Cleaning map updating method, cleaning robot and storage medium

Abstract

The embodiment of the invention relates to the technical field of cleaning robots, and discloses a method for updating a clean map, and the method comprises the steps: obtaining a current clean map, carrying out the partition merging and gate feature merging of the current clean map and a historical clean map, and obtaining an updated clean map. And comprehensively considering the current clean map and the historical clean map, and carrying out partition merging and gate feature merging to obtain an updated clean map. That is, the union set of the partitions in the historical clean map and the current clean map and the union set of the gate features are taken, so that partition omission and gate feature omission can be effectively reduced, the partitions and gate features in the updated clean map are accurate, and the reasonability of subsequent path planning is facilitated. Besides, the partition state change and the door opening and closing state change can be monitored in real time, so that the clean map can be updated in real time, manual intervention is reduced, the system is more intelligent and accurate, and the reasonability of subsequent path planning and the high efficiency of navigation are facilitated.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of cleaning robots, and in particular to a method for updating a cleaning map, a cleaning robot, and a storage medium. Background Art

[0002] With the continuous development of automation technology and artificial intelligence technology, various cleaning robots such as floor scrubbers and sweepers are being used more and more widely. These cleaning robots can automatically clean the ground and remove dust and dirt from the ground or other surfaces, bringing great convenience to people's lives. The cleaning robot builds a cleaning map based on the explored environmental data, divides the area on the cleaning map to obtain multiple cleaning partitions, and finally plans the cleaning path for each cleaning partition so that the cleaning work can be performed according to the cleaning path later.

[0003] In actual cleaning operations, the partition results or door information in the cleaning map may change due to changes in the door's open and close status, expansion of new areas, or users' selective division and merging of rooms. The cleaning map needs to be updated and repartitioned. However, due to the influence of scanning errors in the cleaning map and obstacles in the environment, it is easy to cause deviations in partition or door information, affecting the rationality of subsequent path planning. Summary of the invention

[0004] In view of this, some embodiments of the present application provide a method for updating a cleaning map, a cleaning robot and a storage medium, which comprehensively consider the current cleaning map and the historical cleaning map, perform partition merging and door feature merging, and obtain an updated cleaning map, so that the updated cleaning map is more accurate, which is conducive to the rationality of subsequent path planning.

[0005] In a first aspect, some embodiments of the present application provide a method for updating a cleaning map, comprising:

[0006] Get the current cleaning map;

[0007] The current cleaning map and the historical cleaning map are partitioned and gated to obtain an updated cleaning map.

[0008] In some embodiments, the above-mentioned partitioning and merging of the current cleaning map and the historical cleaning map includes:

[0009] The partitions added in the current cleaning map relative to the historical cleaning map are retained and marked as reachable areas;

[0010] The partitions where the current cleaning map is reduced relative to the historical cleaning map are added to the current cleaning map and marked as unreachable areas.

[0011] In some embodiments, the aforementioned merging of gate features of the current cleaning map and the historical cleaning map includes:

[0012] After deduplication processing is performed on the gate feature set, the gate feature set is used as the gate feature in the updated cleaning map, wherein the gate feature set includes the gate features in the current cleaning map and the gate features in the historical cleaning map.

[0013] In some embodiments, the aforementioned deduplication processing of the door feature set includes:

[0014] Perform cluster analysis on the gate feature set and merge similar gate features into one gate feature.

[0015] In some embodiments, the aforementioned cluster analysis of the gate feature set to merge similar gate features into one gate feature includes:

[0016] If the position distance between any two gate features in the gate feature set is less than or equal to the distance threshold, the two gate features are determined to be similar gate features;

[0017] Among the similar door features, the door features belonging to the current clean map are used as the merged door features.

[0018] In some embodiments, the aforementioned cluster analysis of the gate feature set to merge similar gate features into one gate feature includes:

[0019] If the position distance between any two door features in the door feature set is less than or equal to the distance threshold and the parallelism difference is less than or equal to the angle threshold, then the two door features are determined to be similar door features;

[0020] The door features belonging to the current cleaning map among the similar door features are processed horizontally or vertically to serve as updated door features.

[0021] In some embodiments, the method further comprises:

[0022] In the current cleaning map, for the newly added partition, a gate feature is marked between the newly added partition and other adjacent connected partitions according to the area of ​​the newly added partition and / or the slope of the dividing line.

[0023] In some embodiments, the above-mentioned marking of a gate feature between the newly added partition and other adjacent connected partitions according to the area of ​​the newly added partition and / or the slope of the dividing line includes:

[0024] If the area of ​​the newly added partition is greater than or equal to the area threshold, a gate feature is marked between the newly added partition and other adjacent connected partitions; and / or,

[0025] If the slope of the dividing line is within the preset slope range, a door feature is marked between the newly added partition and other adjacent connected partitions.

[0026] In a second aspect, some embodiments of the present application provide a cleaning robot, comprising:

[0027] at least one processor;

[0028] A memory communicatively connected to at least one processor; wherein the memory stores instructions executable by at least one processor, and the instructions are executed by at least one processor so that the at least one processor can execute the method for updating the cleaning map as in the first aspect.

[0029] In a third aspect, some embodiments of the present application provide a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are used to enable a computer device to execute the method for updating a cleaning map in the first aspect.

