KR20170106274A - Robot cleaner and controlling method of the same - Google Patents

Abstract

A robot cleaner and a control method of the robot cleaner are disclosed. The present invention relates to an image forming apparatus which prevents overlapping cleaning by recognizing its own position through an absolute position recognizing unit when performing cleaning again after a forced termination of cleaning for any reason during execution of cleaning, The position recognition error of the recognition unit is improved and cleaning is performed by using the similarity degree of the image detected with the image detection unit and the image of the cleaning region, thereby improving the efficiency and stability of the system and improving the user's convenience.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to a robot cleaner,

BACKGROUND OF THE INVENTION 1. Field of the Invention [0002] The present invention relates to a robot cleaner, and more particularly, to a robot cleaner for accurately recognizing its own position using an image detection unit such as an upper camera and a control method thereof.

In general, robots have been developed for industrial use and have been part of factory automation. In recent years, medical robots, aerospace robots, and the like have been developed, and household robots that can be used in ordinary homes are being developed.

A representative example of the domestic robot is a robot cleaner, which is a type of household appliance that sucks and cleanes dust or foreign matter around the robot while traveling in a certain area by itself. Such a robot cleaner is generally equipped with a rechargeable battery and has an obstacle sensor capable of avoiding obstacles during traveling, so that it can run and clean by itself.

In order to clean all the areas while the robot cleaner runs on its own, a cleaning map should be created and a cleaning area such as a cleaned area and a cleaning area should be determined. The area determination capability is generally determined by the accurate control performance of the robot cleaner.

The robot cleaner according to the related art is not cleaned by unintentional cleaning due to mechanical limitations such as wheel dropping or user intervention such as replacing dust bin or mopping, There is a problem that the position of the user is not recognized. Most of the users generally remove the cause of the cleaning end and then place the robot cleaner at an arbitrary position and then press the clean start button. In this case, the robot cleaner equipped with the relative position recognition sensor is difficult to recognize the current position information, It is impossible to distinguish between the pre-cleaning area and the non-cleaning area. Therefore, the robot cleaner according to the related art has a problem in that it conducts redundant cleaning for the pre-cleaning area or performs cleaning again from the beginning based on the current position.

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems, and it is an object of the present invention to provide a robot cleaner for avoiding redundant cleaning by recognizing its own position through an absolute position recognizing unit when cleaning is forcibly terminated, And a control method therefor.

The present invention relates to a robot cleaner for improving the position recognition error of a relative position recognition unit by using an image detection unit and performing efficient cleaning using the similarity of the image of the cleaning area and the image detected by the image detection unit, There are other purposes in providing a control method.

In order to accomplish the above objects, the present invention provides a robot cleaner comprising: a detection unit that detects structure information in a cleaning area; a storage unit that stores the structure information; And a control unit for comparing the structure information stored in the storage unit beforehand and recognizing the absolute position based on the comparison result and performing cleaning on the cleaning area.

In the robot cleaner according to the present invention, the control unit determines whether the cleaning area is a pre-cleaning area based on the comparison result.

In the robot cleaner according to the present invention, the detection unit may be an image detection unit for detecting image information by photographing upward or forward in the cleaning area, and the storage unit stores the image information .

In the robot cleaner according to the present invention, the control unit extracts one or more feature points from the image information detected by the image detection unit and the image information stored in the storage unit. Here, the minutiae include minutia information composed of a position, a direction, and a descriptor in the image information, and the descriptor indicates extraction information of the minutiae.

Further, the control unit calculates the similarity between the minutiae points by using the minutia information, and recognizes the absolute position using the similarity.

According to an aspect of the present invention, there is provided a robot cleaner including an image detection unit for detecting a video image by detecting a video image, a storage unit for storing the video image, A feature point extraction module for extracting feature points from the image information stored in the storage unit and the image information detected by the image detection unit after the resume of cleaning, a similarity calculation module for calculating the similarity between the feature points, An area judging module for judging whether the cleaning area of the position recognized by the position recognizing module is a non-cleaning area; And a control module for performing cleaning on the area.

