KR20130133591A - A method and apparatus for segmenting a grid map into a plurality of rooms - Google Patents

Abstract

According to a method and an apparatus for segmenting a grid map with a multiple rooms from the present invention, the grid map can be marked off with an optimized form of multiple rooms. The method and apparatus for segmenting the grid map of the present invention with multiple rooms can process an erosion of the grid map according to different of levels, the most frequently room number out of all the room numbers obtained according to the erosion results can be selected. The grid map can be changed based on the selected room number, and therefore, the grid map can be marked off and segmented with the optimized forms of multiple rooms. [Reference numerals] (202) Perform erosion according to multiple levels about grid map;(204) Select the number of most frequently obtained rooms among the number of rooms obtained by erosion result;(206) Transform grid map based on the selected number of rooms;(AA) START;(BB) END

Description

A METHOD AND APPARATUS FOR SEGMENTING A GRID MAP INTO A PLURALITY OF ROOMS}

The present invention relates to a method and apparatus for partitioning a grid map, and more particularly, to a method and apparatus for partitioning a map into a plurality of rooms in a manner optimized for a grid map.

The grid map is a map representing a specific spatial region as a plurality of cells and is used in various industrial regions. As an example, the mobile robot cleaner may set a moving path for the indoor space of the home by using a grid map representing the indoor space of the home and perform cleaning according to the set moving path.

In addition, when analyzing and structuring the topology of the grid map, the grid map may be used more effectively. For example, the grid map may be divided into a plurality of sub areas, and the grid map may be used according to the partitioned sub areas. For example, when a grid map representing an indoor space of a house is analyzed and the indoor space of the home is partitioned into a plurality of rooms, the mobile robot cleaner only cleans a specific room for each of the divided rooms. You can do something like monitor a particular room.

Partitioning the grid map as described above can be performed automatically by a computer, and one of the important problems is partitioning the grid map in the most accurate form. More specifically, when the grid map is to be partitioned, it is most optimal to partition the number of rooms so that the point connecting the rooms, that is, the location of the virtual door, is best to recognize. Must be in the grid map compartment to be an important issue.

An embodiment of the present invention provides a method and apparatus for partitioning a grid map in an optimal form in partitioning a grid map into a plurality of rooms.

In order to achieve the problem to be solved, the method for partitioning a grid map (grid) into a plurality of rooms according to an embodiment of the present invention performs erosion according to a plurality of levels with respect to the grid map Making; Selecting the number of rooms most frequently obtained from the number of rooms acquired for each level according to the erosion result; And modifying the grid map based on the selected number of rooms.

According to an embodiment, the method of partitioning the grid map may include virtually most frequently obtained based on the selected number of rooms among virtual doors obtained for each level according to a result of the erosion. The method may further include selecting a number of doors.

According to an embodiment, the method of partitioning the grid map may include selecting a number of virtual doors based on the selected number of rooms from among the number of virtual doors obtained for each level according to the erosion result. In addition, the number of the selected virtual door may be characterized in that the N or less calculated by the following formula.

N = n (n-1) / 2

(N: maximum number of virtual doors selected, n: number of selected rooms)

According to an embodiment, the method of partitioning the grid map may include at least one based on the selected number of rooms and the selected number of virtual doors, based on the coordinates of the virtual doors obtained for the respective levels according to a result of the erosion. Determining the coordinates of the virtual door of the; may further include.

According to an embodiment, the method of partitioning the grid map may include the selected number of rooms, the number of selected virtual doors, and the selected at least one of directions of a virtual door obtained for each level according to a result of the erosion. The method may further include determining a direction of the selected at least one virtual door based on the coordinates of the virtual door.

The determining of the coordinates of the at least one virtual door may include determining the coordinates of the first virtual door and the coordinates of the second virtual door among the virtual doors obtained as a result of the erosion. When the difference between the coordinates of the and the second virtual door is less than a predetermined value may be determined that the first virtual door and the second virtual door is close to each other.

The determining of the coordinates of the at least one virtual door according to an embodiment may include: a frequency in which coordinates of the at least one virtual door are determined to be the same as or close to another virtual door among the virtual doors acquired according to the levels. May determine the coordinates of the at least one virtual door based on the high rank.