[0030] Beneficial effects of the embodiments of the present application: Different from the prior art, the method for updating the cleaning map provided by the embodiments of the present application, after obtaining the current cleaning map, merges the current cleaning map and the historical cleaning map into partitions and merges the door features to obtain an updated cleaning map. It can be understood that the current cleaning map can be a map scanned after the cleaning is completed or a map obtained after manually setting the partitions. In the case where the current cleaning map changes relative to the historical cleaning map, the current cleaning map and the historical cleaning map are comprehensively considered, and the partitions are merged and the door features are merged to obtain an updated cleaning map. Compared with directly using the current cleaning map as the updated cleaning map, taking the union of the partitions in the historical cleaning map and the current cleaning map and the union of the door features can effectively reduce the omission of partitions and the omission of door features, so that the partitions in the updated cleaning map are accurate and the door features are accurate, which is conducive to the rationality of subsequent path planning. In addition, through the above method, the changes in the state of the partitions and the changes in the state of the door switches can be monitored in real time, so that the cleaning map can be updated in real time, reducing manual intervention, being more intelligent and accurate, and being conducive to the rationality of subsequent path planning and the efficiency of navigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0032] Figure 1 A schematic diagram of an application environment of a method for updating a cleaning map in some embodiments of the present application;

[0033] Figure 2 A flowchart of a method for updating a cleaning map in some embodiments of the present application;

[0034] Figure 3 A schematic diagram of a cleaning map in some embodiments of the present application;

[0035] Figure 4 A schematic diagram of a cleaning map in some embodiments of the present application;

[0036] Figure 5 This is a schematic diagram of the historical cleaning map and the current cleaning map before and after the merging in some embodiments of the present application;

[0037] Figure 6 This is a schematic diagram of the structure of the cleaning robot in some embodiments of the present application. DETAILED DESCRIPTION

[0038] The present application is described in detail below in conjunction with specific embodiments. The following embodiments will help those skilled in the art to further understand the present application, but do not limit the present application in any form. It should be noted that, for those of ordinary skill in the art, several variations and improvements can also be made without departing from the concept of the present application. These all belong to the protection scope of the present application.

[0039] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0040] It should be noted that, if there is no conflict, the various features in the embodiments of the present application can be combined with each other, all within the scope of protection of the present application. In addition, although the functional module division is performed in the device schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a sequence different from the module division in the device or the flow chart. In addition, the words "first", "second", "third", etc. used herein do not limit the data and execution order, but only distinguish the same items or similar items with basically the same functions and effects.

[0041] Unless otherwise defined, all technical and scientific terms used in this specification have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used in this specification and in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used in this specification includes any and all combinations of one or more of the related listed items.

[0042] In addition, the technical features involved in each embodiment of the present application described below can be combined with each other as long as they do not conflict with each other.

[0043] See also Figure 1 , Figure 1 Schematic diagram of an application environment for updating a cleaning map provided by an embodiment of the present application. Figure 1 As shown, the cleaning robot 100 is located on the ground, which may be the ground of a living room, an office, or an outdoor place. The place where the cleaning robot 100 is located includes objects such as a base station 200, a desk, a flower pot, a sofa, a cabinet, or a bed.

[0044] The free walking of the cleaning robot 100 is mainly completed by the mapping, positioning, navigation and obstacle avoidance modules. A cleaning map is constructed based on the explored environmental data, and the area is divided on the cleaning map to obtain multiple cleaning partitions. After sensing the surrounding environment, the cleaning robot 100 plans one or more paths that do not collide with environmental obstacles and achieve full area coverage according to a certain area cleaning sequence or planning method. It is understandable that these modules are implemented by sensors and corresponding control programs.

[0045] In some embodiments, the cleaning robot 100 is equipped with a laser radar and / or a visible light camera, wherein the laser radar scans the surrounding environment of the cleaning robot 100 to obtain a laser point cloud. The visible light camera shoots the surrounding environment of the cleaning robot 100 to obtain an image. The laser radar and the visible light camera are respectively connected to the controller for communication, and the laser point cloud and the image are sent to the controller respectively. The controller calls the program for building a cleaning map pre-set in the memory of the cleaning robot 100, and builds a cleaning map based on the laser point cloud and / or the image. Among them, the program for building a cleaning map may include a program corresponding to the SLAM algorithm (Simultaneous Localization and Mapping, SLAM), which is not described in detail here. In some embodiments, the cleaning map is a grid map. The cleaning map includes a plurality of cleaning partitions, and the passage between two adjacent cleaning partitions is marked with door information. The cleaning map is stored in the memory of the cleaning robot 100. When the robot moves, the controller calls the cleaning map as the basis for autonomous positioning, path planning and obstacle avoidance.

[0046] It is understandable that the SLAM algorithm has both positioning and navigation functions. During the positioning process, the laser radar is controlled to rotate at high speed to emit laser, measure the distance between the cleaning robot and the obstacle, and combine the map to determine the relative position between the cleaning robot and the obstacle, so as to achieve positioning. In some embodiments, the cleaning robot 100 can perform visual positioning based on a visible light camera. During the navigation process, cleaning control is performed based on positioning and cleaning tasks, each partition to be cleaned is cleaned one by one, and a full coverage cleaning path is planned in each partition to be cleaned to complete the corresponding cleaning task.

[0047] The cleaning robot 100 can be configured into any suitable shape to achieve specific business function operations. For example, in some embodiments, the cleaning robot 100 can be a mobile robot based on a SLAM system. The cleaning robot 100 includes but is not limited to a sweeping robot, a vacuuming robot, a mopping robot, or a floor washing robot.

[0048] In some embodiments, the cleaning robot 100 may include a robot body, a laser radar, a controller, and a walking mechanism. The robot body is the main structure of the cleaning robot 100, and can be selected according to the actual needs of the cleaning robot 100. The corresponding shape structure and manufacturing material (such as hard plastic or metal such as aluminum, iron, etc.) can be selected, for example, it is set to a relatively flat cylindrical shape commonly seen in the cleaning robot 100.

[0049] The walking mechanism is a structural device arranged on the robot body to provide mobility for the cleaning robot 100. The walking mechanism can be implemented by any type of mobile device, such as rollers, crawlers, etc.

[0050] The laser radar is arranged on the body of the cleaning robot 100, and is used to sense obstacles in the surrounding environment of the mobile cleaning robot 100, scan and obtain laser point cloud data, and send it to the controller so that the controller can build a map based on the laser point cloud data and perform walking obstacle avoidance, etc. In some embodiments, the laser radar includes pulse laser radar, continuous wave laser radar and other radars.

