KR102048363B1 - A moving-robot - Google Patents

Abstract

The mobile robot according to the present invention includes a traveling unit for moving the main body relative to the floor; A sensing unit which senses an image of an external upper object or a distance to an external upper object while moving; And a controller for dividing a part of the driving zone into a special zone according to whether a predetermined division condition is satisfied at each position based on the sensing information of the sensing unit.

Description

Mobile Robot {A MOVING-ROBOT}

The present invention relates to a sensing technology of a mobile robot.

Robots have been developed for industrial use and have been a part of factory automation. Recently, the application of robots has been further expanded, medical robots, aerospace robots, and the like have been developed, and home robots that can be used in general homes have also been made. Among these robots, a moving robot capable of traveling by magnetic force is called a mobile robot. A representative example of a mobile robot used at home is a robot cleaner.

The prior art (Korean Patent Laid-Open Publication No. 10-2010-0104581) discloses a technique of recognizing an unknown current position using an image captured by a camera at a current position.

In the prior art, a three-dimensional map is generated from feature points extracted from an image photographed in a driving zone, and three or more pairs of feature points matched with feature points in a three-dimensional map among feature points in an image captured at an unknown current location. Detect pairs. Then, using the two-dimensional coordinates of the matched three or more feature points in the image taken at the current position, the three-dimensional coordinates of the matched three or more feature points on the three-dimensional map, and the focal length information of the camera at the current position, A technique for calculating a distance from three or more matched feature points and recognizing a current position therefrom is disclosed in the prior art.

In addition, various techniques are known for mapping driving zones using an image at the current position, and various techniques are known for recognizing the current position on a stored map using the image at the current position.

Publication No. 10-2010-0104581 (published September 29, 2010)

delete

The first task of the present invention is to allow the mobile robot to recognize the difference in the properties of the zones, thereby opening up various possibilities in which the differences in the functions of the zones can occur. Through this, it is possible to provide a smarter mobile robot.

The second task of the present invention is to store the difference in the roughness of the area recognized during the pre-driving, to open the possibility to utilize it in the subsequent driving, and to further diversify the possibility of using the mobile robot of the user.

In the related art, when the mobile robot is located in the lower area of the furniture, the area is relatively dark, so that there is a limitation in mapping through the image or recognizing the current position. The third task of the present invention is to divide the lower area of the furniture into separate zones, to exclude the problematic mapping obstacles or current location recognition obstacles in advance, or to increase the efficiency of mapping or current location recognition.

In the lower region of the furniture, there are generally many obstacles such as support of the furniture and bulky foreign matters, which hinders the running of the mobile robot. The fourth task is to divide the lower area of the furniture into separate zones, to eliminate the problematic driving obstacles in advance, or to increase the driving efficiency.

The fifth task of the present invention is to facilitate separate management of the lower area of the furniture.

The sixth task of the present invention is to increase the efficiency of cleaning of areas that are not underneath the furniture.

The objects of the present invention are not limited to the above-mentioned objects, and other objects that are not mentioned will be clearly understood by those skilled in the art from the following description.

In order to solve the above problems, the mobile robot according to the solution of the present invention, a moving unit for moving the main body with respect to the floor, during sensing, sensing the image of the external upper object or sensing the distance to the external upper object And a control unit for dividing a part of the driving zone into a special zone. The controller divides a part of the driving zone into a special zone according to whether a predetermined division condition is satisfied at each position based on the sensing information of the sensing unit.

The predetermined division condition may be preset such that the lower section of the furniture is determined as the special zone.

The controller may determine that the one location belongs to the special zone when the classification condition is satisfied based on the detection information at one location.

The controller may control the escape of the special zone when the special zone is learned while moving.

The controller may be configured to manage a general zone other than the special zone among the driving zones in a predetermined general mode, and manage the special zone in a predetermined special mode different from the normal mode.

The controller may control the driving modes differently in the general zones other than the special zone among the special zones and the driving zones.

It may further include a cleaning unit for cleaning the floor. The control unit may control to clean any one of the special zones and the general zones other than the special zones of the driving zones before the other one or only one of the driving zones.

The classification condition may include a brightness condition in which the brightness representative value of the image detected at one location is smaller than the brightness reference value.

The brightness reference value may be set as a total brightness value of n images respectively detected at the latest n locations before the mobile robot arrives at the one location. N is a natural number of 2 or more.

The controller may be configured to map the driving zone through the image and to recognize the current location on the mapped map. The controller may be configured based on first brightness representative values respectively corresponding to points successfully recognized for location on the map, and second brightness representative values respectively corresponding to points failed to recognize location on the map. The brightness reference value may be changed.

The controller may classify one image into m regions and generate an m-dimensional brightness representative vector in which the brightness representative values of the m regions are numerical values of each dimension. The classification condition may include a brightness condition in which the brightness representative vector of the image detected at one location does not exceed a group of brightness reference vectors continuous in m-dimension in m-dimension. Where m is a natural number of two or more.

The controller may be configured to map the driving zone through the image and to recognize the current location on the mapped map. The controller may be configured based on the brightness representative vectors respectively corresponding to the points that successfully recognize the position on the map and the brightness representative vectors respectively corresponding to the points that fail to recognize the position on the map. You can change the group.

The controller may include: ⅰ first brightness representative vectors respectively corresponding to the points that successfully recognize the position on the map and ii second brightness representative vectors respectively corresponding to the points that fail to recognize the position on the map; The brightness reference vector group may be changed to be divided into a state in which a false is minimized based on the group.

The classification condition may include a feature point condition in which a feature point is not extracted from an image detected at a single location, and an image condition in which an image detected at one location does not match the p images detected at a recent p position or more than a predetermined reference value. , And 3 3D points generated from q images respectively detected at the latest q positions may include at least one of 3D point conditions in which an image detected at one position is not recognized above a predetermined reference value. Where p is a natural number and q is a natural number of two or more.

The classification condition may include a distance condition in which a distance value detected at one location is smaller than a distance reference value.

Part of the driving zone is divided into special zones, opening up the possibility of having different functions in different zones.

By allowing the lower section of the furniture to be considered the special zone, the following various advantageous possibilities can be provided. For example, there is an effect that can separately manage or clean the special zone where a relatively large amount of foreign matter. As another example, it is possible to shorten the mapping time of the general area, not the lower area of the furniture. As another example, the general area, which may be directly contacted by a person, may be cleaned more or more frequently, thereby providing a more comfortable environment for the user. As another example, by varying the driving mode in the special zone and the general zone, it is possible to set an efficient driving method according to different zones. As another example, the smarter mobile robot may be implemented in such a special zone that the object search function and / or the insect worm control function to be described later are exerted.

By controlling the escape movement of the mobile robot, the controller may shorten the mapping time of the general area. In addition, it is difficult to recognize the position on the map through the image due to the darkness, and by avoiding the special area, which is difficult to recognize the position through the driving part due to the slip due to relatively many foreign substances, the general area can be mapped first. In addition, there is an effect of recognizing the boundary portion of the special zone using the mapped general zone.