The determining of the coordinates of the at least one virtual door according to an embodiment may include: determining that the coordinates of the at least one virtual door are the same as or close to the other virtual door among the virtual doors acquired according to the levels as a result of the erosion. The average of the coordinates of the doors may be used to determine the coordinates of at least one virtual door.

According to an embodiment, the method of partitioning the grid map may further include modifying the grid map based on the selected number of virtual doors, coordinates of the selected at least one virtual door, and the determined direction of the at least one virtual door. The grid map may be modified.

In order to achieve the object to be solved, an apparatus for partitioning a grid map according to an embodiment of the present invention comprises at least one memory; At least one processor that executes a program included in the at least one memory; the program comprising: performing erosion according to a plurality of levels with respect to a grid map; Selecting the number of rooms most frequently obtained from the number of rooms acquired for each level according to the erosion result; And modifying the grid map based on the selected number of rooms.

The present invention also provides a computer readable recording medium having recorded thereon a program including a method of partitioning a grid map of embodiments of the present invention into a plurality of rooms.

According to the above-described problem solving means of the present invention, in partitioning the grid map (Grid Map) into a plurality of rooms, the grid map is partitioned in an optimal form with respect to the number of rooms and the position of the virtual door (Virtual Door), etc. It can provide a method and apparatus that can be.

1 shows an example of a grid map according to the prior art.
2A is a flowchart illustrating a method of dividing a grid map into a plurality of rooms according to an embodiment of the present invention.
2B is a flowchart illustrating a method of partitioning a grid map into a plurality of rooms according to another embodiment of the present invention.
2C is a flowchart illustrating a method of partitioning a grid map into a plurality of rooms according to another embodiment of the present invention.
FIG. 2D is a flowchart illustrating in more detail a step of partitioning the grid map based on the number of rooms, the number of virtual doors, coordinates, and directions obtained in FIG. 3C.
3A shows an example of a grid map displaying an indoor space.
3B to 3J illustrate a map or a figure generated in a process of partitioning a grid map into a plurality of rooms according to an embodiment of the present invention.
FIG. 4 illustrates a correlation graph of the number of rooms generated according to the number of eroding layers in partitioning a grid map according to an exemplary embodiment of the present invention.
FIG. 5 illustrates an embodiment in which a user uses a partitioned grid map according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, which will be readily apparent to those skilled in the art. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification.

Hereinafter, the present invention will be described in detail with reference to the accompanying drawings. FIG. 1 shows an example of a grid map according to the prior art. The grid map according to FIG. 1 is composed of a plurality of cells. The size of one cell may be, for example, 40 cm x 40 cm. Among the plurality of cells, the cell 102 is a cell indicating a position where an obstacle exists. The cell 103 is a cell representing a space surrounded by obstacles. The cell 101 is a cell representing a space outside the obstacle. The robot 104 may generate a grid map by detecting the position of the obstacle cell 102 while moving, or perform a specific task in a specific area by using the generated grid map.

2A is a flowchart illustrating a method of dividing a grid map into a plurality of rooms by an apparatus for performing map segmentation according to an embodiment of the present invention.

In step 202, the device erodes the grid map according to a plurality of levels.

In step 204, the device selects the number of rooms most frequently obtained from the number of rooms obtained according to each level of erosion as a result of performing the erosion.

In step 206 the device transforms the grid map based on the selected number of rooms.

2B is a flowchart illustrating a method of partitioning a grid map into a plurality of rooms according to an embodiment of the present invention. Hereinafter, in describing a method of partitioning a grid map according to the flowchart of FIG. 2A, FIGS. 3A to 3J may be cited. 3A shows an example of a grid map 301 displaying an indoor space.

In step 212 the device erodes inwardly from the grid map 301 of FIG. 3A by a predetermined level to create the inner space 303 of FIG. 3C. According to one embodiment, the predetermined level of erosion may be one layer having a width of one cell. According to another embodiment, the predetermined level of erosion may be one layer having a width of a particular value set by the user. 4A, 4C, and 4E, the interior space 410 of FIG. 4A is an interior space created when the erosion level is 22 layers, and the interior space 420 of FIG. 4C is 23 layers with erosion levels. Is an internal space created when is, and the internal space 430 of FIG. 4E is an internal space created when the erosion level is 15 layers. At this time, the level of the erosion level must be properly determined so that the grid map of FIG. 3A can be partitioned into an optimal shape.

