Cleaning device control method and apparatus, and program product, medium and cleaning device

Abstract

A cleaning device control method and apparatus, and a program product, a medium and a cleaning device. The control method comprises: acquiring an obstacle point-cloud distribution map of the surrounding environment of a cleaning device (210); on the basis of relative positional relationships between each obstacle point cloud in the obstacle point cloud distribution map and the other obstacle point clouds therein, determining a wall-corner point cloud from the obstacle point cloud distribution map (230); and controlling the cleaning device to execute a wall-corner cleaning action in an area where the wall-corner point cloud is located (250). By means of the cleaning device, the accuracy of wall-corner cleaning performed by the cleaning device can be improved.

Description

Cleaning device control method, device, program product, medium and cleaning device

[0001] Cross-reference to Related Applications

[0002] The present application is based on and claims priority to Chinese Patent Application No. 202410850992.0, filed on June 27, 2024, the entire contents of which are incorporated herein by reference. TECHNICAL FIELD

[0003] The present application belongs to the technical field of cleaning device control, and particularly relates to a cleaning device control method, device, program product, medium and cleaning device. BACKGROUND

[0004] In the process of performing a ground cleaning task by a cleaning device (such as a sweeping robot or a mopping robot), if a small corner environment similar to a wall corner (a wall corner) is encountered, the cleaning device can have problems of being unable to identify the corner environment or inaccurately identifying the corner environment, thereby resulting in the wall corner region being unable to be thoroughly cleaned, and often requiring manual cleaning by a user or multiple starts of the robot to achieve an ideal cleaning effect, thereby increasing use cost and time. Based on this, how to improve the accuracy of cleaning a wall corner by a cleaning device is a technical problem to be solved.

[0005] SUMMARY

[0006] Embodiments of the present application provide a cleaning device control method, device, computer program product, computer-readable storage medium and cleaning device, thereby at least to some extent improving the accuracy of cleaning a wall corner by a cleaning device.

[0007] Other characteristics and advantages of the present application will become apparent from the following detailed description, or will be learned by practice of the present application.

[0008] According to a first aspect of embodiments of the present application, a cleaning device control method is provided, the method comprising: obtaining an obstacle point cloud distribution map of an environment around a cleaning device; determining a wall corner point cloud in the obstacle point cloud distribution map based on a relative positional relationship between each obstacle point cloud in the obstacle point cloud distribution map and other obstacle point clouds; and controlling the cleaning device to perform a wall corner cleaning action in a region where the wall corner point cloud is located.

[0009] In some embodiments of the present application, based on the foregoing scheme, the obtaining of the obstacle point cloud distribution map of the environment around the cleaning device comprises: obtaining a plurality of frames of point cloud images of a local environment around the cleaning device collected by a sensor mounted on the cleaning device; and integrating the plurality of frames of point cloud images to obtain the obstacle point cloud distribution map of the environment around the cleaning device.

[0010] In some embodiments of the present application, based on the foregoing scheme, before integrating the plurality of frames of the point cloud images, the method further comprises: removing noise points in the point cloud image of the local environment around the cleaning device in each frame.

[0011] In some embodiments of the present application, based on the foregoing scheme, the determining of the corner point cloud in the obstacle point cloud distribution map based on the relative positional relationship between each obstacle point cloud and other obstacle point clouds in the obstacle point cloud distribution map comprises: traversing each obstacle point cloud in the obstacle point cloud distribution map, defining a region of interest centered on the each obstacle point cloud in the obstacle point cloud distribution map; if the relative positional relationship of the obstacle point clouds in the region of interest meets the wall corner geometric feature, determining the each obstacle point cloud as a candidate corner point cloud; determining the corner point cloud among the various candidate corner point clouds in the obstacle point cloud distribution map.

[0012] In some embodiments of the present application, based on the foregoing scheme, the method further comprises: calculating a bearing difference feature value of each two reference obstacle point clouds relative to the each obstacle point cloud in the region of interest, the bearing difference feature value being used to represent the difference amplitude of the bearing of the each two reference obstacle point clouds relative to the each obstacle point cloud, the reference obstacle point cloud being an obstacle point cloud in the region of interest other than the each obstacle point cloud; if any one of the bearing difference feature values falls within a preset bearing difference feature value interval, determining that the relative positional relationship of the obstacle point clouds in the region of interest meets the wall corner geometric feature.

[0013] In some embodiments of the present application, based on the foregoing scheme, the determining of the corner point cloud among the various candidate corner point clouds in the obstacle point cloud distribution map comprises: traversing each candidate corner point cloud, determining the obstacle point clouds distributed in various extension directions with the each candidate corner point cloud as the starting point; if the relative positional relationship of the obstacle point clouds in two different extension directions both meet the wall surface geometric feature, determining the each candidate corner point cloud as the corner point cloud.

[0014] In some embodiments of the present application, based on the foregoing scheme, the method further comprises: performing linear fitting on the obstacle point clouds in each extension direction respectively, and determining the distance between the first and last obstacle point clouds on the fitted straight line; if the distance between the first and last obstacle point clouds on two different fitted straight lines both fall within a preset distance range, determining that the relative positional relationship of the obstacle point clouds in two different extension directions both meet the wall surface geometric feature.

[0015] In some embodiments of the present application, based on the foregoing scheme, the method further comprises: performing linear fitting on the obstacle point cloud in each extension direction respectively, and determining the distance between the first and last obstacle point clouds on the fitted straight line; if the distance between the first and last obstacle point clouds on two different fitted straight lines both falls within a preset distance range, and the included angle of the two different fitted straight lines falls within a preset angle range, it is determined that the relative position relationship of the obstacle point clouds in the two different extension directions both conforms to the wall surface geometric feature.

[0016] In some embodiments of the present application, based on the foregoing scheme, the method further comprises: calculating the distance between the cleaning device and the two different fitted straight lines; if the distance between the cleaning device and the two different fitted straight lines is both less than a first preset distance, controlling the cleaning device to perform a wall corner cleaning action in the area where the wall corner point cloud is located.

[0017] In some embodiments of the present application, based on the foregoing scheme, the method further comprises: if there is only one wall corner point cloud in the obstacle point cloud distribution map, controlling the cleaning device to perform a wall corner cleaning action in the area where the wall corner point cloud is located.

[0018] In some embodiments of the present application, based on the foregoing scheme, before controlling the cleaning device to perform a wall corner cleaning action in the area where the wall corner point cloud is located, the method further comprises: controlling the cleaning device to adjust its position until the distance to the one side wall surface corresponding to the wall corner point cloud is a second preset distance, and the distance to the other side wall surface corresponding to the wall corner point cloud is a third preset distance, and controlling the cleaning device to adjust its orientation until it is parallel to the one side wall surface.