Through the brightness condition, the feature point condition, the image condition, the 3D point condition and / or the distance condition, the lower area of the furniture can be effectively divided into a special area.

In addition, the controller may determine whether the special area is in consideration of a factor according to a living environment by changing the brightness reference value or the brightness reference vector group according to the solving means.

1 is a perspective view showing a mobile robot 100 and a charging table 200 for charging a mobile robot according to an embodiment of the present invention.
2 is an elevation view of the mobile robot 100 of FIG. 1 as viewed from above.
3 is an elevation view of the mobile robot 100 of FIG. 1 viewed from the front.
4 is an elevation view of the mobile robot 100 of FIG. 1 as viewed from below.
FIG. 5 is a block diagram illustrating a control relationship between main components of the mobile robot 100 of FIG. 1.
6 is a flowchart illustrating a control method of a mobile robot according to an embodiment of the present invention.
7 is a flowchart illustrating a control method of a mobile robot according to another embodiment of the present invention.
8 is a plane conceptual view illustrating an escape movement process of the mobile robot 100 according to the control method of FIG. 7.
9 is a flowchart illustrating a control method of a mobile robot according to a first embodiment of the present invention.
FIG. 10 is a conceptual diagram illustrating an image of the mobile robot 100 according to the control method of FIG. 9. The image detected at each position according to the flow of time t and the brightness representative value Fr of each image are shown. Illustrated.
FIG. 11 shows first brightness representative values So respectively corresponding to the points which successfully recognize the position on the m-map, and ii second brightness representative values Sx respectively corresponding to the points where the position recognition failed on the map. Based on this, it is a conceptual diagram showing that the brightness reference value Fs of FIG. 9 is set.
12 is a flowchart illustrating a control method of a mobile robot according to a second embodiment of the present invention.
FIG. 13 is a conceptual diagram illustrating an image of the mobile robot 100 according to the control method of FIG. 12. The image detected at one position is divided into six regions, and respective brightness representative values f1 of the six regions are illustrated. is a conceptual diagram showing a six-dimensional brightness representative vector in which, f2, f3, f4, f5, and f6) are numerical values of each dimension.
FIG. 14 shows first brightness representative vectors So respectively corresponding to the points which successfully recognize the position on the m-map, and ii second brightness representative vectors Sx respectively corresponding to the points where the position recognition failed on the map. Based on this, it is a conceptual diagram illustrating that the brightness reference vector group FVs of FIG. 12 is set.
15 is a flowchart showing a control method of a mobile robot according to a third embodiment of the present invention.
16 is a flowchart showing a control method of a mobile robot according to a fourth embodiment of the present invention.
17 is a flowchart illustrating a control method of a mobile robot according to a fifth embodiment of the present invention.
18 is a flowchart illustrating a method for controlling a mobile robot according to a sixth embodiment of the present invention, and shows an example of combining the first to fifth embodiments.
19 is a flowchart illustrating a control method of a mobile robot according to still another embodiment of the present invention.
FIG. 20 is a conceptual diagram showing a mobile robot 100 cleaning the general area Ag first according to the control method of FIG. 19 on a residential plane.

The mobile robot 100 of the present invention means a robot that can move itself by using a wheel or the like, and may be a home helper robot or a robot cleaner. Hereinafter, referring to FIGS. 1 to 5, the robot cleaner 100 of the mobile robot is described as an example, but is not necessarily limited thereto.

In the comparison of verbal / mathematical expressions throughout this description, 'small or equal' and 'small' are less than or equal to each other and can be easily substituted for a person of ordinary skill in the art. (Above) and "greater than" are the extent to which a person skilled in the art can easily replace each other, and of course, the substitution of the present invention does not cause any problem in exerting the effect.

The mobile robot 100 includes a main body 110. Hereinafter, in defining the respective parts of the main body 110, the portion facing the ceiling in the driving zone is defined as the upper surface portion (see FIG. 2), and the portion facing the bottom 1 in the driving zone is the bottom portion (see FIG. 4). ), And a portion facing the traveling direction among the portions forming the circumference of the main body 110 between the upper surface portion and the lower surface portion is defined as a front portion (see FIG. 3). In addition, a portion of the main body 110 facing in the opposite direction to the front portion may be defined as the rear portion. The main body 110 may include a case 111 forming a space in which various components of the mobile robot 100 are accommodated.

The mobile robot 100 includes a sensing unit 120 for sensing information of an external upper object. The sensing unit 120 may detect information of the external upper object during the movement of the mobile robot 100. The external upper object means an obstacle limiting a space in an upward direction. The external upper object may be a ceiling or a lower surface of the furniture 3 disposed in an upward direction of the mobile robot 100. The external object information may include image information photographed by the mobile robot 100 in an upward direction. The information on the external upper object may include distance information from the mobile robot 100 to the external upper object.

The sensing unit 120 may be provided at an upper surface of the main body 110. The sensing direction of the sensing unit 120 is an upward direction.

The sensing unit 120 may detect an image of an external upper object or detect a distance to an external upper object. The sensing unit 120 may detect the image at each position according to the time t during the movement. The sensing unit 120 may detect the distance at each position according to the time t during the movement.

The sensing unit 120 may include an image sensing unit 120 for sensing an image of an external upper object. The sensing unit 120 may include a distance detecting unit 120 that detects a distance to an external upper object.

The image acquisition unit 120 photographs the driving zone, and may include a digital camera. The digital camera includes at least one optical lens and a plurality of photodiodes (eg, pixels) formed by the light passing through the optical lens, for example, a CMOS image sensor. And a digital signal processor (DSP) for constructing an image based on the signals output from the photodiodes. The digital signal processor may generate not only a still image but also a moving image including frames composed of still images.

The mobile robot 100 includes a driving unit 160 for moving the main body 110. The driving unit 160 moves the main body 110 with respect to the floor 1. The driving unit 160 may include at least one driving wheel 166 to move the main body 110. The driving unit 160 may include a driving motor. The driving wheels 166 may be provided on the left and right sides of the main body 110, respectively, hereinafter referred to as left wheels 166 (L) and right wheels 166 (R).

The left wheel 166 (L) and the right wheel 166 (R) may be driven by a single drive motor, but the left wheel drive motor and the right wheel 166 (R) which drive the left wheel 166 (L) as necessary. Each right wheel drive motor for driving) may be provided. The driving direction of the main body 110 can be switched to the left or the right by varying the rotational speeds of the left wheel 166 (L) and the right wheel 166 (R).

The mobile robot 100 includes a cleaning unit 180 for cleaning the floor 1. The mobile robot 100 may move and clean the traveling area. The cleaning unit 180 may include a suction device for suctioning foreign substances, brushes 184 and 185 for dusting, a dust container (not shown) for storing the foreign matter collected by the suction apparatus or brush, and / or a mop for dusting. (Not shown) and the like.

