Control system, robot system, and control method

Patent metadata

Field	Value
Publication number	US-9652660-B2
Application number	US-201514810657-A
Country	US
Kind code	B2
Filing date	Jul 28, 2015
Priority date	Jul 29, 2014
Publication date	May 16, 2017
Grant date	May 16, 2017

Abstract

A control system includes a projection section that projects predetermined patterned light on a target object, a first imaging section that captures an image of the target object on which the predetermined patterned light is projected by the projection section, a second imaging section that is disposed in a position different from a position where the first imaging section is disposed and captures an image of the target object on which the predetermined patterned light is projected by the projection section, and a calculation section that calculates a three-dimensional shape of the target object based on a first point in a first captured image captured by the first imaging section and a second point in a second captured image captured by the second imaging section.

First claim

What is claimed is:

1. A control system comprising:
a projector that projects predetermined patterned light on a target object;
a first camera that captures a first image of the target object on which the predetermined patterned light is projected by the projector;
a second camera that is disposed in a position different from a position where the first camera is disposed and captures a second image of the target object on which the predetermined patterned light is projected by the projector;
a memory including computer-readable instructions; and
a processor configured to execute the computer-readable instructions to:
calculate a three-dimensional shape of the target object based on a first point in the first image and a second point in the second image;
calculate, based on the first and second images, a reliability that serves as an index representing probability of coincidence of a position identified by a certain point in the first image and a position identified by each point in the second image; and
associate each point in the first image to the each point in the second image based on the reliability.

2. The control system according to claim 1 ,
wherein the processor is configured to execute the computer-readable instructions to:
derive a first likelihood function corresponding to the each point in the first image;
derive a second likelihood function corresponding to the each point in the second image; and
calculate the reliability based on the first and second likelihood functions.

3. The control system according to claim 2 ,
wherein the patterned light has luminance or hue that periodically changes in a certain direction, and
the processor configured to execute the computer-readable instructions to:
calculate a first phase associated with a change in the luminance or the hue of the patterned light at the each point in the first image and a second phase associated with the change in the luminance or the hue of the patterned light at the each point in the second image;
derive the first likelihood function based on the first phase; and
derive the second likelihood function based on the second phase.

4. A robot system comprising: the control system according to claim 3 ; and a robot,
wherein the control system includes a robot controller configured to control the robot based on the three-dimensional shape of the target object.

5. A robot system comprising: the control system according to claim 2 ; and a robot,
wherein the control system includes a robot controller configured to control the robot based on the three-dimensional shape of the target object.

6. A robot system comprising: the control system according to claim 1 ; and a robot,
wherein the control system includes a robot controller configured to control the robot based on the three-dimensional shape of the target object.

7. A control method for causing a processor to execute computer-readable instructions stored in a memory, the method comprising executing on the processor the step of:
projecting predetermined patterned light on a target object;
causing a first camera to capture a first image of the target object on which the predetermined patterned light is projected;
causing a second camera that is disposed in a position different from a position where the first camera is disposed to capture a second image of the target object on which the predetermined patterned light is projected;
calculating a three-dimensional shape of the target object based on a first point in the first image captured by the first camera and a second point in the second image captured by the second camera;
calculating, based on the first and second images, a reliability that serves as an index representing probability of coincidence of a position identified by a certain point in the first image and a position identified by each point in the second image; and
associating each point in the first image to the each point in the second image based on the reliability.

8. The control method according to claim 7 ,
wherein the processor is configured to execute the computer-readable instructions to:
derive a first likelihood function corresponding to the each point in the first image;
derive a second likelihood function corresponding to the each point in the second image; and
calculate the reliability based on the first and second likelihood functions.

9. The control method according to claim 8 ,
wherein the patterned light has luminance or hue that periodically changes in a certain direction, and
the processor which is further configured to execute computer-readable instructions to:
calculate a first phase associated with a change in the luminance or the hue of the patterned light at the each point in the first image and a second phase associated with the change in the luminance or the hue of the patterned light at the each point in the second image;
derive the first likelihood function based on the first phase; and
derive the second likelihood function based on the second phase.

Assignees

• Seiko Epson Corp

Inventors

• Harada Tomoki
• Hashimoto Koichi
• Arai Shogo

Classifications

• G06V20/64

  Three-dimensional [3D] objects · CPC title

• G06T7/521 Primary

  from laser ranging, e.g. using interferometry; from the projection of structured light · CPC title

• G06V10/421

  by analysing segments intersecting the pattern · CPC title

• B25J9/1697

  Vision controlled systems · CPC title

• Y10S901/47

  Optical · CPC title