[0019] In some embodiments of the present application, based on the foregoing scheme, after controlling the cleaning device to adjust its orientation until it is parallel to the one side wall surface, the method further comprises: controlling the cleaning device to retreat by a fourth preset distance, and controlling the cleaning device to extend the side brush close to the one side wall surface.

[0020] In some embodiments of the present application, based on the foregoing scheme, the control of the cleaning device to perform a wall corner cleaning action in the area where the wall corner point cloud is located comprises: controlling the cleaning device to travel according to the current orientation; if the cleaning device travels to the wall corner position corresponding to the wall corner point cloud, controlling the cleaning device to retract the side brush close to the one side wall surface, and controlling the cleaning device to adjust its orientation until it is parallel to the other side wall surface corresponding to the wall corner point cloud, to perform other cleaning tasks.

[0021] According to a second aspect of the embodiments of the present application, a cleaning device control apparatus is provided, the apparatus comprising: an acquisition unit configured to acquire an obstacle point cloud distribution map of an environment surrounding a cleaning device; a determination unit configured to determine a corner point cloud in the obstacle point cloud distribution map based on a relative positional relationship between each obstacle point cloud in the obstacle point cloud distribution map and other obstacle point clouds; and a control unit configured to control the cleaning device to perform a corner cleaning action in a region in which the corner point cloud is located.

[0022] According to a third aspect of the embodiments of the present application, a computer program product is provided, the computer program product comprising computer instructions stored in a computer readable storage medium and adapted to be read and executed by a processor to cause a computer device having the processor to perform operations implemented by the method according to any one of the first aspect.

[0023] According to a fourth aspect of the embodiments of the present application, a computer readable storage medium is provided, the computer readable storage medium storing at least one computer program instruction, the at least one computer program instruction being loaded and executed by a processor to implement operations performed by the method according to any one of the first aspect.

[0024] According to a fifth aspect of the embodiments of the present application, a cleaning device is provided, the cleaning device comprising one or more processors and one or more memories, the one or more memories storing at least one computer program instruction, the at least one computer program instruction being loaded and executed by the one or more processors to implement operations performed by the method according to any one of the first aspect.

[0025] Based on the technical solutions proposed in the present application, by acquiring an obstacle point cloud distribution map of an environment surrounding a cleaning device, and based on a relative positional relationship between each obstacle point cloud in the obstacle point cloud distribution map and other obstacle point clouds, a corner point cloud in the obstacle point cloud distribution map can be accurately determined, i.e., the position of a corner can be accurately determined, and thus the cleaning device can be accurately controlled to perform a corner cleaning action in a region in which the corner point cloud is located, improving the accuracy of cleaning a corner by the cleaning device.

[0026] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, and are not limiting to the present application. BRIEF DESCRIPTION OF DRAWINGS

[0027] The accompanying drawings, which are incorporated herein and constitute part of the specification, illustrate embodiments consistent with the application and, together with the description, further serve to explain the principles of the application. It is to be understood that the drawings are only schematic, and that they do not necessarily represent a limiting

[0028] Fig. 1 shows a schematic view of a scenario in which a cleaning device according to an embodiment of the application cleans a floor;

[0029] Fig. 2 shows a flow chart of a method of controlling a cleaning device according to an embodiment of the application;

[0030] Fig. 3 shows a schematic view of a scenario in which a cleaning device according to an embodiment of the application cleans a floor;

[0031] Fig. 4 shows a schematic view of a scenario in which a cleaning device according to an embodiment of the application cleans a floor;

[0032] Fig. 5 shows a schematic view of a scenario in which a cleaning device according to an embodiment of the application cleans a floor;

[0033] Fig. 6 shows a block diagram of a control device for a cleaning device according to an embodiment of the application;

[0034] Fig. 7 shows a schematic view of a cleaning device according to an embodiment of the application. DETAILED DESCRIPTION

[0035] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0036] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the application can be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In other instances, well-known structures, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the application.

[0037] The block diagrams illustrated in the drawings are merely functional entities, and do not necessarily have to correspond to physically independent entities. That is, the functional entities can be implemented in the form of software, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices. It should also be noted that in some of the drawings, in order to ensure the simplicity of the drawings, some components in the drawings are omitted, which do not affect the explanation of the technical solutions of the present application.

[0038] The flowcharts illustrated in the drawings are merely exemplary illustrations, and do not necessarily include all contents and operations / steps, nor necessarily executed in the order described. For example, some operations / steps can be further decomposed, and some operations / steps can be combined or partially combined, so the actual execution order can be changed according to the actual situation.

[0039] In the description of the present application, it should be understood that the terms "first", "second" are only for the purpose of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, the meaning of "multiple" is two or more.

[0040] In order for those skilled in the art to better understand the present application, first, the application scenario involved in the present application will be briefly described in conjunction with FIG. 1.

[0041] Referring to FIG. 1, a schematic diagram of a scenario in which a cleaning device cleans the ground is shown.

[0042] In the embodiment as shown in FIG. 1, the cleaning device 101 involved can be a sweeping machine, or a mopping machine, or a sweeping and mopping integrated machine, and the present application does not make specific limitation thereon.

[0043] Further, as shown in FIG. 1, the cleaning device 101 can be provided with a sensor 102 and a sensor 103 on the body of the cleaning device, wherein the sensor 102 can be used to collect point cloud data in the environment around the cleaning device, such as a binocular light sensor, a structured light sensor, a laser radar sensor, a millimeter wave radar sensor, an ultrasonic radar sensor, etc. The sensor 103 can be used to collect distance data between the cleaning device and the side obstacle (such as a wall obstacle), such as an ultrasonic ranging sensor, an infrared ranging sensor, a laser ranging sensor, etc. The body of the cleaning device 101 can also be provided with a first cleaning element 104 and a second cleaning element 105, wherein the first cleaning element 104 (such as a mop) can be used for mopping, and the second cleaning element 105 (such as a sweeper) can be used for sweeping. Specifically, when the cleaning action is not needed to be performed, the first cleaning element 104 and the second cleaning element 105 can be hidden at the bottom of the body of the cleaning device, and when the cleaning action is needed to be performed, the first cleaning element 104 and the second cleaning element 105 can be extended at a certain angle from the bottom of the body of the cleaning device, so as to clean the ground. It should be noted that the number of cleaning elements in the cleaning device can be one or more, which can be determined according to the actual situation of the cleaning device, and the present application does not make a specific limitation.

[0044] The present application provides a cleaning device control scheme, which can detect the environment around the cleaning device 101 during the execution of the cleaning task, such as detecting the point cloud data of the environment around the cleaning device 101 based on the sensor installed on the cleaning device. By analyzing the point cloud data, it can be determined whether there is a corner around the cleaning device, so as to realize accurate cleaning of the area where the corner is located and improve the cleaning coverage. The use cost and time are reduced, and the accuracy of cleaning the corner by the cleaning device is improved.

