KR102564813B1 - Region segmentation apparatus and method for map decomposition of robot - Google Patents

Abstract

An apparatus and method for dividing a region for map decomposition of a robot according to a preferred embodiment of the present invention can divide a grid map into a plurality of regions by taking into consideration both the graphical characteristics of the space and the obstacles placed in the space. there is.

Description

Region segmentation apparatus and method for map decomposition of robot {Region segmentation apparatus and method for map decomposition of robot}

The present invention relates to an apparatus and method for dividing a region for map decomposition of a robot, and more particularly, to an apparatus and method for dividing a grid map into a plurality of regions.

When a person cleans a house, he or she separates spaces according to the structure (room or furniture) of the house, and cleans each space sequentially, rather than going around and cleaning several rooms. In addition, even when cleaning a sufficiently wide space (such as a large living room and square), the space is unconsciously separated and cleaned according to a certain area or furniture arrangement.

When a robot thinks and behaves similarly to a human, it is usually judged to be smart. Accordingly, the cleaning robot performs an operation of separating and cleaning a space similarly to a human.

An object to be achieved by the present invention is to provide an area division apparatus and method for map decomposition of a robot that divides a grid map into a plurality of areas in consideration of both the graphical characteristics of the space and the obstacles placed in the space. is to provide

Other non-specified objects of the present invention may be additionally considered within the scope that can be easily inferred from the following detailed description and effects thereof.

An apparatus for dividing a region for map decomposition of a robot according to a preferred embodiment of the present invention for achieving the above object includes: a map construction unit for constructing a grid map; and a region dividing unit dividing the grid map constructed through the map building unit into a plurality of regions.

Here, the area division unit may include a critical point acquisition module for acquiring a critical point based on the grid map; a critical line acquiring module for obtaining a critical line based on the critical point obtained through the critical point acquiring module; and an area acquiring module configured to divide the grid map into a plurality of areas based on the critical line acquired through the critical line acquiring module.

Here, the threshold point acquisition module obtains an obstacle distance map based on a minimum distance to an obstacle of each pixel located on the grid map, obtains a topology based on the obstacle distance map, and obtains the topology Based on this, the critical point can be obtained.

Here, the threshold point acquiring module acquires points having the same distance from obstacles located on the left and right sides based on the obstacle distance map, obtains the topology based on the obtained points, and obtains the intersection point and endpoint based on the topology. , and the critical point may be obtained based on the obtained intersection point and end point.

Here, the critical line obtaining module may acquire the critical line dividing the space based on the critical point by using a topology obtained based on an obstacle distance map corresponding to the grid map.

Here, the critical line acquisition module may acquire the critical line by using a difference in distance between obstacles located on the left and right while moving from one critical point to another critical point along the topology.

Here, the critical line acquisition module acquires the critical line based on a point where the degree of change in the difference in the distance between the left and right obstacles is greater than a preset first reference value, and the distance between the left and right obstacles is The critical line may be obtained based on a start point and an end point at which the degree of change of the difference is constantly maintained within a preset second reference value.

Here, the area acquisition module acquires a plurality of labels corresponding to the grid map based on the threshold line, and performs label combining based on connectivity between labels to obtain a plurality of regions corresponding to the grid map. can be obtained.

Here, for each of a plurality of labels, the area acquisition module obtains a label located adjacent to the label while moving along the outer line of the label, obtains connectivity between labels, and uses the connectivity between labels based on a preset combination condition. to perform label combination.

Here, the preset combining condition is a first combining condition for merging a target label having a size smaller than a preset minimum size into an adjacent label having the largest size among adjacent labels adjacent to the target label; When one adjacent label is adjacent to all outlines, a second combining condition for merging target labels into adjacent labels, and a size of an adjacent part of a target label and an adjacent label adjacent to the target label is greater than a preset reference size; A third combining condition for merging target labels into adjacent labels may be included.

In order to achieve the above object, an area division method for map decomposition of a robot according to a preferred embodiment of the present invention includes the steps of constructing a grid map; and dividing the grid map into a plurality of regions.

