Method for controlling a laser processing operation by means of a reinforcement learning agent and laser material processing head using the same

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 st, wherein the workpiece is processed using an actuator having an initial actuator value at; (b) determining a basis function Φ(st) from the set of sensor signals st; (c) determining a reward function rt giving the probability of good results of the processing operation; (d) choosing a next actuator value at+1 on the basis of a policy π depending on the reward function rt and the basis function Φ(st); and (e) repeating the steps (a) to (d) for further time points to perform a RL controlled processing operation.

Dependencies are inferred from the claim text.