In the robot cleaner according to the present invention, the minutiae include minutia information constituted by a position, a direction, and a descriptor in the image information, and the descriptor represents extraction information of the minutiae.

In order to accomplish the above objects, a method of controlling a robot cleaner according to the present invention includes a first detecting step of detecting structure information in a cleaning area during cleaning, a storing step of storing the structure information detected in the first detecting step, A second detecting step of detecting structure information in the cleaning area after cleaning is resumed; a comparison step of comparing structure information detected in the second detecting step with the structure information stored in the storing step; A position recognition step of recognizing an absolute position of the robot cleaner based on a comparison result of the comparison step; and a cleaning step of performing cleaning on the cleaning area based on the recognition result of the position recognition step.

The control method of the robot cleaner according to the present invention further comprises a region determining step of determining whether the cleaning area is a pre-cleaning area based on the comparison result of the comparing step.

In the method of controlling a robot cleaner according to the present invention, the structure information is image information photographed upward or forward in the cleaning area.

The control method of the robot cleaner according to the present invention further comprises a feature point extracting step of extracting at least one feature point from the image information detected in the second detecting step and the image information stored in the storing step. Here, the minutiae include minutia information composed of a position, a direction, and a descriptor in the image information, and the descriptor indicates extraction information of the minutiae.

The control method of the robot cleaner according to the present invention further includes a similarity calculating step of calculating the similarities between the minutiae points using the minutia information, and the comparing step compares the similarities with each other.

The control method of the robot cleaner according to the present invention is characterized in that if the similarity degree is smaller than a certain degree of similarity as a result of the comparison, the robot cleaner moves to another cleaning area and performs operations after the second detection step again.

The robot cleaner and the robot cleaner control method according to the present invention recognize the self position through the absolute position recognition unit when cleaning is performed after the cleaning is forcibly terminated for any reason during the cleaning, do.

The present invention improves the position recognition error of the relative position recognition unit using an image detection unit and performs cleaning using the similarity of the image of the cleaning area and the image detected through the image detection unit, And the convenience of the user is increased.

FIG. 1 and FIG. 2 are block diagrams schematically showing a configuration of a robot cleaner according to embodiments of the present invention; FIG.
3 is a perspective view showing the appearance of a robot cleaner according to the present invention;
4 is a view for explaining an operation of extracting feature points by the robot cleaner according to the present invention;
5 is a block diagram schematically showing the configuration of a robot cleaner according to another embodiment of the present invention;
6 to 8 are flowcharts schematically illustrating a method of controlling a robot cleaner according to embodiments of the present invention.

DETAILED DESCRIPTION OF THE INVENTION Hereinafter, a robot cleaner and a control method thereof according to the present invention will be described in detail with reference to the accompanying drawings.

Referring to FIG. 1, a robot cleaner according to the present invention includes a detection unit 100 for detecting structure information in a cleaning area, a storage unit 300 for storing the structure information, a detection unit 100 And a control unit (200) for comparing the detected structure information with the structure information stored in the storage unit before stopping the cleaning and recognizing the absolute position based on the comparison result and performing cleaning on the cleaning area do.

The structure information may be an upper region including a ceiling or a straight line or a picture extracted by a fluorescent lamp, an interior structure, a wall, a ceiling or the like existing in front of the ceiling. The control unit 200 compares the detected structure information with the structure information stored in the storage unit before stopping the cleaning to determine whether the cleaning area is the pre-cleaning area.