In step 214 the device checks the number of rooms from the interior space 303 created through erosion.

In step 216 the device determines whether the number of rooms acquired in step 214 is at least one person.

When eroding the grid map 301 according to the low erosion level, there may be one room included in the interior space 430, as in the interior space 430 of FIG. 4E. If the erosion level is gradually increased, the number of rooms may be two, as in FIG. 4A or 4B. According to another erosion level, the number of rooms may be two or more. In addition, when the erosion level is higher than a certain level, the erosion is performed on the entire grid map 301 so that the internal space 303 cannot be generated, and the number of rooms may be zero.

If it is determined that the number of rooms included in the interior space 303 created in step 216 is at least one, the device performs step 218; otherwise, the device performs step 220.

In step 218 the device increases the predetermined level. The device may increase the predetermined level by increasing the number of layers used for erosion.

After the device performs step 218, the device then performs steps 212 through 216 again according to the increased predetermined level.

The method of increasing the predetermined erosion levels in steps 212 to 218 and acquiring the number of rooms according to each level is only one embodiment of acquiring the number of rooms for each of the various erosion levels. The number of rooms can be obtained for each of several erosion levels. In another embodiment, the device can determine the number of rooms according to each erosion level while decreasing the predetermined erosion level. In another embodiment, the device may acquire the number of rooms by performing erosion in any order for each of the plurality of erosion levels defined by the user. In another embodiment, the device may acquire the number of rooms by performing erosion in the order defined by the user for each of the plurality of erosion levels defined by the user. Those skilled in the art understand that it is possible to obtain the number of rooms according to each of the various erosion levels in a variety of other ways, including the methods introduced above.

In step 220 the device selects one of the number of rooms acquired according to each erosion level in step 214 as the final number of rooms for partitioning the grid map 301. According to one embodiment, the device may select at step 214 the number of rooms acquired most frequently among the number of rooms acquired according to each erosion level.

In step 222 the device partitions the grid map 301 based on the number of rooms selected in step 220. According to an embodiment, the device may partition the grid map 301 based on the coordinate information of the internal cells of the grid map 301 and the number of rooms selected in step 220.

2C is a flowchart illustrating a method of partitioning a grid map into a plurality of rooms according to another embodiment of the present invention.

In step 252 the device generates the Voronoi Graph 302 of FIG. 3B from the grid map 301 of FIG. 3A. The Voronoi graph is one of the methods of decomposing and displaying a given metric space. Each line of the Voronoi graph has a different distance from a specific object with objects arranged in the given metric space. When the points that are not larger than the distance to the object are configured as a set, the lines representing the boundaries of the sets of the points configured as described above are included. In other words, it is a line connecting intermediate points at the same distance to two objects in a given metric space. In the present invention, the outlines shown in bold in FIGS. 3A and 3B serve as objects, and the thinner inner lines in FIG. 3B are Voronoi graphs generated based on these objects.

In step 254, the device erodes inward from the grid map 301 of FIG. 3A by a predetermined level to create the interior space 303 of FIG. 3C. The manner of performing erosion in step 254 is the same as in step 212 of FIG. 2B.

Steps 252 and 254 may be performed either one before or the other.

The operation of steps 256 and 258 is as described in steps 214 and 216 of FIG. 2B.

If the device determines in step 258 that the number of rooms included in the generated interior space 303 is at least one, the device performs step 260; otherwise, the device performs step 270. do.

In step 260 the device creates the configuration space 304 of FIG. 3D using the Voronoi graph 302 generated in step 252 and the internal space 303 generated in step 254. do. The shape space 304 is generated by overlapping the Voronoi graph 302 and the internal space 303. As shown in FIG. 3D, the shape space 304 is composed of an interior space 303 and a plurality of tails shown outside of the interior space 303.

In step 262, the device generates the Voronoi tails 305 of FIG. 3E by pulling the interior space 303 out of the shape space 304.

