Base station identification method and cleaning robot

Abstract

The embodiment of the invention relates to the technical field of robots, and discloses a base station identification method and a cleaning robot, firstly, arc point clouds in laser point cloud data are identified in a fitting manner, point clouds in other shapes are filtered out, then, secondary screening is carried out by adopting an arc opening orientation, and the point clouds in other shapes are filtered out; and most point clouds corresponding to obstacles with arc openings back to the cleaning robot are filtered out, so that the potential point cloud set has a smaller range, and the point clouds corresponding to the base station are more easily and accurately found. Based on the morphological characteristics of each point cloud in the potential point cloud set, the target point cloud corresponding to the base station can be accurately identified, and the base station is identified. Namely, secondary filtering is performed on the laser point cloud data through arc fitting and arc opening orientation, interference of obstacle point clouds can be reduced, accurate identification of the point clouds corresponding to the base station is facilitated, the base station can be accurately identified and positioned from a potential point cloud set after multiple times of filtering and limiting based on morphological characteristics of the point clouds, and the positioning accuracy of the base station is improved. And the subsequent cleaning robot can return to the base station.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of robotics technology, and in particular to a method for identifying a base station and a cleaning robot. Background Art

[0002] The cleaning robot can automatically complete the work in conjunction with the base station. Here, the base station is an electronic device that automatically completes the work in conjunction with the cleaning robot. For example, the base station can provide docking and charging services for the cleaning robot. The cleaning robot autonomously docks at the base station and connects to the charging port on the base station for charging. In addition, in addition to providing charging services, the cleaning robot can also return to the base station for water replenishment, sewage discharge, detergent replenishment, and self-cleaning, and dock at the base station when not working.

[0003] Cleaning robots are generally equipped with laser radar and other equipment to scan the environment where the cleaning robot is located and build a map based on the laser scanning results. The cleaning robot moves according to the established map and completes the corresponding cleaning tasks. When the cleaning robot is recharging, it needs to identify and locate the location of the base station and move in the direction of the base station to achieve recharging.

[0004] In some solutions known to the inventor of the present application, the cleaning robot identifies the base station based on the laser point cloud obtained by scanning. However, it is easily affected by other obstacles in the environment, which interfere with the point cloud corresponding to the base station, thereby making it difficult to identify and locate the base station. Summary of the invention

[0005] In view of this, some embodiments of the present application provide a method for identifying a base station and a cleaning robot, which can accurately identify and locate the base station, thereby facilitating the subsequent return of the cleaning robot to the base station.

[0006] In a first aspect, some embodiments of the present application provide a method for identifying a base station, which is applied to a cleaning robot including a laser radar, wherein a docking cavity in the base station for accommodating the cleaning robot has an arc surface, and the method comprises:

[0007] Acquire laser point cloud data obtained by scanning the current environment of the cleaning robot by laser radar;

[0008] The point cloud in the shape of an arc is fitted and identified from the laser point cloud data to obtain an arc point cloud set;

[0009] Filter out the point cloud of the arc opening facing the cleaning robot from the arc point cloud set to obtain a potential point cloud set;

[0010] According to the morphological features of each point cloud in the potential point cloud set, the target point cloud corresponding to the base station is determined to identify the base station.

[0011] In some embodiments, the aforementioned step of fitting and identifying arc point clouds from laser point cloud data to obtain an arc point cloud set includes:

[0012] Clustering and grouping the laser point cloud data to obtain a first point cloud set, performing straight line fitting on each point cloud in the first point cloud set, segmenting and filtering out straight line point clouds in the first point cloud set, and obtaining a second point cloud set;

[0013] Arc fitting is performed on each point cloud in the second point cloud set, and point clouds that are arcs and have a radius within a preset range are screened out to form an arc point cloud set.

[0014] In some embodiments, the arc fitting is performed on any point cloud in the second point cloud set in the following manner to screen out point clouds that are arcs and have a radius within a preset range:

[0015] Use distance threshold to split the point cloud into multiple arc segments;

[0016] Eliminate an arc segment located in the part of the point cloud and perform arc fitting. If the absolute value of the difference between the fitting radius and the preset radius is greater than the preset threshold, continue to eliminate an arc segment located in the part of the point cloud until the absolute value of the difference between the fitting radius and the preset radius is less than or equal to the preset threshold, and obtain an updated point cloud. The updated point cloud is used as a point cloud in the form of an arc with a radius within a preset range.

[0017] In some embodiments, the above-mentioned removing an arc segment located in the middle of the point cloud includes:

[0018] Obtain a first arc segment and a second arc segment located at two ends of the point cloud respectively, obtain a first radius by fitting the points in the point cloud except the first arc segment, and obtain a second radius by fitting the points in the point cloud except the second arc segment;

[0019] One of the first arc segment and the second arc segment is eliminated according to the first radius and the second radius.

[0020] In some embodiments, the above-mentioned removing one of the first arc segment and the second arc segment according to the first arc radius and the second arc radius includes:

[0021] Determine a first radius proximity between the first radius and the preset radius, and a second radius proximity between the second radius and the preset radius;

[0022] If the first radius proximity is greater than or equal to the second radius proximity, the first arc segment is removed, otherwise the second arc segment is removed.

[0023] In some embodiments, the aforementioned method of filtering out the point cloud of the arc opening facing the cleaning robot from the arc point cloud set to obtain the potential point cloud set includes:

[0024] For any point cloud in the arc point cloud set, take any laser point of the point cloud, obtain a first vector pointing from the laser point to the center of the point cloud, and obtain a second vector pointing from the laser point to the cleaning robot;

[0025] If the angle between the first vector and the second vector is an acute angle, the point cloud is determined to be a point cloud with an arc opening facing the cleaning robot, and is added to the potential point cloud set.

[0026] In some embodiments, the above-mentioned determining the target point cloud corresponding to the base station according to the morphological features of each point cloud in the potential point cloud set includes:

[0027] Determine the proximity of each point cloud in the potential point cloud set to a preset arc;

[0028] The point cloud with the greatest degree of proximity is determined as the target point cloud corresponding to the base station.