[0051] The controller is an electronic computing core built into the robot body, which is used to perform logical operation steps to realize intelligent control of the cleaning robot. In the embodiment of the present application, the controller is connected to the laser radar for establishing a cleaning map based on the laser point cloud data and controlling the cleaning robot to walk. It is also used for cleaning control based on the cleaning map and cleaning tasks, such as dividing the cleaning area, generating the cleaning order of the cleaning area, controlling the cleaning robot to clean the cleaning area one by one according to the cleaning order, and planning the cleaning path in each cleaning area to cover the entire area.

[0052] It is understood that the controller can be a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a single chip microcomputer, an ARM (Acorn RISC Machine) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination of these components. The controller can also be any conventional processor, controller, microcontroller or state machine. The controller can also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors combined with a DSP and / or any other such configuration, or a combination of one or more of a microcontroller unit (MCU), a field programmable gate array (FPGA), and a system on chip (SoC).

[0053] In some embodiments, the robot body may further include a clean water tank, a sewage tank, a detergent box, a dust collection box, and the like. In this embodiment, the base station 200 includes a base, a cleaning device, a water supply device, a dust collection device, a power supply device, a detergent replenishing device, and a sewage collection device (not shown). The base, the cleaning device, the water supply device, the dust collection device, the power supply device, the detergent replenishing device, and the sewage collection device are not shown in the figure. The base is used to dock the cleaning robot, the cleaning device is used to clean the cleaning robot, the water supply device is used to supply water to the cleaning robot and / or to the cleaning device, and the dust collection device is used to collect dust in the dust collection box of the cleaning robot. The power supply device is used to charge the cleaning robot. The sewage collection device is used to collect sewage in the sewage tank of the cleaning robot.

[0054] It is understandable that the surface of the base station 200 for approaching the cleaning robot 100 matches the shape of the cleaning robot. For example, the cleaning robot 100 is commonly a relatively flat cylindrical shape, and accordingly, the base station 200 is provided with an open docking cavity for accommodating the cleaning robot 100, and the docking cavity is semi-cylindrical, and its surface is an arc surface. In some embodiments, the radius of the docking cavity is 5-10 cm larger than the radius of the cleaning robot, so that when the cleaning robot 100 is docked with the base station 200, the cleaning robot 100 is accommodated in the docking cavity.

[0055] It should be noted that, depending on the tasks to be completed, in addition to the above functional modules, the main body of the cleaning robot can also be equipped with one or more other different functional modules (such as a water tank, a mop, etc.) to cooperate with each other to perform corresponding tasks.

[0056] In actual cleaning operations, the partitioning results or door information in the cleaning map may change due to changes in the door's open or closed state, expansion of new areas, or users' selective division or merging of rooms or setting of no-entry zones. This may necessitate updating the cleaning map and performing secondary partitioning.

[0057] In some schemes for updating the cleaning map known to the inventors of the present application, a newly generated cleaning map is usually directly used to replace the original cleaning map, which will cause the updated cleaning map to be inaccurate and affect the cleaning operation. However, based on the scanning error of the cleaning map, obstacles in the environment (such as placing or moving long straight board obstacles), etc., the partition position or door position in the newly generated cleaning map may be offset or the number may change based on the original partition. If the newly generated cleaning map is directly put into use as the updated cleaning map, it is easy to cause errors in the partition and door position, such as the loss of features such as partitions or doors, changes in the original door position, etc., but in the actual environment, the environmental area and the door therein are fixed. This will affect the rationality of subsequent path planning and the effectiveness of navigation.

[0058] In view of the above problems, some embodiments of the present application provide a method for updating a cleaning map. After obtaining the current cleaning map, the current cleaning map and the historical cleaning map are partitioned and merged and the door features are merged to obtain an updated cleaning map. It is understandable that the current cleaning map can be a map obtained by scanning after the cleaning is completed or a map obtained after manually setting the partitions. In the case where the current cleaning map changes relative to the historical cleaning map, the current cleaning map and the historical cleaning map are comprehensively considered, and the partitions are merged and the door features are merged to obtain an updated cleaning map. Compared with directly using the current cleaning map as the updated cleaning map, taking the union of the partitions in the historical cleaning map and the current cleaning map and the union of the door features can effectively reduce the omission of partitions and the omission of door features, so that the partitions in the updated cleaning map are accurate and the door features are accurate, which is conducive to the rationality of subsequent path planning. In addition, through the above method, the changes in the state of the partitions and the changes in the state of the door switches can be monitored in real time, so that the cleaning map can be updated in real time, reducing manual intervention, being more intelligent and accurate, and being conducive to the rationality of subsequent path planning and the efficiency of navigation.

[0059] It can be understood from the above that the method for updating the cleaning map provided in the embodiment of the present application can be implemented by the cleaning robot, for example, by one or more processors of the cleaning robot. In some embodiments, the method for updating the cleaning map provided in the embodiment of the present application can also be implemented by other devices with computing and processing capabilities. Other devices with computing and processing capabilities can be intelligent devices that are connected to the cleaning robot in communication, such as servers.

[0060] The following describes the method for updating the cleaning map provided by the embodiment of the present application in combination with the exemplary application and implementation of the cleaning robot provided by the embodiment of the present application. Figure 2 , Figure 2 1 is a flow chart of a method for updating a cleaning map provided in an embodiment of the present application. It is understandable that the execution subject of the method for updating a cleaning map may be one or more processors of a cleaning robot.

[0061] like Figure 2 As shown, the method S00 includes but is not limited to the following steps:

[0062] S10: Obtain a current cleaning map.

[0063] Among them, the cleaning map is a map of the environment space where the cleaning robot is located. In some embodiments, the cleaning map can be a grid map or other graphical map. The grid map represents a two-dimensional space description method, which divides the two-dimensional space into sub-units with a minimum resolution. For example, a two-dimensional space of 1m*1m is described as a 20*20 grid matrix after being divided with a resolution of 5cm. The size of each element in the grid matrix corresponding to the actual physical size is 5cm*5cm. In the grid map, a free grid refers to a grid that is not occupied by an object, and an obstacle grid refers to a grid occupied by an object.

