algorithm taking into account a position of the object with respect to a respective operating range of the plurality of robots, positions of other objects, other objects in the operating range of the plurality of robots and possible gripping processes of the plurality of robots, and the specifiable optimization criterion;
- and
- select and grip the object, depending on the assignment and the priority characteristic.
Dependencies are inferred from the claim text.