US 12,456,050 B2
Device and method for training a neural network for controlling a robot for an inserting task
Oren Spector, Modiin Maccabim Reut (IL); and Dotan Di Castro, Haifa (IL)
Assigned to ROBERT BOSCH GMBH, Stuttgart (DE)
Filed by Robert Bosch GmbH, Stuttgart (DE)
Filed on Mar. 21, 2022, as Appl. No. 17/699,531.
Claims priority of application No. 10 2021 109 336.8 (DE), filed on Apr. 14, 2021.
Prior Publication US 2022/0335295 A1, Oct. 20, 2022
Int. Cl. G06F 17/00 (2019.01); G05B 19/4155 (2006.01); G06N 3/08 (2023.01)
CPC G06N 3/08 (2013.01) [G05B 19/4155 (2013.01); G05B 2219/50391 (2013.01)] 7 Claims
OG exemplary drawing
 
1. A method for training a neural network to derive, from a force and a moment exerted on an object when pressed on a plane in which an insertion for inserting the object is located, a movement vector to insert an object into an insertion, the method comprising:
for each position of a plurality of positions in which the object or a part of the object held by the robot touches a plane in which the insertion is located:
controlling the robot to move to a position of the plurality of positions,
controlling the robot to press the object onto the plane,
measuring the force and the moment experienced by the object,
scaling a pair formed of the measured force and moment by a number randomly chosen between zero and a predetermined positive maximum number, and
labelling the scaled pair of force and moment by a movement vector between the position and the insertion; and
training the neural network using the labelled pairs of force and moment.