Here, the dividing of the region may include obtaining a critical point based on the grid map; obtaining a critical line based on the critical point; and dividing the grid map into a plurality of regions based on the critical line.

Here, the threshold point acquisition step may include obtaining an obstacle distance map based on a minimum distance to an obstacle of each pixel located on the grid map, obtaining a topology based on the obstacle distance map, and obtaining the topology. Based on this, the critical point may be obtained.

Here, the step of acquiring the critical line may include acquiring the critical line dividing the space based on the critical point using a topology obtained based on an obstacle distance map corresponding to the grid map.

A computer program according to a preferred embodiment of the present invention for achieving the above technical problem is stored in a computer-readable recording medium and executes any one of the area division methods for map decomposition of the robot on a computer.

According to an apparatus and method for dividing regions for map decomposition of a robot according to a preferred embodiment of the present invention, a grid map can be divided into a plurality of regions by taking into consideration both the graphical characteristics of a space and obstacles disposed in the space. can

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

1 is a block diagram illustrating an apparatus for dividing a region for map decomposition of a robot according to a preferred embodiment of the present invention.
2 is a diagram showing an example of a grid map according to a preferred embodiment of the present invention.
FIG. 3 is a diagram showing an example of an obstacle distance map according to a preferred embodiment of the present invention, and shows an obstacle distance map corresponding to the grid map shown in FIG. 2 .
FIG. 4 is a diagram showing an example of a topology according to a preferred embodiment of the present invention, and shows a topology corresponding to the obstacle distance map shown in FIG. 3 .
FIG. 5 is a diagram showing an example of a critical point according to a preferred embodiment of the present invention, and shows a critical point corresponding to the topology shown in FIG. 4 .
6 is a diagram for explaining an example of a threshold line acquisition process according to a preferred embodiment of the present invention.
7 is a diagram for explaining another example of a threshold line acquisition process according to a preferred embodiment of the present invention.
FIG. 8 is a view showing an example of a critical line according to a preferred embodiment of the present invention, and shows a critical line corresponding to the critical point shown in FIG. 5 .
FIG. 9 is a diagram showing an example of a label according to a preferred embodiment of the present invention, and shows a label corresponding to the critical line shown in FIG. 8 .
10 is a diagram for explaining a process of obtaining connectivity between labels according to a preferred embodiment of the present invention.
FIG. 11 is a diagram showing an example of a region division result of a lattice map according to a preferred embodiment of the present invention, showing region division results corresponding to the labels shown in FIG. 9 .
12 is a diagram showing another example of a region division result of a grid map according to a preferred embodiment of the present invention.
13 is a flowchart for explaining a method for dividing regions for map decomposition of a robot according to a preferred embodiment of the present invention.
FIG. 14 is a flowchart for explaining detailed steps of the area division step shown in FIG. 13 .

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various forms different from each other, and only the present embodiments make the disclosure of the present invention complete, and common knowledge in the art to which the present invention belongs. It is provided to completely inform the person who has the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numbers designate like elements throughout the specification.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used in a meaning commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

In this specification, terms such as "first" and "second" are used to distinguish one component from another component, and the scope of rights should not be limited by these terms. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element.

In this specification, identification codes (eg, a, b, c, etc.) for each step are used for convenience of explanation, and identification codes do not describe the order of each step, and each step is clearly Unless a specific order is specified, it may occur in a different order from the specified order. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

In this specification, expressions such as "has", "may have", "includes" or "may include" indicate the existence of a corresponding feature (eg, numerical value, function, operation, or component such as a part). indicated, and does not preclude the presence of additional features.

In addition, the term '~unit' described in this specification means software or a hardware component such as a field-programmable gate array (FPGA) or ASIC, and '~unit' performs certain roles. However, '~ part' is not limited to software or hardware. '~bu' may be configured to be in an addressable storage medium and may be configured to reproduce one or more processors. Therefore, as an example, '~unit' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuitry, data structures and variables. Functions provided within components and '~units' may be combined into smaller numbers of components and '~units' or further separated into additional components and '~units'.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, a preferred embodiment of an apparatus and method for dividing a region for map decomposition of a robot according to the present invention will be described in detail with reference to the accompanying drawings.