[0029] In some embodiments, the aforementioned determining the proximity of each point cloud in the potential point cloud set to a preset arc includes:

[0030] For any point cloud in the potential point cloud set, determine the radius closeness between its radius and the radius of the preset arc, and the fit of the point cloud relative to its fitted arc;

[0031] The proximity of the point cloud to the preset arc is determined based on the radius proximity and fit.

[0032] In a second aspect, some embodiments of the present application provide a cleaning robot, comprising:

[0033] LiDAR,

[0034] At least one processor, wherein the at least one processor is communicatively connected to the laser radar;

[0035] 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 identifying a base station as in the first aspect.

[0036] In a third aspect, some embodiments of the present application provide a computer-readable storage medium, the computer-readable storage medium storing computer-executable instructions, and the computer-executable instructions are used to enable a computer device to execute the method for identifying a base station in the first aspect.

[0037] Beneficial effects of the embodiments of the present application: Different from the prior art, the method for identifying a base station provided in the embodiments of the present application is applied to a cleaning robot including a laser radar, and the surface of the base station for accommodating the cleaning robot is an arc surface. The method obtains laser point cloud data obtained by scanning the current environment of the cleaning robot by a laser radar, fits and identifies arc point clouds from the laser point cloud data, and obtains an arc point cloud set. From the arc point cloud set, the point cloud with the arc pointing to the cleaning robot is screened out to obtain a potential point cloud set. According to the morphological characteristics of each point cloud in the potential point cloud set, the target point cloud corresponding to the base station is determined to identify the base station.

[0038] In this embodiment, the point clouds in the shape of arcs in the laser point cloud data are first fitted and identified, and the point clouds in other shapes are filtered out. The obtained arc point cloud set includes the point clouds corresponding to the base station, and may also include the point clouds corresponding to obstacles such as cylinders or spheres. Therefore, the arc opening direction is used for secondary screening to filter out the point clouds corresponding to obstacles with most of the arc openings facing away from the cleaning robot, so that the obtained potential point cloud set has a smaller range, and it is easier to accurately find the point clouds corresponding to the base station. Therefore, based on the morphological features of each point cloud in the potential point cloud set (such as radius or smoothness, etc.), the target point cloud corresponding to the base station can be accurately identified, thereby identifying the base station. That is, by performing secondary filtering on the laser point cloud data through arc fitting and arc opening direction, the interference of most obstacle point clouds can be reduced, which is conducive to accurately identifying the point cloud corresponding to the base station. Based on the morphological features of the point cloud from the potential point cloud set after multiple filtering and narrowing, the base station can be accurately identified and located, which is conducive to the subsequent cleaning robot returning to the base station. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] 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.

[0040] Figure 1 A schematic diagram of an application environment of a method for identifying a base station in some embodiments of the present application;

[0041] Figure 2 This is a schematic diagram of the structure of the cleaning robot in some embodiments of the present application;

[0042] Figure 3 A schematic diagram of a flow chart of a method for identifying a base station in some embodiments of the present application;

[0043] Figure 4 This is a schematic diagram of laser point cloud data in some embodiments of the present application;

[0044] Figure 5A schematic diagram of filtering point clouds corresponding to long-side obstacles in some embodiments of the present application;

[0045] Figure 6 This is a schematic diagram of a point cloud of obstacles near a base station in some embodiments of the present application;

[0046] Figure 7 A schematic diagram of the arc fitting process in some embodiments of the present application;

[0047] Figure 8 This is a schematic diagram of arc fitting in some embodiments of the present application;

[0048] Fig. 9 Schematic diagrams of some arc point clouds in some embodiments of the present application;

[0049] Fig.10 This is a schematic diagram of the first vector and the second vector in some embodiments of the present application. DETAILED DESCRIPTION

[0050] 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.

[0051] 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.

[0052] 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.

[0053] 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.

[0054] 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.

[0055] See also Figure 1 , Figure 1 Schematic diagram of an application environment of a method for identifying a base station provided in 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 or an office, etc. The place where the cleaning robot 100 is located includes objects such as a base station 200, a desk, a flower pot, and a sofa.

[0056] The cleaning robot 100 is equipped with a laser radar (not shown), wherein the laser radar scans the surrounding environment of the cleaning robot 100 to obtain laser point cloud data. The laser radar is connected to the control chip for communication, and the laser radar sends the laser point cloud data to the control chip. When the cleaning robot needs to return to the base station, the control chip calls the program of the method of identifying the base station pre-set in the memory of the cleaning robot, identifies and locates the base station based on the laser point cloud data, and controls the robot to move in the direction of the base station.

[0057] 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. In some embodiments, the cleaning robot 100 can include a robot body, a laser radar, a control chip, a walking mechanism, and a docking device (not shown).

[0058] The robot body is the main structure of the cleaning robot 100. The corresponding shape structure and manufacturing material (such as hard plastic or metals such as aluminum and iron) can be selected according to the actual needs of the cleaning robot 100. For example, it can be set to a relatively flat cylindrical shape that is common in the cleaning robot 100.

[0059] 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.

[0060] The laser radar is arranged on the body of the cleaning robot 100 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 control chip so that the control chip can control the robot to walk based on the distance of surrounding objects. In some embodiments, the laser radar includes pulse laser radar, continuous wave laser radar and other radars.

[0061] The control chip is an electronic computing core built into the robot body, which is used to execute logical operation steps to realize intelligent control of the robot. In this embodiment, the control chip is connected to the laser radar for identifying and locating the base station according to the laser point cloud data, so as to control the cleaning robot 100 to move in the direction of the base station, so that the cleaning robot 100 returns to the base station 200.

[0062] It is understandable that in some embodiments, the robot body may further include a clean water tank, a sewage tank, a detergent box, a dust box, etc. The robot docking device may include an interface for a clean water tank, an interface for a sewage tank, an interface for a detergent box, an interface for a dust box, or a charging electrode, etc.

