IP Library › Granted Patent US 9,052,719
Granted Patent B2
US 9,052,719 · App. 13/281,018 · Granted Jun 9, 2015

Robot cleaner and controlling method of the same

Inventors: Seongsu Lee (Seoul, KR); Yiebin Kim (Seoul, KR); Suuk Choe (Seoul, KR); Donghoon Yi (Seoul, KR); Seungmin Baek (Seoul, KR)
Assignee: LG Electronics Inc.
G05D1/0246G05D1/0227G05D1/024G05D1/0242G05D1/0255G05D1/0257G05D1/027G05D1/0272G05D1/0274G05D2201/0203G05D2201/0215
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,052,719
App. No.
13/281,018
Granted
Jun 9, 2015
Kind
B2
Abstract

Disclosed are a robot cleaner and a method for controlling the same. The robot cleaner may prevent repeated executions of a cleaning operation by recognizing its position through an absolute position recognition unit, in a case that the cleaning operation is performed again after being forcibly stopped due to arbitrary causes. And, the robot cleaner may solve a position recognition error by a relative position recognition unit with using an image detection unit, and may effectively perform a cleaning operation based on a similarity between an image detected by the image detection unit and an image with respect to a cleaning region. This may improve the system efficiency and stability, and enhance a user's convenience.

Claims (36)

1. A robot cleaner, comprising:

an image detection unit to capture one or more images within a cleaning region;

a storage unit to store the captured images with respect to a plurality of cleaning regions; and

a control unit to compare the captured one or more images by the image detection unit after a stopped cleaning operation is restarted with the captured images with respect to the plurality of cleaning regions stored in the storage unit before the cleaning operation was stopped, and to initiate a cleaning operation with respect to the cleaning region by recognizing an absolute position of the robot cleaner based on the comparison after the robot cleaner has performed in sequence, the sequence comprising:

(a) stopping the cleaning operation when the cleaning operation is unexpectedly interrupted; and

(b) receiving a user's input to start cleaning when the robot cleaner is put on an arbitrary position, wherein the arbitrary position is not a position where the robot cleaner has been stopped from the cleaning operation,

wherein the control unit determines whether the cleaning region is a cleaned region or a non-cleaned region based the comparison, and then the control unit initiates the cleaning operation with respect to the non-cleaned region based on a result of the determination,

wherein the control unit calculates one or more similarities between the captured one or more images by the image detection unit and the one or more images stored in the storage unit and recognizes the absolute position of the robot cleaner based the calculated similarities,

wherein if the one or more similarities are less than a predetermined value, then the robot cleaner is moved to another cleaning region to initiate the cleaning operation, and

wherein the recognized absolute position is a position corresponding to one of the plurality of cleaning regions.

2. The robot cleaner of claim 1 , wherein the image detection unit captures one or more images at an upper side or a front side of the robot cleaner.

3. The robot cleaner of claim 1 , wherein the control unit comprises:

a feature point extraction module to extract one or more feature points from image information of the images stored in the storage unit before the cleaning operation was stopped and to extract one or more feature points from the image information of the one or images captured by the image detection unit after the stopped cleaning operation was restarted;

a similarity calculation module to calculate a similarity between the feature points; and

a position recognition module to recognize the absolute position of the robot cleaner based on the similarity calculation.

4. The robot cleaner of claim 3 , wherein the control unit further comprises:

a region determination module to determine whether a cleaning region on a position recognized by the position recognition module is a non-cleaned region; and

a control module to initiate a cleaning operation with respect to the non-cleaned region based on a determination of the region determination module.

5. The robot cleaner of claim 1 , wherein the control unit extracts one or more feature points from image information of the one or more images captured after the stopped cleaning operation was re-started, and wherein the control unit extracts one or more feature points from image information of the images stored in the storage unit before the cleaning operation was stopped.

6. The robot cleaner of claim 5 , wherein the feature points comprise feature point information including at least one of a position of the feature point, an orientation of the feature point and a descriptor of the feature point.

7. The robot cleaner of claim 6 , wherein when the control unit calculates one or more similarities, the control unit calculates between the one or more feature points from image information of the of the captured images after the stopped cleaning operation was restarted and the one or more feature points from image information stored in the storage unit before the cleaning operation was stopped, wherein the similarities are calculated based on the feature point information of the feature points.

8. A method for controlling a robot cleaner, the method comprising:

capturing one or more images within each of a plurality of cleaning regions by an image detection unit;

storing the captured images with respect to the plurality of cleaning regions;

stopping a cleaning operation when the cleaning operation is unexpectedly interrupted;

receiving a user's input to start cleaning when the robot cleaner is put on an arbitrary position, wherein the arbitrary position is not a position where the robot cleaner has been stopped from the cleaning operation;

capturing one or more images within the cleaning region;

comparing the captured one or more images by the image detection unit after the stopped cleaning operation is re-started with the stored images with respect to the plurality of cleaning regions;

calculating one or more similarities between the captured one or more images by the image detection unit after the stopped cleaning operation is re-started and the stored images;

recognizing an absolute position of the robot cleaner based the comparison, wherein the absolute position is a position corresponding to one of the plurality of cleaning regions;

determining whether the cleaning region is a cleaned region or a non-cleaned region based on the comparison; and

initiating the cleaning operation with respect to the non-cleaning region based on a result of the determination, wherein if the one or more similarities are less than a predetermined value, then the robot cleaner is moved to another cleaning region to initiate the cleaning operation.

9. The method of claim 8 , wherein the captured one images is captured at an upper side or a front side of the robot cleaner.

10. The method of claim 9 , further extracting one or more feature points from image information of the one or more images captured after the stopped cleaning operation is restarted and extracting one or more feature points from image information of the images stored before the cleaning operation was stopped.

11. The method of claim 10 , wherein the feature points comprise feature point information including at least one of a position of the feature point, an orientation of the feature point and a descriptor of the feature point.

12. The method of claim 11 , wherein the calculating one or more similarities is between the one or more feature points from the image information of the captured one or more images after the stopped cleaning operation was restarted and the one or more feature points from the stored image information, wherein the similarities are calculated based on the feature point information.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 26, 2011
From: LEE, SEONGSU; KIM, YIEBIN; CHOE, SUUK; YI, DONGHOON; BAEK, SEUNGMIN
To: LG ELECTRONICS INC.
Reel/Frame 027120/0781 →
Priority Claims (1)
KR 10-2010-0106246 · Oct 28, 2010 · national
Continuity (1)
Related Publication 20120109376A1 · May 3, 2012