KR102891096B1 - System for robot evasion and robot movement regarding obstacle depending on generation of virtual map, and method for robot evasion and robot movement of obstacle - Google Patents

Abstract

The present invention relates to a system for robot obstacle avoidance and movement based on virtual map generation, comprising: a robot moving within a specific space; a first image information acquisition unit for receiving a first three-dimensional image of a specific space and acquiring first image information; And a server that extracts an area of interest based on the color of the boundary of the floor tiles among the first photo information, creates an area in which a floor tile pattern is detected among the first photo information as a target space, creates a map formed by dividing the target space into a plurality of areas based on the floor tile pattern, extracts the shape of each object of the first photo information from the map, merges a first 3D image of the shape of each extracted object with the map, determines whether the shape of the object exists on each side of the map, and if the shape of the object exists, determines whether the shape of the object on each side is a robot marker, and if the shape of the object on each side is a robot marker, recognizes the location of the inner side of the map as the current location of the robot, extracts the shortest path that minimizes the sum of the horizontal and vertical lengths of an obstacle-free side between the current location of the robot and the target location based on the current location of the robot, determines whether the robot has arrived at the target location, and stops the movement of the robot if the robot has arrived at the target location.

Description

{SYSTEM FOR ROBOT EVASION AND ROBOT MOVEMENT REGARDING OBSTACLE DEPENDING ON GENERATION OF VIRTUAL MAP, AND METHOD FOR ROBOT EVASION AND ROBOT MOVEMENT OF OBSTACLE}

The present invention relates to a system for robot obstacle avoidance and movement based on virtual map generation, and a method for robot obstacle avoidance and movement, and more particularly, to a system for robot obstacle avoidance and movement based on virtual map generation, and a method for robot obstacle avoidance and movement, in which a robot identifies the location of an object through an image processing process for information on a space and an object projected from a three-dimensional image input within a specific space, avoids obstacles, and arrives at a target location via an optimal path.

For robots to operate in spaces with high levels of human and material interaction, such as airports, schools, government offices, hotels, offices, factories, gyms, and cultural facilities like performance halls, they must continuously sense and navigate the space. Furthermore, the spaces where robots move are often filled with numerous pedestrians or various objects moving alongside them, requiring robots to avoid these objects as they navigate.

In particular, in spaces where human and material interactions are active, people can appear from various directions, and the objects accompanying them also become targets for robots to avoid. However, how a robot maintains its distance from and avoids these moving obstacles significantly impacts its movement path and operational capabilities. Furthermore, the robot's ability to navigate to specific locations during its movement significantly impacts its performance.

Furthermore, existing obstacle avoidance methods for mobile robots utilize big data from various sensors and lidar technologies based on the mobile robot. However, optimal paths are established through learning data from the mobile robot, which reduces the efficiency of detour search when specific exceptions occur. Furthermore, the installation of multiple sensors and lidar sensors to improve recognition accuracy increases device costs.

Domestic Patent Publication No. 10-2090590 (published on April 23, 2020)

One of the technical challenges to be solved by the present invention is to maximize the efficiency of a robot's detour route search when an exception occurs by using a CCTV camera that is less expensive than sensors and lidar equipment.

One of the technical challenges to be solved by the present invention is to precisely recognize the presence and location of obstacles in a specific space so that the robot can safely reach the target location via an optimal path.

The above objects are achieved by, according to the present invention, a robot moving within a specific space; a first image information acquisition unit that receives a first three-dimensional image of a specific space and acquires first image information; And a server that extracts an area of interest based on the color of the floor tile boundary among the first photo information, creates an area where a floor tile pattern is detected among the first photo information as a target space, creates a map formed by dividing the target space into a plurality of areas based on the floor tile pattern, extracts the shape of each object of the first photo information from the map, merges the first 3D image of the shape of each extracted object with the map, determines whether the shape of the object exists on each side of the map, and if the shape of the object exists, determines whether the shape of the object on each side is a robot marker, and if the shape of the object on each side is a robot marker, recognizes the location of the inner side of the map as the current location of the robot, extracts the shortest path that minimizes the sum of the horizontal and vertical lengths of an obstacle-free side between the current location of the robot and the target location based on the current location of the robot, determines whether the robot has arrived at the target location, and stops the movement of the robot when the robot has arrived at the target location. Can be.