In step 264 the device generates the Voronoi cut tails 306 of FIG. 3F from the Voronoi tail 305. The Voronoi cuttail 306 shows only the tails remaining after deleting the tails intersecting the internal space 303 of FIG. 3C only once among the tails included in the Voronoi tail 305. Referring to FIGS. 3E and 3F, the tails left in FIG. 3F of the tails shown in FIG. 3E are the tails that intersect the interior space 303 of FIG. 3C twice, and the rest all intersect only once with the interior space 303. Tails.

In step 266 the device obtains information about the virtual doors from the generated Voronoi cuttail 306. More specifically, the device may recognize a line as a virtual door by drawing a line having a predetermined length in a direction perpendicular to the Voronoi cuttail 306 from an intermediate point of the generated Voronoi cuttail 306. 3G is an example of a virtual door recognized in this manner. The device may obtain information on the number, coordinates, and directions of the virtual doors from the recognized virtual door.

Information about the virtual door that is obtained as a result in step 266 is affected by the degree of level of performing erosion. In the case of performing erosion on 22 layers as in FIG. 4A, a virtual door as in 412 of FIG. 4B is recognized, and in the case of performing erosion in 23 layers as in FIG. 4C, as in 422 and 424 in FIG. 4D. The virtual door is recognized, and when erosion is performed on 15 layers as shown in FIG. 4E, the virtual door as shown at 432 of FIG. 4F is recognized. As will be explained later, the virtual door 424 of FIG. 4D obtained by erosion of 23 layers and the virtual door 432 of FIG. 3F obtained by erosion of 15 layers consequently define the grid map 301. Information about the virtual door that is not suitable.

The device then performs step 268 to increase the predetermined level. The operation of increasing the predetermined level is as described in step 218 of FIG. 2B.

After the device performs step 268, the device then performs steps 254 to 258 again according to the increased predetermined level.

In step 270, the device determines the grid based on the number of rooms acquired according to each erosion level in step 256, the number of virtual doors acquired according to each erosion level in step 266, the coordinates and directions of the virtual doors. The map 301 is partitioned.

2D more specifically illustrates how the device partitions grid map 301 at step 270.

In step 272 the device selects one of the number of rooms acquired according to each erosion level in step 256 as the final number of rooms for partitioning the grid map 301. According to one embodiment, the device may select the most frequently acquired room number from among the number of rooms acquired according to each erosion level in step 256.

In step 274 the device selects the number of virtual doors based on the number of rooms selected in step 272. According to one embodiment, the device may select the number of virtual doors most frequently obtained based on the number of rooms selected from among the number of virtual doors obtained in step 266 according to each erosion level.

In operation 276, the device may determine the coordinates and directions of the final virtual door to partition the grid map 301 based on the number of selected rooms and the number of selected virtual doors. According to one embodiment the coordinates of the final virtual door to partition grid map 301 may be the coordinates of at least one virtual door determined from the coordinates of the virtual doors obtained according to the respective erosion levels in step 266. have.

According to an embodiment, the apparatus may determine that the virtual doors are adjacent to each other when the difference between the coordinates of two different virtual doors among the coordinates of the virtual doors acquired according to each erosion level is less than a predetermined value in step 266. Can be determined to be. For example, when the coordinate of the first virtual door is (X1, Y1) and the coordinate of the second virtual door is (X2, Y2), the deviation D of the coordinates of the first virtual door and the second virtual door is defined as follows. and,

When D is less than or equal to a predetermined value, the two virtual doors may be determined to be virtual doors in close proximity to each other.

According to one embodiment, in determining the coordinates of the final virtual door in step 276, the apparatus has a high frequency of determining that the virtual doors obtained according to each erosion level have the same or closest coordinates to each other. Based on the ranking, the coordinates of at least one virtual door to finally partition the grid map 301 may be determined.

In step 278 the device determines the grid map 301 according to the number of rooms selected in step 272, the number of virtual doors selected in step 274, and the coordinates and directions of the at least one virtual door selected in step 276. Section. As an example, FIG. 3H partitions the grid map 301 based on the coordinates and directions of the virtual doors determined in FIG. 3G.