[0064] In order to reflect the distribution of obstacles in the environment, a corresponding grid value can be set for each grid. For example, the free grid can be represented by a value of 255, and the obstacle grid can be represented by a value of 0. The area formed by the free grid is the area where the cleaning robot can pass, that is, the reachable area. The area formed by the obstacle grid is the area where the cleaning robot cannot pass, that is, the unreachable area.

[0065] It is understood by those skilled in the art that the cleaning robot can generate a cleaning map based on sensor data, wherein the sensor data can be collected by the cleaning robot through a laser radar and / or a camera and / or various motion sensors. Exemplarily, the cleaning robot establishes a cleaning map based on point cloud data obtained by laser radar scanning and a SLAM algorithm.

[0066] From the cleaning map, we can know the ground pattern of the cleaning robot and the obstacles on the ground. To facilitate subsequent cleaning, the cleaning map is divided into multiple partitions based on the environment pattern, the continuity of the accessible areas in the cleaning map, or by identifying door features, and each partition is marked with a different name or a different logo. Figure 3As shown, the cleaning map includes 5 partitions, which are room 1, room 2, room 3, room 4 and room 5, and each partition is marked with a door feature. In some achievable methods, the door feature can be represented by two end point coordinates, the two end point coordinates are the two end points of the door width, and the line connecting the two coordinates represents the door line segment.

[0067] Exemplarily, one or more processors in the cleaning robot can determine the door feature based on the shape characteristics of the contour line by extracting the outer contour line in the cleaning map. For example, most partitions are enclosed shapes with openings, and their contour lines are also enclosed shapes with openings; doors have certain widths and are horizontal or vertical; when the opening of the contour line reaches a certain width and the opening line is horizontal or vertical, the opening is determined to be a door feature. Exemplarily, one or more processors in the cleaning robot can receive images captured by the camera and determine the door feature based on existing image recognition algorithms. After determining the door feature, two endpoint coordinates can be used in the cleaning map to represent the door feature.

[0068] After the initial map building is completed, the cleaning robot will automatically partition the area and mark the features of each partition and door. Based on the full coverage of the cleaning path, each full-area cleaning is equivalent to an automatic scan of the environment, and a new cleaning map will be regenerated. In some possible scenarios, when the door switch status changes or the ground conditions change, the new cleaning map will change.

[0069] In some other possible scenarios, the user can modify the cleaning map through an application associated with the cleaning robot on the terminal, such as selectively splitting or merging rooms, causing changes to the cleaning map.

[0070] In some embodiments, one or more processors of the cleaning robot can obtain the cleaning map in real time, or obtain the cleaning map at a certain frequency. In some embodiments, the cleaning robot obtains the cleaning map after each cleaning operation is completed, or, after receiving a modification instruction, obtains the cleaning map modified according to the modification instruction. The current cleaning map refers to the latest cleaning map obtained at the current moment, which can be a new cleaning map scanned and obtained after the above cleaning operation is completed, or it can be the above cleaning map modified by the user.

[0071] S20: The current cleaning map and the historical cleaning map are partitioned and gated to obtain an updated cleaning map.

[0072] The historical cleaning map refers to the latest cleaning map before the current cleaning map is obtained. For example, if new cleaning maps are obtained at both time t and time t+i, then for time t+i, the current cleaning map is the cleaning map obtained at time t+i, and the historical cleaning map is the cleaning map obtained at time t.

[0073] Partition merging refers to taking the union of the partitions in the current clean map and the partitions in the historical clean map. Exemplarily, the historical clean map includes room 1, room 2, room 3, and room 4, and each room is marked as a reachable area. In one possible scenario, the door of room 4 is closed or room 4 is set as a no-go zone, and a new extension area is added (for example, when a room door is closed or a no-go zone is set when the map is first built, and then the door is opened or the no-go zone is cancelled). In this scenario, the current clean map obtained by re-building the map includes room 1, room 2, room 3, and room 5, that is, the current clean map does not include room 4, including the newly added extension area (room 5). The same partition identifier (number or name) represents the same actual partition in the real environment. After taking the union of the partitions, the partitions obtained include room 1, room 2, room 3, room 4, and room 5. The updated clean map includes the partitions after taking the union, and the reachable state of each partition can be determined based on the reachable state in the current clean map.

[0074] It can be understood that by retaining the partitions that appear twice in the cleaning map through partition merging, partition omissions can be effectively reduced, so that the partitions in the updated cleaning map are accurate.

[0075] Gate feature merging refers to taking the union of the gate features in the current clean map and the gate features in the historical clean map. For example, the gate features in the historical clean map include gate 1, gate 2, gate 3, and gate 4, and the current clean map includes gate 1, gate 2, gate 3, and gate 5. The same gate identifier represents the same actual door in the real environment. After taking the union of the gate features, the gate features obtained include gate 1, gate 2, gate 3, gate 4, and gate 5. The updated clean map is marked with the gate features after the union. It can be understood that by merging the gate features to retain the gate features that appear twice in the clean map, it can effectively reduce the omission of gate features and make the gate features in the updated clean map accurate.

[0076] In this embodiment, when the current cleaning map changes relative to the historical cleaning map, the current cleaning map and the historical cleaning map are comprehensively considered, and partitions are merged and door features are merged to obtain an updated cleaning map. Compared with directly using the current cleaning map as the updated cleaning map, taking the union of the partitions in the historical cleaning map and the current cleaning map and the union of the door features can effectively reduce the omission of partitions and door features, so that the partitions and door features in the updated cleaning map are accurate, which is conducive to the rationality of subsequent path planning. In addition, through the above method, the changes in the state of the partitions and the changes in the state of the door switches can be monitored in real time, so that the cleaning map can be updated in real time, reducing manual intervention, being more intelligent and accurate, and being conducive to the rationality of subsequent path planning and the efficiency of navigation.