The detection unit 100 detects information on the surrounding structure in the cleaning area during cleaning or while driving, and the storage unit 300 stores the structure information. Here, the storage unit 300 may store the structure information in the cleaning area in the form of a database as well as the detected structure information. Then, when the cleaning operation is interrupted by the user or the like or by another cause and then restarted, the detection unit 100 again detects the structure information at the position where the robot cleaner is placed. At this time, the control unit 200 compares the structure information detected by the detection unit 100 and the structure information stored in the storage unit 300, and recognizes the position of the robot cleaner using the comparison result. The position at this time is not a relative position due to the movement of the robot cleaner by a distance sensor, for example, a gyro sensor, an encoder, etc., but a cleaning area of any of the cleaning areas, Is an absolute position. The storage unit 300 stores information about cleaning such as a cleaning route, a cleaning pattern, and cleaning area information in advance, and the control unit 200 uses the cleaning information stored in the storage unit 300, It is determined whether the cleaning area at the recognized position is a non-cleaning area or a pre-cleaning area.

Referring to FIG. 2, the detection unit 100 is an image detection unit 110 for detecting image information by photographing upward or forward in the cleaning area, and the storage unit 300 stores the image information .

The image detecting unit 110 is an upper camera installed on the upper part of the robot cleaner and detecting an upper image by photographing the upper part, or a front camera detecting a forward image by photographing anterior part. In addition, the image detecting unit 110 may include a lens. The lens may include a lens having a wide angle of view such that all areas of the upper side or the front side, for example, the entire area of the ceiling, For example, it is better to use an angle of view of 160 degrees or higher.

Here, the control unit 200 extracts one or more feature points from the image information detected by the image detection unit 110 and the image information stored in the storage unit 300. The control unit (200) extracts one or more feature points having coordinate information for each of the plurality of images. Referring to FIG. 4, in the image detected through the image detecting unit 110, the feature points are natural markings such as a fluorescent lamp, an interior structure, or the like existing in an upper region including a ceiling or a front region. Here, the minutiae point includes minutia information constituted by a position, a direction, and a descriptor in the image, and the descriptor indicates extraction information of the minutiae. The descriptor represents a feature of the feature point, and becomes a matrix of a fixed size including the feature point in the image. The descriptor includes the shape or shape of the structure at the position extracted from the image.

Further, the control unit 200 calculates the similarity degree between the minutiae points by using the minutia information, and recognizes the absolute position using the similarity degree. At this time, the control unit 200 matches feature points using image information stored in the storage unit 300, that is, image information of the image detected through the image detection unit 110, The position of the robot cleaner is recognized. There is a distance in the minutiae space that determines the degree of similarity between the minutiae. That is, if the distance is short, the feature points have a large degree of similarity, and if the distance is long, the similarity degree of the feature points becomes small. The feature point may be expressed, for example, as (x1 _{, i} , y1 _{, i} ), (x2 _{, i} , y2 _{, i} ). Of course, the minutiae can be displayed as points on a three-dimensional coordinate system. At this time, the distance? Between the minutiae points can be expressed by the following equation (1).

[Equation 1]

For example, when the distance is less than a predetermined distance using Equation 1, the control unit 200 determines the same minutiae to match.

FIG. 3 is a perspective view showing the outer appearance of the robot cleaner according to the present invention, and FIG. 5 is a block diagram showing the configuration thereof.

3 and 5, the robot cleaner according to the present invention includes an image detection unit 110 for photographing a cleaning area to detect image information, a storage unit for storing the image information, the pre-cleaning area and the non- A feature point extraction module 210 for extracting feature points from the image information stored in the storage unit 300 and the image information detected by the image detection unit 110 after the resumption of cleaning, A position recognition module 230 for recognizing a position of the robot cleaner by comparing the similarities with each other, and a cleaning area for a position recognized by the position recognition module, And a control module 250 for performing cleaning on the uncleaned area based on the determination result of the area determination module, .

The feature point extraction module 210, the similarity calculation module 220, the position recognition module 230, the region determination module 240, and the control module 250 may be configured in different units , A control unit 200 such as another microprocessor.