Table 1 shows an example of the number of rooms and the number of virtual doors obtained by performing erosion according to various erosion levels on the grid map 301 according to the present invention. In Table 1 the erosion level is indicated as the number of layers eroded.

Number of erosion layers Number of rooms acquired Number of virtual doors acquired Frequency of number of rooms acquired One One One 15th 2 One 0 3 One 0 4 One 0 5 One 0 6 One 0 7 One One 8 One One 9 One 0 10 One 0 11 One 0 12 One One 13 One 0 14 One 0 15 One One 16 2 One 21 times 17 2 One 18 2 3 19 2 3 20 2 One 21 2 One 22 2 One 23 2 2 24 2 3 25 2 2 26 2 One 27 2 2 28 2 One 29 2 One 30 2 2 31 2 One 32 2 2 33 2 3 34 2 2 35 2 2 36 2 3 37 3 3 3rd time 38 3 3 39 3 2 40 One One 4 times 41 One 0 42 One One 43 One One 44 0 0 1 time

FIG. 5 is a graph illustrating the correlation of the number of rooms generated according to the number of erosion layers.

According to Table 1 and FIG. 5, the number of rooms obtained when eroding one layer in the grid map 301 is one. As the number of erosion layers increases, the number of rooms acquired gradually increases. When erosion is performed on 16 layers, two rooms are obtained. When erosion is performed on 37 layers, three rooms are obtained. In addition, when the number of erosion layers is 44, the total number of rooms obtained by eroding the entire internal space of the grid map 301 is zero.

The device selects the number of rooms most frequently obtained based on the result data as above. In the case of Table 1, the number of cases in which the number of rooms is obtained as one is 19 times, the number of cases in which the number of rooms is obtained as two rooms is 21, and the number of cases in which the number of rooms is three is Three times, the number of cases obtained by the number of rooms is zero is a total of one time. In this regard, the device selects the number of rooms most frequently obtained, so the number of rooms is two.

According to one embodiment, the device may select the number of rooms acquired most frequently consecutively based on the resulting data. For example, even if the total number of cases obtained by having one room is 22 and the number of cases obtained by having two rooms is 21, the total number of cases obtained by two rooms is eroded. The result is obtained continuously as the number of layers increases, whereas when the number of rooms is one, it is obtained when the number of erosion layers is less than or equal to a predetermined number. If the sum is a result, the device selects the number of rooms acquired most frequently in succession, so the number of rooms can be selected as two.

As described above, after the device selects the number of rooms, the device may perform an operation of selecting the number of virtual doors based on the selected number of rooms. According to an embodiment, the device may determine the number of virtual doors through the following formula from the number of rooms based on the combination theory.

N = n (n-1) / 2

N: number of virtual doors

n: number of rooms

For example, if the number of rooms is selected as two rooms, the device selects the number of virtual doors as one (N = 2 (2-1) / 2 = 1), and if the number of rooms is selected as three rooms, the device is virtual. Choose three doors (N = 3 (3-1) / 2 = 3).

In another embodiment, the number of virtual doors most frequently obtained may be selected based on the number of rooms selected in step 268 of the number of virtual doors obtained in step 264. Referring to Table 1, since the device selects two rooms, the erosion is performed on 36 layers since the rooms appear to have two rooms, that is, the erosion on 16 layers. In this case, the number of virtual doors most frequently obtained may be selected from the number of virtual doors acquired. Table 2 below shows only the cases where the number of rooms in Table 1 is two.

Number of erosion layers Number of rooms acquired Number of virtual doors acquired Frequency of number of rooms acquired 16 2 One 21 times 17 2 One 18 2 3 19 2 3 20 2 One 21 2 One 22 2 One 23 2 2 24 2 3 25 2 2 26 2 One 27 2 2 28 2 One 29 2 One 30 2 2 31 2 One 32 2 2 33 2 3 34 2 2 35 2 2 36 2 3

Referring to Table 2, the number of virtual doors is obtained 9 times and the number of virtual doors is 9 times, and when the number of virtual doors is 7 times, the number of virtual doors is 3 The case occurred five times. Thus, the device selects the number of virtual doors most frequently obtained, namely one.