[0077] In such Figure 4 In the scenario shown in (a), the passage between room 7 and room 1 is marked with door feature 7-1 in the historical cleaning map. Even if the current cleaning map misses door feature 7-1, the updated cleaning map still retains door feature 7-1. Therefore, when the cleaning robot performs subsequent path planning or target point selection, it can use door 7-1 marked in room 7 as the door location navigation point and directly enter room 7 from room 1, thereby improving navigation efficiency. If the current cleaning map does not retain door feature 7-1, the cleaning robot can only follow the path from room 1, room 5, room 6, and then detour to room 7, resulting in low navigation efficiency.

[0078] In such Figure 4 In the scenario shown in (b), the passage between room 1 and room 3 in the historical cleaning map is marked with door features 1-3. Even if the current cleaning map misses door features 1-3, the updated cleaning map still retains door features 1-3. Therefore, when the cleaning robot is planning its path, it can clean room 1 first and then room 3. If the current cleaning map does not retain door features 1-3, the cleaning robot may walk from a corner point A in room 1 to a corner point B in room 3 and then return, and start cleaning along a bow-shaped path, thus causing room 1 and room 3 to start cleaning at the same time. When room 1 is cleaned, there is still part of room 3 that is not cleaned. The cleaning robot needs to walk through the cleaned part to the uncleaned part, which is easy to bring stains into the cleaned part, causing secondary pollution. It can be seen that if the door feature is omitted, it will also affect the cleaning strategy, and then affect the cleaning effect.

[0079] It can be seen that compared with directly using the current cleaning map as the updated cleaning map, the embodiment of the present application takes the union of the partitions in the historical cleaning map and the current cleaning map, and takes the union of the door features, which can effectively reduce the omission of partitions and door features, so that the partitions and door features in the updated cleaning map are accurate, which is conducive to the rationality of subsequent path planning and the efficiency of navigation.

[0080] In some embodiments, for the same partition, the current cleaning map retains the partition identification (number or name) in the historical cleaning map to facilitate the accuracy of the union and facilitate display and viewing. For example, after the user merges room 3 and room 4 in the historical cleaning map, the current cleaning map records the merged area as room 3, and retains the door feature between the original room 3 and room 4.

[0081] In some embodiments, the aforementioned partition merging of the current cleaning map and the historical cleaning map includes: retaining the partitions that are added to the current cleaning map relative to the historical cleaning map and marking them as reachable areas; adding the partitions that are reduced from the current cleaning map relative to the historical cleaning map to the current cleaning map and marking them as unreachable areas.

[0082] Among them, the partition added to the current cleaning map relative to the historical cleaning map refers to the newly expanded area. For example, if the balcony door was closed before, there is no balcony partition in the historical cleaning map obtained by mapping; when the cleaning robot is cleaning later, the balcony door is open, then the cleaning robot will explore the new area of ​​the balcony, and the current cleaning map includes the balcony partition. In other words, the balcony partition is the partition added to the current cleaning map relative to the historical cleaning map, so the balcony partition is retained in the updated cleaning map and marked as a reachable area.

[0083] For example, if the kitchen was previously set as a restricted zone, the kitchen area is marked as an unreachable area in the historical cleaning map or the historical cleaning map does not include the kitchen partition. After the user removes the restricted zone setting for the kitchen, the current cleaning map includes the kitchen partition, which is equivalent to the kitchen partition being an added partition of the current cleaning map relative to the historical cleaning map, and thus the kitchen partition is retained in the updated cleaning map and marked as a reachable area.

[0084] Among them, the partitions that are reduced in the current cleaning map relative to the historical cleaning map may be the partitions that are reduced due to the closing of the door or the partitions that are set as no-go areas. For example, if the balcony door was open before, the balcony partition is included in the historical cleaning map obtained by mapping; later, when the cleaning robot is cleaning, the balcony door is closed, then the cleaning robot cannot explore the balcony area, and the current cleaning map does not include the balcony partition. In other words, the balcony partition is the partition that is reduced in the current cleaning map relative to the historical cleaning map. However, the balcony area actually exists, so the balcony partition is retained in the updated cleaning map and marked as an unreachable area.

[0085] For example, if the kitchen was previously a passable area, the kitchen partition is included in the historical cleaning map and marked as a reachable area. After the user sets the kitchen as a no-go area, the current cleaning map includes the kitchen but not the kitchen partition, which is equivalent to the kitchen partition being the partition that is reduced in the current cleaning map relative to the historical cleaning map. However, the kitchen partition actually exists, so the kitchen partition is retained in the updated cleaning map and marked as an unreachable area.

[0086] In this embodiment, through the above method, the existing cleaning map (historical cleaning map) is updated according to the changes of the new cleaning map (current cleaning map). When the cleaning map changes, each newly added partition can be effectively increased and the reduced partition can be saved. Therefore, the updated cleaning map is accurate and reliable, which is conducive to reducing omissions during the cleaning process.

[0087] In some embodiments, the aforementioned merging of gate features of the current cleaning map and the historical cleaning map includes: deduplicating the gate feature set and using it as the gate features in the updated cleaning map, wherein the gate feature set includes the gate features in the current cleaning map and the gate features in the historical cleaning map.

[0088] It is understandable that the physical doors in the environment where the cleaning robot is located generally do not change position. However, due to the open and close states of the doors and the addition or reduction of areas, the number of door features in the cleaning map may change.

[0089] Exemplarily, if the balcony sliding door was previously closed, the balcony area and the balcony sliding door are not included in the historical cleaning map. In the subsequent cleaning operation, if the balcony sliding door is opened to a width of 0.4m, this width enables the cleaning robot to enter the balcony area, so that the cleaning robot explores a new expansion area. Since the 0.4-meter width does not conform to the conventional width interval of the door (e.g., the 1m-1.5m width interval), the balcony area is added to the current cleaning map but the balcony sliding door is not marked as a door feature. In subsequent cleaning operations, if the balcony sliding door is opened to a width of 1.1m, the cleaning robot recognizes that the opening width of the balcony outline is greater than 1m, and the balcony sliding door is marked as a door feature. Here, the balcony sliding door is a newly added door feature.