[0063] 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 receiving 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 receiving 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 box of the cleaning robot. The power supply device is used to charge the cleaning robot. The sewage receiving device is used to collect sewage in the sewage tank of the cleaning robot.

[0064] It can be understood that the base 200 is provided with a docking device for docking the above-mentioned devices with the cleaning robot 100. The docking device of the base station may include an interface for a cleaning device, an interface for a water supply device, an interface for a dust collection device, an interface for a power supply device, an interface for a detergent replenishing device, or a charging electrode, etc.

[0065] In this embodiment, when the docking device of the cleaning robot 100 completes docking with the docking device of the base station 200, the interface of the clean water tank on the cleaning robot 100 is docked and connected with the interface of the water supply device on the base station 200, so that the water supply device can supply water to the clean water tank; the interface of the sewage tank on the cleaning robot 100 is docked and connected with the interface of the sewage receiving device on the base station 200, so that the sewage receiving device can collect the sewage in the sewage tank; the interface of the detergent box on the cleaning robot 100 is docked and connected with the interface of the detergent replenishing device on the base station 200, so that the detergent replenishing device can replenish the detergent box with detergent; the interface of the dust box on the cleaning robot 100 is docked and connected with the interface of the dust collecting device, so that the dust collecting device can collect dust in the dust box; the charging electrode on the cleaning robot 100 is docked and electrically connected with the charging electrode on the base station 200, so that the power supply device on the base station 200 can charge the cleaning robot.

[0066] It is understandable that, in order to facilitate the above-mentioned docking, the surface of the base station 200 used to approach the cleaning robot 100 matches the appearance 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.

[0067] When the laser radar on the cleaning robot 100 scans, the laser scans the surface of the docking cavity to form an arc-shaped point cloud with a certain radius. It can be understood that based on the presence of other obstacles around the base station, such as walls, shoes, stools, table corners or basins, the laser point cloud data also includes the point clouds corresponding to these obstacles. When the cleaning robot 100 needs to return to the base station 200, the control chip identifies the arc-shaped point cloud corresponding to the base station from the laser point cloud data, thereby locating the base station.

[0068] It should be noted that, depending on the tasks to be completed, in addition to the above functional modules, the main body of the robot can also be equipped with one or more other different functional modules, and the base station can also be equipped with one or more functional modules for cooperation to perform corresponding tasks.

[0069] In some related schemes known to the inventors of the present application, multiple groups are obtained by clustering the laser point cloud data, and the point cloud corresponding to the base station is identified according to the characteristic attributes of each group. However, when there are other obstacles in the vicinity of the base station, such as walls, shoes, stools, table corners, etc., the point clouds corresponding to these obstacles are closely connected to the point clouds corresponding to the base station and are divided into one group, thereby affecting the identification of the base station point cloud. In addition, when there are other spherical or cylindrical obstacles that form arcs in the environment where the cleaning robot is located, the point clouds corresponding to these obstacles are also arc-shaped, which will interfere with the arc-shaped point clouds corresponding to the base station, and it is easy to mistakenly identify other spherical or cylindrical obstacles as base stations.

[0070] In response to the above problems, some embodiments of the present application provide a method for identifying a base station and a cleaning robot, wherein the method for identifying a base station is applied to a cleaning robot including a laser radar, and the surface of the base station for accommodating the cleaning robot is an arc surface. The method obtains laser point cloud data obtained by scanning the current environment of the cleaning robot by a laser radar, fits and identifies arc point clouds from the laser point cloud data, and obtains an arc point cloud set. From the arc point cloud set, the point cloud with the arc pointing to the cleaning robot is filtered out to obtain a potential point cloud set. According to the morphological characteristics of each point cloud in the potential point cloud set, the target point cloud corresponding to the base station is determined to identify the base station.

[0071] In this embodiment, the point clouds in the shape of arcs in the laser point cloud data are first fitted and identified, and the point clouds in other shapes are filtered out. The obtained arc point cloud set includes the point clouds corresponding to the base station, and may also include the point clouds corresponding to obstacles such as cylinders or spheres. Therefore, the arc opening direction is used for secondary screening to filter out the point clouds corresponding to obstacles with most of the arc openings facing away from the cleaning robot, so that the obtained potential point cloud set has a smaller range, and it is easier to accurately find the point clouds corresponding to the base station. Therefore, based on the morphological features of each point cloud in the potential point cloud set (such as radius or smoothness, etc.), the target point cloud corresponding to the base station can be accurately identified, thereby identifying the base station. That is, by performing secondary filtering on the laser point cloud data through arc fitting and arc opening direction, the interference of most obstacle point clouds can be reduced, which is conducive to accurately identifying the point cloud corresponding to the base station. Based on the morphological features of the point cloud from the potential point cloud set after multiple filtering and narrowing, the base station can be accurately identified and located, which is conducive to the subsequent cleaning robot returning to the base station.

[0072] Some embodiments of the present application provide a cleaning robot. Figure 2 The cleaning robot 100 includes a laser radar 101, at least one processor 102 and a memory 103 ( Figure 2 (a bus connection and a processor are used as an example).

[0073] The laser radar 101 obtains laser point cloud data by scanning and senses obstacles in the surrounding environment of the cleaning robot 100. In some embodiments, the laser radar includes pulse laser radar, continuous wave laser radar and other radars.

[0074] The laser radar 101 is communicatively connected to the processor 102 and can send laser point cloud data to the processor 102. The processor 102 calls the program corresponding to the method for identifying the base station in any of the following embodiments stored in the memory 103, and identifies the point cloud corresponding to the base station based on the laser point cloud data, that is, identifies the location of the base station, and controls the cleaning robot to walk in the direction of the base station to return to the base station.

[0075] 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 identifying base stations provided in the following embodiments.

[0076] 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.

[0077] 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 identifying a base station in an embodiment of the present invention. The processor 102 can implement any of the methods for identifying a base station provided in the following 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.

[0078] 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.

[0079] It can be understood from the above that the method for identifying a base station provided in the embodiment of the present application can be implemented by a cleaning robot, for example, by one or more processors of the cleaning robot. In some embodiments, the method for identifying a base station 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.