A suction port 180h through which air is sucked may be formed at the bottom of the main body 110. In the main body 110, a suction device (not shown) that provides suction power so that air can be sucked through the suction port 180h, and a dust container (not shown) that collects dust sucked with air through the suction port 180h. It may be provided.

An opening for inserting and removing the dust container may be formed in the case 111, and a dust container cover 112 that opens and closes the opening may be rotatably provided with respect to the case 111.

A roll-shaped main brush 184 having brushes exposed through the suction port 180h, and an auxiliary brush 185 having a brush composed of a plurality of radially extending wings positioned at the front side of the bottom of the main body 110. It may be provided. The rotation of these brushes 184 and 185 removes dust from the floor in the travel zone, and the dust separated from the floor is sucked through the inlet 180h and collected in the dust bin.

The battery 138 may supply power required for the overall operation of the mobile robot 100 as well as the driving motor. When the battery 138 is discharged, the mobile robot 100 may travel to return to the charging station 200 for charging, and during such a return travel, the mobile robot 100 itself positions the charging station 200. Can be detected.

Charging station 200 may include a signal transmitter (not shown) for transmitting a predetermined return signal. The return signal may be an ultrasonic signal or an infrared signal, but is not necessarily limited thereto.

The mobile robot 100 may include a communication unit 190 provided to communicate with an external server, a terminal, and / or a charging stand. The communicator 190 may include a signal detector (not shown) that receives the return signal. The charging unit 200 may transmit an infrared signal through a signal transmitter, and the signal detector may include an infrared sensor that detects the infrared signal. The mobile robot 100 moves to the position of the charging stand 200 according to the infrared signal transmitted from the charging stand 200 and docks with the charging stand 200. The docking is performed between the charging terminal 133 of the mobile robot 100 and the charging terminal 210 of the charging table 200.

In addition, the mobile robot 100 may further include an obstacle detecting sensor 131 for detecting an obstacle in front of the moving robot 100. The mobile robot 100 may further include a cliff detection sensor 132 for detecting the presence of a cliff on the floor in the driving zone, and a lower image sensor 139 for acquiring an image of the floor.

In addition, the mobile robot 100 includes an input unit 171 for inputting On / Off or various commands. The mobile robot 100 may include an output unit 173 for notifying the user of various kinds of information. The output unit 173 may include a speaker and / or a display.

The mobile robot 100 includes a controller 140 for processing and determining various information such as recognizing a current position. The controller 140 may control overall operations of the mobile robot 100 through control of various components of the mobile robot 100. The controller 140 may map the driving zone through the image and may be provided to recognize the current location on the mapped map. That is, the controller 140 may perform a slam (SLAM: Simultaneous Localization and Mapping) function.

The controller 140 may receive information from the input unit 171 and process the information. The controller 140 may receive and process the sensing information from the sensing unit 120. The sensing information means information of the external upper object. The controller 140 may receive information or transmit information through the communication unit 190.

The controller 140 may control the output of the output unit 173. The controller 140 may control the driving of the driving unit 160. The controller 140 may control the operation of the cleaner 180.

The mobile robot 100 includes a storage unit 150 for storing various data. The storage unit 150 records various types of information necessary for the control of the mobile robot 100 and may include a volatile or nonvolatile recording medium.

The storage unit 150 may store a map of the driving zone. The map may be input by an external terminal capable of exchanging information through the mobile robot 100 and the communication unit 190, or may be generated by the mobile robot 100 by learning itself. In the former case, examples of the external terminal may include a remote controller, a PDA, a laptop, a smartphone, a tablet, and the like equipped with an application for setting a map.

The actual driving zone may correspond to the driving zone on the map. The driving zone may be defined as the sum of all the plane zones in which the mobile robot 100 has a driving experience and the zones on the plane in which the mobile robot 100 is currently traveling.

The special zone As in reality and the special zone As on the map correspond. The general area Ag on the map that corresponds to the general area Ag in reality corresponds. The location of the rooms may be displayed on the map. In addition, the current position of the mobile robot 100 may be displayed on the map, and the current position of the mobile robot 100 on the map may be updated during the driving process.

The controller 140 may determine the movement path of the mobile robot 100 based on the operation of the driving unit 160. For example, the driving control module 141 may grasp the current or past moving speed of the mobile robot 100, the distance traveled, and the like based on the rotational speed of the driving wheel 166, and each driving wheel 166 ( L) and 166 (R) may also determine the current or past direction change process. Based on the driving information of the mobile robot 100 thus identified, the position of the mobile robot 100 on the map may be updated. In addition, by using the image information, the position of the mobile robot 100 on the map may be updated.

6 to 19, the control method of the mobile robot 100 according to embodiments of the present invention will be described. Contents overlapping each other in the flowcharts are denoted by the same reference numerals, and redundant descriptions are omitted.

The control method may be performed by the controller 140. The present invention may be a control method of the mobile robot 100 or may be a mobile robot 100 including a control unit 140 performing the control method. The present invention may be a computer program including each step of the control method, or may be a recording medium on which a program for implementing the control method with a computer is recorded. The term 'recording medium' means a computer-readable recording medium. The present invention may be a mobile robot control system including both hardware and software.

Flowchart of the control method Each step of the flowchart drawings and combinations of the flowchart drawings may be performed by computer program instructions. The instructions may be mounted on a general purpose computer or special purpose computer, etc., such that the instructions create means for performing the functions described in the flowchart step (s).

It is also possible in some embodiments that the functions mentioned in the steps occur out of order. For example, the two steps shown in succession may in fact be performed substantially simultaneously or the steps may sometimes be performed in the reverse order, depending on the function in question.

The controller 140 divides a part of the driving zone into a special zone As according to whether a predetermined division condition is satisfied at each location based on the sensing information of the sensing unit 120. The controller 140 determines that the one location belongs to the special zone As when the classification condition is satisfied based on the detection information at one location. The controller 140 may determine that the current location belongs to the special zone As when the classification condition is satisfied based on the detection information at the current location.

The control unit 140 may determine a part of the driving zone as the special zone As using a predetermined algorithm. The determined positions of the special zone As among the driving zones may be gathered to form the special zone As. According to an exemplary embodiment, the controller 140 may form a boundary of the special zone As by gathering respective positions determined as the special zone As among the driving zones, and based on the boundary, The area across may be considered a special zone (As).

The controller 140 divides some of the driving zones into a special zone As determined to be a lower zone of the furniture, based on the sensing information of the sensing unit 120. The control unit 140 may designate a special area As determined to be a lower area of the furniture by a predetermined algorithm. Because the determination is based on a predetermined algorithm of the controller 140, the special area As on the map corresponds to the lower area of the furniture in the real world, but there may be a part that does not correspond to the lower area of the furniture in the real world. It may be. The algorithm is preset so that, with a relatively high degree of confidence, the lower area of the household in the real world is divided into a special area As on the map. The division condition is preset so that the lower section of the furniture is determined as the special section. The dividing condition is preset so that the probability that the lower section of the household is determined to be a special section As is relatively high. The special zone As determined by the controller 140 has a higher probability that the lower section of the furniture is a lower section of the ceiling in real life.