According to an embodiment of the present invention, the target space can be configured by dividing an area where a floor tile pattern is detected by forming a boundary based on a difference in color.

According to an embodiment of the present invention, a two-dimensional plane can be created and configured based on the boundary in the target space.

According to an embodiment of the present invention, the server may be configured to extract a plurality of exterior edges from the first photo information, detect a minimum size area having four intersections of the plurality of extracted exterior edges as one floor tile pattern, and detect the first floor tile pattern by recognizing the arrangement between the first floor tile and an adjacent second floor tile.

According to an embodiment of the present invention, the server may be configured to recognize the arrangement between the first floor tile and the adjacent second floor tile by recognizing the repetition of the intersection of the exterior edges or by calculating the size of the minimum size area recognized as the exterior edge.

According to an embodiment of the present invention, the server recognizes the continuous area of the array as a floor tile, and generates a serial number for each tile based on the floor tile.

According to an embodiment of the present invention, the server may be configured to generate a serial number by dividing the floor tile based on the floor tile and the movement width of the robot.

According to an embodiment of the present invention, the server may be configured to analyze an image acquired after the map is generated, and when an obstacle is detected on an edge formed between a first floor tile and an adjacent second floor tile among a plurality of floor tiles, recognize that an obstacle is placed between the first floor tile and the adjacent second floor tile.

According to an embodiment of the present invention, the server may be configured to calculate the movement distance of the robot between the first floor tile and the second floor tile as the average distance of the edge corresponding to the movement path of the robot.

According to an embodiment of the present invention, the server may be configured to determine a movement path between the current location of the robot and the target location by determining a movement path having a minimum movement distance between two obstacle-free floor tiles among a plurality of floor tiles as the movement path of the robot.

According to an embodiment of the present invention, a second image information acquisition unit is further included to receive a second three-dimensional image of a specific space and acquire second image information, and the server may be configured to detect the presence of an obstacle in the first floor tile when an edge is occluded between the first floor tile and a third floor tile opposite to the direction in which the first floor tile is directed toward a position where the second floor tile is arranged, in a state in which there is no obstacle occlusion of the edge between the first floor tile and the second floor tile in the second image information.

The above objects are achieved, according to the present invention, by a first step in which a first photo information acquisition unit receives a first three-dimensional image of a specific space and acquires first photo information; a second step in which a server creates an area in which a floor tile pattern is detected from the first photo information as a target space; a third step in which the server creates a map formed by dividing the target space into a plurality of areas based on the floor tile pattern; a fourth step in which the server extracts the shape of each object of the first photo information from the map; a fifth step in which the server merges the first three-dimensional image of the shape of each object extracted with the map; a sixth step in which the server determines whether the shape of the object exists on each side of the map; a seventh step in which, if the condition of the sixth step is satisfied, the server determines whether the shape of the object on each side is a robot marker; an eighth step in which, if the condition of the seventh step is satisfied, the server recognizes the position of an inner side of the map as the current position of the robot; The method for obstacle avoidance and movement based on virtual map generation can be achieved by a ninth step in which the server extracts the shortest path that minimizes the sum of the horizontal and vertical lengths of an obstacle-free surface between the current position of the robot and the target position based on the current position of the robot; a tenth step in which the server determines whether the robot has arrived at the target position; and an eleventh step in which the server stops the movement of the robot when the condition of the tenth step is satisfied.

According to an embodiment of the present invention, if the sixth step is not satisfied, the server further includes a step of recognizing that no obstacle is located on the inner surface of the map.

According to an embodiment of the present invention, if the seventh step is not satisfied, the server further includes a step of recognizing that an obstacle is located on an inner surface of the map.

The present invention has the effect of increasing the efficiency of a robot's detour route search when an exception occurs by using a CCTV camera that is less expensive than sensor and lidar equipment.

The present invention has the effect of enabling a robot to safely reach a target location via an optimal path by precisely recognizing the presence and location of obstacles in a specific space.