[0045] It should be noted that the corner described in the present application is a general term for corner structures similar to corners by those skilled in the art, which is not limited to the literal meaning of corners, but also can be a corner structure formed by furniture and electrical appliances.

[0046] It should be further noted that in the drawings provided by the present application, the body shape of the cleaning device is circular, but in actual application, there can be other shapes of the body of the cleaning device, such as rectangular, trapezoidal, and irregular.

[0047] Referring to FIG. 2, a flow chart of a cleaning device control method in an embodiment of the present application is shown, which can be executed by a device with computing processing function. Referring to FIG. 2, the cleaning device control method at least includes steps 210 to 250, which are described in detail as follows:

[0048] In step 210, an obstacle point cloud distribution map of the surrounding environment of the cleaning device is acquired.

[0049] In the present application, the acquisition of the obstacle point cloud distribution map of the surrounding environment of the cleaning device can be performed according to steps 211 to 212 as follows:

[0050] In step 211, a plurality of point cloud images of the local environment around the cleaning device are acquired by a sensor installed on the cleaning device.

[0051] In step 212, the plurality of point cloud images are integrated to obtain the obstacle point cloud distribution map of the surrounding environment of the cleaning device.

[0052] In the present application, the sensor installed on the cleaning device, such as the sensor 103 shown in FIG. 1, can collect point cloud images of the surrounding environment of the cleaning device in real time or at regular intervals. Specifically, in actual application, when the cleaning device is moving or stopped on the ground, the sensor installed on the cleaning device can emit a sensing signal (such as a laser signal) in a certain direction around it, and receive the sensing signal reflected by the obstacles (such as walls, furniture, etc.) in that direction, thereby obtaining a frame of point cloud image in that direction of the cleaning device. Since the sensor installed on the cleaning device emits signals in all directions around it, a plurality of point cloud images of the local environment around the cleaning device can be collected.

[0053] In the present application, the point cloud image actually includes a plurality of 2D points with x and y coordinates (i.e., coordinates representing each obstacle point). It should be noted that in some embodiments, after the cleaning device acquires the point cloud image of the local environment around it, only the point clouds within a certain distance around it can be retained in the point cloud image.

[0054] After acquiring a plurality of point cloud images of the local environment around the cleaning device, the plurality of point cloud images can be integrated to obtain the obstacle point cloud distribution map of the surrounding environment of the cleaning device. Through the obstacle point cloud distribution map, it can be determined which positions around the cleaning device have obstacles.

[0055] In the present application, before step 212 is performed, i.e., before the plurality of point cloud images are integrated, the following step 2121 can also be performed:

[0056] In step 2121, noise points in the point cloud image of the local environment around the cleaning device are removed.

[0057] In the present application, the inventors consider that light reflection, too fast sensor moving speed and other reasons may cause the point cloud data in the point cloud image to fail to accurately reflect the position of the obstacle point, and therefore propose a scheme for removing the noise point cloud in the point cloud image of the local environment around the cleaning device in each frame. Specifically, the point cloud in the point cloud image can be filtered, smoothed and the like, and the point cloud with a small light intensity is filtered, and then a relatively accurate and smooth point cloud is obtained. In this way, the accuracy of the obstacle point cloud distribution map can be improved, and the accuracy of the subsequent cleaning of the corner by the cleaning device can be indirectly improved.

[0058] With continuous reference to FIG. 2, in step 230, based on the relative positional relationship between each obstacle point cloud and other obstacle point clouds in the obstacle point cloud distribution map, a corner point cloud is determined in the obstacle point cloud distribution map.

[0059] In the present application, if there is actually a corner in the environment around the cleaning device, based on the relative positional relationship between each obstacle point cloud and other obstacle point clouds in the obstacle point cloud distribution map, a corner point cloud can be determined in the obstacle point cloud distribution map, that is, by analyzing the obstacle point cloud in the obstacle point cloud distribution map, the shapes of different structures such as corners and furniture edges can be accurately distinguished based on the geometric characteristics of the obstacles.

[0060] Specifically, the determination of the corner point cloud in the obstacle point cloud distribution map based on the relative positional relationship between each obstacle point cloud and other obstacle point clouds in the obstacle point cloud distribution map can be performed according to the following steps 231 to 233:

[0061] Step 231: Each obstacle point cloud in the obstacle point cloud distribution map is traversed, and a region of interest centered on each obstacle point cloud in the obstacle point cloud distribution map is defined.

[0062] Step 232: If the relative positional relationship of the obstacle point clouds in the region of interest meets the geometric characteristics of the corner, the each obstacle point cloud is determined as a candidate corner point cloud.

[0063] Step 233: A corner point cloud is determined in each candidate corner point cloud in the obstacle point cloud distribution map.

[0064] In the present application, a region of interest of a predetermined size can be defined in the obstacle point cloud distribution map with each obstacle point cloud in the obstacle point cloud distribution map as the center of the region. Specifically, for example, the region of interest can be a rectangle with a predetermined side length, of course, it can also be a parallelogram, or a circle, it can be understood that the region of interest can also be other shapes, and the present application does not specifically limit the specific shape of the region of interest.

[0065] In the present application, at least each of the obstacle point clouds in the region of interest can be understood to include other obstacle point clouds in some regions of interest.

[0066] In the present application, after defining the region of interest in the obstacle point cloud distribution map, it can be judged whether the relative position relationship of the obstacle point clouds in the region of interest conforms to the wall corner geometric feature, that is, whether the position of the obstacle point clouds in the region of interest can correspond to the position of the wall corner. Specifically, the following steps 2321 to 2322 can be performed:

[0067] Step 2321, calculate the orientation difference feature value of each two reference obstacle point clouds relative to each obstacle point cloud in the region of interest, the orientation difference feature value is used to represent the difference amplitude of the orientation of each two reference obstacle point clouds relative to each obstacle point cloud, and the reference obstacle point cloud is the obstacle point cloud in the region of interest except the each obstacle point cloud.

[0068] Step 2322, if any of the orientation difference feature values falls within the preset orientation difference feature value interval, it is determined that the relative position relationship of the obstacle point clouds in the region of interest conforms to the wall corner geometric feature.