In another invention, the device is obtained from the number of virtual doors obtained from the selected number of rooms based on the combination theory, i.e., N = n (n-1) / 2 (N is the number of virtual doors, n is the number of rooms). The number of virtual doors may be set as a candidate maximum value of the number of virtual doors to be selected, and the number of virtual doors most frequently obtained among the number of virtual doors having a set maximum or less may be selected. Referring to Table 1, the number of virtual doors selected from this embodiment is one.

As described above, after the device selects the number of rooms and the number of virtual doors, the device performs an operation of selecting coordinates of the virtual doors. As described in step 272 of FIG. 2B, if the difference between the coordinates of two different virtual doors is less than or equal to a predetermined value, the device determines that the two virtual doors are adjacent virtual doors, and is obtained according to each erosion level. The coordinates of the at least one virtual door may be determined based on a high frequency ranking in which the coordinates of the virtual doors are determined to have the same or adjacent coordinates with each other.

Referring to Table 2, the virtual doors that will be used to finally partition the grid map 301 when the device has finally obtained the coordinates of the virtual doors at each erosion level obtained as two room numbers are obtained as shown in Table 3 below. The method of determining the coordinates of is described below.

Number of erosion layers X coordinate of the virtual door Y coordinate of the virtual door 16 384 235 17 385 235 18

386 236 385 357 390 395 19

413 232 385 358 389 394 20 387 375 21 387 375 22 387 375 23
325 293 387 375 24

325 292 428 333 387 399 25
428 333 386 402 26 427 332 27
427 332 393 410 28 385 405 29 394 405 30
383 405 367 481 31 383 405 32
406 316 382 405 33

405 317 382 405 351 490 34
349 309 381 405 35
381 405 345 482 36

349 308 380 404 354 476

In Table 3 above, a total of 38 coordinates of the virtual doors acquired from the erosion of 16 layers to the erosion of 36 layers corresponding to the total number of rooms are recorded. As described above, since the device has selected one virtual door from Table 2, the device determines the coordinate of one virtual door from the 38 coordinates recorded in Table 3 above.

According to one embodiment, as described in step 272 of FIG. 2B, the device defines a deviation D of the coordinates of the first virtual door and the coordinates of the second virtual door, and defines the coordinates of the defined first virtual door and the second. When the deviation D of the coordinates of the virtual door is less than or equal to a predetermined value, the first virtual door and the second virtual door may be determined to be virtual doors having the same coordinates or close to each other. The device performs the determination of the proximity of the coordinates of all the virtual doors to determine a high frequency ranking where the coordinates are determined to be the same or close, and based on the determined ranking, the coordinates are determined to be the same or close to each other. The average value calculated by calculating the average of the coordinates of the virtual doors may be determined as the coordinates of the final virtual door to partition the grid map 301.

FIG. 3I illustrates an approximated model generated from the partitioned grid map 308 of FIG. 3H, in accordance with an embodiment of the present invention. According to FIG. 3I, the device generates an approximated model 309 based on the number and coordinates of the partitioned grid map 308 and the number and coordinates of the virtual doors.

According to one embodiment, the approximated model may include rectangles corresponding to each room of the partitioned grid map 308 of FIG. 3H. When the grid map 308 is approximated with rectangles corresponding to each room, the device may determine the position, size, and shape of the rectangle in the following manner.

1. Number each room (eg, assume k rooms exist).

2. When i is the number of a specific room, repeat steps (i) to (vi) below from room 1 to room k (for i = 1 to K do).

(i) Calculate the coordinates (Xi, Yi) of the center point of the i-th room.

(ii) Calculate the area Ai of the i-th room. The area of the i-th room may be calculated through the number of cells included in the i-th room.

(iii) Calculate the average width Xaveragei and height Yaveragei of the i-th room. When Xaveragei divides cells included in the i-th room into cells included in horizontal lines, Xaveragei may calculate the average of the number of cells included in each line. Yaveragei can also be calculated in the same way using vertical lines.

(iv) Calculate the ratio Ri = Yaveragei / Xaveragei in the horizontal and vertical directions.

