Robot intelligent partitioning method and device, robot, and storage medium

Abstract

The application is suitable for the technical field of robots, and provides a robot intelligent partition method, device, robot and storage medium.The method comprises the following steps: acquiring a slam map after the robot completes the last work, and comparing the slam map with a partition map to obtain the area attribute of at least one new area which is added in the cleaning area, and the area number of the adjacent area of the new area; judging whether the area attribute meets a preset first condition and whether the area number meets a preset second condition for each new area; and when it is judged that the area attribute meets the first condition and the area number meets the second condition, locally partitioning the new area.The application solves the problem that the existing robot automatic partitioning technology re-partitions the already partitioned area, which makes the two partitioning results inconsistent, and causes the robot sweeping work parameters set by the user to be invalid.

Description

Technical Field

[0001] This invention belongs to the field of robotics technology, and particularly relates to a robot intelligent partitioning method, device, robot, and computer-readable storage medium. Background Technology

[0002] Cleaning robots, such as mopping robots and floor scrubbing robots, are intelligent devices used to automatically complete cleaning tasks. For example, a household cleaning robot, during its initial cleaning, will create a working map of the home environment while cleaning. When certain conditions are met, it will automatically divide the room into zones based on the information from the working map.

[0003] Specifically, in the prior art, after the robot completes the overall cleaning of the home environment, it will automatically divide the entire working map in the following situations: (1) the working map of the home environment has not been divided before; (2) during the cleaning process, there are unknown areas, which refer to one or more newly added areas in the working map.

[0004] The existing automatic zoning method mainly re-zones the entire map, which leads to the following problems: (1) For the same residential environment, if objects in the environment have been moved compared to before, the map will only change locally and the working map will not be zoned, which will cause abnormal display of the user's graphical interface, such as empty white blocks, affecting the user experience; (2) For the same residential environment, when zoning the entire working map, the original zoning will be disrupted due to the local changes in the working map, which will cause the working parameters such as the suction power and water flow rate of the robot that the user has set for the working map to become invalid. Summary of the Invention

[0005] Firstly, the present invention provides a robot intelligent zoning method, which aims to solve the problem that the existing robot automatic zoning method re-divides the already divided areas, resulting in inconsistencies between the two zoning processes, and thus causing the robot sweeping parameters set by the user to become invalid.

[0006] The present invention is implemented as follows: a robot intelligent partitioning method, the method comprising:

[0007] Obtain the SLAM map after the robot's most recent work is completed, and compare it with the zoning map to obtain the zoning attributes of at least one newly added zoning area in the cleaning area, as well as the zoning numbers of the adjacent zoning areas of the newly added zoning area.

[0008] For each newly added region, determine whether the region attribute meets a preset first condition and whether the region number meets a preset second condition.

[0009] When it is determined that the region attribute meets the first condition and the region number meets the second condition, the newly added region is partially partitioned.

[0010] Furthermore, the step of locally partitioning the newly added region includes:

[0011] Obtain local map data corresponding to the newly added area in the SLAM map, and identify line segments in the local map data;

[0012] Determine whether the first end of the line segment intersects with other line segments, and whether there is an intersection within a preset range from the second end of the line segment;

[0013] When it is determined that the first end of the line segment intersects with other line segments, and there are no intersections within a preset range from the second end of the line segment, the line segment is extended towards the second end and the extension stops after encountering an obstacle, thus obtaining the threshold line of the newly added area.

[0014] The newly added area is filled according to the threshold line and updated in the partition map.

[0015] Furthermore, the step of identifying line segments in the local map data includes:

[0016] The local map data is binarized, and line segments in the binarized local map data are identified using a line recognition model.

[0017] Furthermore, after determining whether the region attribute meets a preset first condition and whether the region number meets a preset second condition for each newly added region, the method further includes:

[0018] When it is determined that the region attribute does not meet the first condition or the region number does not meet the second condition, the newly added region will be merged with the adjacent region, and the partition map will be updated.

[0019] In a second aspect, the present invention provides a robot intelligent partitioning device, the device comprising:

[0020] A new area acquisition module is added to acquire the SLAM map after the robot's most recent work is completed, and compare it with the partition map to obtain the area attributes of at least one newly added area in the cleaning area, as well as the area numbers of the adjacent areas of the newly added area.

[0021] The first judgment module is used to determine whether the region attributes meet the preset first condition and whether the region number meets the preset second condition for each newly added region.

[0022] The local partitioning module is used to perform local partitioning on the newly added region when it is determined that the region attribute meets the first condition and the region number meets the second condition.

[0023] Furthermore, the local partitioning module includes:

[0024] The line segment recognition submodule is used to obtain local map data corresponding to the newly added area in the SLAM map and identify line segments in the local map data.

[0025] The first judgment submodule is used to determine whether the first end of the line segment intersects with other line segments, and whether there is an intersection within a preset range from the second end of the line segment;

[0026] The threshold recognition submodule is used to extend the line segment toward the second end when it is determined that the first end of the line segment intersects with other line segments and there are no intersections within a preset range from the second end of the line segment, and to stop extending the line segment after encountering an obstacle, so as to obtain the threshold line of the newly added area.