[0080] The following describes the method for identifying a base station provided in the embodiment of the present application in conjunction with the exemplary application and implementation of the cleaning robot provided in the embodiment of the present application. Figure 3 , Figure 3 It is a flow chart of the method for identifying a base station provided in an embodiment of the present application. It can be understood that the execution subject of the method for identifying a base station can be one or more controllers of the cleaning robot.

[0081] like Figure 3 As shown, the method S100 may specifically include the following steps:

[0082] S10: Acquire laser point cloud data obtained by scanning the current environment of the cleaning robot by a laser radar.

[0083] The laser radar performs a 360° scan of the environment where the cleaning robot is located to generate laser point cloud data. The laser radar sends the generated laser point cloud data to the processor, so that the processor can obtain the laser point cloud data.

[0084] It is understandable that the laser radar generally rotates one circle starting from 0° of the radar polar coordinate system to generate a frame of 360° laser point cloud data. The angular resolution of the laser point cloud data can be 0.5°. There are base stations and other obstacles (such as walls, shoes, stools, table corners or sofas, cabinets, etc.) in the environment where the robot is located. Based on the working principle of the laser radar, it can be known that the laser radar performs laser scanning and ranging on the surrounding objects. Its own chip calculates the distance and angle of each light spot (the light spot formed by the laser hitting the object) based on the emitted laser information and the echo laser information. Among them, the calculation of the distance and angle of the light spot is an existing calculation method of the laser radar and is not described in detail here. It is understandable that based on the continuity of the scan, the distance and angle of each light spot constitute the laser point cloud data. Thus, after the scan is completed, the laser point cloud data is generated. The laser points in the laser point cloud data are arranged in order of angular resolution intervals.

[0085] In the laser point cloud data, the distance and angle of each laser point can be obtained. The distance is the distance from the spot formed by the laser hitting the object to the laser radar, and the angle is the angle of the spot formed by the laser hitting the object in the radar polar coordinate system.

[0086] From the above work on LiDAR, we can see that Figure 4 As shown, the laser point cloud data can reflect the scanning contours of objects that intersect with the scanning surface of the laser radar in the environment where the cleaning robot is located. For example, the scanning contours of long-side obstacles such as walls or square cabinets are straight lines, the scanning contours of spherical or cylindrical objects are arcs, and the scanning contours of irregular objects are irregular shapes.

[0087] In some embodiments, the cleaning robot is a flat cylindrical sweeping robot, and the base station is provided with a docking cavity, the shape of which matches the flat cylindrical sweeping robot, and has a concave semi-cylinder, and its surface is an arc surface. Therefore, the docking cavity intersects with the scanning surface of the laser radar, and therefore, the base station is reflected as an arc-shaped point cloud in the laser point cloud data.

[0088] S20: fitting and identifying arc point clouds from the laser point cloud data to obtain an arc point cloud set.

[0089] It is understandable that the base station is reflected as an arc point cloud in the laser point cloud data. Therefore, the point cloud in the shape of an arc may be the point cloud corresponding to the base station. However, the point cloud in the shape of an arc may also be the point cloud corresponding to a spherical or cylindrical object. Here, in order to filter out the point cloud in the shape of an arc, the laser point cloud data is fitted, and the point cloud with the fitting line in the shape of an arc is formed into an arc point cloud set.

[0090] In some embodiments, the laser point cloud data can be converted from the radar polar coordinate system to the rectangular coordinate system, so that the laser points are distributed in the rectangular coordinate plane. It can be understood that the laser points are distributed in clusters in the rectangular coordinate plane, and a circular fitting can be performed on each cluster of laser point clouds to identify the point clouds in the form of circular arcs, and the point clouds in the form of circular arcs constitute a circular arc point cloud set.

[0091] In some embodiments, the aforementioned step S20 specifically includes:

[0092] S21: clustering and grouping the laser point cloud data to obtain a first point cloud set, performing straight line fitting on each point cloud in the first point cloud set, segmenting and filtering out straight line point clouds in the first point cloud set, and obtaining a second point cloud set.

[0093] Clustering refers to dividing the laser point cloud data into different classes or clusters according to distance, so that the similarity of elements within a class is as large as possible, and the similarity of elements between classes is as small as possible, so as to cluster similar data and achieve the effect of clustering. For example, the laser point cloud data is classified according to the Euclidean distance. Two laser points with a Euclidean distance less than a preset distance threshold belong to one class, that is, the point cloud of one object, and two laser points with a Euclidean distance greater than or equal to a certain distance threshold belong to different classes, that is, the point clouds of different objects.

[0094] It is understandable that after clustering the laser point cloud data, multiple point clouds (point cloud clusters) are obtained, and these multiple point clouds constitute the first point cloud set. Then, straight line fitting is performed on each point cloud in the first point cloud set. Among them, straight line fitting refers to using a straight line to perform linear regression on the point cloud, that is, finding a straight line so that most of the points of the point cloud fall on this straight line. In some embodiments, the least squares method can be used for straight line fitting.

[0095] Some point clouds are fitted into straight lines, while some point clouds cannot be fitted into straight lines. It is understandable that the point clouds that are in straight lines cannot belong to the point clouds corresponding to the base station. Therefore, the point clouds that are in straight lines belong to interference point clouds, which are easy to affect the identification of the point clouds corresponding to the base station. For example, Figure 5 As shown in (a) in the figure, when the base station is placed close to a long-side obstacle such as a wall or a corner, the point cloud A corresponding to the base station is closely connected to the point cloud B corresponding to the wall. After the processor clusters and groups the laser point cloud data, it is easy for the processor to classify point cloud A and point cloud B into one category, which interferes with the recognition of point cloud A corresponding to the base station, that is, interferes with the recognition of the base station, resulting in the cleaning robot being unable to accurately find the base station when recharging.