[0069] In the present application, since the wall corner is generally a included angle formed by two faces, the distribution shape (i.e. geometric feature) of the obstacle point cloud corresponding to the wall corner should also form a included angle, that is, the distribution pattern of the obstacle point cloud corresponding to the wall corner will not equal or approximately equal to a straight line, but can be a zigzag line. Therefore, theoretically, the orientation difference feature value of each two reference obstacle point clouds relative to each obstacle point cloud should fall within the preset orientation difference feature value interval, that is, it can be understood that the included angle formed by the connecting line of the other obstacle point cloud and the obstacle point cloud corresponding to the wall corner is greater than 0° and less than 180°, or it can be understood that the curvature value of the obstacle point cloud corresponding to the wall corner is greater than 0.

[0070] In the present application, by calculating the orientation difference feature value of each two reference obstacle point clouds relative to each obstacle point cloud in the region of interest, it can be further judged whether the orientation difference feature value falls within the preset orientation difference feature value interval to judge whether the relative position relationship of the obstacle point clouds in the region of interest conforms to the wall corner geometric feature.

[0071] In an embodiment of the present application, the orientation distinguishing feature value can be an included angle formed by a line connecting the other obstacle point cloud and the each obstacle point cloud, i.e. if the included angle falls into a preset angle interval (such as 60°-120°, it can be understood by those skilled in the art that in actual application, the preset angle interval can be determined according to the specific model or specific structural features of the cleaning device, and the present application does not limit the specific preset angle interval), it can be determined that the relative position relationship of the obstacle point cloud in the region of interest conforms to the wall corner geometric feature.

[0072] In an embodiment of the present application, the orientation distinguishing feature value can be a curvature value of the each obstacle point cloud, i.e. if the curvature value of the each obstacle point cloud falls into a preset curvature value interval, it can be determined that the relative position relationship of the obstacle point cloud in the region of interest conforms to the wall corner geometric feature.

[0073] In order for those skilled in the art to better understand the present application, a specific embodiment will be described below in conjunction with FIG. 3.

[0074] Referring to FIG. 3, a schematic diagram of a scenario in which a cleaning device cleans a ground surface to which embodiments of the present application can be applied is shown.

[0075] As shown in FIG. 3, three regions of interest are determined in the obstacle point cloud distribution map, i.e. a region of interest 106, a region of interest 107, and a region of interest 108, wherein only one obstacle point cloud A exists in the region of interest 108, and therefore the obstacle point cloud A can not be a wall corner point cloud. Three obstacle point clouds exist in the region of interest 107, but the orientation distinguishing feature values of two reference obstacle point clouds in the region of interest 107 with respect to the obstacle point cloud B do not fall into a preset orientation distinguishing feature value interval (i.e. the included angles formed by lines connecting the two reference obstacle point clouds and the obstacle point cloud B do not fall into a preset angle interval, or the curvature value of the obstacle point cloud B does not fall into a preset curvature value interval), and therefore the obstacle point cloud B can not be a wall corner point cloud. Three obstacle point clouds exist in the region of interest 108, wherein the orientation distinguishing feature values of two reference obstacle point clouds with respect to the obstacle point cloud C fall into a preset orientation distinguishing feature value interval (i.e. the included angles formed by lines connecting the two reference obstacle point clouds and the obstacle point cloud C fall into a preset angle interval, or the curvature value of the obstacle point cloud C falls into a preset curvature value interval), and are local maximum values. Therefore, the obstacle point cloud C can be a wall corner point cloud, i.e. the obstacle point cloud C is determined as a candidate wall corner point cloud.

[0076] In the present application, by defining a region of interest in the obstacle point cloud distribution map, and based on the orientation distinguishing feature value of each two reference obstacle point clouds relative to each obstacle point cloud, it is determined whether there is a candidate corner point cloud in the region of interest, which can accurately screen the obstacle point clouds that may be corner point clouds, thereby providing accurate data support for subsequent determination of corner point clouds, and further improving the accuracy of cleaning equipment in cleaning corners.

[0077] In the present application, it should be noted that the candidate corner point cloud determined in the obstacle point cloud distribution map does not mean that the candidate corner point cloud is the point cloud corresponding to the corner in the actual environment, and further judgment needs to be made on whether the candidate corner point cloud is the actual corner point cloud.

[0078] Further, in the present application, the determination of the corner point cloud in each candidate corner point cloud in the obstacle point cloud distribution map can be performed according to the following steps 2331 to 2332:

[0079] Step 2331, each candidate corner point cloud is traversed to determine the obstacle point clouds distributed in various extension directions with the each candidate corner point cloud as the starting point.

[0080] Step 2332, if the relative position relationship of the obstacle point clouds in two different extension directions both conforms to the wall surface geometric feature, the each candidate corner point cloud is determined as the corner point cloud.

[0081] In the present application, after determining the candidate corner point cloud in the obstacle point cloud distribution map, it can be determined whether the relative position relationship of the obstacle point clouds in two different extension directions both conforms to the wall surface geometric feature with the candidate corner point cloud as the starting point, and if so, the candidate corner point cloud is determined as the corner point cloud. Specifically, in an embodiment of the present application, whether the relative position relationship of the obstacle point clouds in two different extension directions both conforms to the wall surface geometric feature can be determined according to the following steps 23321 to 23322:

[0082] Step 23321, straight line fitting is performed on the obstacle point clouds in each extension direction, and the distance between the first and last two obstacle point clouds on the fitted straight line is determined.

[0083] Step 23322, if the distance between the first and last two obstacle point clouds on two different fitted straight lines both falls within a predetermined distance range, it is determined that the relative position relationship of the obstacle point clouds in two different extension directions both conforms to the wall surface geometric feature.

[0084] In order for those skilled in the art to better understand the present application, a specific embodiment will be described below with reference to FIG. 4.

[0085] Referring to FIG. 4, a schematic diagram of a scenario in which a cleaning device cleans a ground surface is shown.

[0086] As shown in FIG. 4, starting from the candidate wall corner point cloud C, straight line fitting is performed on the obstacle point clouds in the extension direction F and the extension direction G respectively (i.e., straight line fitting is performed on the obstacle point clouds in the region 111 and the obstacle point clouds in the region 110), obtaining the fitted straight line CD and the fitted straight line CE. If the distance between the obstacle point clouds C and D at the head and tail of the fitted straight line CD falls within the preset distance range, and the distance between the obstacle point clouds C and E at the head and tail of the fitted straight line CE also falls within the preset distance range, it can be determined that the relative position relationship of the obstacle point clouds in the extension direction F and the extension direction G both conform to the wall surface geometric feature, and then the candidate wall corner point cloud C can be determined as the wall corner point cloud.

[0087] In one practical application of the present application, the preset distance range can be 5cm-10cm. It can be understood by those skilled in the art that, in practical applications, the preset distance range can be determined according to the specific model or specific structural features of the cleaning device, and the present application does not limit the specific preset distance range.