The controller 140 determines a part of the driving zone as a special zone based on the sensing information of the sensing unit 120 and a predetermined division criterion. The division criterion is a threshold for determining whether to determine the one position as a special zone As in the information processing using the sensed information at one position in the driving zone as an input value. The division criteria may be a criterion for dividing the driving zone into a general zone Ag and a special zone As.

The special zone As may be a zone other than the general zone Ag of the driving zone. Special Areas (As) include the lower areas of the household. Special Areas (As) correspond to areas below the furniture. The special zone As may be a relatively dark zone with the lighting of the room turned on. The special area As may be an area in which the distance between the mobile robot 100 and an external upper object is equal to or less than a predetermined reference. In the special zone As, the distance between the mobile robot 100 and the external upper object is relatively small.

The general zone Ag may be a zone excluding the special zone As of the driving zone. The general zone Ag may comprise the lower zone of the ceiling. The general area Ag may be an area in which no obstacle such as furniture is disposed between the mobile robot 100 and the ceiling. The general area Ag may be a relatively bright area with the lighting of the room turned on. The general area Ag may be an area in which the distance between the mobile robot 100 and an external upper object becomes a predetermined reference or more. In the general area Ag, the distance between the mobile robot 100 and the external upper object is relatively large.

Referring to Figure 6, the control method of the mobile robot 100 according to an embodiment are as follows. First, the mobile robot 100 detects information of the external upper object during the movement (S10). In operation S10, a process of determining whether the division condition is satisfied based on the sensing information of one position is performed (S30). In the process (S30), if the classification condition is satisfied, the mobile robot 100 learns a special zone (As). In operation S50, it may be learned that one location from which the detection information, which is the basis for determining whether the division condition is satisfied, belongs to a special zone As. Here, the term 'learning' means that the mobile robot 100 generates new information or updates existing information through self-recognition. If the driving is not finished, if the classification condition is not satisfied in the process (S30), the process (S10) may proceed again without learning a new special zone (As). It is also possible to learn that one location from which the sensing information on which the classification condition is satisfied is belonged to the general area Ag. According to a preset condition or a user input, a process (S80) of determining whether the driving of the mobile robot 100 is terminated may be performed. If the driving is not finished, the process S10 is performed again after the process S50. If the driving is not finished, if the classification condition is not satisfied in the process (S30), the process (S10) proceeds again.

Referring to FIGS. 7 and 8, a control method of the mobile robot 100 according to another embodiment is as follows. When the controller 140 learns the special zone As during the movement, the controller 140 may control to escape from the special zone As. If it is determined in step S30 that the division condition is satisfied, step S55 is performed in which the mobile robot 100 escapes and moves out of the special area As belonging to the current position of the mobile robot 100. After the process (S55), the mobile robot 100 continues to move and the process (S10) proceeds again. If it is determined in step S30 that the division condition is unsatisfactory, step S10 is performed again.

Referring to Figure 8, the scenario of the escape movement of the mobile robot 100 will be described as follows. FIG. 8 is a plan conceptual view showing the mobile robot 100 traveling on the floor 1 and the furniture 3 spaced apart from the floor 1 with arrows indicating the travel path of the mobile robot 100. it means. In FIG. 8A, the mobile robot 100 is shown just before entering the lower section of the furniture 3. In FIG. 8B, the mobile robot 100 is shown immediately after entering the lower section of the furniture 3. The mobile robot 100 obtains the sensing information at the current position in the state where the mobile robot enters the lower area of the furniture 3, and determines whether the division condition is satisfied based on the sensing information of the current position. In FIG. 8B, the control unit 140 determines that the division condition is satisfied based on the sensing information of one position of the lower area of the furniture 3. Accordingly, the mobile robot 100 learns a new special zone As. Then, referring to FIG. 8C, the mobile robot 100 performs an escape movement from the special zone As to the general zone Ag.

As shown in FIG. 8C, the escape movement may be implemented by rotating 180 degrees in the existing traveling direction (the moving direction of the mobile robot in FIG. 8B). As another example, the escape movement may be implemented such that the moving robot 100 moves backward in the existing traveling direction.

The mobile robot 100 may determine whether the classification condition is satisfied based on brightness information of the upper image sensed by the sensing unit 120. The mobile robot 100 may determine whether the one location belongs to the special zone As based on the brightness information of the one location and the classification criteria.

Hereinafter, a control method of the mobile robot 100 according to the first embodiment will be described with reference to FIGS. 9, 10, and 11 as follows.

The classification condition according to the first embodiment includes a brightness condition in which the brightness representative value Fr of the image detected at one position is smaller than the brightness reference value Fs. When the brightness representative value Fr is smaller than the brightness reference value Fs, the brightness condition is satisfied.

In order to determine the brightness condition, the sensing unit 120 detects an upper image.

The brightness representative value Fr means a value that can represent the brightness of one image detected at one position. In the present embodiment, the brightness representative value Fr is an average brightness value of one image. As another example, the brightness representative value Fr may be an intermediate value of brightness values of each region of an image. As another example, the brightness representative value Fr may be an average value or a median value of remaining brightness values except for brightness value (s) that exceed or fall below a predetermined value among brightness values of each region of one image. As another example, the brightness representative value Fr may be a value obtained by correcting the average value or the median value.

The brightness reference value Fs means a value to be compared with the brightness representative value Fr. Brightness reference value Fs becomes the said division reference. The brightness reference value Fs may be preset to a predetermined value. The brightness reference value Fs may be changed based on the data learned by the mobile robot 100.

An example in which the brightness reference value Fs is changed based on the data learned by the mobile robot 100 will be described below. The brightness reference value Fs may be set as a total brightness value of the n images respectively detected at the latest n locations before the mobile robot 100 arrives at one location. Here, n is a natural number of 2 or more. Here, one position of the mobile robot 100 means a position at which one image on which the brightness condition is satisfied is detected. In addition, the recent n positions mean positions corresponding to the recently detected n images before the one image is detected.

The total brightness values of the n images mean a value that can represent the respective brightness representative values Fr of the n images. For example, the overall brightness value may be an average value of brightness representative values Fr of the n images. As another example, the overall brightness value may be a median value of brightness representative values Fr of the n images. As another example, the brightness total value may be an average value or a median value of the remaining brightness representative values except for the brightness representative value (s) that exceeds or falls below a predetermined value among the brightness representative values Fr of the n images. It may be. As another example, the brightness total value may be a value obtained by correcting the average value or the median value of the brightness representative values Fr of the n images.

Another example of changing the brightness reference value Fs based on the data learned by the mobile robot 100 is as follows. The controller 140 may change the brightness reference value Fs based on data on whether the SLAM operation is performed at each position of the driving zone.

