Robot control device for issuing motion command to robot on the basis of motion sequence of basic motions

Patent metadata

Field	Value
Publication number	US-11673266-B2
Application number	US-201916977472-A
Country	US
Kind code	B2
Filing date	Feb 20, 2019
Priority date	Mar 14, 2018
Publication date	Jun 13, 2023
Grant date	Jun 13, 2023

Abstract

This control device for controlling the motion of a robot comprises a first processing part and a command part. The first processing part sets a first state of the robot and a second state to which the robot transitions from the first state as inputs, and sets at least one basic motion selected from a plurality of basic motions the robot is instructed to perform for transitioning from the first state to the second state and the order in which the basic motions are to be performed as outputs. Prescribed operating parameters are set for each of the basic motions. The command part executes motion commands for the robot on the basis of the output from the first processing part.

First claim

The invention claimed is:

1. A control device for a robot that controls a motion of the robot, the control device for the robot comprising:
a processor, configured to:
set a first state of the robot and a second state to which the first state transitions as inputs of a first learning machine and set basic motions selected out of a predetermined number of prepared basic motions which are performed by the robot for transition from the first state to the second state and a motion sequence of the basic motions as outputs of the first learning machine, a predetermined first motion parameter being set for each of the basic motions;
set the first state, the second state and the basic motions and the motion sequence output from the first learning machine as inputs of a second learning machine and set a second motion parameter of each of the basic motions selected as the outputs of the first learning machine for transition from the first state to the second state as outputs of the second learning machine; and
adjust a current motion parameter of each of the basic motions for the robot and issue a motion command to the robot on the basis of the outputs from the first learning machine and the second learning machine,
wherein the current motion parameter is for indicating aspect and degree of motions expressed by the basic motions.

2. The control device for the robot according to claim 1 , wherein, when the robot is not able to transition to the second state using a predetermined criterion depending on the outputs from the first learning machine, the processor is configured to use the second motion parameter of the second learning machine to output as the current motion parameter for the robot.

3. The control device for the robot according to claim 2 , wherein the current motion parameter is output within a predetermined range.

4. The control device for the robot according to claim 2 , further comprising an input device configured to receive adjustment of the current motion parameter of each of the basic motions.

5. The control device for the robot according to claim 1 , wherein the current motion parameter is output within a predetermined range.

6. The control device for the robot according to claim 1 , further comprising an input device configured to receive adjustment of the current motion parameter of each of the basic motions.

7. The control device for the robot according to claim 1 , wherein the input device is configured to receive designation of the second state.

8. A control system for a robot comprising:
the robot; and
the control device for the robot according to claim 1 ,
wherein the robot transitions from the first state to the second state in accordance with the motion command from the control device.

9. A control method for a robot that controls a motion of the robot, the control method for the robot comprising steps as follows:
preparing for a first learning machine to set a first state of the robot and a second state to which the first state transitions as inputs of the first learning machine and set basic motions selected out of a predetermined number of prepared basic motions which are performed by the robot for transition from the first state to the second state and a motion sequence of the basic motions as outputs of the first learning machine, a predetermined first motion parameter being set for each of the basic motions;
preparing for a second learning machine to set the first state, the second state and the basic motions and the motion sequence output from the first learning machine as inputs of the second learning machine and set a second motion parameter of each of the basic motions selected as the outputs of the first learning machine for transition from the first state to the second state as outputs of the second learning machine;
inputting the first state and the second state to the first learning machine and the second learning machine and outputting the basic motions and the motion sequence of the basic motions; and
adjusting a current motion parameter of each of the basic motions for the robot and issuing a motion command to the robot on the basis of the outputs from the first learning machine and the second learning machine,
wherein the current motion parameter is for indicating aspect and degree of motions expressed by the basic motions.

10. A non-transitory computer-readable storage medium storing a control program that controls a motion of a robot, the control program causing a computer to perform steps as follows:
preparing for a first learning machine to set a first state of the robot and a second state to which the first state transitions as inputs of the first learning machine and set basic motions selected out of a predetermined number of prepared basic motions which are performed by the robot for transition from the first state to the second state and a motion sequence of the basic motions as outputs of the first learning machine, a predetermined first motion parameter being set for each of the basic motions;
preparing for a second learning machine to set the first state, the second state and the basic motions and the motion sequence output from the first learning machine as inputs of the second learning machine and set a second motion parameter of each of the basic motions selected as the outputs of the first learning machine for transition from the first state to the second state as outputs of the second learning machine;
inputting the first state and the second state to the first learning machine and the second learning machine and outputting the basic motions and the motion sequence of the basic motions; and
adjusting a current motion parameter of each of the basic motions for the robot and issuing a motion command to the robot on the basis of the outputs from the first learning machine and the second learning machine,
wherein the current motion parameter is for indicating aspect and degree of motions expressed by the basic motions.

11. A processing device that processes a processing object, the processing device comprising:
a processor, configured to:
set a first state of the processing object and a second state to which the first state transitions as inputs of a first learning machine and set basic processes selected out of a predetermined number of prepared basic processes which are performed on the processing object and a process sequence of the basic processes as outputs of the first learning machine for transition from the first state to the second state, a predetermined first process parameter being set for each of the basic processes;
set the first state, the second state and the basic processes and the process sequence output from the first learning machine as inputs of a second learning machine and set a second process parameter of each of the basic processes selected as the outputs of the first learning machine for transition from the first state to the second state as outputs of the second learning machine; and
adjust a current process parameter of each of the basic processes for the processing object and perform processes on the processing object on the basis of the outputs from the first learning machine and the second learning machine,
wherein the current process parameter is for indicating aspect and degree of processes expressed by the basic processes.

12. The processing device according to claim 11 , wherein, when the processing object is not able to transition to the second state using a predetermined criterion depending on the outputs from the first learning machine, the processor is configured to use the second process parameter of the second learning machine to output as the current process parameter for t

Assignees

• Omron Tateisi Electronics Co

Inventors

• Shibata Yoshiya

Classifications

• G05B2219/39271

  Ann artificial neural network, ffw-nn, feedforward neural network · CPC title

• B25J9/163

  learning, adaptive, model based, rule based expert control · CPC title

• B25J9/1664 Primary

  characterised by motion, path, trajectory planning · CPC title