[0027] The region filling submodule is used to fill the newly added region according to the threshold line and update it in the partition map.

[0028] Furthermore, the local partitioning module also includes:

[0029] A new area numbering submodule is added, which is used to configure a unique area number for the newly added area and update it in the partition map according to the numbering rules of the partition map when it is determined that the first end of the line segment intersects with other line segments and there are intersections within a preset range from the second end of the line segment.

[0030] Furthermore, the line segment recognition submodule includes:

[0031] The line segment recognition unit is used to perform binarization processing on the local map data and identify the line segments in the binarized local map data according to the line recognition model.

[0032] Thirdly, the present invention provides a robot, the robot including the above-mentioned robot intelligent partitioning device.

[0033] Fourthly, the present invention provides a computer-readable storage medium storing a computer program, the computer program being executed by a processor of the above-described robot intelligent partitioning method.

[0034] The robot intelligent zoning method provided by this invention obtains the SLAM map of the robot's completed work, compares it with the zoning map, obtains the region attributes of the newly added region and the region numbers of adjacent regions, and determines whether the region attributes and region numbers meet the first and second conditions respectively. If so, intelligent zoning is performed. For environmental maps where robot cleaning parameters have already been set, when the environment changes, there is no need to reset the map zoning to a large extent, avoiding the invalidation of robot cleaning parameters set by the user for that environmental map, improving the robot's intelligence level, and providing an excellent user experience. Attached Figure Description

[0035] Figure 1 This is a flowchart of the robot intelligent partitioning method provided in the embodiments of the present invention;

[0036] Figure 2 This is another flowchart of the robot intelligent partitioning method provided in the embodiments of the present invention;

[0037] Figure 3 This is a schematic diagram of the robot intelligent partitioning device provided in an embodiment of the present invention;

[0038] Figure 4 This is a map diagram illustrating the identification of newly added areas in one embodiment of the robot intelligent partitioning method provided by the present invention;

[0039] Figure 5 This is a schematic diagram of a map after local partitioning in one embodiment of the robot intelligent partitioning method provided in this invention. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0041] In this invention, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Furthermore, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. If the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0042] The robot intelligent zoning method provided by this invention, for an environment map where robot sweeping parameters have been set, does not require a major reset of map zoning when the environment changes. This avoids the failure of robot sweeping parameters set by the user for that environment map, improves the robot's intelligence level, and provides an excellent user experience.

[0043] Example 1

[0044] Please see Figure 1-2 This is a flowchart illustrating the intelligent partitioning method for robots provided by the present invention. For ease of explanation, only the parts relevant to the embodiments of the present invention are shown. The intelligent partitioning method for robots includes:

[0045] Step S10: Obtain the SLAM map after the robot's most recent work is completed, and compare it with the partition map to obtain the area attributes of at least one newly added area in the cleaning area, as well as the area numbers of the adjacent areas of the newly added area.

[0046] The robot intelligent zoning method is applied to automated robots that do not require human operation or control.

[0047] In this embodiment of the invention, SLAM (Simultaneous Localization and Mapping) and related technologies in the field of robotics can be applied as follows: a robot is placed in an unknown location within an unknown environment. During its movement, it locates its own position and orientation by repeatedly observing map features (e.g., corners, room furnishings, etc.), and then incrementally builds a map based on its own position, thereby achieving simultaneous localization and map construction. The SLAM map refers to the environmental map constructed by the robot after completing a cleaning cycle through the above process. One purpose of constructing the SLAM map is to enable the robot to cover all areas of the environmental map without obstacles along a planned path during cleaning operations.

[0048] Optionally, taking a home cleaning robot as an example, the robot operates in a residential home, which typically consists of multiple rooms or halls. These rooms and halls are separated by walls or interior furnishings, and interconnected by doorways. For the robot, the environmental parameters of each room or hall are different, thus requiring different sweeping parameters. For example, cleaning the bathroom requires a strong dehumidification function, while cleaning the kitchen requires a function to remove grease. Therefore, the robot usually divides the space into zones based on an environmental map. Users can configure the robot's sweeping parameters according to the zoning results and specific cleaning needs to achieve quick and efficient cleaning. In this embodiment of the invention, the zoning map refers to the map data generated based on the environmental map.

[0049] In this embodiment of the invention, the user can configure the robot's sweeping parameters according to the pre-defined areas on the environmental map by interacting with the robot. The interaction can be achieved through an application, specifically an application installed on the device terminal, which can be a smart terminal, smart tablet, remote control, etc. The application on the device terminal can communicate with the robot or a cloud server that communicates with the robot.