Referring to FIG. 11, the control unit 140 may include first brightness representative values So corresponding to points successfully recognized for position on the map, and points corresponding to positions failing to recognize position on the ii map, respectively. Based on the two brightness representative values Sx, the brightness reference value Fs is changed. The controller 140 is configured such that the first brightness representative value So and ii the second brightness representative values Sx are divided in a state where the error is minimized based on the brightness reference value Fs. , The brightness reference value (Fs) can be changed. In FIG. 11, a distribution of the first brightness representative values So and the second brightness representative values Sx is illustrated on a straight line in one dimension. Here, the brightness reference value Fs is set to a value that minimizes the error (False). Here, the error False means the second brightness representative value Sx exceeding the brightness reference value Fs and the first brightness representative value So that does not exceed the brightness reference value Fs. In order to minimize the error (False), the brightness reference value (Fs) is set as shown in FIG. If the brightness reference value Fs of FIG. 11 is smaller than the adjacent second brightness representative value Sx or larger than the adjacent first brightness representative value So, the number of false increases, and thus the brightness reference value of FIG. Fs) is set to minimize the error. Here, the brightness reference value Fs may be set to an intermediate value between the adjacent second brightness representative value Sx and the adjacent first brightness representative value So. The first brightness representative value So and / or the second brightness representative value Sx may be added through later learning, and thus the brightness reference value Fs may be changed.

The process of changing the brightness reference value Fs will be described in more detail as follows. The controller 140 calculates the number e1 of errors F1 by assuming an arbitrary value s1 as the brightness reference value Fs, and then increases or decreases the brightness reference value Fs by another value s2. It is assumed that the number of errors e2 is calculated. By comparing the calculated number of errors False and e2, if the number e2 is smaller than the number e1, the hypothetical value of the brightness reference value Fs is changed to the value s2. By repeating this process, the brightness reference value Fs may be converged in a direction in which the number of errors is reduced, and the brightness reference value Fs may be changed to the converged value.

In the control method according to the first embodiment with reference to FIG. 9, a process (S11) of detecting an upper image of a current position during the movement of the mobile robot 100 is performed. After the process S11, a process S21 of generating the brightness representative value Fr of the image at the current position is performed. After the process S21, a process S31 of determining whether the brightness representative value Fr of the current position is smaller than the brightness reference value Fs is performed. When the brightness condition is satisfied in the process S31, the process S50 is performed, and then the process S11 is performed again. If the brightness condition is not satisfied in the step S31, the step S11 is performed again without the step S50.

Referring to FIG. 10, the scenario of the first embodiment will be described below. The mobile robot detects the image at each location at regular time intervals. Here, the numerical value of the brightness representative value Fr may be a value proportional to the illuminance. In this scenario, the brightness reference value Fs is set to 30. The brightness representative value Fr of the image detected at one position at one time point T is 140, and the brightness representative value Fr of the image detected at one position at one time point T + 1 is 140, after The brightness representative value Fr of the image detected at one position at one time point T + 2 decreases rapidly to two. Since the brightness representative value Fr 140 of the one point T and the one point T + 1 is greater than the brightness reference value Fs 30, the positions of the one point T and the one point T + 1 are represented. The brightness condition is unsatisfactory. Since the brightness representative value Fr 2 of the one time point T + 2 is smaller than the brightness reference value Fs 30, the brightness condition is satisfied at the position of the one time point T + 2. Accordingly, one position of the one time point T + 2 is learned to belong to the special zone As. After that, the driving process (S11) is performed again to obtain an image. Thereafter, the brightness representative value Fr of the image detected at one position at one time point T + a is 100, and thereafter, the brightness representative value of the image detected at one position at one time point T + a + 1 ( Fr) is 40, and the brightness representative value Fr of the image detected at one position at one time point T + a + 2 is zero. Since the brightness representative values Fr 100 and 40 of the one point T + a and the one point T + a + 1 are greater than the brightness reference value Fs 30, the one point T + a and one point The brightness condition is unsatisfactory at the positions of (T + a + 1). Since the brightness representative value Fr 0 of the one time point T + a + 2 is smaller than the brightness reference value Fs 30, the brightness condition is satisfied at the position of the one time point T + a + 2. Accordingly, one position of the one time point T + a + 2 is learned to belong to the special zone As.

Hereinafter, a control method of the mobile robot 100 according to the second embodiment will be described with reference to FIGS. 12, 13, and 14 as follows.

The classification condition according to the second embodiment is a brightness condition (brightness vector condition) in which the brightness representative vector (FVr) of the image detected at one position does not exceed the brightness reference vector group (FVs) continuously m-dimensionally (m-dimension). It includes. M is a natural number of 2 or more. If the brightness representative vector FVr does not exceed the brightness reference vector group FVs on the m-dimensionality, the brightness vector condition is satisfied. When the brightness reference vector group FVs divides the m-dimensional space, the brightness vector condition is satisfied when the brightness representative vector FVr exists on one side preset based on the brightness reference vector group FVs. If the vector FVr exists on the other side of the brightness reference vector group FVs, the brightness vector condition is unsatisfactory.

In order to determine the brightness vector condition, the sensing unit 120 senses an upper image.

Referring to FIG. 13, the controller 140 according to the second embodiment divides an image into m regions. The control unit 140 generates an m-dimensional brightness representative vector FVr in which the brightness representative values of the m areas are numerical values of each dimension. Here, the brightness representative vector FVr refers to data that can be represented as a vector, regardless of the actual format of the generated data.

The brightness representative value of one region among the m regions, which are numerical values of each dimension of the brightness representative vector FVr, means a value that can represent the brightness of the one region. The brightness representative value of the one area is an average brightness value of one area. As another example, the brightness representative value of the one region may be a median value of brightness values of each small region of the one region. As another example, the brightness representative value of the one area may be an average value or a median value of remaining brightness values except for brightness value (s) that exceed or fall below a predetermined value among brightness values of each small area of the one area. As another example, the brightness representative value of the one region may be a value obtained by correcting the average value or the median value.

The brightness reference vector group FVs means a set of vectors to which the brightness representative value Fr is compared. The brightness reference vector group FVs is a threshold on the m-dimensional surface. Brightness reference vector group FVs becomes the said division reference. The brightness reference vector group FVs may be preset to a predetermined value. The brightness reference vector group FVs may be changed based on the data learned by the mobile robot 100.

An example in which the brightness reference vector group FVs is changed based on the data learned by the mobile robot 100 will be described below. The controller 140 may change the brightness reference vector group FVs based on data on whether the SLAM operation is performed at each location of the driving zone.