First, a region dividing apparatus for map decomposition of a robot according to a preferred embodiment of the present invention will be described with reference to FIGS. 1 to 12 .

1 is a block diagram for explaining an area division device for map decomposition of a robot according to a preferred embodiment of the present invention, and FIG. 2 is a diagram showing an example of a grid map according to a preferred embodiment of the present invention. 3 is a diagram showing an example of an obstacle distance map according to a preferred embodiment of the present invention, and shows an obstacle distance map corresponding to the grid map shown in FIG. 2, and FIG. 4 is an example of a topology according to a preferred embodiment of the present invention. , which shows a topology corresponding to the obstacle distance map shown in FIG. 3, and FIG. 5 is a diagram showing an example of a threshold point according to a preferred embodiment of the present invention, which shows a threshold point corresponding to the topology shown in FIG. 6 is a diagram for explaining an example of a process for obtaining a threshold line according to a preferred embodiment of the present invention, and FIG. 7 is a view for explaining another example of a process for obtaining a threshold line according to a preferred embodiment of the present invention. , FIG. 8 is a diagram showing an example of a critical line according to a preferred embodiment of the present invention, showing a critical line corresponding to the critical point shown in FIG. 5, and FIG. 9 shows an example of a label according to a preferred embodiment of the present invention. As a diagram, labels corresponding to the threshold line shown in FIG. 8 are shown. FIG. 10 is a diagram for explaining a process of obtaining connectivity between labels according to a preferred embodiment of the present invention, and FIG. 11 is a preferred embodiment of the present invention. This is a diagram showing an example of a region division result of a grid map according to , showing a region division result corresponding to a label shown in FIG. 9, and FIG. 12 is another example of a region division result of a grid map according to a preferred embodiment of the present invention. is a drawing representing

Referring to FIG. 1 , an apparatus for dividing a region for map decomposition of a robot according to a preferred embodiment of the present invention (hereinafter, referred to as a 'region dividing apparatus') 100 is configured to distinguish between graphical features of a space and obstacles disposed in the space. Together, the grid map can be divided into a plurality of regions.

Meanwhile, the region dividing device 100 according to the present invention may be implemented in hardware or software form and mounted on a robot (not shown) such as a cleaning robot or a mobile robot. In this case, the region dividing device 100 mounted on the robot may divide a plurality of regions based on a lattice map built while the robot moves. Then, the robot may perform an operation such as cleaning in units of regions based on a plurality of regions corresponding to the grid map.

To this end, the region dividing device 100 may include a map building unit 110 and a region dividing unit 130 .

The map builder 110 may build a grid map.

For example, the map builder 110 uses an infrared (ir) sensor, a position sensitive device (PSD) sensor, a 2D light detection and ranging (LiDAR) sensor, a 3D lidar (LiDAR) sensor, and the like in FIG. 2 . A two-dimensional grid map as shown in can be obtained. The grid map may include an inner area (white area in FIG. 2 ) representing a space in which the robot can move and an outer area (black area in FIG. 2 ) indicating a space in which the robot cannot move due to an obstacle such as a wall.

The region division unit 130 may divide the grid map constructed by the map construction unit 110 into a plurality of regions.

More specifically, the region divider 130 may include a threshold point acquisition module 131 , a threshold line acquisition module 133 , and a region acquisition module 135 .

The critical point obtaining module 131 may obtain a critical point based on the lattice map.

That is, the threshold point acquisition module 131 may obtain an obstacle distance map based on the minimum distance to the obstacle of each pixel located on the grid map. For example, as shown in FIG. 3 , the obstacle distance map may display the distance to the obstacle of each pixel of the grid map in color for each pixel. Here, the closer the pixel color is to white, the greater the distance from the obstacle.