FIG. 1 is a block diagram of a robot obstacle avoidance and movement system based on virtual map generation according to one embodiment of the present invention.
FIG. 2 is first photographic information obtained by inputting a first three-dimensional image according to one embodiment of the present invention.
Figure 3 is photographic information showing the area where the floor tile pattern was detected in Figure 2.
Figure 4 is merged first photo information according to one embodiment of the present invention.
Figure 5 is an image converted from Figure 4 and displayed as a line.
Figure 6 is a map divided into multiple zones according to one embodiment of the present invention.
Figure 7 is photo information recognizing the current location of a robot according to one embodiment of the present invention.
Figure 8 is a map showing a robot and an object according to one embodiment of the present invention.
Figure 9 is a map showing the current location, target location, and obstacles of a robot according to one embodiment of the present invention.
FIG. 10 is a map showing the shortest path that minimizes the sum of the horizontal and vertical lengths of an obstacle-free surface between the current position and the target position of the robot according to one embodiment of the present invention.
FIG. 11 is a first flowchart of a method for robot obstacle avoidance and movement by creating a virtual map according to one embodiment of the present invention.
Fig. 12 is a second flowchart of a method for avoiding obstacles and moving a robot by creating a virtual map according to one embodiment of the present invention.

Hereinafter, a 'robot obstacle avoidance and movement system based on virtual map creation and an obstacle avoidance and movement method thereof' according to a preferred embodiment of the present invention will be described.

FIG. 1 is a block diagram of a system for robot obstacle avoidance and movement by creating a virtual map according to an embodiment of the present invention, FIG. 2 is first image information acquired by inputting a first three-dimensional image according to an embodiment of the present invention, FIG. 3 is image information showing an area where a floor tile pattern is detected in FIG. 2, and FIG. 4 is merged first image information according to an embodiment of the present invention. In addition, FIG. 5 is an image converted from FIG. 4 and indicated by lines, FIG. 6 is a map formed by dividing into a plurality of areas according to an embodiment of the present invention, FIG. 7 is image information recognizing the current location of the robot according to an embodiment of the present invention, FIG. 8 is a map showing a robot and an object according to an embodiment of the present invention, FIG. 9 is a map showing the current location, target location, and obstacles of the robot according to an embodiment of the present invention, and FIG. 10 is a map showing a shortest path that minimizes the sum of the horizontal and vertical lengths of an obstacle-free surface between the current location and the target location of the robot according to an embodiment of the present invention.

Referring to FIG. 1, a robot obstacle avoidance and movement system (1000) according to virtual map creation may include a first photo information acquisition unit (100), a second photo information acquisition unit (200), a robot (robot, 300), and a server (server, 400).

The first image information acquisition unit (100) receives a first three-dimensional image of a specific space and acquires first image information as shown in Fig. 2. The first image information acquisition unit (100) may be implemented using multiple closed-circuit television (CCTV) cameras, but is not limited thereto. The specific space may be an indoor space of a building.

The server (400) extracts an area of interest based on the color of the floor tile boundary among the first photo information, and creates an area in which a floor tile pattern such as that in FIG. 3 is detected among the first photo information as a target space.

At this time, the server (400) extracts only the indoor area composed of floor tiles as the region of interest by differentiating the color between the floor and the wall surface at the bottom of the wall to distinguish the area where the floor tile pattern is detected from the wall. The first photo information acquired from the plurality of first photo information acquisition units (100) is merged as shown in Fig. 4.

The target space is divided into areas where floor tile patterns are detected by forming boundaries based on color differences. When the floor tiles are white and the mop base at the bottom of the wall is black, the pattern of color differences is detected, and the space captured as white is set as the area where the robot can move and the floor tile pattern is detected. The black part that borders the area where the floor tile pattern is detected can be recognized separately.

A two-dimensional plane can be generated and configured based on the boundary in the target space. Let's say that the first photo information acquisition unit (100) is a CCTV camera. The CCTV camera that acquires an image including the movement path of the robot corrects the area detected by the floor tiles that are distorted due to mechanical characteristics such as the image and lens distance and angle into a square shape. Among the images acquired through the CCTV camera, the image taken based on the boundary of the generated area is corrected to the YZ plane (floor) by calculating the angles of the X-axis, Y-axis, and Z-axis (image processing calibration). In addition, the CCTV camera detects the entire indoor space area of the floor in a square shape based on a specific RGB color of the boundary line of the area detected by the floor tiles.

And, the server (400) extracts a plurality of external edges from the first photo information, and detects a minimum size area having four intersections of the extracted plurality of external edges as one floor tile pattern, and detects the first floor tile pattern by recognizing the arrangement between the first floor tile and the adjacent second floor tile.