Referring to FIG. 14, the controller 140 may include first brightness representative vectors So respectively corresponding to the points that successfully recognize the position on the map, and second points corresponding to the points that fail to recognize the position on the ii map. The brightness reference vector group FVs is changed based on the two brightness representative vectors Sx. The controller 140 may include first brightness representative vectors So corresponding to the points that successfully recognize the position on the m-map and second brightness representative vectors Sx respectively corresponding to the points that fail to recognize the position on the ii map. ) May change the brightness reference vector group FVs so that the error is divided into a state where the error is minimized based on the brightness reference vector group FVs. FIG. 14 is a conceptual diagram illustrating only two dimensions of m-dimensional vectors for convenience of expression, but in fact, in the m-dimensional space, the brightness reference vector group FVs, the first brightness representative vectors So, and the second brightness are shown. Representative vectors Sx are disposed. Here, the brightness reference value Fs is set to a value that minimizes the error (False). Here, the error False means the second brightness representative vector Sx that exceeds the brightness reference vector group FVs and the first brightness representative vector So that does not exceed the brightness reference vector group FVs.

Here, the brightness reference vector group FVs may be set to a median value between the adjacent second brightness representative vector Sx and the adjacent first brightness representative vector So. The first brightness representative vector So and / or the second brightness representative vector Sx may be added through later learning, and thus the brightness reference vector group FVs may be changed.

For example, the brightness reference vector group FVs may be represented by a reference function f (f1, f2, f3, f4, f5, f6) = 0, and the first brightness representative vector So is input to the reference function. Error (False) with f (f1, f2, f3, f4, f5, f6) <0 and f (f1, f2, f3, f4 when inputting the second brightness representative vector (Sx) to the reference function. , f5, f6)> 0 Coefficients constituting the reference function may be changed to minimize the false (False). In order to minimize the error (False), the brightness reference vector group (FVs) is set as shown in FIG. The brightness reference vector group FVs may be defined by the linear reference function.

The process of changing the brightness reference vector group (FVs) will be described in more detail as follows. The control unit 140 calculates the number of errors e1 using the reference function assuming the arbitrary coefficient s1 as the brightness reference vector group FVs, and increases or decreases the coefficient of the reference function. Assuming a different value s2, the number e2 of errors is calculated. By comparing the calculated number of errors (e1, e2), if the number e2 is smaller than the number e1, the hypothesized value of the coefficient of the reference function is changed to the value s2. Each hypothesis of the plurality of coefficients of the reference function may be changed in the above manner. By repeating this process, the brightness reference vector group FVs may be converged in a direction in which the number of errors is reduced, and the brightness reference vector group FVs may be changed to the converged value.

In the control method according to the second embodiment with reference to FIG. 12, a process (S11) of detecting an upper image of a current position during the movement of the mobile robot 100 is performed. After the process S11, a process S22 of generating the brightness representative vector FVr of the image at the current position is performed. After the process S22, the process of determining whether the brightness representative vector FVr at the current position does not exceed the brightness reference vector group FVs is performed (S32). If the brightness vector condition is satisfied in step S32, step S50 is performed, and then step S11 is performed again. If the brightness vector condition is unsatisfactory in step S31, step S11 is performed again without step S50.

15 to 18, the classification condition according to the third to sixth embodiments may include a feature point condition in which the feature point is not extracted from the image detected at the single location, and ii the p position of the image detected at the one location. An image condition that does not match each of the p images detected at &lt; RTI ID = 0.0 &gt; and &lt; / RTI &gt; At least one of 3D point conditions is included. Where p is a natural number and q is a natural number of two or more. The division conditions according to the third to sixth embodiments may include a condition that all of the feature point conditions are satisfied at x consecutive positions, ii a condition that the image condition satisfies all y consecutive positions, and the 3D point. The condition may include at least one of conditions satisfying all of the consecutive z positions. Where x, y and z are natural numbers.

In order to determine the feature point condition, the sensing unit 120 senses an upper image. In order to determine the image condition, the sensing unit 120 detects an image from above. In order to determine the 3D point condition, the sensing unit 120 detects an upper image.

Hereinafter, a control method of the mobile robot 100 according to the third embodiment will be described with reference to FIG. 15.

The classification condition according to the third embodiment includes a feature point condition in which the feature point is not extracted from the image detected at one location. The feature point condition is a condition in which the controller 140 cannot extract the feature point from an image of one position by a predetermined feature point extraction method such as SIFT. If the feature point is not extracted from the image of one position, the feature point condition is satisfied.

The Scale Invariant Feature Transform (SIFT) technique is a method of transforming feature points in an image into a descriptor. For example, SIFT selects easy-to-identify feature points such as corner points in an image, and then distributes the gradients of brightness gradients of pixels belonging to a certain area around each feature point (the direction of the change in brightness and the degree of change of brightness). Is an image recognition technique that obtains an n-dimensional vector whose value is a numerical value for each dimension as a sudden degree of change in each direction. SIFT can detect invariant features of scale, rotation, and brightness change of a photographing target, and thus the same area is unchanged even when the robot cleaner 100 is photographed with different postures (ie, rotation invariant (Rotation) -invariant)) feature can be detected. Of course, for extracting feature points in an image, other various techniques (eg, HOG: Histogram of Oriented Gradient, Haar feature, Fems, LBP: Local Binary Pattern, MCT: Modified Census Transform) may be applied.

The classification condition may include a condition (additional feature point condition) that all of the feature point conditions satisfy at x consecutive positions. Where x is a natural number of two or more. For example, when x = 3, the feature point in the image detected at one position of one point in time T is not extracted, and the feature point in the image detected at one position in the next captured point in time T + 1. Is not extracted, and if the feature point in the image sensed at one position of the next photographed time point T + 2 is not extracted, the additional feature point condition is satisfied.

In the control method according to the third embodiment with reference to FIG. 15, first, a process (S33a) of setting the i value to 0 is performed. Thereafter, a process (S11) of detecting an upper image of the current position during the movement of the mobile robot 100 is performed. After the process S11, a process of determining whether the number of feature points in the image of the current position is 0 is performed (S33b). If the feature point condition is satisfied in the step S33b, the i value increases by +1 (S33c), and a process of determining whether the increased i value matches the x value is performed (S33d). If the i value does not coincide with the x value in step 33d, the process proceeds from step S11 again. If the feature point condition is satisfied x times in succession, the process (S33c) is repeated x times, so the i value becomes the x value. If the i value coincides with the x value in the process S33d, the process S50 of learning that the current position belongs to the special zone As is performed. In the state where the driving is not finished (S80), after the step S50, the i value is reset to 0 (S33a), and proceeds again from the step S11. If the feature point condition is not satisfied in the process (S33b) (when the feature point in the image of the current position is extracted), the process proceeds again from the process (S33a) where the i value is set to 0 without the process (S50).

Hereinafter, referring to FIG. 16, a control method of the mobile robot 100 according to the fourth embodiment is as follows.

The classification condition according to the fourth embodiment includes an image condition in which an image detected at one position does not match the p images detected at the latest p positions, respectively, by more than a predetermined reference value. Where p is a natural number. For example, when the similarity is calculated between the 'image detected at one position' and the 'p images', and all of the calculated similarities are less than a predetermined value, the additional image condition is satisfied. In order to determine similarity between two images, various known means may be used.

