US 12,240,114 B2
Optimizing an automated process to select and grip an object via a robot
Mathias Witt, Nuremberg (DE)
Assigned to Siemens Aktiengesellschaft, Munich (DE)
Filed by Siemens Aktiengesellschaft, Munich (DE)
Filed on Sep. 13, 2018, as Appl. No. 16/130,444.
Claims priority of application No. 17191304 (EP), filed on Sep. 15, 2017.
Prior Publication US 2019/0084153 A1, Mar. 21, 2019
Int. Cl. B25J 9/16 (2006.01); G05B 19/418 (2006.01)
CPC B25J 9/1612 (2013.01) [B25J 9/163 (2013.01); B25J 9/1679 (2013.01); G05B 19/4183 (2013.01); G05B 19/41865 (2013.01); G05B 19/4189 (2013.01); G05B 2219/39102 (2013.01); G05B 2219/40007 (2013.01); G05B 2219/40053 (2013.01); G05B 2219/40499 (2013.01)] 19 Claims
OG exemplary drawing
 
1. 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.