Task teaching method and task teaching system

Patent metadata

Field	Value
Publication number	US-12515334-B2
Application number	US-202118291339-A
Country	US
Kind code	B2
Filing date	Sep 27, 2021
Priority date	Sep 27, 2021
Publication date	Jan 6, 2026
Grant date	Jan 6, 2026

Abstract

Provided is a task teaching method for teaching a task to a robot that includes a gripper unit configured to grip a grip target object and moves the grip target object gripped by the gripper unit, the task teaching method including: a generation step (S701) of outputting, as a reference path, time-series data regarding a position and an attitude of the grip target object when a teacher grips and moves the grip target object and generating teaching data of the robot corresponding to the reference path; and a modification step (S702) of outputting, as an operation path, time-series data regarding a position and an attitude of the grip target object or the gripper unit when the robot is operated using the teaching data before an actual task is executed by the robot and modifying the teaching data such that the operation path matches with the reference path.

First claim

The invention claimed is:

1 . A task teaching method executed by a task teaching apparatus for teaching a task to a robot that includes a gripper unit configured to grip a grip target object and moves the grip target object gripped by the gripper unit,
the task teaching method comprising: a first step of preparing a marker of a coordinate system in a task environment; a second step of outputting first time-series data regarding a position and an attitude of the grip target object obtained by gripping and moving the grip target object in the task environment and generating first teaching data regarding an operation of the robot corresponding to the first time-series data; a third step of moving the robot to the task environment after the second step; a fourth step of outputting second time-series data regarding a position and an attitude of the grip target object or the gripper unit obtained by operation of the robot using the first teaching data before an actual task is executed by the robot and after the third step; and a fifth step of generating second teaching data regarding an operation of the robot corresponding to a difference between the first time-series data and the second time-series data, wherein the first time-series data, the second time-series data, the first teaching data, and the second teaching data are generated based on the coordinate system, and the third step includes getting the robot to measure the marker of the coordinate system and to recognize the coordinate system.

2 . The task teaching method according to claim 1 , wherein
the marker of the coordinate system is provided on a work table.

3 . The task teaching method according to claim 1 , wherein
the second step includes outputting the first time-series data from a plurality of images of the grip target object obtained by gripping and moving the grip target object, the plurality of images being acquired by a plurality of capturers provided in the task environment where the robot executes the task, and the fourth step includes outputting the second time-series data from a plurality of images of the grip target object obtained by operation of the robot, the plurality of images being acquired by the plurality of capturers.

4 . The task teaching method according to claim 3 , wherein
the plurality of capturers captures three or more markers attached to the grip target object or three or more markers attached to the gripper unit.

5 . The task teaching method according to claim 1 , wherein
the first time-series data and the second time-series data are time-series data regarding a position and an attitude of the grip target object.

6 . The task teaching method according to claim 1 , wherein
in response to an error between the second time-series data and the first time-series data is more than a defined value, the generation of the second teaching data is executed.

7 . The task teaching method according to claim 1 , wherein
in the fifth step, the second teaching data is generated using an error between the second time-series data and the first time-series data.

8 . A task teaching system comprising:
a marker of a coordinate system that is provided in a task environment; a robot that is movable to the task environment, includes a gripper unit configured to grip a grip target object, and moves the grip target object gripped by the gripper unit; an outputter for outputting first time-series data regarding a position and an attitude of the grip target object obtained when a teacher grips and moves the grip target object in the task environment; and a generator for generating first teaching data regarding an operation of the robot corresponding to the first time-series data, wherein; when the robot is moved to the task environment, the outputter outputs second time-series data regarding a position and an attitude of the grip target object or the gripper unit obtained when the robot is operated using the first teaching data before an actual task is executed by the robot; the generator generates second teaching data regarding an operation of the robot corresponding to a difference between the first time-series data and the second time-series data before the actual task is executed by the robot; the first time-series data, the second time-series data, the first teaching data, and the second teaching data are based on the coordinate system; and the robot measures the marker of the coordinate system and recognizes the coordinate system.

9 . The task teaching system according to claim 8 , wherein
the marker of the coordinate system is provided on a work table.

10 . The task teaching system according to claim 8 , further comprising a plurality of capturers provided in a task environment where the robot executes the task, wherein
the outputter outputs the first time-series data and the second time-series data from a plurality of images of the grip target object acquired by the capturers.

11 . The task teaching system according to claim 10 , wherein
the plurality of capturers captures three or more markers attached to the grip target object or three or more markers attached to the gripper unit.

12 . The task teaching system according to claim 8 , wherein
the first time-series data and the second time-series data are time-series data regarding a position and an attitude of the grip target object.

13 . The task teaching system according to claim 8 , wherein
when an error between the second time-series data and the first time-series data is more than a defined value, the generator generates the second teaching data.

14 . The task teaching system according to claim 8 , wherein
the generator generates the second teaching data using an error between the second time-series data and the first time-series data.

Assignees

• Hitachi High Tech Corp

Inventors

• Takahashi Hiroki
• Koyama Masahiro
• Inoue Tomohiro
• Saegusa Takashi
• Ishikawa Shinichi

Classifications

• B25J9/1697

  Vision controlled systems · CPC title

• B25J9/1653

  parameters identification, estimation, stiffness, accuracy, error analysis · CPC title

• G05B2219/36442

  Automatically teaching, teach by showing · CPC title

• G05B2219/40116

  Learn by operator observation, symbiosis, show, watch · CPC title

• G05B19/42

  Recording and playback systems, i.e. in which the program is recorded from a cycle of operations, e.g. the cycle of operations being manually controlled, after which this record is played back on the same machine · CPC title