Robot cleaner and method of controlling the same

• US 10,782,702 B2
• Filed: 01/31/2018
• Issued: 09/22/2020
• Est. Priority Date: 02/03/2017
• Status: Active Grant

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Akazawa, Yoshiaki
• Primary Examiner(s): Kleinman, Lail A
• Application Number:
  US15/885,575
• Publication Number:
  US 20180224862A1
• Time in Patent Office: 965 Days
• Field of Search: None
• CPC Class Codes: A47L 11/4011 Regulation of the cleaning machine by electric means; Control systems and remote control systems therefor
• CPC Class Codes: A47L 11/4061 Steering means; Means for avoiding obstacles; Details related to the place where the driver is accommodated
• CPC Class Codes: A47L 2201/04 Automatic control of the travelling movement; Automatic obstacle detection
• CPC Class Codes: A47L 9/2805 Parameters or conditions being sensed
• CPC Class Codes: A47L 9/2852 Elements for displacement of the vacuum cleaner or the accessories therefor, e.g. wheels, casters or nozzles
• CPC Class Codes: B25J 11/0085 Cleaning
• CPC Class Codes: B25J 5/007 mounted on wheels
• CPC Class Codes: B25J 9/00 Programme-controlled manipulators
• CPC Class Codes: B25J 9/0003 Home robots, i.e. small robots for domestic use
• CPC Class Codes: B25J 9/1666 Avoiding collision or forbidden zones
• CPC Class Codes: B25J 9/1697 Vision controlled systems
• CPC Class Codes: G05D 1/0214 in accordance with safety or protection criteria, e.g. avoiding hazardous areas monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13
• CPC Class Codes: G05D 1/0246 using a video camera in combination with image processing means
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30
• CPC Class Codes: G06T 2207/10048 Infrared image
• CPC Class Codes: G06T 2207/30204 Marker
• CPC Class Codes: G06T 7/74 involving reference images or patches
• CPC Class Codes: G06V 10/245 by locating a pattern; Special marks for positioning
• CPC Class Codes: G06V 20/10 Terrestrial scenes scenes under surveillance with static cameras G06V20/52; scenes perceived from the exterior of a vehicle G06V20/56; scenes perceived from the interior of a vehicle G06V20/59
• CPC Class Codes: G06V 40/107 Static hand or arm
• CPC Class Codes: Y10S 901/01 : Mobile robot
• CPC Class Codes: Y10S 901/47 : Optical

Abstract

Disclosed is a mobile robot provided to randomly store a landmark object and to set a no-entering region on the basis of a plurality of landmark objects and a method of controlling the mobile robot. The mobile robot includes a body, a moving portion configured to move the body, a memory, a collector configured to collect information on an object near the mobile robot, and a processor configured to compare the object information collected by the collector with the object information of the landmark candidate object stored in the memory and recognize a location of a landmark object which is an objective of a landmark on the basis of a result of comparison. When locations of at least two landmark objects are specified, the processor sets a no-entering region between the landmark objects and controls the moving portion to prevent the mobile robot from entering the no-entering region.

Claims

1. A mobile robot comprising:

a body;

a driving system configured to move the body;

a memory configured to store object information of a plurality of landmark candidate objects;

a sensor configured to collect object information on an object near the mobile robot; and

at least one processor configured to;

compare the object information collected by the sensor with the object information of the landmark candidate object stored in the memory,

recognize a location of a landmark object based on a result of comparison,

wherein when locations of two landmark objects are recognized, the at least one processor is further configured to;

set a no-entering region between the two landmark objects, and

control the driving system to prevent the mobile robot from entering the no-entering region,

wherein when the landmark candidate object is asymmetrical, the at least one processor is further configured to;

control the sensor to collect object information of different aspects of the landmark candidate object in a circumferential direction of the landmark candidate object, and

store the object information of the landmark candidate object, which is asymmetrical, in the memory on a basis of the object information collected by the sensor.

2. The mobile robot of claim 1, wherein:

the memory is further configured to store at least one landmark group obtained by grouping the plurality of landmark candidate objects, and

the at least one processor is further configured to set the no-entering region between landmark objects that belong to a same landmark group of the landmark objects.

3. The mobile robot of claim 2, wherein when the location of the landmark object is recognized and another landmark candidate object is present in the landmark group to which the landmark object belongs, the sensor is further configured to collect the object information to detect whether the other landmark candidate object is present near the landmark object.

4. The mobile robot of claim 3, wherein the at least one processor is further configured to compare the object information collected by the sensor with the object information of the landmark candidate object stored in the memory, recognize a location of another landmark object that is an object of the other landmark candidate object on a basis of a result of comparison, and set the no-entering region between the landmark object and the other landmark object.

5. The mobile robot of claim 1, wherein the at least one processor is further configured to set the no-entering region, that connects the two landmark objects to each other, between the two landmark objects.

6. The mobile robot of claim 1, wherein the at least one processor is further configured to set the no-entering region with a certain area around each landmark object and the certain area is centered on each landmark object.