[0088] In another embodiment of the present application, whether the relative position relationship of the obstacle point clouds in the region of interest conforms to the wall corner geometric feature can also be determined according to the following steps 2323 to step 2324:

[0089] Step 23323, straight line fitting is performed on the obstacle point clouds in each extension direction respectively, and the distance between the two obstacle point clouds at the head and tail of the fitted straight line is determined.

[0090] Step 23324, if the distance between the two obstacle point clouds at the head and tail of two different fitted straight lines both falls within the preset distance range, and the included angle of the two different fitted straight lines falls within the preset angle range, it is determined that the relative position relationship of the obstacle point clouds in the two different extension directions both conforms to the wall surface geometric feature.

[0091] In order for those skilled in the art to better understand the present application, a specific embodiment will be described below in conjunction with FIG. 4.

[0092] As shown in FIG. 4, taking the candidate wall corner point cloud C as a starting point, straight line fitting is performed on the obstacle point clouds in the extension direction F and the extension direction G (i.e., straight line fitting is performed on the obstacle point clouds in the region 111 and the obstacle point clouds in the region 110), to obtain a fitted straight line CD and a fitted straight line CE. If the distance between the obstacle point clouds C and D at the head and tail of the fitted straight line CD falls within a preset distance range, the distance between the obstacle point clouds C and E at the head and tail of the fitted straight line CE also falls within the preset distance range, and the included angle θ of the fitted straight line CD and the fitted straight line CE falls within a preset angle range, it can be determined that the relative position relationship of the obstacle point clouds in the extension direction F and the extension direction G both conform to the wall surface geometric feature, and the candidate wall corner point cloud C can be determined as the wall corner point cloud.

[0093] In an actual application of the present application, the preset distance range can be 5cm-10cm, and the preset angle range can be 60°-120°. It can be understood by those skilled in the art that, in actual application, the preset distance range and the preset angle range can be determined according to the specific model or specific structural features of the cleaning device, and the present application does not limit the specific preset distance range.

[0094] In the present application, taking each candidate wall corner point cloud as a starting point, by judging whether the relative position relationship of the obstacle point clouds in two different extension directions thereof conforms to the wall surface geometric feature, it can be accurately determined whether the candidate wall corner point cloud is a wall corner point cloud, so that the accuracy of the cleaning device in cleaning the wall corner can be improved subsequently.

[0095] Continuing to refer to FIG. 2, in step 250, the cleaning device is controlled to perform a wall corner cleaning action in the region where the wall corner point cloud is located.

[0096] In the present application, if a wall corner point cloud is determined in the obstacle point cloud distribution map, the following steps 241-242 can be performed to determine whether to control the cleaning device to perform a wall corner cleaning action in the region where the wall corner point cloud is located:

[0097] Step 241, the distance between the cleaning device and the two different fitted straight lines is calculated.

[0098] Step 242, if the distance between the cleaning device and the two different fitted straight lines is less than a first preset distance, the cleaning device is controlled to perform a wall corner cleaning action in the region where the wall corner point cloud is located.

[0099] In some embodiments of the present application, the first preset distance can be 6 cm, 6.5 cm or 7 cm. It can be understood by those skilled in the art that in actual application, the first preset distance can be determined according to the specific model or specific structural features of the cleaning device, and the present application does not limit the specific first preset distance.

[0100] In the present application, if the distance between the cleaning device and the two different fitted straight lines is greater than or equal to the first preset distance, it means that the cleaning device is far away from the corner at this time, and there is no need to give up the current cleaning task to clean the corner area. Only when the distance between the cleaning device and the two different fitted straight lines is less than the first preset distance, the cleaning device is controlled to perform a corner cleaning action in the area where the corner point cloud is located. In this way, the continuity of the cleaning device in performing the ground cleaning task can be avoided, and the orderliness of the cleaning device in performing the ground cleaning task is improved.

[0101] Of course, for those skilled in the art, in some other embodiments, after determining the corner point cloud in the obstacle point cloud distribution map, the cleaning device can be directly triggered to perform a corner cleaning action in the area where the corner point cloud is located.

[0102] In the present application, if the corner point cloud is determined in the obstacle point cloud distribution map, the following step 243 can be made to determine whether to control the cleaning device to perform a corner cleaning action in the area where the corner point cloud is located:

[0103] Step 243, if there is only one corner point cloud in the obstacle point cloud distribution map, the cleaning device is controlled to perform a corner cleaning action in the area where the corner point cloud is located.

[0104] Of course, for those skilled in the art, in some other embodiments, after determining the corner point cloud in the obstacle point cloud distribution map, no matter how many corner point clouds are determined, the cleaning device can be directly triggered to perform a corner cleaning action in the area where the corner point cloud is located.

[0105] In the present application, before controlling the cleaning device to perform a corner cleaning action in the area where the corner point cloud is located, the following step 244 can be performed:

[0106] Step 244, the cleaning device is controlled to adjust its position until the distance to the side wall surface corresponding to the corner point cloud is a second preset distance, and the distance to the other side wall surface corresponding to the corner point cloud is a third preset distance, and the cleaning device is controlled to adjust its orientation until it is parallel to the side wall surface.

[0107] In some embodiments of the present application, the second preset distance and the third preset distance can be 2 cm or 1.5 cm. It can be understood by those skilled in the art that in actual application, the second preset distance and the third preset distance can be determined according to the specific model or specific structural features of the cleaning device, and the present application does not limit the specific second preset distance.

[0108] In the present application, before controlling the cleaning device to perform the wall corner cleaning action in the area where the wall corner point cloud is located, it is also necessary to adjust the position and orientation of the cleaning device, that is, to control the cleaning device to adjust its position until the distance to the side wall surface corresponding to the wall corner point cloud is the second preset distance, and the distance to the other side wall surface corresponding to the wall corner point cloud is the third preset distance, and to control the cleaning device to adjust its orientation until it is parallel to the side wall surface, so that after the side brush of the cleaning device is extended, the side brush can be aligned with the wall corner to clean the edge of the side wall surface, thereby reducing the cleaning omission rate, achieving accurate cleaning of the wall corner by the cleaning device, and avoiding hard collision with the side wall surface, thereby improving the safety of the cleaning device in performing wall corner cleaning.

[0109] It should be noted that the orientation of the cleaning device described in the present application can specifically refer to the advancing direction of the body of the cleaning device during normal cleaning task execution.

[0110] In order for those skilled in the art to better understand the present application, a specific embodiment will be described below with reference to FIG. 5.

[0111] Referring to FIG. 5, a scene schematic diagram of a cleaning device cleaning the ground to which the embodiments of the present application can be applied is shown.