[0050] Optionally, by comparing the SLAM map with the zonal map, the region attributes of at least one newly added area in the cleaning area can be obtained. The SLAM map is synchronously constructed by the robot during actual cleaning operations and includes unknown areas, passable areas, and impassable areas in the environment. The zonal map is a grid map obtained by dividing the SLAM map according to the room layout after the last cleaning. Each grid is filled with the room number to which the location belongs. If a passable area on the current SLAM map does not have a corresponding room number, then that area is an unknown area left over from the last cleaning. The newly added area is obtained by comparing the mapping values ​​of the same location on the SLAM map and the zonal map. For example: the mapping value of the SLAM map: 0 represents an unknown area, 1 represents a passable area, and 2 represents an impassable area; the mapping value of the zonal map: 0-253 represents room numbers, 254 represents an unknown area, and 255 represents an impassable area. If the mapping value of a certain area on the SLAM map is 1, and the mapping value of the sub-map is 255 or 254, it means that the area is a newly added area. If the mapping value of the sub-map is 0-253 (room number), it means that the area is not a newly added area.

[0051] The regional attributes include, but are not limited to, attributes that characterize the new region, such as its length, width, and area, and are not limited here. It should be noted that, in order to accurately delineate the new region, reduce errors, and decrease the amount of computation, as many regional attributes as possible can be set.

[0052] Typically, new areas are located between zones with clear physical boundaries (such as different rooms), connecting adjacent zones.

[0053] Step S20: For each newly added region, determine whether the region attribute meets the preset first condition and whether the region number meets the preset second condition.

[0054] In this embodiment of the invention, it is determined whether the first condition is met by comparing the specific value of the regional attribute of the newly added region with one or a set of pre-set thresholds for the same attribute. If the regional attribute of the newly added region is greater than the threshold, it is determined that the first condition is met, and the determination of the second condition continues; if the regional attribute of the newly added region is less than the threshold, it is determined that the first condition is not met, and step S21 is executed.

[0055] As mentioned above, it can be determined whether the first condition is met by comparing the specific value of the regional attribute of the newly added region with one or a set of pre-set thresholds for the same attribute. If the regional attribute of the newly added region is less than the threshold, it is determined that the first condition is not met.

[0056] It is understandable that if the regional attribute of the newly added area is less than the threshold, it means that the newly added area occupies a small proportion in the environmental map. It can be merged with the adjacent areas. In this way, there is no need to change the original partition, which avoids the failure of the user's preset robot sweeping parameters, and at the same time, it has no impact on the robot's cleaning work.

[0057] In this embodiment of the invention, whether the second condition is met can be determined by comparing whether the numbers of the adjacent regions of the newly added region are consistent. If the adjacent regions of the newly added region have the same numbers, it is determined that the second condition is not met, and step S21 is executed. If the region attributes meet the first condition and the region number meets the second condition, step S30 is executed.

[0058] In some embodiments, when it is determined that the region attribute does not meet the first condition or the region number does not meet the second condition, step S21 is executed.

[0059] Step S21: Merge the newly added area with the adjacent areas and update the partition map.

[0060] As mentioned earlier, it can be determined whether the second condition is met by comparing the numbers of the adjacent areas of the newly added area. If the adjacent areas of the newly added area have the same numbers, it is determined that the second condition is not met.

[0061] It is understandable that if the adjacent areas of the newly added area have the same number, it means that the adjacent areas of the newly added area have the same attributes. For the robot, the same sweeping parameters can be used to clean it. Therefore, the newly added area can be merged with its adjacent areas. This way, there is no need to change the original partitions, avoiding the failure of the robot's preset sweeping parameters, and it has no impact on the robot's ability to complete the cleaning work.

[0062] Step S30: Partition the newly added area.

[0063] In this embodiment of the invention, the judgment of the first condition and the second condition can be regarded as the identification and confirmation of the changed parts of the original partition map. One purpose is to improve the certainty as much as possible, reduce the error, reduce the amount of calculation, filter out areas that do not need to be partitioned, and merge the newly added areas that do not need to be partitioned into the adjacent areas.

[0064] When a newly added region passes the first and second conditions, it indicates that there are no parts in the newly added region that can be merged into adjacent regions. Therefore, the newly added region can be locally partitioned.

[0065] In some possible embodiments, please refer to Figure 4 ,exist Figure 4 In the map, different areas are assigned different numbers. For example, taking the numerical numbering as an example, the areas with area numbers 0, 1, and 2 are known areas in the partition map. After one sweep, the three areas ①, ②, and ③ in the map are added. That is, the three areas ①, ②, and ③ are the newly added areas.

[0066] For example, taking the first condition being that the area is greater than a set threshold and the second condition being that the adjacent areas have different numbers, the adjacent areas of the newly added area ① include number 1 and number 255. Number 1 can be regarded as a room and number 255 can be regarded as a wall. The area numbers of the adjacent areas of the newly added area ① meet the second condition, but the area of ​​the newly added area ① is too small to reach the set threshold, so the first condition is not met. Therefore, the newly added area ① can be merged with area number 1.