7. The mobile robot of claim 1, wherein the at least one processor, when it is confirmed that the landmark object is not present in the recognized location, is further configured to remove the no-entering region.

8. The mobile robot of claim 1, wherein the sensor comprises at least one of an image obtainer, that obtains image information with respect to an image capturing direction, or an infrared (IR) light receiver, that receives IR light emitted by the landmark object.

9. The mobile robot of claim 8, wherein:

the memory is further configured to store image information of the plurality of landmark candidate objects as the object information, and

the at least one processor is further configured to;

compare the image information collected by the image obtainer with the image information of the landmark candidate objects stored in the memory, and

recognize the location of the landmark object.

10. The mobile robot of claim 8, wherein the at least one processor is further configured to:

separate the landmark candidate object and background in the image information obtained by the image obtainer,

extract feature information of the landmark candidate object from the image information, and

store the feature information as the object information of the landmark candidate object in the memory.

11. The mobile robot of claim 10, wherein the at least one processor is further configured to:

store a background image obtained by the image obtainer when the landmark candidate object is not present in the image capturing direction, in the memory,

subtract the background image from an image, in which the landmark candidate object is present, obtained by the image obtainer, and

extract the feature information of the landmark candidate object, that is present in the image capturing direction, from image information of the image from which the background image is subtracted.

12. The mobile robot of claim 10, wherein the at least one processor is further configured to:

extract a local feature of the landmark candidate object from the feature information of the landmark candidate object, and

store the local feature in the memory as the object information of the landmark candidate object.

13. The mobile robot of claim 12, wherein:

the image obtainer is configured to sequentially obtain images in the image capturing direction for a certain period of time, and

the at least one processor is further configured to store a local feature, that accompanies sequential changes, among local features with respect to the image obtained by the image obtainer as the object information of the landmark candidate object in the memory.

14. The mobile robot of claim 13, wherein:

the memory is further configured to store features of a human body, and

the at least one processor is further configured to store some of the local features that accompany the sequential changes, except the features of the human body, as the object information of the landmark candidate object in the memory.

15. The mobile robot of claim 8, wherein the at least one processor, when the landmark candidate object in the image capturing direction obtained by the image obtainer is asymmetrical, is further configured to:

control the image obtainer to obtain a plurality of pieces of image information of the landmark candidate object from a plurality of angles in the circumferential direction of the landmark candidate, and

store the object information of the landmark candidate object in the memory on a basis of the obtained plurality of pieces of image information.

16. The mobile robot of claim 8, further comprising a transceiver that is configured to transmit a viewed image in the image capturing direction obtained by the image obtainer to a terminal device and receive landmark region information that indicates the landmark object in the viewed image from the terminal device.

17. The mobile robot of claim 16, wherein the at least one processor is further configured to store image features of the landmark object in the memory on a basis of the landmark region information, compare a feature information of the image information obtained by the image obtainer with the feature information of the landmark object stored in the memory, and recognize the landmark object on a basis of a result of comparing, by the at least one processor, the feature information and controls the driving system.

18. A method of controlling a mobile robot comprising a body, driving system configured to move the body, a memory configured to store object information of a plurality of landmark candidate objects, and a sensor configured to collect information on an object near the mobile robot, the method comprising:

collecting object information of different aspects of the landmark candidate object in a circumferential direction of the landmark candidate object when the landmark candidate object is asymmetrical;

storing the object information of the landmark candidate object, which is asymmetrical, in the memory on a basis of the object information collected by the sensor;

comparing the object information collected by the sensor with the object information of the landmark candidate object stored in the memory;

recognizing a location of a landmark object based on a result of comparison;

setting, when locations of two landmark objects are recognized, a no-entering region between the two landmark objects; and

controlling the driving system to prevent the mobile robot from entering the no-entering region.

19. The method of claim 18, wherein:

the memory stores at least one landmark group obtained by grouping the plurality of landmark candidate objects, and

the setting of the no-entering region between the two landmark objects when the locations of the two landmark objects are recognized comprises;

setting the no-entering region between the two landmark objects that belong to a same landmark group; and

removing the set no-entering region, when at least one processor has confirmed that the landmark object is not present in the recognized location.

20. A robot cleaner comprising:

a body;

a driving system configured to move the body;

a memory configured to store object information of a plurality of landmark candidate objects;

a sensor configured to collect information on an object near the robot cleaner; and

at least one processor configured to;

compare the object information collected by the sensor with the object information of the landmark candidate object stored in the memory,

recognize a location of a landmark object based on a result of comparison,

wherein when locations of two landmark objects are recognized, the at least one processor is further configured to;

set a no-entering region between the two landmark objects, and

control the driving system to allow the robot cleaner to clean without entering the no-entering region,

wherein, when the landmark candidate object is asymmetrical, the at least one processor is further configured to;

control the sensor to collect object information of different aspects of the landmark candidate object in a circumferential direction of the landmark candidate object; and

store the object information of the landmark candidate object, which is asymmetrical, in the memory on a basis of the information collected by the sensor.