The image detecting unit 110 is an upper camera installed on the upper part of the robot cleaner and detecting an upper image by photographing the upper part, or a front camera detecting a forward image by photographing anterior part. In addition, the image detecting unit 110 may include a lens. The lens may include a lens having a wide angle of view such that all areas of the upper side or the front side, for example, the entire area of the ceiling, For example, it is better to use an angle of view of 160 degrees or higher.

The feature point extraction module 210 extracts one or more feature points from the image information detected by the image detection unit 110 and the image information stored in the storage unit 300. The feature point extraction module 210 extracts one or more feature points having coordinate information for each of the plurality of images. Referring to FIG. 4, in the image detected through the image detecting unit 110, the feature points are natural markings such as a fluorescent lamp, an interior structure, or the like existing in an upper region including a ceiling or a front region. Here, the minutiae point includes minutia information constituted by a position, a direction, and a descriptor in the image, and the descriptor indicates extraction information of the minutiae. The descriptor represents a feature of the feature point, and becomes a matrix of a fixed size including the feature point in the image. The descriptor includes the shape or shape of the structure at the position extracted from the image.

Also, the similarity calculation module 220 calculates a similarity between minutiae points using the minutia information, and the position recognition module 230 recognizes the absolute position using the similarity. At this time, the similarity calculation module 220 matches feature points using image information stored in the storage unit 300, that is, images, minutiae points, and the like, and image information of an image detected through the image detection unit 110 , And the degree of similarity is calculated through the feature point matching. There is a distance in the minutiae space that determines the degree of similarity between the minutiae. That is, if the distance is short, the feature points have a large degree of similarity, and if the distance is long, the similarity degree of the feature points becomes small.

The image detection unit 110 detects surrounding image information in the cleaning area during cleaning or while driving, and the storage unit 300 stores the image information. Here, the storage unit 300 may store the detected image information as well as image information in the cleaning area in the form of a database. Then, if the cleaning operation is interrupted by the user or the like or is restarted again due to another cause, the image detecting unit 110 detects the image information at the position where the robot cleaner is placed again. At this time, the position recognition module 230 recognizes the position of the robot cleaner using the result of comparing the image information detected by the image detection unit 110 and the image information stored in the storage unit 300. [ The position at this time is an absolute position indicating which one of the cleaning areas, or the various rooms, among the cleaning areas, not by the relative position due to the movement of the robot cleaner by the distance sensor, for example, the gyro sensor or the encoder. The area determination module 240 compares the detected image information with the image information stored in the storage unit before stopping the cleaning so that the absolute position of the robot cleaner recognized by the position recognition module 230 is compared with the pre- Or not. The storage unit 300 stores in advance information about cleaning such as a cleaning route, a cleaning pattern, and cleaning area information, and the area determination module 240 uses the information about the cleaning stored in the storage unit 300 And determines whether the cleaning area at the position recognized by the position recognition module 230 is a non-cleaning area or a pre-cleaning area, as described above.

In addition, the robot cleaner according to the present invention further includes a drive unit 500 for moving the robot cleaner by driving the wheels, and a distance sensor (not shown) connected to the wheel and measuring a travel distance. The drive unit 500 drives a predetermined wheel motor that rotates the plurality of wheels including a plurality of main wheels and at least one auxiliary wheel so that the robot cleaner moves. The robot cleaner according to the present invention detects the plurality of image information through the image detection unit 110 during traveling or cleaning through the drive unit 500. [ As the distance sensor, an encoder for detecting a speed connected to a wheel motor for driving wheels of the robot cleaner can be used. Instead, an acceleration sensor for recognizing the speed and the position, a gyro sensor for detecting the rotation speed of the robot cleaner Etc. may also be used.