(v) The horizontal length Xlengthi and the vertical length Ylengthi of the i-th room are calculated based on Ai and Ri.

(vi) Represents a rectangle whose length is Xlengthi and whose length is Ylengthi and whose coordinates are (Xi, Yi).

3. A diagram showing a virtual door connecting rectangles corresponding to each room to each other based on the coordinates of the virtual doors obtained in step 272 of FIG. 2B is shown.

FIG. 6 illustrates an application of an approximated model 309 of the grid map 301 generated in FIG. 3I to a user interface of a user control device according to an embodiment of the present invention.

610 of FIG. 6 illustrates a screen of the user control device. 612 and 614 are approximated rectangles corresponding to the respective rooms when the respective rooms are approximated as in FIG. 3I. 616 is a diagram illustrating a virtual door connecting the approximated rectangles corresponding to the respective rooms.

In 620, the user monitors the status of each room using the user control device screen of 610 or intuitively inputs a command that the device will perform for specific rooms. For example, by touching 612, the user can enter a command to cause the device to perform cleaning in the room corresponding to 612. In operation 630, the device may move to a real space corresponding to 612 and perform cleaning according to a user's command. In another embodiment, the device may be at least one of an audit of a particular room, monitoring of a baby or elderly person, running an entertainment program, rescue work, and remote communication using the 610.

7 is a block diagram illustrating a schematic configuration of an apparatus 700 for performing map segmentation according to an embodiment of the present invention.

As shown in FIG. 7, the map segmentation apparatus 700 according to the present invention includes at least one processor 710 and a memory 720.

The memory 720 includes at least one program. A program included in the memory 720 may cause the processor 710 to execute certain operations when executed by the processor 710. According to one embodiment, a program included in memory 720 may cause processor 710 to execute all or at least a portion of the method included in FIG. 2A when executed by processor 710. According to another embodiment, a program included in memory 720 may, when executed by processor 710, cause processor 710 to execute all or at least a portion of the method included in FIG. 2B. According to another embodiment, a program included in memory 720 may, when executed by processor 710, cause processor 710 to execute all or at least a portion of the methods included in FIGS. 2C and 2D.

The above-described embodiments of the present invention can be embodied in a general-purpose digital computer that can be embodied as a program that can be executed by a computer and operates the program using a computer-readable recording medium. The computer readable recording medium may be a magnetic storage medium such as a ROM, a floppy disk, a hard disk, etc., an optical reading medium such as a CD-ROM or a DVD and a carrier wave such as the Internet Lt; / RTI > transmission).

So far I looked at the center of the preferred embodiment for the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the disclosed embodiments should be considered in an illustrative rather than a restrictive sense. The scope of the present invention is defined by the appended claims rather than by the foregoing description, and all differences within the scope of equivalents thereof should be construed as being included in the present invention.

Claims (19)