Also, the threshold point acquisition module 131 may obtain a topology based on the obstacle distance map.

At this time, the threshold point acquisition module 131 acquires points (ie, center points of the obstacle distance map) at the same distance from obstacles located on the left and right based on the obstacle distance map, and obtains the topology (ie, center points of the obstacle distance map) based on the obtained points. , the skeleton of the lattice map) can be obtained. For example, as shown in FIG. 4 , the topology may be formed of lines connecting points, ie, center points of an obstacle distance map, with the same distance from left and right obstacles.

Also, the critical point obtaining module 131 may obtain a critical point based on the topology.

In this case, the critical point obtaining module 131 may obtain an intersection point (ie, a point where the structure is changed) and an end point based on the topology, and may obtain a critical point based on the obtained intersection point and end point. For example, as shown in FIG. 5 , the threshold point may include an intersection point where lines constituting the topology meet each other and an end point of the lines constituting the topology.

The critical line acquisition module 133 may obtain a critical line based on the critical points acquired through the critical point acquisition module 131 .

That is, the critical line acquisition module 133 may obtain a critical line dividing a space based on a critical point using a topology obtained based on an obstacle distance map corresponding to the grid map.

In this case, the critical line acquisition module 133 may acquire the critical line by using a difference in distance between obstacles located on the left and right while moving from one critical point to another critical point along the topology.

For example, the threshold line acquisition module 133 may acquire a threshold line based on a point where the degree of change in the difference in distance between the left and right obstacles is greater than a preset first reference value. Here, the preset first reference value may be set based on the size of the robot in which the region dividing device 100 according to the present invention is mounted, the size of the space in which the robot is used, and the like. For example, since the size of a house visit is typically 700 mm to 900 mm, and the size of a household cleaning robot is approximately 350 mm, a place having a width within three times that of the cleaning robot may be determined as a place where the width is narrowed. As shown in the boxes shown in (a) and (b) of FIG. 6, the point at which the change in the difference in the distance between the left and right obstacles is rapidly lowered and the change in the difference in the distance between the obstacles on the left and right is abrupt. The point where it rises can be obtained as a critical line. Here, the horizontal axis of FIG. 6 (a) and (b) represents a point according to the topology, and the vertical axis represents a difference in distance from obstacles located on the left and right of the corresponding point.

Also, the threshold line acquisition module 133 may obtain a threshold line based on a start point and an end point at which the degree of change in the distance between the left and right obstacles is maintained constant within a preset second reference value. Here, the preset second reference value may be set based on the size of the robot in which the region dividing device 100 according to the present invention is mounted, the size of the space in which the robot is used, and the like. As shown in (a) and (b) of FIG. 7 , a start point and an end point at which a difference in distance between left and right obstacles is kept constant may be obtained as critical lines. Here, the horizontal axis of FIG. 7 (a) and (b) represents a point according to the topology, and the vertical axis represents a difference in distance from obstacles located on the left and right of the corresponding point.

Then, the critical line acquisition module 133 may acquire the critical line as shown in FIG. 8 . Here, the pink critical line shown in FIG. 8 represents a critical line obtained based on a point where the degree of change in the difference in the distance between the left and right obstacles is greater than a preset first reference value, and the red critical line indicates the left and right critical lines. Indicates a threshold line obtained based on a start point and an end point at which the degree of change in the difference in distance from an obstacle located at is kept constant within a preset second reference value.

The area obtaining module 135 may divide the grid map into a plurality of areas based on the critical lines obtained through the critical line obtaining module 133 .

That is, the area acquisition module 135 may obtain a plurality of labels corresponding to the grid map based on the threshold line. For example, the area acquisition module 135 may obtain a plurality of labels as shown in FIG. 9 using obstacle position information and threshold lines corresponding to the grid map. Here, the color of the label shown in FIG. 9 is arbitrarily determined to distinguish the labels from each other, and the color of the label does not have a special meaning.