[0112] As shown in subgraph (a) of FIG. 5, when the cleaning device 101 identifies a wall corner (i.e., determines a wall corner point cloud), it controls the cleaning device to adjust its position until the distance to the side wall surface corresponding to the wall corner point cloud is the second preset distance, and the distance to the other side wall surface corresponding to the wall corner point cloud is the third preset distance, and controls the cleaning device to adjust its orientation until it is parallel to the side wall surface, as shown in the position and orientation in subgraph (b) of FIG. 5. In this process, the side brush of the cleaning device can be in an extended state or in a retracted state, which is not limited in the present application.

[0113] After controlling the cleaning device to adjust its orientation until it is parallel to the side wall surface, the following step 245 can also be performed:

[0114] Step 245: controlling the cleaning device to retreat by a fourth preset distance, and controlling the cleaning device to extend the side brush close to the side wall surface.

[0115] For better understanding of the present application by those skilled in the art, please continue to combine FIG. 5, as in subgraph (c) of FIG. 5, after controlling the cleaning device to adjust its orientation until parallel to the one side wall surface, the cleaning device can be controlled to retreat a fourth preset distance, and the cleaning device is controlled to extend the side brush 105 close to the one side wall surface, so as to ensure that the cleaning device can clean the area where the wall corner point cloud is located in the subsequent full cleaning, reduce the cleaning omission rate, and improve the cleaning coverage rate.

[0116] In an actual application in the present application, the fourth preset distance can be 5 cm, 5.5 cm, or 4.5 cm. It can be understood by those skilled in the art that in actual application, the fourth preset distance can be determined according to the specific model or specific structural features of the cleaning device, and the present application does not limit the specific fourth preset distance.

[0117] In the present application, in the above step 250, that is, the control of the cleaning device to perform wall corner cleaning action in the area where the wall corner point cloud is located, the following steps 251 to 252 can be performed:

[0118] Step 251, control the cleaning device to travel according to the current orientation.

[0119] Step 252, if the cleaning device travels to the wall corner position corresponding to the wall corner point cloud, control the cleaning device to retract the side brush close to the one side wall surface, and control the cleaning device to adjust its orientation until parallel to the other side wall surface corresponding to the wall corner point cloud, to perform other cleaning tasks.

[0120] For better understanding of the present application by those skilled in the art, please continue to combine FIG. 5, as in subgraph (c) to subgraph (f) of FIG. 5, control the cleaning device to travel according to the current orientation, if the cleaning device travels to the wall corner position corresponding to the wall corner point cloud, control the cleaning device to retract the side brush 105 close to the one side wall surface, and control the cleaning device to adjust its orientation until parallel to the other side wall surface corresponding to the wall corner point cloud, to perform other cleaning tasks. In this process, the cleaning device side brush can fully clean the area where the wall corner point cloud is located, thereby reducing the cleaning omission rate and achieving the accuracy of the cleaning device in cleaning the wall corner.

[0121] After controlling the cleaning device to adjust its orientation until parallel to the other side wall surface corresponding to the wall corner point cloud, the side brush of the cleaning device can be in an extended state or in a retracted state, which is not limited in the present application.

[0122] In the present application, it is reminded that although the preferred embodiments of the embodiments of the present application have been described above, those skilled in the art can make further changes and modifications to the embodiments once they know the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present application.

[0123] Based on the technical solutions proposed in the present application, by obtaining the obstacle point cloud distribution map of the environment around the cleaning device, and based on the relative positional relationship between each obstacle point cloud and other obstacle point clouds in the obstacle point cloud distribution map, the wall corner point cloud can be accurately determined in the obstacle point cloud distribution map, i.e., the position of the wall corner can be accurately determined, and then the cleaning device can be accurately controlled to perform a wall corner cleaning action in the area where the wall corner point cloud is located, thereby improving the accuracy of cleaning the wall corner by the cleaning device.

[0124] In actual application, by combining the obstacle point cloud data, the present application effectively solves the deficiency of the traditional cleaning device in cleaning small corners, improves the cleaning efficiency and accuracy of the cleaning device in complex home environment, and brings a more convenient and efficient cleaning experience for the user.

[0125] The device embodiments of the present application are introduced below, which can be used to execute the cleaning device control method in the above-mentioned embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the above-mentioned embodiments of the cleaning device control method.

[0126] Referring to FIG. 6, a block diagram of a cleaning device control device in an embodiment of the present application is shown.

[0127] As shown in FIG. 6, the cleaning device control device 600 according to the embodiments of the present application comprises an obtaining unit 601, a determining unit 602 and a control unit 603.

[0128] The obtaining unit 601 is configured to obtain an obstacle point cloud distribution map of the environment around the cleaning device; the determining unit 602 is configured to determine a wall corner point cloud in the obstacle point cloud distribution map based on the relative positional relationship between each obstacle point cloud and other obstacle point clouds in the obstacle point cloud distribution map; and the control unit 603 is configured to control the cleaning device to perform a wall corner cleaning action in the area where the wall corner point cloud is located.

[0129] In some embodiments of the present application, based on the foregoing scheme, the obtaining unit 601 is configured to: obtain a plurality of frame point cloud images of the local environment around the cleaning device collected by a sensor mounted on the cleaning device; and integrate the plurality of frame point cloud images to obtain the obstacle point cloud distribution map of the environment around the cleaning device.

[0130] In some embodiments of the present application, based on the foregoing scheme, the acquisition unit 601 is further configured to: remove the noise point cloud in the point cloud image of the local environment around the cleaning equipment of each frame before integrating the plurality of frames of the point cloud image.

[0131] In some embodiments of the present application, based on the foregoing scheme, the determination unit 602 is configured to: traverse each obstacle point cloud in the obstacle point cloud distribution map, define a region of interest with the each obstacle point cloud as the region center in the obstacle point cloud distribution map; if the relative position relationship of the obstacle point cloud in the region of interest conforms to the wall corner geometric feature, determine the each obstacle point cloud as a candidate wall corner point cloud; and determine the wall corner point cloud in each candidate wall corner point cloud in the obstacle point cloud distribution map.

[0132] In some embodiments of the present application, based on the foregoing scheme, the determination unit 602 is further configured to: calculate the orientation difference feature value of each two reference obstacle point clouds relative to the each obstacle point cloud in the region of interest, the orientation difference feature value being used to represent the difference amplitude of the orientation of the each two reference obstacle point clouds relative to the each obstacle point cloud, the reference obstacle point cloud being the obstacle point cloud in the region of interest except the each obstacle point cloud; and if any one of the orientation difference feature values falls into a preset orientation difference feature value interval, determine that the relative position relationship of the obstacle point cloud in the region of interest conforms to the wall corner geometric feature.