The boundary line of the floor tile is extracted in the form of an edge through an edge detection process that extracts only lines within the area detected as a floor tile, and when the corners where the lines meet form a square with four corners, it is recognized as a pattern and a line is drawn up to the area detected horizontally and vertically.

At this time, the server (400) recognizes the repetition of the intersection of the exterior edges or calculates the size of the minimum size area recognized as the exterior edge to recognize the arrangement between the first floor tile and the adjacent second floor tile.

Additionally, the server (400) recognizes a continuous area of arrays as a floor tile, and generates a serial number for each tile based on the floor tile.

At this time, the server (400) divides the floor tile based on the movement width of the floor tile and the robot (300) and generates a serial number. Specifically, when the size of the floor tile is larger than the movement width of the robot (e.g., more than twice), the floor tile can be divided, and when the size of the floor tile is smaller than the movement width of the robot (e.g., less than 0.5 times), two adjacent tiles can be merged and recognized as one floor tile.

In addition, the server (400) merges the first 3D image of the shape of each extracted object and the map, and determines whether the shape of the object exists on each side of the map. At this time, the server (400) extracts only the edges from the merged image, converts it into an image indicated by lines as in FIG. 5, and then connects the parts corresponding to the tile boundaries with lines so that a single virtual indoor map can be set up, allowing a movement path to be set up on the floor.

In addition, the server (400) creates a map divided into multiple zones as shown in Fig. 6 based on the floor tile pattern within the target space, and extracts the shape of each object of the first photo information from the map.

The server (400) analyzes the image acquired after the map is created, and when an obstacle is detected on the edge formed between a first floor tile and an adjacent second floor tile among a plurality of floor tiles, it recognizes that an obstacle is placed between the first floor tile and the adjacent second floor tile.

Additionally, if an object shape exists, the server (400) determines whether the shape of the object on each side is a robot marker (a marker recognized by the robot head, robot marker). At this time, the server (400) recognizes that an obstacle exists on the floor tile and displays the obstacle on the virtual indoor map.

Additionally, if the shape of the object on each side is a robot marker, the server (400) recognizes the location of the inner side of the map as the current location of the robot (300). At this time, the current location of the robot (300) is displayed differently, and the destination location to which the robot (300) must move is displayed on the map.

The server (400) recognizes the current location of the robot from the photo information as in Fig. 7, and then recognizes the robot and objects as in Fig. 8 and displays them on the map. Thereafter, the server (400) extracts the shortest path that minimizes the sum of the horizontal and vertical lengths of the obstacle-free surface between the current location of the robot (300) and the target location from the map displayed as in Fig. 9, based on the current location of the robot (300), as in Fig. 10, so that the robot (300) can move while avoiding obstacles.

At this time, the server (400) calculates the movement distance of the robot (300) between the first floor tile and the second floor tile as the average distance of the edge corresponding to the movement path of the robot (300).

In addition, when determining a movement path between the current position and the target position of the robot (300), the server (400) determines a movement path having the minimum movement distance among the movement distances between two floor tiles without obstacles among a plurality of floor tiles as the movement path of the robot (300).

In this way, the server (400) transmits the extracted shortest path to the robot (300) so that the robot (300) can move along the shortest path.

In addition, the server (400) determines whether the robot (300) has arrived at the target location, and if the robot (300) has arrived at the target location, stops the movement of the robot (300). In this way, the server (400) continuously acquires photo information from the first photo information acquisition unit (100) until the robot (300) arrives at the target location, thereby recognizing the presence and location of obstacles, and enabling the robot to safely reach the target location.

In addition, the second photo information acquisition unit (200) can acquire second photo information by receiving a second 3D image of a specific space.

In addition, when the server (400) detects that there is an obstacle in the first floor tile when the edge between the first floor tile and the second floor tile is occluded in the second photo information and the third floor tile is opposite to the direction in which the first floor tile is directed toward the position where the second floor tile is placed, the server (400) detects that there is an obstacle in the first floor tile.

Fig. 11 is a first flowchart of a method for robot obstacle avoidance and movement according to virtual map creation according to one embodiment of the present invention, and Fig. 12 is a second flowchart of a method for robot obstacle avoidance and movement according to virtual map creation according to one embodiment of the present invention. A and B indicate the portion where Figs. 11 and 12 are connected.