The classification condition may include a condition (additional image condition) in which the image condition satisfies all y consecutive positions. Here, y is a natural number of two or more. For example, when y = 3, the image condition is satisfied based on the image detected at one position of one point in time T, and then detected at one position of one point in time T + 1 captured next. The additional image condition is satisfied when the image condition is satisfied based on an image and the image condition is satisfied based on an image sensed at a position at a time point T + 2 captured next.

In the control method according to the fourth embodiment with reference to FIG. 16, first, a process (S34a) of setting a j value to 0 is performed. Thereafter, a process (S11) of detecting an upper image of the current position during the movement of the mobile robot 100 is performed. After the process S11, a process (S34b) of determining whether or not the matching of the current position of the image and the recent p images is in progress. When the image condition is satisfied in the step S34b, the j value increases by +1 (S34c), and a process of determining whether the increased j value matches the y value is performed (S34d). If the j value does not coincide with the y value in step 34d, the process proceeds again from step S11. If the feature point condition is satisfied y times in succession, the process (S34c) is repeated y times so that the j value becomes the y value. If the j value coincides with the y value in the process S34d, the process S50 of learning that the current position belongs to the special zone As is performed. In the state where the driving is not finished (S80), after the step S50, the j value is reset to 0 (S34a), and proceeds again from the step S11. If the image condition is not satisfied in the step S34b, the process proceeds again from the step S34a in which the j value is set to 0 without the step S50.

Hereinafter, a control method of the mobile robot 100 according to the fifth embodiment will be described with reference to FIG. 17.

The classification condition according to the fifth embodiment includes a 3D point condition in which a 3D point generated from q images recently detected at q locations is not recognized above a predetermined reference value in the image detected at one location. Where q is a natural number of 2 or more. For example, 3D point (s) may be generated by creating the 3D map. 3D point (s) may be generated by using the positional difference between the feature points recognized in q different images. For example, it may be determined whether a pre-generated 3D point is recognized in an image of one location. In the image at one position, if the feature point matching the plurality of 3D points generated from q images is less than C, the 3D point condition is satisfied. Where C is a natural number.

The classification condition may include a condition (additional 3D point condition) that all of the 3D point conditions satisfy at z consecutive positions. Where z is a natural number of two or more. For example, when z = 3, the 3D point condition is satisfied based on an image detected at one position of one point in time T, and then detected at one position of one point of time T + 1 captured next. If the 3D point condition is satisfied based on the captured image and the 3D point condition is satisfied based on the image detected at one position of the next time point (T + 2), the additional 3D point condition is satisfied. do.

In the control method according to the fifth embodiment with reference to FIG. 17, first, a process (S35a) of setting a k value to 0 is performed. Thereafter, a process (S35b) of generating 3D points from the latest q images during the movement of the mobile robot 100 is performed. Thereafter, a process (S11) of detecting an upper image of the current position during the movement is performed. After the process S11, the process of determining whether the number of feature points matching the 3D point in the image of the current position is less than C (S35c) is performed. (Where C is a natural number) In step S35c, if the 3D point condition is satisfied, a value of k increases by +1 (S35d) and a process of determining whether the increased k value coincides with the value of z ( S35e) proceeds. If the k value does not coincide with the z value in the process 35e, the process proceeds again from the process S35b. If the feature point condition is satisfied z times in succession, the process (S35d) is repeated z times, so the k value becomes a z value. If the k value coincides with the z value in the process S35e, the process S50 of learning that the current position belongs to the special zone As is performed. In the state in which the driving is not finished (S80), after the process S50, the k value is reset to 0 (S35a), and proceeds again from the process (S35b). If the 3D point condition is not satisfied in the process S35c, the process proceeds again from the process S35a in which the k value is set to 0 without the process S50.

Hereinafter, a control method of the mobile robot 100 according to the sixth embodiment will be described with reference to FIG. 18.

The classification condition according to the sixth embodiment includes a first condition that satisfies at least one of the feature point condition, the image condition, and the 3D point condition. The classification condition includes a condition in which both the first condition and the brightness condition are satisfied. The first condition may be a condition satisfying at least one of 하나 the additional feature point condition, ii the additional image condition, and, the additional 3D point condition.

In the control method according to the sixth embodiment with reference to FIG. 18, a process (S11) of first detecting an upper image of a current position during a movement is performed. Thereafter, the process of determining whether the feature point condition (or the additional feature point condition) is satisfied (S33) is performed. If the feature point condition is unsatisfactory in step S33, a step S34 of determining whether the image condition (the additional image condition) is satisfied is performed. If the image condition is unsatisfactory in the step S34, the process of determining whether the 3D point condition (the additional 3D point condition) is satisfied (S35) is performed. When the driving is not finished (S80), if the 3D point condition is not satisfied in the process (S35), the process proceeds again from the process (S11). That is, if the first condition is not satisfied, the process proceeds again from the process S11 without learning the special zone As. In at least one of the processes S33, S34, and S35, if at least one of the feature point condition, the image condition, and the 3D point condition is satisfied, the brightness condition is determined. Process S31 or S32 is performed. Here, the process of determining whether the brightness condition is satisfied may be preset to any one of the process S31 and the process S32. When the brightness condition is satisfied in the process S31 or S32, a process S50 of learning that the current position belongs to the special zone As is performed. Thereafter, in the state in which the driving is not finished (S80), the process proceeds again from the process S11.

Although not shown, a control method of the mobile robot 100 according to the seventh embodiment will be described below.

The classification condition according to the seventh embodiment includes a distance condition in which the distance value Dr detected at one position is smaller than the distance reference value Ds. If the distance value Dr is smaller than the distance reference value Ds, the distance condition is satisfied.

In order to determine the distance condition, the sensing unit 120 detects a distance to an upper external object.

The distance reference value Ds means a value to be compared with the distance value Dr. The distance reference value Ds becomes the said division reference. The distance reference value Ds may be preset to a predetermined value.

In the control method according to the seventh exemplary embodiment, a process (S11) of detecting a distance value Dr to an upper object of a current position during the movement of the mobile robot 100 is performed. Thereafter, a process (not shown) for determining whether the distance value Dr at the current position is smaller than the distance reference value Ds is performed. If the distance condition is satisfied, the process (S50) proceeds. Thereafter, the process S11 is performed again. If the distance condition is not satisfied, the process S11 is performed again without the process S50.

Hereinafter, embodiments in which the mobile robot 100 learns and utilizes a special zone As are described.

For example, if a special zone As is found (first recognition of the special zone), the above-described escape movement may proceed.

As another example, the controller 140 manages the general zone Ag, not the special zone As, of the driving zone in a predetermined general mode, and manages the special zone As in a predetermined special mode different from the normal mode. Can be controlled.

The normal mode and the special mode may differ in a driving plan (schedule). The control unit 140 may control the vehicle to travel ahead of any one of the ⅰspecial zone As and the ii general zone Ag or to travel only in any one of them. For example, in one driving, the general zone Ag may be driven first and the special zone As may be driven later, or in one driving, the general zone Ag may be set to travel.