5, the robot cleaner according to the present invention further includes an obstacle detection unit 600 for detecting an obstacle around the robot cleaner. The control module 250 generates an internal map based on the obstacle, A cleaning route or a traveling route is set based on the internal map. Here, the control module 250 modifies the cleaning path or the traveling path based on the position, and performs cleaning or running based on the modified cleaning path or the modified traveling path. The obstacle detection unit 600 detects an obstacle around the robot cleaner while traveling in a room such as a home or an office or during cleaning and displays obstacle information such as the presence or absence of the obstacle, ). As the obstacle detecting unit 600, an infrared sensor, an ultrasonic sensor, a RF sensor, a bumper, or the like can be used. In addition, the obstacle detecting unit 600 may include an ultrasonic sensor, a PSD (Positive Sensitive Device) sensor that can accurately calculate the distance using an infrared triangulation method, or a laser that is reflected and returned after emitting a laser The laser range finder (LRF) measures the distance to the wall, and the shape and position of the wall can be detected based on the measured distance. The obstacle information detected through the obstacle detection unit 600 may be stored in the storage unit 300.

The control module 250 generates an internal map based on the obstacle detected by the obstacle detection unit 600, and sets a cleaning route or a traveling route based on the internal map.

The storage unit 300 may further store obstacle information detected during traveling or cleaning. The storage unit 300 may store information on a plurality of images detected through the image detection unit 110 and feature points extracted through the feature extraction module 210. [ The storage unit 300 is preferably a non-volatile memory. Here, the non-volatile memory (NVM) is a storage device that keeps stored information even when power is not supplied. The storage device includes a ROM, a flash memory, a magnetic computer storage device A hard disk, a diskette drive, and a magnetic tape), an optical disk drive, and the like, and includes a magnetic RAM, a PRAM, and the like. In addition, the storage unit 300 may further store a movement record, a cleaning history, and the like of the robot cleaner in the cleaning area, and may further include a program for driving the robot cleaner.

In addition, the control module 250 may correct the cleaning route or the traveling route using the verified position using the matching result of the minutiae or the moving distance, and may further modify the cleaning route or the traveling route based on the corrected cleaning route or the corrected traveling route Perform cleaning or running.

The robot cleaner may further include a power source unit 400 having a power supply unit that can be charged and supplies power to the robot cleaner. The power source unit 400 may include a robot cleaner, And supplies power to the robot cleaner when the power supply means, that is, the battery remaining amount, is insufficient.

The robot cleaner further comprises an input unit 700 for inputting a direct control command or receiving an obstacle information or a command for outputting information stored in the storage unit 300. The input unit 700 is configured to input information such as position information of the obstacle, position of the robot cleaner, information on the minutiae, an internal map, a cleaning route, a cleaning area, A setting button for inputting a command, a reset button for inputting a command to be reset, a delete button, a cleaning start button, and a stop button.

The robot cleaner may further include an output unit 800 for displaying information such as image information, structure information, and minutiae stored in the storage unit 300, obstacle information, or the internal map. The output unit 800 may further display status information such as the current status of each unit constituting the robot cleaner and the current cleaning status. The output unit 800 may include a light emitting diode (LED), a liquid crystal display (LCD), a plasma display panel, an organic light emitting diode (OLED) It may be formed of any one of the elements.

A user or the like can input a control command through the input unit 700 to perform a cleaning operation by selecting a cleaning area or a room requiring cleaning from an internal map displayed on the output unit 800, A control command for setting a cleaning order and the like can be input. The input unit 700 and the output unit 800 may have the form of a touch screen capable of both inputting and outputting.

6 is a view for explaining an operation of the robot cleaner according to the present invention for recognizing an absolute position using image information and performing cleaning according to the absolute position.

Referring to FIG. 6, a method for controlling a robot cleaner according to the present invention includes steps S110 and S120 of photographing the cleaning area while moving a cleaning area to detect image information, (S140) of calculating a similarity between the minutiae points, S150 and S160 of recognizing the position of the robot cleaner by comparing the similarities with each other, And a step (S170) of determining whether the cleaning area of the recognized position is an uncleaned area in step S160 and performing cleaning on the uncleaned area based on the determination result (S170).