Also, the area acquisition module 135 may acquire a plurality of areas corresponding to the grid map by performing label combining based on connectivity between labels.

In this case, the region acquisition module 135 may obtain connectivity between labels by acquiring a label located adjacent to each of the plurality of labels while moving along the outer line of the label. For example, as shown in (a) to (c) of FIG. 10 , the area acquiring module 135 may find labels adjacent to the corresponding label while moving along the outer line of the label.

Then, the region obtaining module 135 may perform label combining using connectivity between labels based on a preset combining condition.

Here, the preset combination condition may include a first combination condition, a second combination condition, and a third combination condition.

The first combining condition represents a combining condition for merging a target label having a size smaller than a preset minimum size with an adjacent label having the largest size among adjacent labels adjacent to the target label. Here, the preset minimum size may be set based on the size of the robot on which the region dividing device 100 according to the present invention is mounted, the size of the space used by the robot, and the like.

The second combining condition represents a combining condition for merging a target label with an adjacent label when one adjacent label is adjacent to all outlines of the target label.

A third combining condition represents a combining condition for merging a target label into an adjacent label when a size of a target label and an adjacent portion of an adjacent label adjacent to the target label is larger than a preset reference size. Here, the preset standard size may be set based on the size of the robot on which the region dividing device 100 according to the present invention is mounted, the size of the space used by the robot, and the like.

Then, the area acquisition module 135 may acquire a plurality of areas corresponding to the grid map as shown in FIGS. 11 and 12 . That is, FIG. 11 shows the result of dividing a plurality of areas according to the present invention based on the grid map obtained for the house, and FIG. 12 shows the present invention based on the grid map obtained for the mart space having a large size. It shows the result of dividing a plurality of areas according to . Here, the color of the area shown in FIGS. 11 and 12 is arbitrarily determined to distinguish the areas from each other, and the color of the area does not have a special meaning.

In this case, the area acquisition module 135 may acquire area information for each of a plurality of areas corresponding to the grid map. Here, the region information includes region identification information such as the name of the region, total area of the region, dominant angle of the region, centroid of the region, and region identification information of regions adjacent to the region. It may include connectivity information such as, etc., information on each point of a rectangle corresponding to the corresponding area, information on the outer points constituting the corresponding area, and the like.

In this way, the plurality of labels obtained based on the critical line are divided in terms of structure without considering the size. At this time, if the labels are divided into too small pieces, low efficiency may be brought about in terms of the operation of the robot. Therefore, combining the labels is performed in consideration of the size of the labels, the connectivity between the labels, etc., and the final plurality corresponding to the lattice map. You get a dog's territory.

Next, a method for dividing regions for map decomposition of a robot according to a preferred embodiment of the present invention will be described with reference to FIGS. 13 and 14 .

13 is a flowchart for explaining a method for dividing regions for map decomposition of a robot according to a preferred embodiment of the present invention.

Referring to FIG. 13 , the region dividing device 100 may build a grid map (S110).

For example, the area dividing device 100 may acquire a 2D grid map as shown in FIG. 2 through an infrared (ir) sensor, a PSD sensor, a 2D LiDAR sensor, a 3D LiDAR sensor, and the like. can The grid map may include an inner area (white area in FIG. 2 ) representing a space in which the robot can move and an outer area (black area in FIG. 2 ) indicating a space in which the robot cannot move due to an obstacle such as a wall.

Then, the region dividing device 100 may divide the grid map into a plurality of regions (S130).

FIG. 14 is a flowchart for explaining detailed steps of the area division step shown in FIG. 13 .

Referring to FIG. 14 , the region dividing device 100 may obtain a critical point based on the grid map (S131).

That is, the area dividing device 100 may obtain an obstacle distance map based on the minimum distance to the obstacle of each pixel located on the grid map.

Also, the area dividing device 100 may obtain a topology based on the obstacle distance map. At this time, the area dividing device 100 acquires points (ie, center points of the obstacle distance map) at the same distance from the left and right obstacles based on the obstacle distance map, and determines the topology (ie, center points of the obstacle distance map) based on the obtained points. , the skeleton of the lattice map) can be obtained.