Referring to FIGS. 11 and 12, a method for robot obstacle avoidance and movement based on virtual map generation may include S100 to S1100. For detailed descriptions related to FIGS. 11 and 12, refer to the description of FIG. 1.

First, the first photo information acquisition unit (100) receives a first 3D image of a specific space and acquires photo information (S100).

After S100, the server (400) creates an area in which a floor tile pattern is detected among the first photo information as a target space (S200).

After S200, the server (400) creates a map divided into multiple zones based on the floor tile pattern within the target space (S300).

After S300, the server (400) extracts the shape of each object of the first photo information from the map (S400).

After S400, the server (400) merges the first 3D image and map of the shape of each extracted object (S500).

After S500, the server (400) determines whether an object shape exists on each side of the map (S600).

If the condition of S600 is satisfied, the server (400) determines whether the shape of the object on each side is a robot marker (S700). However, if the condition of S600 is not satisfied, the server (400) recognizes that no obstacle is located on the inner side of the map (S650).

If the condition of S700 is satisfied, the server (400) recognizes the location of the inner surface of the map as the current location of the robot (300) (S800). However, if S700 is not satisfied, the server (400) recognizes that an obstacle is located on the inner surface of the map (S750).

After S800, the server (400) extracts the shortest path that minimizes the sum of the horizontal and vertical lengths of the obstacle-free surface between the current position of the robot (300) and the target position based on the current position of the robot (300) (S900).

After S900, the server (400) determines whether the robot (300) has arrived at the target location (S1000).

If the condition of S1000 is satisfied, the server (400) stops the movement of the robot (300) (S1100). However, if the condition of S1000 is not satisfied, S100 is performed again.

The system described above may be implemented using hardware components, software components, and/or a combination of hardware components and software components. For example, the devices and components described in the embodiments may be implemented using one or more general-purpose computers or special-purpose computers, such as a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing instructions and responding to them.

A processing unit can execute an operating system (OS) and one or more software applications running on the OS. Furthermore, the processing unit can access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit is sometimes described as being used singly; however, those skilled in the art will appreciate that the processing unit may include multiple processing elements and/or multiple types of processing elements. For example, the processing unit may include multiple processors, or a processor and a controller. Other processing configurations, such as parallel processors, are also possible.

Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing device to perform a desired operation or may independently or collectively command the processing device. The software and/or data may be embodied in any type of machine, component, physical device, computer storage medium, or device for interpretation by the processing device or for providing instructions or data to the processing device. The software may also be distributed over networked computer systems and stored or executed in a distributed manner. The software and data may be stored on one or more computer-readable recording media.

The method described above can be implemented in the form of program instructions that can be executed via various computer means and recorded on a computer-readable medium. The medium may be used to permanently store a computer-executable program or temporarily store it for execution or download.

In addition, the medium may be a variety of recording or storage means in the form of a single or multiple hardware combinations, and is not limited to media directly connected to a computer system, but may also exist distributedly on a network. Examples of the medium may include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and those configured to store program instructions, including ROM, RAM, and flash memory. In addition, examples of other media may include recording or storage media managed by app stores that distribute applications, sites that supply or distribute various software, servers, etc.

As described above, the present invention has been described with reference to an embodiment shown in the drawings, but is not limited to the embodiment, and can be implemented by modifying and changing within a scope that does not depart from the gist of the present invention, and the modifications and changes made are included in the technical spirit of the present invention.

100: 1st photo information acquisition unit 200: 2nd photo information acquisition unit
300: Robot 400: Server

Claims (12)

