Mobile robot and method for controlling the same

Patent metadata

Field	Value
Publication number	US-10229501-B2
Application number	US-201615340496-A
Country	US
Kind code	B2
Filing date	Nov 1, 2016
Priority date	Nov 26, 2015
Publication date	Mar 12, 2019
Grant date	Mar 12, 2019

Abstract

A mobile robot and method for controlling the same are provided creating patches in images captured by a camera while the mobile robot is moving, estimating motion blur of the patches, and correcting the position of the mobile robot based on the patch from which the motion blur is eliminated, thereby increasing precision in tracking and reliability through accurate mapping. The mobile robot includes a main body, a traveler to move the main body, a camera combined with the main body to capture an image of a surrounding of the main body, a position detector to create a patch in the image captured by the camera, estimate a motion blur of the patch, and track a position of the main body based on the created patch from which the motion blur is eliminated, and a controller to control the traveler based on the position of the main body.

First claim

What is claimed is:

1. A mobile robot comprising:
a main body;
a traveler configured to move the main body by a moving wheels or two legs;
a camera combined with the main body and configured to capture an image of a surrounding of the main body;
a position detector configured
to create a patch in the image captured by the camera,
to estimate motion blur of the patch by a processor, and
to track a position of the main body based on the created patch from which the motion blur is eliminated by the processor; and

a controller configured to control the traveler based on the position of the main body tracked by the position detector,
wherein the position detector is configured to
obtain an aspect of motion blur in the captured image based on the image captured by the camera and movement information of the main body determined by the controller,
detect a position of features in the captured image based on the obtained aspect of the motion blur and
create the patch based on the position of features, and

wherein the position detector
creates a plurality of pieces of blur information estimated for the patch,
selects motion blur of the patch from the plurality of pieces of blur information based on an objective function and
estimates the motion blur in the created patch based on the selected motion blur.

2. The mobile robot of claim 1 , wherein the position detector is configured to create the plurality of piece of blur information based on at least one of three dimensional (3D) feature coordinates, movement information of the main body, and a capturing time interval of the camera.

3. The mobile robot of claim 1 , wherein the at least the piece of blur information comprises a curved form of blur information.

4. The mobile robot of claim 1 , wherein the position detector is configured to
estimate motion blur of the patch using a Gaussian distribution or a Poisson distribution as the objective function.

5. The mobile robot of claim 1 , wherein the position detector is configured to estimate motion blur of the patch using the objective function to which a normalization term is added.

6. The mobile robot of claim 1 , wherein the position detector is configured to determine matching relations between patches of previous and current images captured by the camera based on the patches from which motion blur is eliminated.

7. The mobile robot of claim 6 , wherein the position detector is configured to track a position of the main body using the least square method based on the matching relations.

8. The mobile robot of claim 1 , further comprising:
a storage configured to store an image captured by the camera and the patch created in the image.

9. A method for controlling a mobile robot, the method comprising:
capturing an image of a surrounding of a mobile robot;
creating a patch in the captured image;
estimating motion blur in the created patch; and
tracking a position of the mobile robot based on the created patch from which the estimated motion blur is eliminated,
wherein the creating of the patch in the captured image comprises
obtaining an aspect of the motion blur in the captured image based on the captured image and movement information of the mobile robot,
detecting a position of features in the captured image based on the obtained aspect of the motion blur and
creating the patch based on the position of features, and

wherein the estimating of the motion blur in the created patch comprises
creating a plurality of pieces of blur information estimated for the patch,
selecting the motion blur of the patch from the plurality of piece of blur information based on an objective function and
estimating the motion blur in the created patch based on the selected motion blur.

10. The method of claim 9 ,
wherein the estimating the motion blur in the created patch comprises:
creating the plurality of piece of blur information based on at least one of three dimensional (3D) feature coordinates, movement information of the mobile robot, and a capturing time interval.

11. The method of claim 10 , wherein the at least the piece of blur information comprises a curved form of motion blur.

12. The method of claim 9 , wherein the estimating the motion blur in the created patch comprises:
estimating the motion blur of the patch using a Gaussian distribution or a Poisson distribution as the objective function.

13. The method of claim 9 , wherein the estimating the motion blur in the created patch comprises:
estimating the motion blur of the patch using the objective function to which a normalization term is added.

14. The method of claim 9 , wherein tracking a position of the mobile robot based on the patch from which the estimated motion blur is eliminated comprises:
determining matching relations between patches of previous and current images captured, based on the patches from which the motion blur is eliminated, and
tracking a position of the mobile robot using a least square method based on the determined matching relations.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Kim Bo Young
• Kwak No San
• Roh Kyung Shik
• Park Soon Yong
• Yoon Suk June
• Lee So Hee
• Choi Min Yong

Classifications

• G06T2207/10028

  Range image; Depth image; 3D point clouds · CPC title

• G06T2207/30252

  Vehicle exterior; Vicinity of vehicle · CPC title

• G06T2207/30241

  Trajectory · CPC title

• G06K9/00664

  Physics · mapped topic

• Y10S901/01

  Mobile robot · CPC title