Also, the region dividing apparatus 100 may obtain a critical point based on the topology. In this case, the region dividing apparatus 100 may obtain an intersection point (ie, a point where the structure is changed) and an end point based on the topology, and may obtain a critical point based on the obtained intersection point and end point.

Then, the region dividing device 100 may obtain a critical line based on the critical point (S133).

That is, the area dividing device 100 may obtain a critical line dividing a space based on a critical point using a topology obtained based on an obstacle distance map corresponding to the grid map.

In this case, the region dividing apparatus 100 may obtain a critical line by using a difference in distance between obstacles located on the left and right while moving from one critical point to another critical point along the topology.

For example, the area dividing apparatus 100 may obtain a threshold line based on a point where the degree of change in the difference in distance between the left and right obstacles is greater than a preset first reference value. Here, the preset first reference value may be set based on the size of the robot on which the region dividing device 100 according to the present invention is mounted.

In addition, the area dividing device 100 may obtain a threshold line based on a start point and an end point at which a degree of change in a difference in distance between left and right obstacles is kept constant within a preset second reference value.

Then, the region dividing device 100 may obtain the critical line as shown in FIG. 8 .

Thereafter, the region dividing device 100 may divide the grid map into a plurality of regions based on the critical line (S135).

That is, the region dividing device 100 may obtain a plurality of labels corresponding to the grid map based on the critical line. For example, the area dividing apparatus 100 may obtain a plurality of labels as shown in FIG. 9 by using obstacle position information and critical lines corresponding to the grid map.

In addition, the region dividing apparatus 100 may obtain a plurality of regions corresponding to the grid map by performing label combining based on connectivity between labels. In this case, the area dividing apparatus 100 may obtain connectivity between labels by acquiring labels located adjacent to each of the plurality of labels while moving along the outer line of the labels.

Then, the region division device 100 may perform label combining using connectivity between labels based on a preset combining condition. Here, the preset combination condition may include a first combination condition, a second combination condition, and a third combination condition. The first combining condition represents a combining condition for merging a target label having a size smaller than a preset minimum size with an adjacent label having the largest size among adjacent labels adjacent to the target label. The second combining condition represents a combining condition for merging a target label with an adjacent label when one adjacent label is adjacent to all outlines of the target label. A third combining condition represents a combining condition for merging a target label into an adjacent label when a size of a target label and an adjacent portion of an adjacent label adjacent to the target label is larger than a preset reference size.

Then, the region dividing device 100 may obtain a plurality of regions corresponding to the grid map as shown in FIGS. 11 and 12 . At this time, the region dividing device 100 may obtain region information for each of a plurality of regions corresponding to the grid map. Here, the region information includes region identification information such as the name of the region, total area of the region, dominant angle of the region, centroid of the region, and region identification information of regions adjacent to the region. It may include connectivity information such as, etc., information on each point of a rectangle corresponding to the corresponding area, information on the outer points constituting the corresponding area, and the like.

Even though all components constituting the embodiments of the present invention described above are described as being combined or operated as one, the present invention is not necessarily limited to these embodiments. That is, within the scope of the object of the present invention, all of the components may be selectively combined with one or more to operate. In addition, although all of the components may be implemented as a single independent piece of hardware, some or all of the components are selectively combined to perform some or all of the combined functions in one or a plurality of pieces of hardware. It may be implemented as a computer program having. In addition, such a computer program may implement an embodiment of the present invention by being stored in a computer readable medium such as a USB memory, a CD disk, or a flash memory and read and executed by a computer. A recording medium of a computer program may include a magnetic recording medium, an optical recording medium, and the like.