The robot cleaner is installed on the upper side and detects a plurality of pieces of image information through an image detecting unit such as an up camera for photographing an upside and an upside camera for photographing an upside and detecting a forward image S120). Then, the robot cleaner extracts feature points from a plurality of pieces of image information from a natural marker such as a fluorescent lamp or an interior structure existing in an upper region including a ceiling or a front region (S130), calculates a distance between the feature points (S140), and the feature points are matched based on the similarity (S150). Here, the distance is not an actual distance but a distance in a minutia point space. At this time, if the distance is short, the feature points have a large degree of similarity, and if the distance is long, the similarity degree of the feature points becomes small. Here, the minutiae are constituted by a position, a direction, and a descriptor in the image, and the descriptor indicates extraction information of the minutiae. In addition, the robot cleaner recognizes the absolute position of the robot using the matching result (S160), determines whether the recognized absolute position cleaning area is a preliminary cleaning area, and performs cleaning (S170). That is, the robot cleaner preliminarily stores information on cleaning such as a cleaning route, a cleaning pattern, and cleaning area information, and determines whether the cleaning area at the recognized position is a non-cleaning area or a pre-cleaning area. As a result, the robot cleaner according to the present invention unintentionally terminates the cleaning by unintentional user intervention such as mechanical limit such as wheel drop, replacement of the dust bin or mop during cleaning, unlike the prior art, Even after the cleaning is performed, the cleaning efficiency is increased by performing redundant cleaning or performing cleaning again from the beginning, and performing cleaning around the uncleaned area.

Referring to FIG. 7, a method of controlling a robot cleaner according to the present invention includes a first detecting step (S210) of detecting structure information in a cleaning area during cleaning, a step of detecting the structure information detected in the first detecting step A second detection step (S250) of detecting structure information in the cleaning area after cleaning is resumed, a structure information detected in the second detection step, and a structure information stored in the structure A step S260 of comparing the information of the robot cleaner with a comparison result of the robot cleaner, a step S260 of recognizing the absolute position of the robot cleaner based on the comparison result of the comparing step S270, And a cleaning execution step (S280) for performing cleaning for the cleaning operation.

The control method of the robot cleaner according to the present invention further comprises a region determining step (not shown) for determining whether the cleaning area is a pre-cleaning area based on the comparison result of the comparing step.

The robot cleaner detects the surrounding structure information in the cleaning area during the cleaning or running (S210), and stores the structure information (S220). Herein, the robot cleaner may store not only the detected structure information but also the structure information in the cleaning area in the form of a database. Then, if the cleaning operation is interrupted by a user or the like or by another cause (S230, S240), the robot cleaner detects the structure information at the current position again (S250). Further, the robot cleaner compares the detected structure information with the stored structure information (S260), and recognizes its own position using the comparison result (S270). The position at this time is an absolute position indicating which one of the cleaning areas, or the various rooms, among the cleaning areas, not the relative position by the movement of the robot cleaner by the distance sensor, e.g., the gyro sensor or the encoder. In addition, the robot cleaner stores information about cleaning such as a cleaning route, a cleaning pattern, and cleaning area information in advance, and determines whether the cleaning area at the recognized position is a non-cleaning area or a pre-cleaning area Next, cleaning is performed (S280).

Referring to FIG. 8, a method for controlling a robot cleaner according to the present invention includes a first detecting step (S310) of detecting image information in a cleaning area during cleaning, a step of detecting the image information detected in the first detecting step (S360) for detecting the image information in the cleaning area after the cleaning is resumed; a second detection step (S360) of detecting the image information in the cleaning area after the cleaning is resumed; A similarity calculation step S380 for calculating the similarities between the minutiae points using the minutia information, a comparing step S390 for comparing the similarities with each other, A position recognition step (S400) of recognizing an absolute position of the robot cleaner based on a comparison result of the comparing step; and a step of determining whether the cleaning area is a preliminary cleaning area based on a comparison result of the comparing step And the area determining step (S410), is configured to include a cleaning step performed (S420) to perform the cleaning with respect to the cleaning area. If the similarity is less than a certain degree of similarity or the recognized position is a preliminary cleaning area, the operation moves to another cleaning area and the operation after the second detection is performed again at step S430. The construction of the apparatus will be described with reference to Figs. 2 to 5. Fig.

