IP Library Granted Patent US 10,486,306
Granted Patent B2
US 10,486,306 · App. 15/724,417 · Granted Nov 26, 2019

Control device for controlling robot by learning action of person, robot system, and production system

Inventor: Yukio Shibata (Yamanashi, JP)
Assignee: FANUC CORPORATION
B25J9/163B25J9/1674B25J9/1697G05B2219/40116G05B2219/40202
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,486,306
App. No.
15/724,417
Granted
Nov 26, 2019
Kind
B2
Abstract

A control device for a robot for performing an operation in cooperation with a person, the control device includes a machine learning device including a recognition unit for classifying an action of the person, and a learning unit for learning the action of the person, while the person performs an operation in cooperation with the robot; and an action control unit for controlling the action of the robot based on a result of the classification of the recognition unit.

Claims (24)

1. A control device for a robot for performing an operation in cooperation with a person, the control device comprising:

a machine learning device including a recognition unit which recognizes a face of the person to classify an action of the person based on a weight in a neural network corresponding to the person, and a learning unit for receiving data based on an image input as state variable, and learning and outputting the action of the person based on the action of the person classified by the recognition unit, while the person performs an operation in cooperation with the robot; and

an action control unit for controlling the action of the robot based on the action of the person classified by the recognition unit and a learned result of the learning unit.

2. The control device according to claim 1 , wherein

the recognition unit receives the state variable and generates an output obtained by classifying the action of the person, and

the learning unit comprises:

an error calculation unit that receives the output obtained by classifying the action of the person, which is generated by the recognition unit, and calculates an error based on teacher data which have been input; and

an error model update unit that updates, based on an output of the error calculation unit, an error model for controlling an action of the robot by the action of the person.

3. The control device according to claim 1 , wherein

the robot is an industrial robot, a field robot, or a service robot.

4. The control device according to claim 1 , wherein

the recognition unit uses at least one of a neural network and template matching.

5. The control device according to claim 1 , further comprising a plurality of cameras for photographing, wherein

the recognition unit recognizes an action of the person based on an image photographed by each camera, and uses an output of the recognition unit as an input of an AND circuit, and an output of the AND circuit as an output of the recognition unit.

6. The control device according to claim 1 , wherein

the control device transmits, after the person acts in cooperation with the robot, operation information and learning information to a higher-level controller.

7. The control device according to claim 6 , wherein

the operation information includes at least one of an item name, a process, a person specified by image recognition, the type of the robot, and the operation time of the person and the robot, and

the operation time includes at least one of a time from the start to the end of an operation, and a motion time and a downtime of the person and the robot at every operation.

8. The control device according to claim 6 , wherein

the learning information is a weight in the neural network.

9. A robot system comprising a plurality of control devices according to claim 1 , wherein

the plurality of control devices are connected to one another via a communication line, and

the control devices each learn an action of a person separately, and transmit the learned information via the communication line, to share the same.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 4, 2017
From: SHIBATA, YUKIO
To: FANUC CORPORATION
Reel/Frame 043778/0676 →
Priority Claims (1)
JP 2016-200378 · Oct 11, 2016 · national
Continuity (1)
Related Publication 20180099408A1 · Apr 12, 2018