[0090] It is understandable that if the historical cleaning map includes door 1, door 2 and door 3, after adding the balcony sliding door, the current cleaning map includes door 1', door 2', door 3' and balcony door. These door features can be represented by endpoint coordinates. The door features in the current cleaning map and the historical cleaning map are put into a set to obtain the door feature set {door 1, door 2, door 3, door 1', door 2', door 3', balcony door}.

[0091] Duplicate door features in the door feature set are removed. For example, in the above example, door 1 and door 1' reflect the same door, door 2 and door 2' reflect the same door, and door 3 and door 3' reflect the same door. The same door retains one door feature. For example, retain door 1', door 2', and door 3' in the door feature set, and remove door 1, door 2, and door 3. The door feature set after deduplication includes {door 1', door 2', door 3', balcony door}

[0092] It can be understood that deduplication here means removing one of the two door features that reflect the same door and retaining the other. It is worth noting that due to calculation errors, the endpoint coordinates of the same door in the environment may be different twice, that is, for the same door, its endpoint coordinates in the historical clean map and the current clean map may be different. Therefore, deduplication does not mean removing one of the door features with the same endpoint coordinates in the door feature set, but identifying two door features that reflect the same door, removing one of them and retaining the other.

[0093] In this embodiment, by deduplicating the gate feature set, the gate features added and reduced in the current cleaning map relative to the historical cleaning map can be effectively retained, reducing the number of missed gate features, and making the gate features in the updated cleaning map accurate.

[0094] In some embodiments, the aforementioned deduplication processing of the gate feature set includes: performing cluster analysis on the gate feature set, and merging similar gate features into one gate feature.

[0095] It is understandable that any gate feature in the gate feature set is represented by two endpoint coordinates. Here, cluster analysis refers to cluster analysis of the gate line segments formed by the lines connecting the two endpoint coordinates, finding similar gate features, and merging them into one gate feature. In some embodiments, if the distance between the midpoints of two gate line segments is small, the two gate line segments (gate features) are determined to be similar gate features.

[0096] like Figure 5 As shown, Figure 5 (a) in the figure is the gate line segment in the historical cleaning map. Figure 5 (b) in the figure is the gate line segment set in the historical cleaning map superimposed on the current cleaning map. Figure 5 From (b) in FIG. 1 , it can be seen that the distance between the midpoint of gate segment 1 and the midpoint of gate segment 1 ' is small, and they are close gate segments. Therefore, gate segment 1 and gate segment 1 ' are merged into one gate segment. Figure 5(c) in FIG. 1 is the effect after merging. Exemplarily, two similar gate line segments may be fused to achieve merging. The fusion process may include calculating the mean of the coordinates of the two endpoints at the same end of the two gate line segments. In other embodiments, one of the two similar gate line segments is retained and the other is discarded to achieve merging.

[0097] In this embodiment, by performing cluster analysis on all gate feature sets in the current cleaning map and the historical cleaning map, the gate features reflecting the same gate can be accurately found, and the gate features of the same gate can be merged, so that the gate features of each gate in the cleaning maps generated twice before and after can be effectively retained, reducing omissions, so that the gate features in the updated cleaning map are accurate.

[0098] In some embodiments, the aforementioned cluster analysis of the gate feature set to merge similar gate features into one gate feature includes: if the position distance between any two gate features in the gate feature set is less than or equal to a distance threshold, then the two gate features are determined to be similar gate features. The gate features belonging to the current cleaning map among the similar gate features are used as the merged gate features.

[0099] The position distance refers to the distance between two door features on the cleaning map. In some embodiments, the position distance includes the starting distance between the starting coordinates and the starting coordinates and / or the end distance between the end coordinates and the end coordinates of the two door features. When both the starting distance and the end distance are less than or equal to the distance threshold, the two door features are determined to be similar door features.

[0100] For example, if the starting coordinates of a gate feature A in the historical cleaning map are (3,5) and the ending coordinates are (3,17), and the starting coordinates of a gate feature B in the current cleaning map are (2,5) and the ending coordinates are (2,17). Comparing the position distances of these two gate features in the gate feature set, it can be seen that the starting coordinates differ by one grid and the ending coordinates differ by one grid, and one grid is 5cm, that is, both the starting distance and the ending distance are small, less than the distance threshold (for example, the distance threshold is set to 0.2m). Thus, it is determined that gate feature A and gate feature B are similar gate features. It is understandable that those skilled in the art can set the distance threshold according to actual conditions, such as 1-5 grids, etc., and no limitation is imposed on the distance threshold here.

[0101] When merging, the gate features in the current clean map are preferentially used as the gate features in the updated clean map, for example, the gate feature B is retained and the gate feature A is removed. It can be understood that for gates that exist twice before and after, the gate features obtained the most recently are preferentially retained, which is beneficial to the timely accuracy of the gate feature data.

[0102] In this embodiment, similar door features can be accurately determined through position comparison, and the door features in the current cleaning map are preferentially used as the door features in the updated cleaning map, which is beneficial to the timeliness and accuracy of the door feature data.

[0103] In some embodiments, the aforementioned cluster analysis of the gate feature set to merge similar gate features into one gate feature includes: if the position distance between any two gate features in the gate feature set is less than or equal to the distance threshold and the parallelism difference is less than or equal to the angle threshold, then the two gate features are determined to be similar gate features. The gate features belonging to the current cleaning map among the similar gate features are processed horizontally or vertically to serve as updated gate features.