A robot moving within a specific space; a first image information acquisition unit that receives a first three-dimensional image of the specific space and acquires first image information; And a server that extracts a floor tile boundary from the first photo information to create a target space in an area where a floor tile pattern is detected, and creates a map formed by dividing the target space into a plurality of areas based on the floor tile pattern, extracts the shape of each object of the first photo information from the map and merges the first 3D image and the map into images, and if the shape of an object existing on each side of the map is a robot marker, recognizes the current position of the robot on the inner side of the map and extracts the shortest path that minimizes the sum of the horizontal and vertical lengths of an obstacle-free surface between the current position of the robot and the target position, and stops the movement of the robot when the robot arrives at the target position; In a system for robot obstacle avoidance and movement according to virtual map creation, the target space is a region of interest extracted based on the color of the floor tile boundary and created as a target space in an area where a floor tile pattern is detected, and a boundary is formed based on a difference in color, and the server generates a plurality of external appearances from the first photo information. A robot obstacle avoidance and movement system based on virtual map generation, characterized in that the system extracts edges and detects a minimum size area having four intersections of a plurality of extracted exterior edges as a single floor tile pattern, and detects the first floor tile pattern by recognizing the arrangement between a first floor tile and an adjacent second floor tile. delete In the first paragraph,
A robot obstacle avoidance and movement system based on virtual map generation, characterized in that a two-dimensional plane is generated based on the boundary in the above target space. delete In the first paragraph,
A robot obstacle avoidance and movement system according to virtual map generation, characterized in that the server recognizes the arrangement between the first floor tile and the adjacent second floor tile by recognizing the repetition of the intersection of the exterior edges or calculating the size of the minimum size area recognized as the exterior edge. In paragraph 5,
A robot obstacle avoidance and movement system based on virtual map generation, characterized in that the server recognizes the continuous area of the above arrangement as a floor tile and generates a serial number for each tile based on the floor tile. In paragraph 6,
A robot obstacle avoidance and movement system based on virtual map generation, characterized in that the above server generates a serial number by dividing the floor tiles based on the floor tiles and the robot's movement width. In paragraph 7,
A system for robot obstacle avoidance and movement according to virtual map generation, characterized in that the server analyzes an image acquired after the map is generated, and when an obstacle is detected on an edge formed between a first floor tile and an adjacent second floor tile among a plurality of floor tiles, the system recognizes that an obstacle is placed between the first floor tile and the adjacent second floor tile. In paragraph 8,
A system for robot obstacle avoidance and movement based on virtual map generation, characterized in that the server calculates the robot's movement distance between the first floor tile and the second floor tile as the average distance of the edge corresponding to the robot's movement path. In paragraph 9,
A system for robot obstacle avoidance and movement by creating a virtual map, characterized in that the server determines the movement path of the robot as the movement path having the minimum movement distance among the movement distances between two floor tiles without obstacles among a plurality of floor tiles when determining the movement path between the current location of the robot and the target location. In the first paragraph,
A system for robot obstacle avoidance and movement according to virtual map generation, characterized in that it further includes a second image information acquisition unit that receives a second three-dimensional image of a specific space and acquires second image information, and the server detects an edge occlusion between the first floor tile and a third floor tile opposite to the direction in which the first floor tile is directed toward the position where the second floor tile is arranged in a state in which there is no obstacle occlusion of the edge between the first floor tile and the second floor tile in the second image information, and detects that there is an obstacle in the first floor tile. A first step in which a first image information acquisition unit receives a first three-dimensional image of a specific space and acquires first image information; a second step in which a server creates an area in which a floor tile pattern is detected from the first image information as a target space; a third step in which the server creates a map divided into a plurality of areas based on the floor tile pattern within the target space; a fourth step in which the server extracts the shape of each object of the first image information from the map; a fifth step in which the server merges the first three-dimensional image of the shape of each extracted object with the map; a sixth step in which the server determines whether an object shape exists on each side of the map; a seventh step in which, if the condition of the sixth step is satisfied, the server determines whether the shape of the object on each side is a robot marker; an eighth step in which, if the condition of the seventh step is satisfied, the server recognizes a location of an inner side of the map as a current location of the robot; A ninth step in which the server extracts the shortest path that minimizes the sum of the horizontal and vertical lengths of an obstacle-free surface between the current position of the robot and the target position based on the current position of the robot; A tenth step in which the server determines whether the robot has arrived at the target position; And in a method for robot obstacle avoidance and movement according to virtual map generation, including an 11th step in which the server stops the movement of the robot when the condition of the 10th step is satisfied; wherein the 2nd step includes a step in which the server creates an area in which a floor tile pattern is detected from the first photo information as a target space, wherein the target space is created by extracting an area of interest based on the color of the floor tile boundary and creating an area in which a floor tile pattern is detected as a target space, and forming a boundary based on the color difference to divide the area in which the floor tile pattern is detected; and the 4th step includes a step in which the server extracts a plurality of exterior edges from the first photo information, detects a minimum size area in which four intersections of the plurality of extracted exterior edges are present as one floor tile pattern, and recognizes an arrangement between the first floor tile and an adjacent second floor tile to detect the first floor tile pattern.