The above description is merely an example of the technical idea of the present invention, and those skilled in the art can make various modifications, changes, and substitutions without departing from the essential characteristics of the present invention. will be. Therefore, the embodiments disclosed in the present invention and the accompanying drawings are not intended to limit the technical idea of the present invention, but to explain, and the scope of the technical idea of the present invention is not limited by these embodiments and the accompanying drawings. . The protection scope of the present invention should be construed according to the claims below, and all technical ideas within the equivalent range should be construed as being included in the scope of the present invention.

100: area division device,
110: map building unit,
130: area dividing unit,
131: critical point acquisition module,
133: critical line acquisition module,
135: area acquisition module

Claims (15)

In the area division device for map decomposition of the robot,
a map building unit that builds a grid map; and a region dividing unit dividing the grid map constructed through the map building unit into a plurality of regions,
The area division unit may include a critical point acquisition module for obtaining a critical point based on the grid map; a critical line acquiring module for obtaining a critical line based on the critical point obtained through the critical point acquiring module; and an area acquisition module dividing the lattice map into a plurality of areas based on the threshold line obtained through the threshold line acquisition module;
The threshold point obtaining module acquires a threshold point by obtaining an obstacle distance map using a minimum distance to an obstacle for each pixel of the lattice map, and obtaining a topology based on a distance from the obstacle distance map to an obstacle, Acquiring critical points based on the obtained topology,
The threshold line acquisition module may include, among points between one critical point and another critical point existing along the topology, a point according to a section in which a degree of change in a difference in distance from the obstacle is greater than a preset first reference value, or an obstacle An area division device for map decomposition of a robot, characterized in that a threshold line is determined based on a point according to a section where the degree of change in the difference between the interval and the distance is maintained constant within a preset second reference value. delete delete In paragraph 1,
The threshold point acquisition module acquires points at equal distances from left and right obstacles based on the obstacle distance map, and acquires the topology based on the acquired points;
The threshold point obtaining module obtains an intersection point and an end point based on the topology, and obtains the critical point based on the obtained intersection point and end point.
Area separator for robot map decomposition. delete delete delete The method of claim 1, wherein the area acquisition module,
Obtaining a plurality of labels corresponding to the lattice map based on the critical line, and obtaining a plurality of regions corresponding to the lattice map by performing label combining based on connectivity between labels,
Area separator for robot map decomposition. In paragraph 8,
The area acquisition module,
For each of the plurality of labels, obtaining a label at an adjacent position while moving along the outline of the label to obtain connectivity between the labels;
performing label combining using connectivity between labels based on preset combining conditions;
Area separator for robot map decomposition. In paragraph 9,
The preset bonding condition is,
A first combining condition for merging target labels having a size smaller than the preset minimum size into adjacent labels having the largest size among adjacent labels adjacent to the target label, and one adjacent label adjacent to all outlines of the target label , a second combining condition for merging the target label into an adjacent label, and a condition for merging the target label into an adjacent label when the size of the adjacent part of the target label and the adjacent label adjacent to the target label is greater than a preset reference size. Including 3 binding conditions,
Area separator for robot map decomposition. In the area division method for map decomposition of the robot,
building a grid map; and
Dividing the grid map built by the map construction unit into a plurality of regions;
Dividing the lattice map into a plurality of regions may include: acquiring a critical point based on the lattice map; obtaining a critical line based on the critical point obtained through the critical point acquiring module; and dividing the lattice map into a plurality of areas based on the critical line acquired through the critical line acquisition module,
The obtaining of the critical point may include obtaining an obstacle distance map using a minimum distance to an obstacle for each pixel of the lattice map, obtaining a topology based on a distance from the obstacle distance map to an obstacle, and obtaining the obtained Including obtaining critical points based on the topology,
The obtaining of the critical line may include, among points between one critical point and another critical point existing along the topology, a point according to a section in which a degree of change in a difference in distance from the obstacle is greater than a preset first reference value; Alternatively, the threshold line is determined based on a point according to a section where the degree of change in the difference in distance from the obstacle is constantly maintained within a preset second reference value. delete delete delete A computer program stored in a computer-readable recording medium to execute the area division method for map decomposition of a robot according to claim 11 on a computer.

Images