[0104] In this embodiment, in addition to the above-mentioned distance comparison, a parallelism comparison is also added. Only when both the position distance and the parallelism meet the conditions, the two door features are determined to be similar door features. Among them, parallelism refers to the degree of parallelism between two door segments. In some embodiments, the parallelism difference can be calculated based on the angle between the two door segments, and the parallelism difference is compared with a preset angle threshold. For example, the parallelism difference is the angle between the two, and the angle threshold is the critical value of the angle. When the position distance between the two door segments is less than or equal to the distance threshold and the angle is less than or equal to the angle threshold, the two door segments are determined to be similar door segments.

[0105] For example, if the starting coordinates of a gate feature A in the historical cleaning map are (3,5) and the ending coordinates are (3,17), and the starting coordinates of a gate feature B in the current cleaning map are (2,5) and the ending coordinates are (4,17). Comparing the position distances of these two gate features in the gate feature set, it can be seen that the starting coordinates differ by one grid and the ending coordinates differ by one grid, and one grid is 5cm, that is, both the starting distance and the ending distance are small, less than the distance threshold (for example, the distance threshold is set to 0.2m). In addition, gate feature A is parallel to the y-axis in the cleaning map, and the angle between gate feature B and the y-axis (or gate feature A) in the cleaning map is less than 10°, which is less than the angle threshold of 15°, that is, the angle between gate feature A and gate feature B is less than the angle threshold. Therefore, based on the fact that the position distance between gate feature A and gate feature B is less than the distance threshold and the angle is less than the angle threshold, the two are determined to be similar gate features.

[0106] When merging, the gate features in the current clean map are preferentially used, and the gate features in the current clean map are processed horizontally or disposed as the gate features in the updated clean map. It is understandable that when the gate feature is close to horizontal, it is processed horizontally; when the gate feature is close to vertical, it is processed vertically. For example, the gate feature A is removed, and the above-mentioned gate feature B is processed vertically and then retained. It is understandable that for the gate that exists twice before and after, the gate feature obtained the most recently is retained first, and horizontal or vertical processing is performed, which is beneficial to the timely accuracy of the gate feature data.

[0107] In this embodiment, similar door features can be accurately determined through position comparison and parallelism comparison, and the door features in the current cleaning map are preferentially used and used as the door features in the updated cleaning map after horizontal or vertical processing, which is beneficial to the timeliness and accuracy of the door feature data.

[0108] In some embodiments, the method S100 further includes:

[0109] S30: In the current cleaning map, for the newly added partition, a gate feature is marked between the newly added partition and other adjacent connected partitions according to the area of ​​the newly added partition and / or the slope of the dividing line.

[0110] The newly added partition may be discovered by the cleaning robot after the closed door is opened, or may be caused by the user segmenting the area on the terminal through an application associated with the cleaning robot. When the added partition is detected, a current cleaning map is generated, which includes the newly added partition.

[0111] According to the area of ​​the newly added partition and / or the slope of the dividing line, a door feature is marked between the newly added partition and other adjacent connected partitions. It can be understood that whether the newly added partition meets the conditions for setting a door is determined based on the area and / or the dividing line. If it meets the conditions, a door feature is marked between the newly added partition and other adjacent connected partitions. Exemplarily, if the area of ​​the newly added partition is too small and does not meet the conditions for being a separate room, the door feature is not marked.

[0112] In this embodiment, the newly added partitions are evaluated for door characteristics by area and / or dividing lines, so that the door characteristic marking is more accurate.

[0113] In some embodiments, the aforementioned step S30 specifically includes: if the area of ​​the newly added partition is greater than or equal to the area threshold, marking a door feature between the newly added partition and other adjacent connected partitions; and / or, if the slope of the dividing line is within a preset slope range, marking a door feature between the newly added partition and other adjacent connected partitions.

[0114] Among them, the area threshold is set by technicians in this field based on actual conditions. For example, in a home scene, the area threshold can be 4 square meters. When the area of ​​the newly added partition is less than the area threshold, it means that the area of ​​the newly added partition is too small to be regarded as a room alone. Therefore, the door feature is not marked between the newly added partition and other adjacent connected partitions. When the area of ​​the newly added partition is greater than or equal to the area threshold, it means that the area of ​​the newly added partition meets the minimum room area condition and can be regarded as a room alone. Therefore, the door feature is marked between the newly added partition and other adjacent connected partitions.

[0115] In some embodiments, it can also be determined whether to mark the door feature based on the dividing line between the newly added partition and other adjacent connected partitions. The dividing line can be recognized by the cleaning robot. For example, in this embodiment, the dividing line is the width of the passage between the newly added partition and other adjacent connected partitions, that is, the opening width of the contour line of the newly added partition. In other embodiments, the dividing line can also be set by the user in the interface displaying the cleaning map.

[0116] Exemplarily, when the slope of the dividing line is within the preset slope range, the door feature is marked between the newly added partition and other adjacent connected partitions. It is understandable that in the grid map, the two end points of a door are usually in the same row or column, and the slope is generally zero or infinite. Thus, the error tolerance can be appropriately set for the error, for example, the preset slope range is set to be included in the ±k1 range, and greater than k2 or less than -k2. Thus, when it is detected that the slope of the dividing line is within the preset slope range, it means that the dividing line is close to horizontal or vertical and meets the door condition (generally horizontal or vertical in the floor plan and meets a certain width), then the door feature is marked between the newly added partition and other adjacent connected partitions. If the slope of the dividing line is detected to be outside the preset slope range, it means that the dividing line is too inclined and does not meet the door condition, then the door feature is not marked.

[0117] In some embodiments, a door feature may also be marked between the newly added partition and other adjacent connected partitions based on the length of the dividing line. For example, if the length of the dividing line is greater than 1 meter and less than 1.5 meters, a door feature is marked between the newly added partition and other adjacent connected partitions. Among them, 1 meter to 1.5 meters is the normal width of a door.

[0118] In this embodiment, the newly added partitions are considered from the perspective of area and the slope of the dividing line, and the gate features are marked only for the newly added partitions that meet the gate conditions, so that the gate features in the updated cleaning map are more accurate.