[0096] In this embodiment, the straight line point clouds in the first point cloud set are segmented and filtered out from the laser point cloud data, so that the obtained second point cloud set is free of interference from the straight line point clouds, which is conducive to improving the subsequent recognition accuracy. Figure 5 As shown in (b) in FIG. 5 , after removing the straight line point cloud, there is no straight line point cloud in the second point cloud set obtained. The point clouds have clear boundaries and do not interfere with each other, which is conducive to the subsequent identification of the point cloud corresponding to the base station based on the morphological features of the base station to locate the base station.

[0097] S22: performing arc fitting on each point cloud in the second point cloud set, screening out point clouds that are arcs and have a radius within a preset range, and forming an arc point cloud set.

[0098] The arc fitting refers to performing linear regression on the point cloud using an arc, that is, finding an arc so that most of the points of the point cloud fall on the arc. In some embodiments, the arc fitting can be performed using the least square method.

[0099] It can be understood that the point cloud corresponding to the base station is in the shape of an arc, and the point clouds corresponding to some spherical or cylindrical obstacles in the environment where the cleaning robot is located are also in the shape of an arc, and the point clouds corresponding to some other obstacles may be irregular shapes, etc. In order to identify the base station, in this embodiment, the point clouds in the shape of an arc in the second point cloud set are identified by arc fitting, and other non-arc point clouds are filtered out to screen out the point clouds in the shape of an arc. On this basis, the radius is further used for screening to screen out the point clouds with a radius within a preset range to form an arc point cloud set. Among them, the preset range can be set by technicians in this field according to the radius of the base station docking cavity. Through radius screening, point clouds that are obviously not base stations, such as those with larger or smaller radii, are excluded, so that the range of the arc point cloud set is more accurate, which is conducive to the subsequent identification of the point cloud corresponding to the base station based on the morphological characteristics of the base station to locate the base station.

[0100] In this embodiment, straight line fitting is used to filter out straight line point clouds in the laser point cloud data, and long side obstacles are eliminated, so that the boundaries between the remaining point clouds are clear and do not interfere with each other; then, arc fitting and radius filtering are performed to filter out arc point cloud sets that may be base stations, so that the arc point cloud set can accurately cover the point cloud corresponding to the base station and have a smaller range, which is conducive to accurately finding the point cloud corresponding to the base station in the subsequent process.

[0101] There may be other irregular obstacles near the base station, such as shoes, stools, or table legs. The point clouds corresponding to these obstacles are connected or close to the point clouds corresponding to the base station. When clustering, they may be divided into one group, that is, these obstacles are misjudged as part of the base station. Therefore, when fitting the arc, the point clouds of these obstacles will interfere with the fitting results of the point clouds corresponding to the base station, causing the fitting results to deviate from the arc of the actual base station, generally making the fitting radius larger and causing the base station position to deviate. In this case, although the cleaning robot can walk towards the base station, it is difficult to accurately find and dock with the base station during docking, and it is easy to mistake the obstacles next to it as the base station.

[0102] In order to make the arc fitting result more accurate, in some embodiments, arc fitting is performed on any point cloud in the second point cloud set in the following manner to screen out point clouds that are arcs and have a radius within a preset range:

[0103] (1) Use distance threshold to segment the point cloud into multiple arc segments.

[0104] (2) Eliminate an arc segment located in the part of the point cloud and perform arc fitting. If the absolute value of the difference between the fitting radius and the preset radius is greater than the preset threshold, continue to eliminate the arc segment located in the part of the point cloud until the absolute value of the difference between the fitting radius and the preset radius is less than or equal to the preset threshold, and obtain an updated point cloud. The updated point cloud is regarded as a point cloud in the form of an arc with a radius within a preset range.

[0105] like Figure 6 As shown, the point cloud includes the point cloud corresponding to the obstacle and the point cloud corresponding to the base station, wherein some point clouds corresponding to the obstacles are close to the point cloud corresponding to the base station, and some point clouds corresponding to the obstacles are far away from the point cloud corresponding to the base station. For continuous surfaces, the laser points generated by scanning are arranged in order of angular resolution intervals, the distance changes little, and the laser points are smooth and continuous; for discontinuous surfaces, the laser points are broken due to sudden changes in distance. It is understandable that when there are other obstacles near the base station, the point clouds corresponding to the base station and the obstacles may be divided into a group of point clouds after cluster analysis. Since they are different objects, this group of point clouds still has slight differences in distance.

[0106] Based on the above subtle differences, a distance threshold is used to divide the point cloud into multiple arc segments. Specifically, if the distance between two laser points is less than the distance threshold, it is classified as an arc segment. If the distance between two laser points is greater than or equal to the distance threshold, it does not belong to an arc segment. It can be understood that the distance threshold used to divide the point cloud in the second point cloud set into arc segments is less than the aforementioned distance threshold used to cluster the laser point cloud data. Here, it is equivalent to using a smaller distance threshold to cluster each point cloud in the second point cloud set separately, and divide each point cloud into multiple arc segments. Among them, the distance threshold is an empirical value set by those skilled in the art. In some embodiments, two grids in a grid map established based on laser point cloud data can be used as the distance threshold.

[0107] In some embodiments, see Figure 7 In (a), after removing an arc segment 1# at the left end, arc fitting is performed to obtain the fitting radius R1. Then, the absolute value of the difference between the fitting radius R1 and the preset radius R is calculated. Among them, the preset radius R is the actual radius of the base station docking cavity. It can be understood that the preset radius R is set in advance in the memory for the processor to call. Since the absolute value of the difference between the fitting radius R1 and the preset radius R is greater than the preset threshold, it means that the fitting radius R1 is far from the preset radius R, and arc segment 1# is the point cloud corresponding to the obstacles around the base station. Among them, the preset threshold is a threshold used to judge the difference between the fitting radius and the preset radius, which can be set by those skilled in the art according to actual conditions.

[0108] In the case where the absolute value of the difference between the fitting radius R1 and the preset radius R is greater than the preset threshold, refer to Figure 7In (b), after removing the arc segment 2# at the right end, arc fitting is performed to obtain the fitting radius R2. The absolute value of the difference between the fitting radius R2 and the preset radius R is greater than the preset threshold, indicating that the fitting radius R2 is far from the preset radius R. Arc segment 2# is the point cloud corresponding to the obstacles around the base station. Figure 7 From (a) and (b), it can be seen that R2 is smaller than R1, and compared with R1, R2 is closer to the preset radius R.