[0067] The area of ​​the newly added region ② is greater than the set threshold, satisfying the first condition. However, the newly added region ② is surrounded by region 2, resulting in adjacent regions of the newly added region ② having the same number, which does not satisfy the second condition. Therefore, the newly added region ② and its adjacent regions ( Figure 4 The newly added area ② (area numbered 2) can be merged with the adjacent area (area numbered 2). Figure 4 Merge areas with the same color (e.g., area number 2).

[0068] In addition, if the area of ​​the newly added region ③ is large enough to satisfy the first condition, and the adjacent regions of the newly added region ③ have different numbers, thus satisfying the second condition, then the newly added region ③ needs to be partially partitioned.

[0069] For example, the final partitioning effect of adding a new region after partial partitioning is as follows: Figure 5 As shown, Figure 5 compared to Figure 4 Two new partitions are added, numbered 3 and 4, derived from the newly added area ③. New areas ① and ② are then merged into partition 1 and partition 2, respectively. In practice, each partition can be filled with a different color than its adjacent areas to distinguish them.

[0070] The robot intelligent zoning method provided in this invention obtains the SLAM map of the robot's completed cleaning process, compares it with the zoning map, obtains the region attributes of the newly added area and the region numbers of adjacent areas, determines whether the region attributes and region numbers meet a first condition and a second condition, and then intelligently zons the newly added area based on the determination result. For environmental maps where robot cleaning parameters have already been set, when the environment changes, there is no need to reset the map zoning to a large extent, avoiding the invalidation of robot cleaning parameters set by the user for that environmental map, improving the robot's intelligence level, and providing an excellent user experience.

[0071] Example 2

[0072] Please see Figure 1-2 This is a flowchart illustrating a robot intelligent partitioning method provided by the present invention. For ease of explanation, only the parts related to the embodiments of the present invention are shown. The processes of Embodiment 2 and Embodiment 1 are largely the same. For the sake of brevity, any parts not mentioned in the embodiments of the present invention can be referred to the corresponding content in Embodiment 1. The robot intelligent partitioning method includes the step of locally partitioning the newly added region, which includes:

[0073] Step S31: Obtain the local map data of the newly added area in the SLAM map and identify the line segments in the local map data;

[0074] This invention provides a method for locally partitioning a newly added area. Based on the acquired local map data of the newly added area, line segments can be further identified. In this invention, the line segments in the local map can be regarded as the walls of each room.

[0075] Optionally, line segments in local map data can be identified by binarizing the local map data and then identifying the line segments in the binarized local map data according to a straight line recognition model.

[0076] Specifically, binarizing local map data includes the following steps:

[0077] A. Convert local map data into images in a preset image format. Existing image formats can be selected as preset image formats.

[0078] B. Obtain the pixel value of each pixel in the image and determine whether the pixel value of each pixel in the image is greater than the preset pixel value.

[0079] C. If the pixel value is greater than the preset pixel value, the corresponding pixel's color is set to the first color. If the pixel value is not greater than the preset pixel value, the corresponding pixel's color is set to the second color. The first color represents the blank areas indoors, and the second color represents the areas of indoor walls and obstacles. Optionally, the first color is white, and the second color is black.

[0080] In this embodiment, the indoor map is converted into an image containing only the first and second colors through binarization processing. Then, the line segment in the local map data after binarization is identified by the line recognition model, which can be regarded as the boundary line between the first and second colors.

[0081] Step S32: Determine whether the first end of the line segment intersects with other line segments, and whether there is an intersection within a preset range from the second end of the line segment;

[0082] In implementation, the first end of the line segment intersects with other line segments. This can be seen as the wall mapped by the line segment intersecting with the wall mapped by the other line segments, meaning the intersection point is the corner of the wall at the boundary between the two walls. Of course, in other embodiments, the intersection point is not limited to the corner of the wall at the boundary between the two walls as described above. The line segment can also be seen as other objects, such as wardrobes, screens, etc., which are not limited here.

[0083] Step S33: When the first end of the line segment intersects with other line segments, and there are no intersections within a preset range from the second end of the line segment, extend the line segment towards the second end and stop extending it after encountering an obstacle to obtain the threshold line of the newly added area.

[0084] It is understandable that when it is determined that there is an intersection point within a preset range from the second end of the line segment, the line segment can be equated with the line segment identified in step S31 for subsequent processing. That is, the line segment can be directly regarded as the boundary of each partition.

[0085] Step S34: Fill the newly added area according to the threshold line and update it in the partition map.

[0086] The newly added region is filled according to the threshold line of the mapped region, and finally a new local partition is generated.

[0087] Specifically, each line segment and its threshold line can be considered together as the aforementioned partition boundary.

[0088] If line segments intersect, it indicates that the intersection connects two walls. Further, for a line segment whose first end intersects with other line segments, it is determined whether there is an intersection within a preset range from the second end of the line segment. If there is no intersection, it indicates that the wall has a doorway or other connecting area. In this case, the line segment is extended towards the second end and stops extending after encountering an obstacle to obtain a threshold line, which can represent a threshold. After identifying the wall and defining the threshold, the newly added area is divided into several areas. The boundary of each area is a closed figure enclosed by line segments and their threshold lines. Each area can be regarded as a room. The rooms can be distinguished from adjacent rooms by numbering them or filling them with different colors.

