IP Library › Granted Patent US 11,584,016
Granted Patent B2
US 11,584,016 · App. 16/372,922 · Granted Feb 21, 2023

Robot controller and system

Inventor: Tatsuhiro Yamazaki (Yamanashi, JP)
Assignee: FANUC CORPORATION
B25J9/1697B25J9/163B25J15/10
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 11,584,016
App. No.
16/372,922
Filed
Apr 2, 2019
Granted
Feb 21, 2023
Kind
B2
Art Unit
3664
USPC
700/253
Abstract

A robot controller is a controller which controls, via a hand control device, a robot hand that grips an article with two or more gripping portions. The robot controller includes, a size information acquisition unit which acquires size information about the article based on an image obtained by a visual sensor for detecting the article, and a gripping adjustment unit which changes, in response to the size information, a gripping distance, which is the space between the gripping portions, in a gripping state or a gripping force of the gripping portions in the gripping state.

Claims (32)

1. A robot controller that controls a robot hand which grips an article with a plurality of gripping portions, wherein a processor of the robot controller is configured to conduct:

a size information acquisition process which acquires size information about the article;

a gripping adjustment process which changes, in response to the size information, a gripping distance that is a space between the gripping portions in a gripping state, or a gripping force of the gripping portions in the gripping state;

a receiving process which receives at least one of information about an observed gripping state obtained by imaging, with an imaging device for observation, a state of gripping the article when the robot grips the article, and information about an observed gripping state obtained by an operator who observes a state of gripping the article when the robot grips the article and inputs an observed result to the robot controller;

a learning process that performs learning for improving the gripping state based on the size information and information about the observed gripping state obtained by the receiving process; and

wherein the processor uses results of the learning process to create a table that correlates the size information with gripping force levels for improving the gripping state.

2. The robot controller according to claim 1 , wherein the processor is configured to conduct an output process that outputs a result of the learning.

3. The robot controller according to claim 1 , wherein the robot controller is configured to output the result of the learning to another robot controller and to receive a result of learning from the other robot controller.

4. The robot controller according to claim 1 , wherein the robot controller is configured to output the result of the learning to a host computer system and to receive a result of learning from the host computer system.

5. The robot controller according to claim 1 , wherein:

the processor is configured to conduct a quality receiving process that receives results about a quality of the article obtained in a quality inspection step; and

the learning process uses the results about the quality.

6. A system comprising:

a robot controller that controls a robot hand for gripping an article;

a host computer system capable of communicating with the robot controller;

wherein a processor of the robot controller is configured to conduct:

a receiving process which receives at least one of information about an observed gripping state obtained by imaging, with an imaging device for observation, a state of gripping the article when the robot grips the article, and information about an observed gripping state obtained by an operator who observes a state of gripping the article when the robot grips the article and inputs an observed result to the robot controller;

a learning process that performs, based on size information about the article and the information about the observed gripping state, learning for improving the gripping state wherein the processor uses results of the learning process to create a table that correlates the size information with gripping force levels for improving the gripping state; and

an output process that outputs a result of the learning to the host computer system; and

wherein the host computer system accumulates the result of the learning received from the robot controller.

7. The system according to claim 6 , wherein the host computer system is configured to transmit, to the robot controller, a result of learning performed in the host computer system using the received result of the learning.

8. The system according to claim 6 wherein the host computer system is configured to transmit, to a robot controller having no learning function, the received result of the learning or a result of learning performed in the host computer system using the received result of the learning.

9. The system according to claim 6 wherein:

the processor is configured to conduct a quality receiving process that receives results about a quality of the article obtained in a quality inspection step; and

the learning process uses the results about the quality.

10. A robot controller that controls a robot hand which grips articles one by one with a plurality of gripping portions, the robot controller comprising a processor, wherein the processor is configured to conduct:

a size information acquisition process which acquires a plurality of pieces of size information corresponding to the articles, respectively, based on an image obtained by a visual sensor; and

a gripping adjustment process which changes, in response to each of the plurality of pieces of size information, a gripping distance that is a space between the gripping portions in a gripping state, or a gripping force of the gripping portions in the gripping state,

wherein the robot controller further comprises:

a hand controller which changes the gripping distance or the gripping force to two or more predetermined levels; and

a memory storing a table which associates the plurality of pieces of size information with the two or more predetermined levels in a situation where the plurality of pieces of size information is within a first range, an other table which associates the plurality of pieces of size information with the two or more predetermined levels in a situation where the plurality of pieces of size information is within a second range narrower than the first range,

wherein the processor is configured to change, in the gripping adjustment process, the gripping distance or the gripping force when the robot hand grips the articles one by one by using the table or the other table, which is selected by a user, and the hand controller.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 2, 2019
From: YAMAZAKI, TATSUHIRO
To: FANUC CORPORATION
Reel/Frame 048768/0224 →
Priority Claims (2)
JP JP2018-083184 · Apr 24, 2018 · national
JP JP2019-011349 · Jan 25, 2019 · national
Continuity (1)
Related Publication 20190321984A1 · Oct 24, 2019
Cited By (1)
US 12,403,613