[0109] See also Figure 7 In (c), after removing arc segment 3# at the left end, arc fitting is performed to obtain the fitting radius R3. The absolute value of the difference between the fitting radius R3 and the preset radius R is less than or equal to the preset threshold, indicating that the fitting radius R3 is close to the preset radius R. Arc segment 3# is the point cloud corresponding to the obstacles around the base station. The point cloud after removing arc segments 1#, 2# and 3# basically belongs to the base station. At this time, stop removing, obtain the updated point cloud, and use the updated point cloud as a point cloud with an arc shape and a radius within the preset range to add to the arc point cloud set.

[0110] It can be understood that in some embodiments, the arc segments at the ends can be alternately eliminated from the two ends to the middle of the point cloud until the absolute value of the difference between the fitting radius and the preset radius is less than or equal to the preset threshold, indicating that the fitting radius is close to the preset radius, making the arc fitting result more accurate, and the corresponding updated point cloud is closer to the point cloud corresponding to the base station, so that the updated point cloud is added to the arc point cloud set.

[0111] It can be understood that if the fitting radius after removing a certain arc segment is closer to the preset radius than the fitting radius before removing the arc segment, it means that the arc segment is a deviation introduced by an obstacle and needs to be removed. If the fitting radius before removing a certain arc segment is closer to the preset radius than the fitting radius after removing the arc segment, it means that the arc segment is part of the base station and needs to be retained.

[0112] In some embodiments, the above-mentioned removing an arc segment located in the middle of the point cloud includes:

[0113] S201: Obtain a first arc segment and a second arc segment located at two ends of the point cloud, respectively, and obtain a first radius by fitting the points in the point cloud except the first arc segment, and obtain a second radius by fitting the points in the point cloud except the second arc segment.

[0114] S202: Eliminate one of the first arc segment and the second arc segment according to the first radius and the second radius.

[0115] The first arc segment and the second arc segment are arc segments located at the two ends of the point cloud in the second point cloud set. Figure 8, arc fitting is performed using the points in the point cloud except the first arc segment, and the radius of the arc obtained by fitting is the first radius; arc fitting is performed using the points in the point cloud except the second arc segment, and the radius of the arc obtained by fitting is the second radius.

[0116] It can be understood that if the radius of the fitted arc is closer to the preset radius (radius of the base station docking cavity), it means that the fitted arc is closer to the actual scanning shape of the docking cavity, and accordingly, the eliminated arc segment is more likely to be the interference point cloud corresponding to the obstacle. Based on this, according to the first radius and the second radius, one of the first arc segment and the second arc segment is selectively eliminated each time, and the point cloud is updated once.

[0117] That is, each time the interference point cloud corresponding to the obstacle is filtered, the arc segments with large radius deviations are filtered out according to the fitting conditions of the arc segments at both ends. During the next filtering, the first arc segment and the second arc segment at both ends of the updated point cloud are obtained again, and fitting is performed in the manner of steps S201 and S202. Based on the fitted radius, the arc segments with large deviations are filtered out, and so on, until the absolute value of the difference between the fitted radius of the updated point cloud and the preset radius is less than or equal to the preset threshold value, the updated point cloud is taken as a point cloud in the form of an arc with a radius within a preset range, and is added to the arc point cloud set.

[0118] In some embodiments, the aforementioned step S202 specifically includes:

[0119] (1) Determine a first radius proximity between the first radius and a preset radius, and a second radius proximity between the second radius and the preset radius.

[0120] (2) If the first radius proximity is greater than or equal to the second radius proximity, the first arc segment is eliminated; otherwise, the second arc segment is eliminated.

[0121] In some embodiments, the first radius proximity is the absolute value between the first radius and the preset radius divided by the preset radius, and the second radius proximity is the absolute value between the second radius and the preset radius divided by the preset radius.

[0122] It can be understood that if the first radius proximity is greater than or equal to the second radius proximity, it means that the point cloud after removing the first arc segment is closer to the actual point cloud of the base station docking cavity. Therefore, the first arc segment is removed and the second arc segment is retained, so that the obstacle point cloud removed by each filtering is more accurate.

[0123] On the contrary, if the first radius proximity is smaller than the second radius proximity, it means that the point cloud after removing the second arc segment is closer to the real point cloud of the base station docking cavity. Therefore, the second arc segment is removed and the first arc segment is retained, so that the obstacle point cloud removed by each filtering is more accurate.

[0124] In this embodiment, the first arc segment or the second arc segment is determined to be removed according to the proximity between the point cloud after the arc segment is removed and the real point cloud of the base station docking cavity, so that the obstacle point cloud removed by filtering is more accurate.

[0125] In this embodiment, each point cloud in the second point cloud set is clustered and divided into multiple arc segments using a smaller distance threshold, and one of the interfering arc segments at both ends is selectively filtered based on the fitting effect after removing the arc segments, so that the arc fitting result gradually approaches the real arc of the base station docking cavity, so that the updated point cloud (point cloud in the form of an arc with a radius within a preset range, used to join the arc point cloud set) can effectively filter out the obstacle point cloud around the base station (such as shoes, stools or table corners, etc.), so that the arc fitting result is more accurate, and each point cloud in the arc point cloud set is closer to the real point cloud of the base station docking cavity. That is, most of the obstacle point clouds can be filtered out, and the arc point cloud set can be further simplified, which is conducive to the subsequent accurate identification of the point cloud corresponding to the base station.

[0126] S30: Filter out point clouds with arc openings facing the cleaning robot from the arc point cloud set to obtain a potential point cloud set.

[0127] Understandably, see Fig. 9 , there may also be obstacles such as cylinders or spheres around the base station, that is, the arc point cloud set may also include arc point clouds corresponding to these cylindrical or spherical obstacles. It is understandable that the point clouds of these cylindrical or spherical obstacles are almost identical to the point clouds of the base station in shape. If the point clouds of these cylindrical or spherical obstacles are not filtered out, it is easy to cause recognition errors, causing the cleaning robot to walk towards the cylindrical or spherical obstacles and fail to dock correctly at the base station.