[0089] It's understandable that by filling and updating newly added areas on top of the existing zone map to create a new zone map, the original zone map can be modified without significantly altering it, thus minimizing disruption to the user's cleaning settings and meeting their cleaning needs.

[0090] It is understandable that for a single partition, a unique area number can be configured for the newly added area according to the numbering rules of the partition map and updated in the partition map. Each independent partition in the partition map has a unique area number.

[0091] The robot intelligent zoning method provided in this invention identifies line segments of the newly added area and divides the newly added area into several closed areas by drawing threshold lines for the line segments. Each closed area can be regarded as a room. The rooms can be distinguished from adjacent rooms by numbering or filling them with different colors. The zoning method is fast, efficient, accurate, and widely adaptable, improving the user experience of the robot. The zoning results are updated in the zoning map to maintain the original zoning results as much as possible and not to change the robot's working parameters set by the user, thereby improving the user experience.

[0092] Example 3

[0093] See Figure 3 This is a schematic diagram of the robot intelligent partitioning device provided in an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown. In this embodiment, the robot intelligent partitioning device includes:

[0094] The new area acquisition module 100 is used to acquire the SLAM map after the robot's most recent work is completed, and compare it with the partition map to obtain the area attributes of at least one new area added to the cleaning area, as well as the area numbers of the adjacent areas of the new area.

[0095] The first judgment module 200 is used to determine, for each newly added region, whether the region attribute meets a preset first condition and whether the region number meets a preset second condition.

[0096] The local partitioning module 300 is used to perform local partitioning on the newly added region when the region attribute meets the first condition and the region number meets the second condition.

[0097] The robot intelligent zoning method is applied to automated robots that do not require human operation or control.

[0098] In this embodiment of the invention, SLAM (Simultaneous Localization and Mapping) and related technologies in the field of robotics can be applied as follows: a robot is placed in an unknown location within an unknown environment. During its movement, it locates its own position and orientation by repeatedly observing map features (e.g., corners, room furnishings, etc.), and then incrementally builds a map based on its own position, thereby achieving simultaneous localization and map construction. The SLAM map refers to the environmental map constructed by the robot after completing a cleaning cycle through the above process. One purpose of constructing the SLAM map is to enable the robot to cover all areas of the environmental map without obstacles along a planned path during cleaning operations.

[0099] Optionally, taking a home cleaning robot as an example, the robot operates in a residential home, which typically consists of multiple rooms or halls. These rooms and halls are separated by walls or interior furnishings, and interconnected by doorways. For the robot, the environmental parameters of each room or hall are different, thus requiring different sweeping parameters. For example, cleaning the bathroom requires a strong dehumidification function, while cleaning the kitchen requires a function to remove grease. Therefore, the robot usually divides the space into zones based on an environmental map. Users can configure the robot's sweeping parameters according to the zoning results and specific cleaning needs to achieve quick and efficient cleaning. In this embodiment of the invention, the zoning map refers to the map data generated based on the environmental map.

[0100] In this embodiment of the invention, the user can configure the robot's sweeping parameters according to the pre-defined areas on the environmental map by interacting with the robot. The interaction can be achieved through an application, specifically an application installed on the device terminal, which can be a smart terminal, smart tablet, remote control, etc. The application on the device terminal can communicate with the robot or a cloud server that communicates with the robot.

[0101] Optionally, by comparing the SLAM map with the zonal map, the region attributes of at least one newly added area in the cleaning area can be obtained. The SLAM map is synchronously constructed by the robot during actual cleaning operations and includes unknown areas, passable areas, and impassable areas in the environment. The zonal map is a grid map obtained by dividing the SLAM map according to the room layout after the last cleaning. Each grid is filled with the room number to which the location belongs. If a passable area on the current SLAM map does not have a corresponding room number, then that area is an unknown area left over from the last cleaning. The newly added area is obtained by comparing the mapping values ​​of the same location on the SLAM map and the zonal map. For example: the mapping value of the SLAM map: 0 represents an unknown area, 1 represents a passable area, and 2 represents an impassable area; the mapping value of the zonal map: 0-253 represents room numbers, 254 represents an unknown area, and 255 represents an impassable area. If the mapping value of a certain area on the SLAM map is 1, and the mapping value of the sub-map is 255 or 254, it means that the area is a newly added area. If the mapping value of the sub-map is 0-253 (room number), it means that the area is not a newly added area.

[0102] The regional attributes include, but are not limited to, attributes that characterize the new region, such as its length, width, and area, and are not limited here. It should be noted that, in order to accurately delineate the new region, reduce errors, and decrease the amount of computation, as many regional attributes as possible can be set.

[0103] Typically, new areas are located between zones with clear physical boundaries (such as different rooms), connecting adjacent zones.