In a method for partitioning a grid map into a plurality of rooms by a device that performs map segmentation,
Performing erosion on the grid map according to a plurality of levels;
Selecting the number of rooms most frequently obtained from the number of rooms acquired for each level according to the erosion result; And
And modifying the grid map based on the selected number of rooms. The method of claim 1,
Selecting the number of virtual doors most frequently obtained based on the selected number of rooms among the number of virtual doors obtained for each level according to the erosion performance result; How to partition a grid map characterized by. The method of claim 1,
Selecting the number of virtual doors based on the selected number of rooms from among the number of virtual doors obtained for each level according to the erosion result;
The number of the selected virtual doors is equal to or less than N calculated by the following formula, where N is n (n-1) / 2 (N: maximum value of the selected virtual doors, n: number of selected rooms) How to partition a grid map. 3. The method of claim 2,
Determining coordinates of at least one virtual door based on the selected number of rooms and the number of the selected virtual doors, from the coordinates of the virtual doors obtained for each level according to the erosion performance result. And partitioning the grid map. 5. The method of claim 4,
The at least one virtual selected based on the selected number of rooms, the number of the selected virtual doors, and the coordinates of the selected at least one virtual door among directions of the virtual doors obtained for each level according to the erosion performance result Determining a direction of the door; the method of partitioning a grid map further comprising. 5. The method of claim 4,
The determining of the coordinates of the at least one virtual door may include: coordinates of the first virtual door and coordinates of the first virtual door with respect to the coordinates of the first virtual door and the coordinates of the second virtual door among the virtual doors obtained as a result of the erosion. And 2, when the difference between the coordinates of the virtual door is less than or equal to a predetermined value, determining that the first virtual door and the second virtual door are close to each other. The method according to claim 6,
The determining of the coordinates of the at least one virtual door may be based on a high frequency ranking in which coordinates of the at least one virtual door are determined to be the same as or close to another virtual door among the virtual doors acquired according to the levels. Determining the coordinates of the at least one virtual door. The method according to claim 6,
The determining of the coordinates of the at least one virtual door may include: an average of the coordinates of the virtual doors determined to be the same as or close to the other virtual door among the virtual doors acquired according to the levels as a result of the erosion generated. Determining the coordinates of the at least one virtual door using the method. 6. The method of claim 5,
The modifying the grid map may include modifying the grid map based on the selected number of virtual doors, coordinates of the selected at least one virtual door, and the determined direction of the at least one virtual door. How to compartmentalize. At least one memory;
At least one processor that executes a program included in the at least one memory;
The program
Performing erosion on the grid map according to a plurality of levels;
Selecting the number of rooms most frequently obtained from the number of rooms acquired for each level according to the erosion result; And
And modifying the grid map based on the selected number of rooms. The method of claim 10,
The program
Selecting the number of virtual doors most frequently obtained based on the selected number of rooms among the number of virtual doors obtained for each level according to the erosion performance result; Apparatus for partitioning the grid map, characterized in that it further comprises. The method of claim 10,
The program
Selecting the number of virtual doors based on the selected number of rooms from among the number of virtual doors obtained for each level according to the erosion result;
The number of the selected virtual doors is equal to or less than N calculated by the following formula, where N is n (n-1) / 2 (N: maximum value of the selected virtual doors, n: number of selected rooms) A device for partitioning grid maps. 12. The method of claim 11,
The program
Determining coordinates of at least one virtual door based on the selected number of rooms and the number of the selected virtual doors from coordinates of the virtual doors obtained for each level according to the erosion performance result; And partitioning the grid map, further comprising instructions. The method of claim 13,
The program
The at least one virtual selected based on the selected number of rooms, the number of the selected virtual doors, and the coordinates of the selected at least one virtual door among directions of the virtual doors obtained for each level according to the erosion performance result Determining the direction of the door; and further comprising instructions for performing a grid map partition. The method of claim 13,
The selecting of the coordinates of the at least one virtual door may include: coordinates of the first virtual door and coordinates of the first virtual door with respect to the coordinates of the first virtual door and the coordinates of the second virtual door among the virtual doors obtained as a result of the erosion. 2. The apparatus of claim 1, wherein the first virtual door and the second virtual door are determined to be close to each other when a difference between the coordinates of the virtual door is less than or equal to a predetermined value. 16. The method of claim 15,
The selecting of the coordinates of the at least one virtual door may include selecting the coordinates of the at least one virtual door in a rank having a high frequency in which the coordinates of the virtual doors are determined to be the same as or close to each other among the virtual doors acquired according to the levels. And determine the coordinates of the at least one virtual door based on the grid map. 16. The method of claim 15,
The selecting of the coordinates of the at least one virtual door may include selecting among the coordinates of the virtual doors that are determined to be the same as or close to another virtual door among the virtual doors acquired according to the levels as a result of the erosion. An apparatus for partitioning a grid map, comprising selecting coordinates of at least one virtual door using an average. The method of claim 14,
The modifying the grid map may include modifying the grid map based on the selected number of virtual doors, coordinates of the selected at least one virtual door, and the determined direction of the at least one virtual door. The device for partitioning. In the method for partitioning the grid map into a plurality of rooms by a device for performing map segmentation,
Performing erosion on the grid map according to a plurality of levels;
Selecting the number of rooms most frequently obtained from the number of rooms acquired for each level according to the erosion result; And
And modifying the grid map based on the selected number of rooms. A computer-readable recording medium having recorded thereon a program for executing a method of partitioning a grid map on a computer.

Images