[0128] Unlike the circular arc point cloud openings corresponding to these obstacles, which may face away from the cleaning robot, the circular arc point cloud openings corresponding to the base station generally face the robot. Therefore, here, the circular arc opening direction is used for further screening to filter out the point clouds corresponding to most obstacles whose circular arc openings face away from the cleaning robot, so that the obtained potential point cloud set has a smaller range, from which it is easier to accurately find the point cloud corresponding to the base station.

[0129] In some embodiments, the aforementioned step S30 specifically includes:

[0130] S31: for any point cloud in the arc point cloud set, take any laser point of the point cloud, obtain a first vector pointing from the laser point to the center of the point cloud, and obtain a second vector pointing from the laser point to the cleaning robot;

[0131] S32: If the angle between the first vector and the second vector is an acute angle, determine that the point cloud is a point cloud with an arc opening toward the cleaning robot, and add it to the potential point cloud set.

[0132] In this embodiment, the point clouds in the arc point cloud set are traversed. For any point cloud in the arc point cloud set, refer to Fig.10 , obtain any laser point J of the point cloud, and obtain the center O of the fitted arc of the point cloud. It can be understood that the laser point J and the center O have their own coordinates in the rectangular coordinate system (converted from the radar polar coordinate system), so the first vector pointing from the laser point J to the center O of the point cloud is calculated. Calculate the second vector of laser point J pointing to cleaning robot Q

[0133] Determine the first vector and the second vector Is the angle between them acute? If the first vector and the second vector The angle between them is an acute angle, indicating that the arc opening of the point cloud is facing the cleaning robot. This point cloud is most likely the point cloud corresponding to the base station, so the point cloud is added to the potential point cloud set.

[0134] If the first vector and the second vector The angle between them is an obtuse angle, indicating that the arc opening of the point cloud is facing away from the cleaning robot. This point cloud is the point cloud corresponding to the obstacle. Therefore, the point cloud corresponding to the obstacle with the arc opening facing away from the cleaning robot is filtered out, so that the obtained potential point cloud set has a smaller range, from which it is easier to accurately find the point cloud corresponding to the base station.

[0135] S40: Determine the target point cloud corresponding to the base station according to the morphological features of each point cloud in the potential point cloud set, so as to identify the base station.

[0136] It is understandable that when the environment where the base station is located is simple and the potential point cloud set includes one point cloud, the point cloud is the target point cloud corresponding to the base station. When the environment where the base station is located is complex, for example, there are obstacles with a similar shape to the docking cavity of the base station, the potential point cloud set may include two or more point clouds. Here, based on the morphological features of each point cloud in the potential point cloud set, further identification is performed to determine the target point cloud corresponding to the base station, so that the base station can be accurately identified.

[0137] Among them, the morphological features refer to the distribution morphological characteristics of the laser points in the point cloud, such as the shape and concentration of the distribution.

[0138] In this embodiment, the base station can be accurately identified and located based on the morphological features of the point cloud from the potential point cloud set after multiple filtering and narrowing, which is conducive to the subsequent return of the cleaning robot to the base station.

[0139] In some embodiments, the aforementioned step S40 specifically includes:

[0140] S41: Determine the proximity of each point cloud in the potential point cloud set to a preset arc.

[0141] Each point cloud in the potential point cloud set is traversed, and for any point cloud in the potential point cloud set, its proximity to a preset arc is calculated. The preset arc is the arc where the base station docking cavity intersects with the laser scanning surface. In some embodiments, the preset arc can be characterized by a radius and an angle range.

[0142] It can be understood that the more laser points distributed on the preset arc in the point cloud, the closer the point cloud is to the preset arc, which means that the point cloud is more realistic to the point cloud corresponding to the base station.

[0143] In some embodiments, the aforementioned step S41 specifically includes:

[0144] S411: For any point cloud in the potential point cloud set, determine the radius proximity between its radius and the radius of the preset arc, and the fit of the point cloud with respect to its fitted arc.

[0145] First, the point cloud is used to fit the arc, and its radius is obtained by fitting. Then, the radius proximity between the radius and the radius of the preset arc is calculated. In some embodiments, the radius proximity is the absolute value of the difference between the radius obtained by fitting and the radius of the preset arc divided by the radius of the preset arc. It can be understood that the greater the radius proximity, the closer the shape of the point cloud is to the scanning surface shape of the base station docking cavity. The point cloud is more likely to be the point cloud corresponding to the base station.

[0146] The degree of fit is the concentration of the point cloud relative to its fitting arc. The more laser points in the point cloud distributed on the fitting arc, the greater the degree of fit.

[0147] In some embodiments, the fitness D is calculated using the following formula:

[0148]

[0149] Where n is the number of laser points in the point cloud, d i is the distance from the ith laser point to the fitting arc. It is worth noting that The smaller it is, the larger the fitting degree D is, which means that the laser point is closer to the fitting arc and the point cloud distribution is closer to the arc shape.

[0150] It can be understood that the proximity of the point cloud to the preset arc is proportional to the radius proximity and proportional to the fit.

[0151] S412: Determine the degree of proximity of the point cloud to the preset arc according to the radius proximity and the fit.

[0152] Since the proximity is proportional to the radius proximity and the fit, in some embodiments, the proximity is determined as the product of the radius proximity and the fit. In some embodiments, the proximity is determined as the weighted sum of the radius proximity and the fit.

[0153] S42: Determine the point cloud with the greatest degree of proximity as the target point cloud corresponding to the base station.

[0154] It can be understood that the point cloud with the greatest degree of proximity indicates that its fitted radius is closest to the surface arc of the base station docking cavity, and the laser points are distributed in a smooth arc, thus being determined as the target point cloud corresponding to the base station.

[0155] In this embodiment, by calculating the proximity of each point cloud in the potential point cloud set to a preset arc, the point cloud with the greatest proximity is used as the target point cloud, so that the target point cloud is accurate, which is conducive to accurately identifying the base station.