The normal mode and the special mode may be different from the driving mode. The controller 140 may control the driving mode in each of the ⅰspecial zone As and the ii general zone Ag differently. The driving mode may include a zigzag pattern in which the vehicle travels in a straight line until an obstacle comes out, and changes the driving direction when the vehicle approaches the obstacle and runs in a straight line until an opposite obstacle comes out. In addition, the driving mode may include a spiral pattern from an edge to a center of a region in a clockwise or counterclockwise direction. For example, the general area Ag may be set to travel in the zigzag pattern, and the special area As may be set to travel in a spiral pattern.

The control unit 140 may control to clean any one of the ⅰspecial zone As and the ii general zone Ag before the other, or to clean only one. In one cleaning of the entire driving zone, the controller 140 may control to clean any one of the special zone As and the general zone Ag before the other one. For example, the controller 140 may control to clean the general area Ag first and the special area As later when the driving area is cleaned once. In addition, the controller 140 may control to clean only the general zone Ag during one driving zone cleaning. In addition, the controller 140 may control to clean only the special zone As during one driving zone cleaning. Here, one cleaning or one driving may mean a one-time process of returning to the charging stand 200 after the mobile robot 100 leaves the charging stand 200 even when the battery is not low.

In the control method referring to FIG. 19, a process S91 of cleaning the general area Ag is performed by the mobile robot 100 first, and then a process of cleaning the special area As by the mobile robot 100 ( S93) proceeds. In FIG. 20, the driving route of the mobile robot 100 is shown while the process S91 is in progress. The mobile robot 100 travels from the general area Ag defined by the wall 2 and the special area As. In FIG. 20, when the mobile robot 100 travels in the general area Ag, the zigzag driving path is shown.

The normal mode and the special mode may differ in whether other smart functions are activated. For example, the smart function may include an object search function and / or a bug fighting function to be described later.

The object search function may be set to be activated only in the special zone As. Set to transmit an output signal for notifying the user when the object placed on the floor is recognized in the special zone As, and not to transmit the output signal to the user when the object placed on the floor is recognized in the general zone As Can be. The object to be recognized may be set to a small object having a predetermined scale or less. The object to be recognized may be set by object information input by the user. The object to be recognized may be set by object information stored on a predetermined database. The object to be recognized may be set by product information received from a server storing a predetermined database.

Only in the special zone As can be set to activate the worm fighting function. When the worm is recognized in the special zone As, it may be set to transmit an output signal for notifying the user, and when the worm is recognized in the general zone As, the output signal may not be transmitted to the user. The worm of the object to be recognized may be set by worm information input by a user. The worm to be recognized may be set by worm information stored on a predetermined database. The worm to be recognized may be set by worm information received from a server storing a predetermined database.

100: mobile robot 120: sensing unit
140: control unit 160: driving unit
180: cleaning unit 200: charging stand
Ag: General Area As: Special Area
Fr: Brightness representative value Fs: Brightness reference value
FVr: Brightness representative vector FVs: Brightness reference vector

Claims (16)

A traveling part for moving the main body relative to the floor;
A sensing unit which senses an image of an external upper object or a distance to an external upper object while moving;
A controller for classifying a part of a driving zone into a special zone according to whether a predetermined division condition is satisfied at each position based on the sensing information of the sensing unit; And,
It includes a cleaning unit for cleaning the floor,
The control unit,
이동 A mobile robot which controls to clean any one of the special zones and ii the general zones other than the special zones before the other one or to clean only one. The method of claim 1,
The predetermined classification condition is,
A mobile robot preset to determine that the lower section of the furniture is said special zone. The method of claim 1,
The control unit,
The mobile robot determines that the one position belongs to the special zone when the classification condition is satisfied based on the detection information at one position. The method of claim 1,
The control unit,
A mobile robot that controls the escape of the special area when the special area is learned while moving. The method of claim 1,
The control unit,
A mobile robot for controlling a general zone other than the special zone among the driving zones in a predetermined general mode, and managing the special zone in a predetermined special mode different from the normal mode. The method of claim 1,
The control unit,
이동 A mobile robot that controls driving modes differently in each of the special zones and the general zones other than the special zones of the driving zones. The method according to claim 5 or 6,
The control unit,
The mobile robot transmits an output signal for notifying the user when the bug is detected in the special zone, and does not transmit the output signal to the user when the bug is recognized in the general area. The method of claim 1,
The sensing unit detects the image,
The division condition is,
A mobile robot including a brightness condition in which the brightness representative value of the image detected at one position is smaller than the brightness reference value. The method of claim 8,
The brightness reference value,
The mobile robot is set to the combined brightness value of the n images respectively detected at the last n locations before the mobile robot arrives at the one location.
Where n is a natural number of 2 or more. The method of claim 8,
The control unit,
The driving zone is mapped through the image and the current location is recognizable on the mapped map,
밝기 the brightness reference value is based on first brightness representative values respectively corresponding to the points on which the position recognition on the map has succeeded, and ii second brightness representative values respectively corresponding to the points on which the position recognition on the map has failed. Modified mobile robot. The method of claim 1,
The sensing unit detects the image,
The control unit,
Dividing one image into m regions, and generating an m-dimensional brightness representative vector in which the brightness representative values of the m regions are numerical values of each dimension,
The division condition is,
And a brightness condition in which the brightness representative vector of the image detected at one position does not exceed a group of brightness reference vectors continuous in m dimensions in m dimensions.
Where m is a natural number equal to or greater than 2. The method of claim 11,
The control unit,
The driving zone is mapped through the image and the current location is recognizable on the mapped map,
Change the brightness reference vector group based on the brightness representative vectors respectively corresponding to the points that successfully recognize the position on the map, and the brightness representative vectors respectively corresponding to the points which fail to recognize the position on the map. Mobile robot. The method of claim 12,
The control unit,
제 first brightness representative vectors respectively corresponding to the points on which the location recognition succeeds on the map, and ii second brightness representative vectors respectively corresponding to the points on which the location recognition failed on the map, based on the brightness reference vector group. A mobile robot for changing the brightness reference vector group so that the error is bisected in a minimized state. The method of claim 1,
The sensing unit detects the image,
The division condition is,
A feature point condition in which the feature point is not extracted from the image detected at the single position, ii an image condition in which the image detected at one position does not match the p images detected at the recent p positions more than a predetermined reference value, and And at least one of 3D point conditions in which 3D points generated from q images respectively detected at the two positions are not recognized above a predetermined reference value in the image detected at one position.
Where p is a natural number and q is a natural number of two or more. The method of claim 1,
The sensing unit detects the distance,
The division condition is,
A mobile robot including a distance condition in which a distance value detected at one position is smaller than a distance reference value. The method of claim 7, wherein
The control unit,
The mobile robot transmits an output signal for notifying the user when the object placed on the floor is recognized in the special zone, and does not transmit the output signal to the user when the object placed on the floor is recognized in the general zone.

Images