[0119] In summary, the method for updating the cleaning map provided by the embodiment of the present application, after obtaining the current cleaning map, merges the current cleaning map and the historical cleaning map into partitions and merges the door features to obtain an updated cleaning map. It is understandable that the current cleaning map can be a map scanned after the cleaning is completed or a map obtained after manually setting the partitions. In the case where the current cleaning map changes relative to the historical cleaning map, the current cleaning map and the historical cleaning map are comprehensively considered, and the partitions are merged and the door features are merged to obtain an updated cleaning map. Compared with directly using the current cleaning map as the updated cleaning map, taking the union of the partitions in the historical cleaning map and the current cleaning map and the union of the door features can effectively reduce the omission of partitions and the omission of door features, so that the partitions in the updated cleaning map are accurate and the door features are accurate, which is conducive to the rationality of subsequent path planning. In addition, through the above method, the changes in the state of the partitions and the changes in the state of the door switches can be monitored in real time, so that the cleaning map can be updated in real time, reducing manual intervention, being more intelligent and accurate, and being conducive to the rationality of subsequent path planning and the efficiency of navigation.

[0120] Some embodiments of the present application provide a cleaning robot. Figure 6 The cleaning robot 100 includes at least one processor 102 and a memory 103 ( Figure 6 (a bus connection and a processor are used as an example).

[0121] It can be understood that the processor 102 is used to provide computing and control capabilities to control the cleaning robot to execute any one of the methods for updating the cleaning map provided in the above embodiments.

[0122] It is understandable that the processor 102 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0123] The memory 103, as a non-transient computer-readable storage medium, can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules corresponding to the method for updating the cleaning map in the embodiment of the present invention. The processor 102 can implement any method for updating the cleaning map provided in the above embodiments by running the non-transient software programs, instructions and modules stored in the memory 103. Specifically, the memory 103 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 103 may also include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0124] In some embodiments, the cleaning robot 100 may also include other sensors such as a gyroscope, an odometer, a magnetic field meter, an accelerometer or a speedometer. It is understood that the structure of the present embodiment example does not constitute a limitation to the cleaning robot 100. In some implementations, the cleaning robot 100 may include more or less components than shown in the figure, or combine some components, or split some components, or different component arrangements. The illustrated components can be implemented in hardware, software, or a combination of software and hardware.

[0125] The present application also provides a computer-readable storage medium, such as a memory including a program code, which can be executed by a processor to complete the method of updating the cleaning map in the above embodiment. For example, the computer-readable storage medium can be a read-only memory (ROM), a random access memory (RAM), a compact disc read-only memory (CDROM), a magnetic tape, a floppy disk, and an optical data storage device.

[0126] The present application also provides a computer program product, which includes one or more program codes stored in a computer-readable storage medium. A processor of an electronic device reads the program code from the computer-readable storage medium, and the processor executes the program code to complete the steps of the method for updating a cleaning map provided in the above embodiment.

[0127] It should be noted that the device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0128] Through the description of the above implementation methods, ordinary technicians in this field can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware. Ordinary technicians in this field can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0129] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Under the concept of the present application, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes in different aspects of the present application as described above, which are not provided in detail for the sake of simplicity. Although the present application has been described in detail with reference to the aforementioned embodiments, a person of ordinary skill in the art should understand that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features can be replaced by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for updating a cleaning map, characterized in that: include: Get the current cleaning map; The current cleaning map and the historical cleaning map are partitioned and gated to obtain an updated cleaning map.

2. The method according to claim 1, characterized in that Partitioning and merging the current cleaning map and the historical cleaning map includes: Retaining and marking the partition added to the current cleaning map relative to the historical cleaning map as a reachable area; The reduced area of ​​the current cleaning map relative to the historical cleaning map is added to the current cleaning map and marked as an unreachable area.

3. The method according to claim 1, characterized in that Merging the current cleaning map and the historical cleaning map with gate features, including: After deduplication processing is performed on the gate feature set, the gate feature set is used as the gate feature in the updated cleaning map, wherein the gate feature set includes the gate features in the current cleaning map and the gate features in the historical cleaning map.

4. The method according to claim 3, characterized in that The deduplication processing of the door feature set includes: A cluster analysis is performed on the gate feature set, and similar gate features are merged into one gate feature.

5. The method according to claim 4, characterized in that The clustering analysis is performed on the gate feature set to merge similar gate features into one gate feature, including: If the position distance between any two door features in the door feature set is less than or equal to the distance threshold, then determining the two door features as the similar door features; The gate features belonging to the current cleaning map among the similar gate features are used as the merged gate features.

6. The method according to claim 4, characterized in that The clustering analysis is performed on the gate feature set to merge similar gate features into one gate feature, including: If the position distance between any two door features in the door feature set is less than or equal to the distance threshold and the parallelism difference is less than or equal to the angle threshold, then the two door features are determined to be the similar door features; The door features belonging to the current cleaning map among the similar door features are processed horizontally or vertically to serve as the updated door features.

7. The method according to claim 1, characterized in that The method further comprises: In the current cleaning map, for a newly added partition, a gate feature is marked between the newly added partition and other adjacent connected partitions according to the area of ​​the newly added partition and / or the slope of the dividing line.

8. The method according to claim 7, characterized in that The step of marking a gate feature between the newly added partition and other adjacent connected partitions according to the area of ​​the newly added partition and / or the slope of the dividing line comprises: If the area of ​​the newly added partition is greater than or equal to the area threshold, marking a gate feature between the newly added partition and other adjacent connected partitions; and / or, If the slope of the dividing line is within a preset slope range, a gate feature is marked between the newly added partition and other adjacent connected partitions.

9. A cleaning robot, characterized in that: include: at least one processor; A memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor so that the at least one processor can execute the method for updating a cleaning map as described in any one of claims 1-8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer device to execute the method for updating a cleaning map according to any one of claims 1 to 8.

Images