[0104] In this embodiment of the invention, it is determined whether the first condition is met by comparing the specific value of the regional attribute of the newly added region with one or a set of pre-set thresholds for the same attribute. If the regional attribute of the newly added region is greater than the threshold, it is determined that the first condition is met, and the determination of the second condition continues; if the regional attribute of the newly added region is less than the threshold, it is determined that the first condition is not met.

[0105] As mentioned above, it can be determined whether the first condition is met by comparing the specific value of the regional attribute of the newly added region with one or a set of pre-set thresholds for the same attribute. If the regional attribute of the newly added region is less than the threshold, it is determined that the first condition is not met.

[0106] It is understandable that if the regional attribute of the newly added area is less than the threshold, it means that the newly added area occupies a small proportion in the environmental map. It can be merged with the adjacent areas. In this way, there is no need to change the original partition, which avoids the failure of the user's preset robot sweeping parameters, and at the same time, it has no impact on the robot's cleaning work.

[0107] In this embodiment of the invention, whether the second condition is met can be determined by comparing the numbers of the adjacent regions of the newly added region. If the adjacent regions of the newly added region have the same numbers, it is determined that the second condition is not met. If the region attributes meet the first condition and the region number meets the second condition, the newly added region is locally partitioned.

[0108] In some embodiments, when it is determined that the region attribute does not meet the first condition or the region number does not meet the second condition, the newly added region is merged with the adjacent region, and the partition map is updated.

[0109] As mentioned earlier, it can be determined whether the second condition is met by comparing the numbers of the adjacent areas of the newly added area. If the adjacent areas of the newly added area have the same numbers, it is determined that the second condition is not met.

[0110] It is understandable that if the adjacent areas of the newly added area have the same number, it means that the adjacent areas of the newly added area have the same attributes. For the robot, the same sweeping parameters can be used to clean it. Therefore, the newly added area can be merged with its adjacent areas. This way, there is no need to change the original partitions, avoiding the failure of the robot's preset sweeping parameters, and it has no impact on the robot's ability to complete the cleaning work.

[0111] In this embodiment of the invention, the judgment of the first condition and the second condition can be regarded as the identification and confirmation of the changed parts of the original partition map. One purpose is to improve the certainty as much as possible, reduce the error, reduce the amount of calculation, filter out areas that do not need to be partitioned, and merge the newly added areas that do not need to be partitioned into the adjacent areas.

[0112] When a newly added region passes the first and second conditions, it indicates that there are no parts in the newly added region that can be merged into adjacent regions. Therefore, the newly added region can be locally partitioned.

[0113] In some possible embodiments, please refer to Figure 4 ,exist Figure 4 In the map, different areas are assigned different numbers. For example, taking the numerical numbering as an example, the areas with area numbers 0, 1, and 2 are known areas in the partition map. After one sweep, the three areas ①, ②, and ③ in the map are added. That is, the three areas ①, ②, and ③ are the newly added areas.

[0114] For example, taking the first condition being that the area is greater than a set threshold and the second condition being that the adjacent areas have different numbers, the adjacent areas of the newly added area ① include number 1 and number 255. Number 1 can be regarded as a room and number 255 can be regarded as a wall. The area numbers of the adjacent areas of the newly added area ① meet the second condition, but the area of ​​the newly added area ① is too small to reach the set threshold, so the first condition is not met. Therefore, the newly added area ① can be merged with area number 1.

[0115] The area of ​​the newly added region ② is greater than the set threshold, satisfying the first condition. However, the newly added region ② is surrounded by region 2, resulting in adjacent regions of the newly added region ② having the same number, which does not satisfy the second condition. Therefore, the newly added region ② and its adjacent regions ( Figure 4 The newly added area ② can be merged with the adjacent area (area numbered 2). Figure 4 Merge areas with the same color (e.g., area number 2).

[0116] In addition, if the area of ​​the newly added region ③ is large enough to satisfy the first condition, and the adjacent regions of the newly added region ③ have different numbers, thus satisfying the second condition, then the newly added region ③ needs to be partially partitioned.

[0117] For example, the final partitioning effect of adding a new region after partial partitioning is as follows: Figure 5 As shown, Figure 5 compared to Figure 4 Two new partitions are added, numbered 3 and 4, derived from the newly added area ③. New areas ① and ② are then merged into partition 1 and partition 2, respectively. In practice, each partition can be filled with a different color than its adjacent areas to distinguish them.

[0118] The robot intelligent zoning method provided in this invention obtains the SLAM map of the robot's completed cleaning process, compares it with the zoning map, obtains the region attributes of the newly added area and the region numbers of adjacent areas, determines whether the region attributes and region numbers meet a first condition and a second condition, and then intelligently zons the newly added area based on the determination result. For environmental maps where robot cleaning parameters have already been set, when the environment changes, there is no need to reset the map zoning to a large extent, avoiding the invalidation of robot cleaning parameters set by the user for that environmental map, improving the robot's intelligence level, and providing an excellent user experience.