[0156] In summary, the method for identifying a base station provided in an embodiment of the present application is applied to a cleaning robot including a laser radar, and the surface of the base station for accommodating the cleaning robot is an arc surface. The method obtains laser point cloud data obtained by scanning the current environment of the cleaning robot by a laser radar, fits and identifies point clouds in the form of arcs from the laser point cloud data, and obtains an arc point cloud set. From the arc point cloud set, the point cloud with the arc pointing toward the cleaning robot is screened out to obtain a potential point cloud set. According to the morphological features of each point cloud in the potential point cloud set, the target point cloud corresponding to the base station is determined to identify the base station.

[0157] In this embodiment, the point clouds in the shape of arcs in the laser point cloud data are first fitted and identified, and the point clouds in other shapes are filtered out. The obtained arc point cloud set includes the point clouds corresponding to the base station, and may also include the point clouds corresponding to obstacles such as cylinders or spheres. Therefore, the arc opening direction is used for secondary screening to filter out the point clouds corresponding to obstacles with most of the arc openings facing away from the cleaning robot, so that the obtained potential point cloud set has a smaller range, and it is easier to accurately find the point clouds corresponding to the base station. Therefore, based on the morphological features of each point cloud in the potential point cloud set (such as radius or smoothness, etc.), the target point cloud corresponding to the base station can be accurately identified, thereby identifying the base station. That is, by performing secondary filtering on the laser point cloud data through arc fitting and arc opening direction, the interference of most obstacle point clouds can be reduced, which is conducive to accurately identifying the point cloud corresponding to the base station. Based on the morphological features of the point cloud from the potential point cloud set after multiple filtering and narrowing, the base station can be accurately identified and located, which is conducive to the subsequent cleaning robot returning to the base station.

[0158] The embodiment of the present application also provides a computer-readable storage medium, such as a memory including a program code, and the program code can be executed by a processor to complete the method of identifying a base station 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.

[0159] 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 identifying a base station provided in the above embodiment.

[0160] 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.

[0161] 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.

[0162] 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 identifying a base station, applied to a cleaning robot including a laser radar, characterized in that: The docking cavity in the base station for accommodating the cleaning robot has an arc surface, and the method comprises: Acquire laser point cloud data obtained by scanning the current environment where the cleaning robot is located by the laser radar; Fitting and identifying arc point clouds from the laser point cloud data to obtain an arc point cloud set; Filter out point clouds with arc openings facing the cleaning robot from the arc point cloud set to obtain a potential point cloud set; According to the morphological features of each point cloud in the potential point cloud set, a target point cloud corresponding to the base station is determined to identify the base station.

2. The method according to claim 1, characterized in that: The step of fitting and identifying arc point clouds from the laser point cloud data to obtain an arc point cloud set includes: Clustering and grouping the laser point cloud data to obtain a first point cloud set, performing straight line fitting on each point cloud in the first point cloud set, segmenting and filtering out straight line point clouds in the first point cloud set, and obtaining a second point cloud set; Arc fitting is performed on each point cloud in the second point cloud set, and point clouds that are arcs and have a radius within a preset range are screened out to form the arc point cloud set.

3. The method according to claim 2, characterized in that For any point cloud in the second point cloud set, arc fitting is performed in the following manner to filter out point clouds that are arcs and have a radius within a preset range: Use distance threshold to split the point cloud into multiple arc segments; An arc segment located in the part of the point cloud is eliminated and arc fitting is performed. If the absolute value of the difference between the fitting radius and the preset radius is greater than the preset threshold, the arc segment located in the part of the point cloud is continuously eliminated until the absolute value of the difference between the fitting radius and the preset radius is less than or equal to the preset threshold, and an updated point cloud is obtained. The updated point cloud is used as the point cloud in the form of an arc with a radius within a preset range.

4. The method according to claim 3, characterized in that The removing of an arc segment located in the middle of the point cloud comprises: Acquire a first arc segment and a second arc segment respectively located at two ends of the point cloud, obtain a first radius by fitting the points in the point cloud except the first arc segment, and obtain a second radius by fitting the points in the point cloud except the second arc segment; One of the first arc segment and the second arc segment is eliminated according to the first radius and the second radius.

5. The method according to claim 4, characterized in that The removing one of the first arc segment and the second arc segment according to the first arc radius and the second arc radius comprises: Determine a first radius proximity between the first radius and the preset radius, and a second radius proximity between the second radius and the preset radius; If the first radius proximity is greater than or equal to the second radius proximity, the first arc segment is removed; otherwise, the second arc segment is removed.

6. The method according to claim 1, characterized in that The step of selecting the point cloud whose arc opening is facing the cleaning robot from the arc point cloud set to obtain a potential point cloud set includes: For any point cloud in the arc point cloud set, take any laser point of the point cloud, obtain a first vector pointing from the laser point to the center of the point cloud, and obtain a second vector pointing from the laser point to the cleaning robot; If the angle between the first vector and the second vector is an acute angle, the point cloud is determined to be a point cloud with an arc opening toward the cleaning robot, and is added to the potential point cloud set.

7. The method according to claim 1, characterized in that The step of determining the target point cloud corresponding to the base station according to the morphological features of each point cloud in the potential point cloud set includes: Determining the proximity of each point cloud in the potential point cloud set to a preset arc; The point cloud with the greatest proximity is determined as the target point cloud corresponding to the base station.

8. The method according to claim 7, characterized in that The determining of the proximity of each point cloud in the potential point cloud set to a preset arc includes: For any point cloud in the potential point cloud set, determining the radius proximity between its radius and the radius of the preset arc, and the fitting degree of the point cloud relative to its fitting arc; The degree of proximity of the point cloud to the preset arc is determined according to the radius proximity and the fit degree.

9. A cleaning robot, characterized in that: include: LiDAR, at least one processor, the at least one processor being communicatively connected to the laser radar; 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 identifying a base station 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 identifying a base station according to any one of claims 1 to 8.

Images