US 12,010,280 B2
Machine learning device, machine learning method, and machine learning program
Tomohiro Kiriyama, Kouhu (JP); Koichi Saito, Toyohashi (JP); Shun Sugai, Hino (JP); Kazuhiko Kowase, Toyokawa (JP); and Naoshi Kashiwagura, Toyohashi (JP)
Assigned to KONICA MINOLTA, INC., Tokyo (JP)
Filed by KONICA MINOLTA, INC., Tokyo (JP)
Filed on Jul. 8, 2020, as Appl. No. 16/923,509.
Claims priority of application No. 2019-134502 (JP), filed on Jul. 22, 2019.
Prior Publication US 2021/0029255 A1, Jan. 28, 2021
Int. Cl. H04N 1/00 (2006.01); G05B 13/04 (2006.01); G06N 20/00 (2019.01)
CPC H04N 1/0061 (2013.01) [G05B 13/047 (2013.01); G06N 20/00 (2019.01); H04N 1/00082 (2013.01); H04N 2201/0094 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A machine learning device that learns an action of a driving source device in a transport device continuously transporting at least two transported objects along a transport path, wherein the driving source device is a motor or a clutch that switches transmission of power of the motor, the machine learning device comprising:
a hardware processor that:
acquires position information of the at least two transported objects on the transport path on the basis of a result of detection by a sensor provided in the transport path;
calculates a reward on the basis of a time interval between the two transported objects or a distance between the two objects using the position information acquired, according to a predetermined rule;
learns an action by calculating an action value in reinforcement learning on the basis of the position information acquired and the reward calculated; and
generates and outputs control information, wherein the control information includes at least one of a control signal, a control current, and a frequency with which the motor and/or the clutch is operated, that causes the driving source device to perform an action determined on the basis of a learning result.