[0119] Example 4

[0120] Please see Figure 3This is a schematic diagram of the robot intelligent partitioning device provided in an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown. In this embodiment, the partial partitioning module 300 of the robot intelligent partitioning device further includes:

[0121] The line segment recognition submodule 301 is used to obtain the local map data of the corresponding newly added area in the SLAM map and identify the line segments in the local map data.

[0122] The first judgment submodule 302 is used to determine whether the first end of the line segment intersects with other line segments, and whether there is an intersection within a preset range from the second end of the line segment;

[0123] The threshold recognition submodule 303 is used to extend the line segment towards the second end when it is determined that the first end of the line segment intersects with other line segments and there are no intersections within a preset range from the second end of the line segment, and to stop extending the line segment after encountering an obstacle, thereby obtaining the threshold line of the newly added area.

[0124] The region filling submodule 304 is used to fill the newly added region according to the threshold line and update it in the partition map.

[0125] This invention provides a method for locally partitioning a newly added area. It is easy to understand that, in this invention, the function of the map data acquisition submodule can be regarded as laying the groundwork for the line segment recognition function of the line segment recognition submodule. As mentioned above, based on the acquired local map data of the newly added area, the line segments therein can be further identified. In this invention, the line segments in the local map can be regarded as the walls of each room.

[0126] It is understandable that when it is determined that there is an intersection point within a preset range from the second end of the line segment, the line segment can be equated with the line segment identified by the line segment recognition submodule for subsequent processing. That is, the line segment can be directly regarded as the boundary of each partition.

[0127] Each line segment and its threshold line can be considered together as the aforementioned partition boundary.

[0128] If line segments intersect, it indicates that the intersection connects two walls. Further, for a line segment whose first end intersects with other line segments, it is determined whether there is an intersection within a preset range from the second end of the line segment. If there is no intersection, it indicates that the wall has a doorway or other connecting area. In this case, the line segment is extended towards the second end and stops extending after encountering an obstacle to obtain a threshold line, which can represent a threshold. After identifying the wall and defining the threshold, the newly added area is divided into several areas. The boundary of each area is a closed figure enclosed by line segments and their threshold lines. Each area can be regarded as a room. The rooms can be distinguished from adjacent rooms by numbering them or filling them with different colors.

[0129] It's understandable that by updating and adding local areas on the existing zone map to form a new zone map, the original zone map can be modified without significantly altering it, thus minimizing disruption to the user's cleaning settings and meeting the user's cleaning needs.

[0130] Furthermore, the line segment recognition submodule 301 includes:

[0131] The line segment recognition unit is used to perform binarization processing on the local map data and identify the line segments in the binarized local map data according to the line recognition model.

[0132] In some possible embodiments, the local partitioning module 300 may only be used to locally partition the newly added area when the area number meets the second condition. For example, the area filling submodule 304 mentioned above is used to fill the newly added area according to the threshold line to generate the newly added local area. The robot intelligent partitioning device provided in this application may also include an area merging module 400, which is used to merge the newly added local area with adjacent areas to finally generate a complete partition map. It can be understood that by updating the newly added local area on the basis of the original partition map to form a new partition map, the original partition map can be modified without too much change, and the user's cleaning parameters can be minimized to meet the user's cleaning needs.

[0133] Example 5

[0134] Please see Figure 3 This is a schematic diagram of the robot intelligent partitioning device provided by the present invention. For ease of explanation, only the parts related to the embodiments of the present invention are shown. In this embodiment, the robot intelligent partitioning device further includes:

[0135] The first region merging module 201 is used to merge the newly added region with the adjacent region and update the partition map when it is determined that the region attribute does not meet the first condition or the region number does not meet the second condition.

[0136] As mentioned above, it can be determined whether the first condition is met by comparing the specific value of the regional attribute of the newly added region with one or a set of pre-set thresholds for the same attribute. If the regional attribute of the newly added region is less than the threshold, it is determined that the first condition is not met.

[0137] It is understandable that if the regional attribute of the newly added area is less than the threshold, it means that the newly added area occupies a small proportion in the environmental map. It can be merged with the adjacent areas. In this way, there is no need to change the original partition, which avoids the failure of the user's preset robot sweeping parameters, and at the same time, it has no impact on the robot's cleaning work.

[0138] As mentioned earlier, it can be determined whether the second condition is met by comparing the numbers of the adjacent areas of the newly added area. If the adjacent areas of the newly added area have the same numbers, it is determined that the second condition is not met.

[0139] It is understandable that if the adjacent areas of the newly added area have the same number, it means that the newly added area has the same attributes as the adjacent areas. For the robot, the same sweeping parameters can be used to clean it. Therefore, the newly added area can be merged with its adjacent areas. This way, there is no need to change the original partitions, avoiding the failure of the user's preset robot sweeping parameters, and it has no impact on the robot's ability to complete the cleaning work.

[0140] Example 6

[0141] This embodiment provides a robot, which includes the robot intelligent partitioning device described in any of the embodiments three to five above.

[0142] Example 7

[0143] This embodiment provides a readable storage medium storing a computer program that, when executed by a processor, implements the robot intelligent partitioning method steps described in the above embodiment. The readable storage medium may be, for example, ROM / RAM, a magnetic disk, or an optical disk.