The robot cleaner detects peripheral image information in the cleaning area during the cleaning or running (S310, S320), and stores the image information (S330). Then, if the cleaning operation is interrupted by a user or the like or is restarted again (S340, S350), the image information is detected at the reset position (S360). At this time, the robot cleaner compares the detected image information with stored image information, and recognizes the position of the robot cleaner using the comparison result (S370 to S400). The position at this time is an absolute position indicating which one of the cleaning areas, or the various rooms, among the cleaning areas, not the relative position by the movement of the robot cleaner by the distance sensor, e.g., the gyro sensor or the encoder.

The robot cleaner extracts one or more minutiae from the detected image information and stored image information (S370). That is, the robot cleaner extracts one or more feature points having coordinate information for each of the plurality of images. Referring to FIG. 4, the minutiae are natural markers such as a fluorescent lamp, an interior structure, etc. existing in an upper area including a ceiling or a front area. Here, the minutiae point includes minutia information constituted by a position, a direction, and a descriptor in the image, and the descriptor indicates extraction information of the minutiae. The descriptor represents a feature of the feature point, and becomes a matrix of a fixed size including the feature point in the image. The descriptor includes the shape or shape of the structure at the position extracted from the image.

Also, the robot cleaner calculates the similarity between the minutiae points using the minutia information (S380), and recognizes the absolute position using the similarity (S390, S400). There is a distance in the minutiae space that determines the degree of similarity between the minutiae. That is, if the distance is short, the feature points have a large degree of similarity, and if the distance is long, the similarity degree of the feature points becomes small. The feature point may be expressed, for example, as (x1 _{, i} , y1 _{, i} ), (x2 _{, i} , y2 _{, i} ). Of course, the minutiae can be displayed as points on a three-dimensional coordinate system. At this time, the distance? Between the minutiae points can be expressed by the following equation (2).

&Quot; (2) "

For example, if the distance is less than a predetermined distance using Equation (2), the robotic cleaner determines that the similarity is equal to or greater than a certain degree of similarity, and matches the same by determining the same minutia. The robot cleaner recognizes the position of the robot cleaner using the matching result (S400). In addition, the robot cleaner compares the detected image information with the image information stored in the storage unit before stopping the cleaning, and determines whether the cleaned area of the recognized absolute position is a pre-cleaning area (S410). The robot cleaner preliminarily stores information about cleaning such as a cleaning route, a cleaning pattern, and cleaning area information, and determines whether the cleaning area at the recognized position is a non-cleaning area or a pre-cleaning area using the information about the cleaning Next, cleaning is performed around the uncleaned area (S430). At this time, if the similarity degree is smaller than a certain degree of similarity, the robot cleaner does not match the feature points, or if the recognized cleaning area is the basic cleaning area, the robot cleaner moves to another cleaning area and detects the image information again.

As described above, in the robot cleaner and the robot cleaner control method according to the present invention, when the cleaning is forcibly terminated for any reason during the cleaning operation and the cleaning is performed again, the self-position is recognized Thereby improving the position recognition error of the relative position recognizing unit by using the image detecting unit and performing the cleaning by using the similarity of the image with respect to the image detected through the image detecting unit and the image of the cleaning area, Thereby improving the efficiency and stability of the user and increasing the convenience of the user.

