The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Jun. 21, 2016

Filed:

Jun. 28, 2011
Applicants:

Ingo Stork Genannt Wersborg, Munich, DE;

Adrian Garcea, Karlsruhe, DE;

Inventors:

Ingo Stork Genannt Wersborg, Munich, DE;

Adrian Garcea, Karlsruhe, DE;

Assignees:

PRECITEC KG, Gaggenau-Bad Rotenfels, DE;

PRECITEC ITM GMBH, Eschborn, DE;

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G05B 13/02 (2006.01); G06T 7/00 (2006.01); B23K 26/03 (2006.01); B23K 1/005 (2006.01); B23K 26/14 (2014.01); B23K 26/20 (2014.01); B23K 26/34 (2014.01); B23K 28/02 (2014.01); G05B 19/408 (2006.01); G06K 9/62 (2006.01); B23K 26/32 (2014.01);
U.S. Cl.
CPC ...
G06T 7/0004 (2013.01); B23K 1/0056 (2013.01); B23K 26/032 (2013.01); B23K 26/1429 (2013.01); B23K 26/20 (2013.01); B23K 26/32 (2013.01); B23K 26/322 (2013.01); B23K 26/34 (2013.01); B23K 28/02 (2013.01); G05B 13/0265 (2013.01); G05B 13/0285 (2013.01); G05B 19/4083 (2013.01); G06K 9/6247 (2013.01); G06K 9/6248 (2013.01); B23K 2201/34 (2013.01); B23K 2203/02 (2013.01); B23K 2203/50 (2015.10); G05B 2219/35085 (2013.01);
Abstract

The present invention relates to a method for controlling a processing operation of a workpiece by means of a Reinforcement Learning (RL) agent unit, comprising the steps of: (a) observing an interaction zone in the workpiece by means of at least one radiation sensor to generate at least one sensor signal s, wherein the workpiece is processed using an actuator having an initial actuator value a; (b) determining a basis function Φ(s) from the set of sensor signals s; (c) determining a reward function rgiving the probability of good results of the processing operation; (d) choosing a next actuator value aon the basis of a policy π depending on the reward function rand the basis function Φ(s); and (e) repeating the steps (a) to (d) for further time points to perform a RL controlled processing operation.


Find Patent Forward Citations

Loading…