[0133] In some embodiments of the present application, based on the foregoing scheme, the determination unit 602 is further configured to: traverse each candidate wall corner point cloud, determine the obstacle point cloud distributed in each extension direction with the each candidate wall corner point cloud as the starting point; and if the relative position relationship of the obstacle point cloud in two different extension directions conforms to the wall surface geometric feature, determine the each candidate wall corner point cloud as the wall corner point cloud.

[0134] In some embodiments of the present application, based on the foregoing scheme, the determination unit 602 is further configured to: perform straight line fitting on the obstacle point cloud in each extension direction respectively, and determine the distance between the first and last two obstacle point clouds on the fitted straight line; and if the distance between the first and last two obstacle point clouds on two different fitted straight lines both falls into a preset distance range, determine that the relative position relationship of the obstacle point cloud in two different extension directions conforms to the wall surface geometric feature.

[0135] In some embodiments of the present application, based on the foregoing scheme, the determining unit 602 is further configured to: perform linear fitting on the obstacle point cloud in each extension direction respectively, and determine the distance between the first and last obstacle point clouds on the fitted straight line; if the distance between the first and last obstacle point clouds on two different fitted straight lines both falls within a preset distance range, and the included angle of the two different fitted straight lines falls within a preset angle range, it is determined that the relative position relationship of the obstacle point clouds in the two different extension directions both conforms to the wall surface geometric feature.

[0136] In some embodiments of the present application, based on the foregoing scheme, the control unit 603 is configured to: calculate the distance between the cleaning device and the two different fitted straight lines; if the distance between the cleaning device and the two different fitted straight lines is both less than a first preset distance, control the cleaning device to perform a wall corner cleaning action in the area where the wall corner point cloud is located.

[0137] In some embodiments of the present application, based on the foregoing scheme, the control unit 603 is further configured to: if there is only one wall corner point cloud in the obstacle point cloud distribution map, control the cleaning device to perform a wall corner cleaning action in the area where the wall corner point cloud is located.

[0138] In some embodiments of the present application, based on the foregoing scheme, the control unit 603 is further configured to: before controlling the cleaning device to perform a wall corner cleaning action in the area where the wall corner point cloud is located, control the cleaning device to adjust its position until the distance to the wall surface corresponding to the wall corner point cloud on one side is a second preset distance, and the distance to the wall surface corresponding to the wall corner point cloud on the other side is a third preset distance, and control the cleaning device to adjust its orientation until it is parallel to the wall surface on one side.

[0139] In some embodiments of the present application, based on the foregoing scheme, the control unit 603 is further configured to: after controlling the cleaning device to adjust its orientation until it is parallel to the wall surface on one side, control the cleaning device to retreat by a fourth preset distance, and control the cleaning device to extend the side brush close to the wall surface on one side.

[0140] In some embodiments of the present application, based on the foregoing scheme, the control unit 603 is further configured to: control the cleaning device to travel in the current orientation; if the cleaning device travels to the wall corner position corresponding to the wall corner point cloud, control the cleaning device to retract the side brush close to the wall surface on one side, and control the cleaning device to adjust its orientation until it is parallel to the wall surface on the other side corresponding to the wall corner point cloud, to perform other cleaning tasks.

[0141] Based on the same inventive concept, the embodiment of the present application provides a computer program product, which comprises computer instructions stored in a computer readable storage medium and adapted to be read and executed by a processor to enable a computer device with the processor to perform operations performed by the cleaning device control method as described above.

[0142] Based on the same inventive concept, the embodiment of the present application provides a computer readable storage medium, which stores at least one computer program instruction, the at least one computer program instruction is loaded and executed by a processor to enable the processor to perform operations performed by the cleaning device control method as described above.

[0143] Based on the same inventive concept, the embodiment of the present application further provides a cleaning device, referring to FIG. 7, which shows a structural schematic diagram of the cleaning device in the embodiment of the present application, the cleaning device comprises one or more memories 704, one or more processors 702, and at least one computer program (computer program instructions) stored in the memory 704 and executable on the processor 702, and the processor 702 executes the computer program to implement the cleaning device control method as described above.

[0144] In FIG. 7, a bus architecture (represented by a bus 700) is included, the bus 700 can include any number of interconnected buses and bridges, the bus 700 links various circuits including one or more processors represented by the processor 702 and the memory represented by the memory 704. The bus 700 can also link various other circuits such as peripheral devices, voltage stabilizers and power management circuits, which are well known in the art, and thus, no further description is given herein. The bus interface 705 provides an interface between the bus 700 and the receiver 701 and the transmitter 703. The receiver 701 and the transmitter 703 can be the same element, i.e., a transceiver, which provides a unit for communicating with various other devices on a transmission medium. The processor 702 is responsible for managing the bus 700 and general processing, while the memory 704 can be used to store data used by the processor 702 in performing operations.

[0145] The functions described herein can be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions can be stored on or transferred over as one or more instructions or code on a computer-readable medium. Other examples and implementations are within the scope and spirit of the disclosure and appended claims. For example, due to the nature of software, functions described above can be implemented using software executed by a processor, hardware, firmware, hardwiring, or combinations of any of these. Features implementing functions can also be physically located at various positions, including being distributed such that portions of functions are implemented at different physical locations. Also, as used herein, including in the claims, "or" as used in a list of items prefaced by "comprising" to indicate a disjunctive list means each single item in the list has been recited before "or" one or more additional disjunctive items also appear in the list. Thus, the list of items formatted "comprising A, or B, or C" means: "A" has been recited, "B" has been recited, "C" has been recited, "A or B" has been recited, "A or C" has been recited, "B or C" has been recited or "A or B or C" has been recited. Further, as used herein, including in the claims, "comprising" or "comprise" means that other steps, options, features, structures, and / or components can be added. Also, as used herein, including in the claims, "exemplary" or "illustrative" means "serving as an example or illustration." As used herein, including in the claims, "or" as used in a list of items prefaced by "comprising" to indicate a disjunctive list means each single item in the list has been recited before "or" one or more additional disjunctive items also appear in the list. Thus, the list of items formatted "comprising A, or B, or C" means: "A" has been recited, "B" has been recited, "C" has been recited, "A or B" has been recited, "A or C" has been recited, "B or C" has been recited or "A or B or C" has been recited. Further, as used herein, including in the claims, "comprising" or "comprise" means that other steps, options, features, structures, and / or components can be added.

[0146] In several embodiments provided in the present application, it should be understood that the disclosed technology can be implemented by other ways. Among them, the above-mentioned device embodiments are only schematic, for example, the division of the units can be a logical function division, and other division ways can be used in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or modules shown or discussed can be indirect coupling or communication connection through some interfaces, units or modules, and can be electrical or other forms.

[0147] The units described as separate components can or can not be physically separate, and the components of the control device can or can not be physical units, i.e. can be located in one place or can be distributed on multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment.