100: detection unit 110: image detection unit
200: control unit 300: storage unit
210: feature point extraction module 220: similarity calculation module
230: position recognition module 240: area determination module
250: control module 300: storage unit
400: power supply unit 500: drive unit
600: obstacle detection unit 700: input unit
800: Output unit

Claims (14)

A driving unit for driving the robot cleaner in a cleaning area;
A detection unit that detects structure information in the cleaning area when the drive unit is running;
A storage unit for storing first structure information in the form of a database formed in advance and second structure information detected when the drive unit is running; And
Wherein when the cleaning of the robot cleaner is interrupted by the user and then resumed, the structure information detected by the detection unit at a position where the robot cleaner is reset,
And a control unit which compares at least one of the first and second structure information stored in the storage unit before stopping the cleaning and recognizes an absolute position based on the comparison result and performs cleaning on the cleaning area,
The structure information includes:
And an image related to an object existing above or in front of the robot cleaner. The apparatus according to claim 1,
And determines whether the cleaning area is a pre-cleaning area based on the comparison result. 3. The method according to claim 1 or 2,
Wherein the detection unit is an image detection unit that photographs upward or forward in the cleaning area to detect image information,
Wherein the storage unit stores the image information. 4. The apparatus according to claim 3,
And extracts one or more feature points from the image information detected by the image detection unit and the image information stored in the storage unit. 5. The method of claim 4,
Wherein the feature point includes minutia information constituted by a position, a direction, and a descriptor in the image information,
Wherein the descriptor indicates extraction information of the minutiae. 6. The apparatus according to claim 5,
Calculates the similarity between the minutiae points by using the minutia information, and recognizes the absolute position using the similarity. A driving unit for driving the robot cleaner in a cleaning area;
An image detecting unit for photographing a cleaning area and detecting image information when the drive unit is running;
A storage unit for storing first image information of a preformed database type, second image information detected when the drive unit is running, and a pre-cleaning area and a non-cleaning area;
Wherein when the cleaning of the robot cleaner is interrupted by the user and then resumed, the image detected by the image detection unit at a position where the robot cleaner is reset and the first and second images A feature point extraction module for extracting feature points from at least one of the information;
A similarity calculation module for calculating a similarity between the minutiae points;
A position recognition module for recognizing the position of the robot cleaner by comparing the degrees of similarity;
An area determining module that determines whether the cleaning area of the location recognized by the location recognition module is a non-cleaning area; And
And a control module for performing cleaning on the uncleaned area based on the determination result of the area determination module. 8. The method of claim 7,
Wherein the feature point includes minutia information constituted by a position, a direction, and a descriptor in the image information,
Wherein the descriptor indicates extraction information of the minutiae. A storage step of storing first structure information in the form of a database in advance associated with structure information in a cleaning area before performing cleaning;
A first detecting step of detecting structure information in a cleaning area during cleaning;
A storing step of storing second structure information detected in the first detecting step;
A second detection step of detecting structure information in the cleaning area at a position where the robot cleaner is placed again when the cleaning of the robot cleaner is interrupted by the user and then resumed;
A comparison step of comparing at least one of the structure information detected in the second detecting step and the first and second structure information;
A position recognition step of recognizing an absolute position of the robot cleaner based on a comparison result of the comparison step; And
And a cleaning step of performing cleaning on the cleaning area based on the recognition result of the position recognition step,
The structure information includes:
And an image related to an object existing above or in front of the robot cleaner. 10. The method of claim 9,
And a region determining step of determining whether the cleaning area is a pre-cleaning area based on a comparison result of the comparing step. 10. The method of claim 9,
And a feature point extracting step of extracting at least one feature point from the image information detected in the second detecting step and the image information stored in the storing step. 12. The method of claim 11,
Wherein the feature point includes minutia information constituted by a position, a direction, and a descriptor in the image information,
Wherein the descriptor indicates extraction information of the minutiae point. 13. The method of claim 12,
And calculating a degree of similarity between the minutiae points using the minutia information,
Wherein the comparing step compares the degrees of similarity with each other. 14. The method of claim 13,
Wherein if the degree of similarity is smaller than a certain degree of similarity, the control unit moves to another cleaning area and performs the operation after the second detection step again.

Images