[0144] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units or modules as needed, that is, the internal structure of the storage device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application.

[0145] Those skilled in the art will understand that Figure 3 The structural composition shown does not constitute a limitation on the robotic intelligent partitioning device of the present invention. It may include more or fewer components than shown, or combine certain components, or have different component arrangements. Figure 1-2 The robot intelligent partitioning method in the article also adopts Figure 3The invention can be implemented using more or fewer components, combinations of certain components, or different component arrangements. The units, modules, etc., referred to in this invention are a series of computer programs that can be executed by the processor (not shown) in the robot's intelligent partitioning device and can perform specific functions, all of which can be stored in the storage device (not shown) of the robot's intelligent partitioning device.

[0146] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A robot intelligent partitioning method, characterized in that, The method includes: Obtain the SLAM map after the robot's most recent work is completed, and compare it with the zoning map to obtain the zoning attributes of at least one newly added zoning area and the zoning numbers of the adjacent zoning areas of the newly added zoning area. For each newly added region, it is determined whether the region attribute meets a preset first condition and whether the region number meets a preset second condition. The region attribute is the area of ​​the newly added region. If the area of ​​the newly added region is greater than a set threshold, it is determined that the first condition is met. If the area of ​​the newly added region is less than the set threshold, it is determined that the first condition is not met. If the region numbers of the adjacent regions of the newly added region are inconsistent, it is determined that the second condition is met. If the region numbers of the adjacent regions of the newly added region are consistent, it is determined that the second condition is not met. When it is determined that the region attribute meets the first condition and the region number meets the second condition, the newly added region is partially partitioned. After determining whether the region attribute meets a preset first condition and whether the region number meets a preset second condition for each newly added region, the method further includes: When it is determined that the region attribute does not meet the first condition or the region number does not meet the second condition, the newly added region is merged with the adjacent region, and the partition map is updated.

2. The robot intelligent partitioning method as described in claim 1, characterized in that, The step of locally partitioning the newly added area includes: Obtain local map data corresponding to the newly added area in the SLAM map, and identify line segments in the local map data; Determine whether the first end of the line segment intersects with other line segments, and whether there is an intersection within a preset range from the second end of the line segment; When it is determined that the first end of the line segment intersects with other line segments, and there are no intersections within a preset range from the second end of the line segment, the line segment is extended towards the second end and the extension stops after encountering an obstacle, thus obtaining the threshold line of the newly added area; The newly added area is filled according to the threshold line and updated in the partition map.

3. The robot intelligent partitioning method as described in claim 2, characterized in that, The step of identifying line segments in the local map data includes: The local map data is binarized, and line segments in the binarized local map data are identified using a line recognition model.

4. A robot intelligent partitioning device, characterized in that, include: A new area acquisition module is added to acquire the SLAM map after the robot's most recent work is completed, and compare it with the partition map to obtain the area attributes of at least one newly added area in the cleaning area, as well as the area numbers of the adjacent areas of the newly added area. The first judgment module is used to determine, for each newly added area, whether the area attribute meets a preset first condition and whether the area number meets a preset second condition, wherein: the area attribute is the area of ​​the newly added area; if the area of ​​the newly added area is greater than a set threshold, it is determined that the first condition is met; if the area of ​​the newly added area is less than the set threshold, it is determined that the first condition is not met; if the area numbers of the adjacent areas of the newly added area are inconsistent, it is determined that the second condition is met; if the area numbers of the adjacent areas of the newly added area are consistent, it is determined that the second condition is not met. The local partitioning module is used to perform local partitioning on the newly added region when it is determined that the region attribute meets the first condition and the region number meets the second condition. The first region merging module is used to merge the newly added region with the adjacent region and update the partition map when it is determined that the region attribute does not meet the first condition or the region number does not meet the second condition.

5. The robot intelligent partitioning device as described in claim 4, characterized in that, The local partitioning module includes: The line segment recognition submodule is used to obtain local map data corresponding to the newly added area in the SLAM map and identify line segments in the local map data. The first judgment submodule is used to determine whether the first end of the line segment intersects with other line segments, and whether there is an intersection within a preset range from the second end of the line segment; The threshold recognition submodule is used to extend the line segment toward the second end when it is determined that the first end of the line segment intersects with other line segments and there are no intersections within a preset range from the second end of the line segment, and to stop extending the line segment after encountering an obstacle, so as to obtain the threshold line of the newly added area. The region filling submodule is used to fill the newly added region according to the threshold line and update it in the partition map.

6. The robot intelligent partitioning device as described in claim 5, characterized in that, The line segment recognition submodule includes: The line segment recognition unit is used to perform binarization processing on the local map data and identify the line segments in the binarized local map data according to the line recognition model.

7. A robot, characterized in that, Including the robot intelligent partitioning device as described in any one of claims 4-6.

8. A computer-readable storage medium, characterized in that, It stores a computer program, characterized in that, when the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1-3.

Images