[0148] The integrated units, if implemented in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the part of the prior art or the whole or part of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a plurality of instructions to make a computer device (which can be a personal computer, a server or a network device, etc.) execute all or part of the steps of the method described in the embodiments of the present application. The foregoing storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and various computer program instruction storage media.

[0149] The above merely provides an example of the present application, and is not intended to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall fall into the scope of claims of the present application.

Claims

1. A method for controlling cleaning equipment, characterized in that, The method includes: Obtain a point cloud distribution map of obstacles in the environment surrounding the cleaning equipment; Based on the relative positional relationship between each obstacle point cloud and other obstacle point clouds in the obstacle point cloud distribution map, corner point clouds are determined in the obstacle point cloud distribution map; The cleaning equipment is controlled to perform corner cleaning actions in the area where the corner point cloud is located.

2. The method according to claim 1, characterized in that, The acquisition of the obstacle point cloud distribution map of the environment surrounding the cleaning equipment includes: Acquire multiple frames of point cloud images of the local environment surrounding the cleaning equipment, collected by sensors installed on the cleaning equipment; By integrating multiple frames of the point cloud images, an obstacle point cloud distribution map of the environment surrounding the cleaning equipment is obtained.

3. The method according to claim 2, characterized in that, Before integrating the point cloud images from multiple frames, the method further includes: Remove noisy point clouds from the point cloud image of the local environment surrounding the cleaning equipment in each frame.

4. The method according to any one of claims 1-3, characterized in that, The step of determining the corner point cloud in the obstacle point cloud distribution map based on the relative positional relationship between each obstacle point cloud and other obstacle point clouds includes: Traverse each obstacle point cloud in the obstacle point cloud distribution map, and define a region of interest centered on each obstacle point cloud in the obstacle point cloud distribution map. If the relative positional relationship of the obstacle point clouds in the region of interest conforms to the corner geometry features, then each obstacle point cloud is determined as a candidate corner point cloud; The corner point cloud is determined from each candidate corner point cloud in the obstacle point cloud distribution map.

5. The method according to claim 4, characterized in that, The method further includes: Calculate the orientational difference feature value of each pair of reference obstacle point clouds relative to each individual obstacle point cloud in the region of interest. This orientational difference feature value is used to characterize each pair of reference obstacle point clouds. The difference in orientation of the cloud relative to each obstacle point cloud, wherein the reference obstacle point cloud is the obstacle point cloud in the region of interest other than each obstacle point cloud; If any of the said azimuth distinguishing feature values ​​falls within the preset azimuth distinguishing feature value range, then it is determined that the relative positional relationship of the obstacle point cloud in the region of interest conforms to the corner geometric features.

6. The method according to claim 4 or 5, characterized in that, Determining the corner point cloud from each candidate corner point cloud in the obstacle point cloud distribution map includes: Traverse each candidate corner point cloud and determine the obstacle point cloud distributed in each extension direction, starting from each candidate corner point cloud; If the relative positional relationship of the obstacle point clouds in two different extension directions both conform to the geometric features of the wall, then each candidate corner point cloud is determined as a corner point cloud.

7. The method according to claim 6, characterized in that, The method further includes: Straight line fitting is performed on the obstacle point clouds in each extension direction, and the distance between the first and last obstacle point clouds on the fitted line is determined. If the distance between the first and last obstacle point clouds on two different fitted lines both fall within a preset distance range, then the relative positional relationship of the obstacle point clouds in the two different extension directions is determined to conform to the geometric features of the wall.

8. The method according to claim 6, characterized in that, The method further includes: Straight line fitting is performed on the obstacle point clouds in each extension direction, and the distance between the first and last obstacle point clouds on the fitted line is determined. If the distance between the first and last obstacle point clouds on two different fitted lines both fall within a preset distance range, and the included angle of the two different fitted lines falls within a preset angle range, then the relative positional relationship of the obstacle point clouds in the two different extension directions is determined to conform to the geometric features of the wall.

9. The method according to claim 7 or 8, characterized in that, The method further includes: Calculate the distance between the cleaning equipment and the two different fitted lines; If the distance between the cleaning device and the two different fitted straight lines is less than the first preset distance, then the cleaning device is controlled to perform a corner cleaning action in the area where the corner point cloud is located.

10. The method according to any one of claims 1-9, characterized in that, The method further includes: If there is only one corner point cloud in the obstacle point cloud distribution map, then the cleaning device is controlled to perform corner cleaning action in the area where the corner point cloud is located.

11. The method according to any one of claims 1-10, characterized in that, Before controlling the cleaning device to perform corner cleaning actions in the area where the corner point cloud is located, the method further includes: The cleaning device is controlled to adjust its position until the distance to the wall on one side corresponding to the corner point cloud is a second preset distance, and the distance to the wall on the other side corresponding to the corner point cloud is a third preset distance, and the cleaning device is controlled to adjust its orientation until it is parallel to the wall on one side.

12. The method according to claim 11, characterized in that, After controlling the cleaning device to adjust its orientation until it is parallel to the side wall, the method further includes: Control the cleaning device to move a fourth preset distance away from the other side wall, and control the cleaning device to extend the side brush close to the other side wall.

13. The method according to claim 11 or 12, characterized in that, The control of the cleaning device to perform corner cleaning actions in the area where the corner point cloud is located includes: Control the cleaning equipment to move in the current orientation; If the cleaning device moves to the corner position corresponding to the corner point cloud, the cleaning device is controlled to retract the side brush close to the wall on that side, and the cleaning device is controlled to adjust its orientation until it is parallel to the other wall corresponding to the corner point cloud, so as to perform other cleaning tasks.

14. A cleaning equipment control device, characterized in that, The device includes: The acquisition unit is used to acquire a point cloud distribution map of obstacles in the environment surrounding the cleaning equipment; The determining unit is used to determine the corner point cloud in the obstacle point cloud distribution map based on the relative positional relationship between each obstacle point cloud and other obstacle point clouds in the obstacle point cloud distribution map; The control unit is used to control the cleaning equipment to perform corner cleaning actions in the area where the corner point cloud is located.

15. A computer program product, characterized in that, The computer program product includes computer instructions stored in a computer-readable storage medium and adapted to be read and executed by a processor to cause a computer device having the processor to perform the method as claimed in any one of claims 1 to 13.

16. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one piece of program code, which is loaded and executed by a processor to perform the operations performed by the method as described in any one of claims 1 to 13.

17. A cleaning device, characterized in that, The cleaning device includes one or more processors and one or more memories, wherein at least one piece of program code is stored in the one or more memories, and the at least one piece of program code is loaded and executed by the one or more processors to implement the method as claimed in any one of claims 1 to 13.

Images