ROBOT CONTROL APPARATUS AND ROBOT CONTROL METHOD

• US 20150148952A1
• Filed: 05/30/2013
• Published: 05/28/2015
• Est. Priority Date: 06/29/2012
• Status: Active Grant

• Current Assignee: Mitsubishi Electric Corporation
• Original Assignee: Mitsubishi Electric Corporation
• Inventors: Shiratsuchi, Koji
• Granted Patent: US 9,517,556 B2
• Time in Patent Office: Days
• US Class Current: 700/248
• CPC Class Codes: B25J 9/0084 comprising a plurality of manipulators
• CPC Class Codes: B25J 9/1682 Dual arm manipulator; Coordination of several manipulators
• CPC Class Codes: G05B 2219/39122 Follower, slave mirrors leader, master
• CPC Class Codes: G05B 2219/39124 Grasp common rigid object, no movement end effectors relative to object
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: Y10S 901/03 Teaching system

Abstract

A robot control apparatus includes a transformation-matrix generating unit that generates, on the basis of N first command values for learning per one robot, which are position-corrected command values for positioning a master robot and a slave robot on tracks of their respective robots during the synchronous driving, concerning the respective N command values for learning, transformation matrices among the command values for learning, a command-value storing unit that outputs a first command value for driving at each of M operation periods for defining the track of the master robot, a transformation-matrix-function generating unit and a command-value generating unit that interpolate the N transformation matrices and generate a transformation matrix at the each first command value for driving, and a command-value generating unit that causes the transformation matrices to act on the M first command values for driving and generates M second command values for driving of the slave robot.

Claims

1. A robot control apparatus that synchronously drives a first robot and a second robot different from the first robot, the robot control apparatus comprising:

a positional-relation-matrix generating unit that generates, on the basis of N first command values for learning per one robot, which are position-corrected command values for positioning the first robot and the second robot on tracks of the first robot and the second robot during the synchronous driving, concerning the respective N first command values for learning, positional relation matrices for defining a positional relation during the synchronous driving between a first command value for learning related to the first robot and a first command value for learning related to the second robot;

a first command-value output unit that outputs a first command value for driving at each of M (M>

N) operation periods, which is a command value for defining the track of the first robot;

a positional-relation-matrix interpolating unit that interpolates the N positional relation matrices and generates a positional relation matrix at the each first command value for driving; and

a second command-value generating unit that causes the positional relation matrices corresponding to the M first command values for driving after the interpolation to act on the respective M first command values for driving and generates M second command values for driving, which are command values for defining the track of the second robot, wherein

the robot control apparatus drives the first robot on the basis of the first command values for driving and drives the second robot on the basis of the second command values for driving.

2. The robot control apparatus according to claim 1, wherein

the first robot and the second robot are caused to move to and stand still at respective N sets of teaching points by a user, and

the robot control apparatus further comprises a position-corrected-command-value generating unit that performs correction of respective finger positions on the basis of an acting force applied to fingers every time the first robot and the second robot are caused to stand still at the respective N sets of teaching points, acquires finger positions after the correction or command values corresponding to the finger positions after the correction, and sets the finger positions or the command values in the first command values for learning.

3. The robot control apparatus according to claim 2, further comprising a positional-relation-matrix-function generating unit that generates a positional relation matrix function for interpolating the N positional relation matrices, wherein

the positional-relation-matrix interpolating unit generates a positional relation matrix at each of the first command values for driving on the basis of the positional relation matrix function.

4. The robot control apparatus according to claim 1, wherein,

the first robot and the second robot are robots that simultaneously grip and convey a same work, and

the robot control apparatus further comprises:

an acting-force calculating unit that calculates an acting force applied to the finger of the first robot or the second robot;

a command correcting unit that applies, during the synchronous driving, to the first command values for driving or the second command values for driving, correction for reducing the acting force applied to the finger of the first robot or the second robot on the basis of a calculated value of the acting-force calculating unit;

a position detecting unit that performs position detection for the first robot and the second robot during the synchronous driving; and

a position-corrected-command-value generating unit configured to calculate the N first command values for learning for each of the robots during the synchronous driving.

5. The robot control apparatus according to claim 4, further comprising a position detecting unit that detects a finger position of the first robot and a finger position of the second robot at each of operation periods, wherein

the position-corrected-command-value generating unit sets, in the first command values for learning, N detection values among detection values of the finger position of the first robot and N detection values among detection values of the finger position of the second robot.

6. The robot control apparatus according to claim 4, wherein

the command correcting unit corrects the first command values for driving and the second command values for driving during the synchronous driving,

the M first command values for driving and the M second command values for driving each include N second command values for learning, and

the position-corrected-command-value generating unit adds up, concerning the respective second command values for learning, the second command values for learning and a representative value of latest correction amounts for a predetermined cycle by the command correcting unit for the second command values for learning to thereby calculate the first command values for learning.

7. The robot control apparatus according to claim 6, further comprising a command-value-for-learning selecting unit that selects command values for driving satisfying a setting condition concerning the acting force among the M first command values for driving and sets the selected command values for driving as the second command values for learning of the first robot.

8. The robot control apparatus according to claim 6, wherein the representative value is an average, a weighted average, a median, or a mode.

9. The robot control apparatus according to claim 1, further comprising a positional-relation-matrix-function generating unit that generates a positional relation matrix function for interpolating the N positional relation matrices, wherein

the positional-relation-matrix interpolating unit generates a positional relation matrix for each of the first command values for driving on the basis of the positional relation matrix function.

10. The robot control apparatus according to claim 1, further comprising:

a speed-setting-value input unit that receives an input of a first speed setting value during the synchronous driving; and

a positional-relation-matrix-function storing unit that stores in advance a positional relation matrix function for interpolating the N positional relation matrices at each second speed setting value different from the first speed setting value, wherein

the positional-relation-matrix interpolating unit reads out, during the synchronous driving, the positional relation matrix function at the each second speed setting value stored by the positional-relation-matrix-function storing unit, corrects the read-out positional relation matrix function at the each speed setting value on the basis of the first speed setting value input to the speed-setting-value input unit, and generates a positional relation matrix at the each first speed setting value on the basis of the positional relation matrix function after the correction.

11. A robot control method for synchronously driving a first robot and a second robot different from the first robot, the robot control method comprising:

a positional-relation-matrix generating step for generating, on the basis of N first command values for learning per one robot, which are position-corrected command values for positioning the first robot and the second robot on tracks of the first robot and the second robot during the synchronous driving, concerning the respective N first command values for learning, positional relation matrices for defining a positional relation during the synchronous driving between a first command value for learning related to the first robot and a first command value for learning related to the second robot;

a first command-value output step for outputting a first command value for driving at each of M (M>

N) operation periods, which is a command value for defining the track of the first robot;

a positional-relation-matrix interpolating step for interpolating the N positional relation matrices and generating a positional relation matrix at the each first command value for driving;

a second command-value generating step for causing the positional relation matrices corresponding to the M first command values for driving after the interpolation to act on the respective M first command values for driving and generating M second command values for driving, which are command values for defining the track of the second robot; and

a synchronous driving step for driving the first robot on the basis of the first command values for driving and driving the second robot on the basis of the second command values for driving.