A method, device and equipment for detecting a wire in a base station of a floor sweeping machine and a storage medium

Abstract

The application discloses a method, device and equipment for detecting a center line of a base station of a sweeping machine and a storage medium. The method comprises the following steps: registering point clouds obtained by the sweeping machine according to a preset base station contour shape, and obtaining actual point clouds after registration; performing equidistant interpolation on the actual point clouds, and obtaining base station point clouds after interpolation; clustering the base station point clouds into different contour parts according to the base station contour shape and a preset point cloud clustering algorithm; performing linear fitting on the point clouds of the different contour parts after clustering respectively by using a preset linear fitting algorithm; determining a base station contour according to the fitted straight lines; and calculating the center line of the base station according to the determined base station contour. The method can accurately detect the center line of the base station and ensure the accuracy of the route of the sweeping machine returning to the base station.

Description

Technical Field

[0001] This invention relates to the field of cleaning equipment technology, and in particular to a method, apparatus, equipment and storage medium for detecting the centerline of a sweeper base station. Background Technology

[0002] With the rapid development of technology, cleaning equipment has been widely used in daily life. As a type of mobile device with intelligent cleaning planning capabilities, cleaning equipment can autonomously plan cleaning routes and the sequence of cleaning tasks.

[0003] Existing robotic vacuum cleaners generally use infrared lights to automatically align with charging stations or base stations to achieve automatic charging or water replacement functions. However, the infrared signal from the base station is sometimes blocked by surrounding walls or obstacles, making it unstable. In addition, the robotic vacuum cleaner needs to go through a series of special movements to detect the base station's infrared signal, which often results in the robotic vacuum cleaner not moving smoothly back to the base station and returning at an angle. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and storage medium for detecting the centerline of a sweeper base station, which can accurately detect the centerline of the base station and ensure the accuracy of the sweeper's route back to the base station.

[0005] This invention provides a method for detecting the centerline of a robot vacuum cleaner base station, the method comprising:

[0006] The point cloud acquired by the sweeping robot is registered according to the preset base station outline shape to obtain the registered actual point cloud;

[0007] The actual point cloud is interpolated at equal intervals to obtain the interpolated base point cloud;

[0008] Based on the base station outline shape and a preset point cloud clustering algorithm, the base station point cloud is clustered into different outline parts;

[0009] A preset line fitting algorithm is used to perform line fitting on the point clouds of different contour parts after clustering.

[0010] The base station outline is determined based on the fitted straight line, and the base station centerline is calculated based on the determined base station outline.

[0011] Preferably, the method further includes:

[0012] If the current position of the sweeping machine is less than the real-time distance between the latest base station centerline and the sweeping machine is less than a preset threshold, then if not, the sweeping machine is controlled to move closer to the base station centerline and the point cloud is reacquired. The reacquired point cloud is then registered, interpolated at equal intervals, clustered and fitted with straight lines to update the base station centerline until the current position of the sweeping machine is less than the threshold.

[0013] When the real-time distance is less than the threshold, the latest base station centerline is taken as the accurate base station centerline.

[0014] As a preferred embodiment, the step of registering the point cloud acquired by the sweeping machine according to the preset base station outline shape to obtain the registered actual point cloud specifically includes:

[0015] Using the pre-acquired base station location as the center, a circular filtering area is planned with a preset filtering radius. This circular filtering area is used to filter the laser point cloud acquired by the sweeping robot, and the laser point cloud within the circular filtering area is stored as the original point cloud. The filtering radius is not less than the radius of the base station.

[0016] The original point cloud is registered to match the actual point cloud that corresponds to the outline shape of the base station.

[0017] Preferably, the step of performing equidistant interpolation on the actual point cloud to obtain the interpolated base point cloud specifically includes:

[0018] Calculate the distance between two adjacent points in the actual point cloud;

[0019] When the distance between two adjacent points is not less than a preset value, interpolation is performed between the two points at equal intervals.

[0020] As a preferred embodiment, the step of clustering the base station cloud into different contour parts based on the base station contour shape and a preset point cloud clustering algorithm specifically includes:

[0021] The Kmeans point cloud clustering algorithm is used to divide the base station point cloud into two side parts and one bottom part according to the U-shaped base station outline shape, and preliminary clustering is performed to obtain the point cloud around the two side parts and the bottom part.

[0022] The Gaussian mixture clustering algorithm is used to perform precise clustering on the initially clustered point cloud, resulting in the left side point cloud, right side point cloud, and bottom side point cloud after clustering.

[0023] Furthermore, the step of using a preset straight-line fitting algorithm to perform straight-line fitting on the point clouds of different contour parts after clustering specifically includes:

[0024] The RANSAC line fitting algorithm is used to fit the left side line corresponding to the left side point cloud. Further, the base station outline is determined based on the fitted lines, and the base station centerline is calculated based on the determined base station outline. Specifically, this includes:

[0025] The left side line, the right side line, and the bottom line are used as the outline of the base station;

[0026] Calculate the center line of symmetry of the two side lines based on the left side line and the right side line;

[0027] Draw a straight line passing through the midpoint of the straight line at the bottom edge, with the same slope as the center line of symmetry, and use it as the center line of the base station.

[0028] This invention also provides a centerline detection device for a robot vacuum cleaner base station, the device comprising:

[0029] The point cloud registration module is used to register the point cloud acquired by the sweeping machine according to the preset base station outline shape, and obtain the registered actual point cloud.

[0030] The point cloud interpolation module is used to perform equidistant interpolation on the actual point cloud to obtain the interpolated base point cloud.

[0031] The clustering module is used to cluster the base station cloud into different contour parts according to the base station contour shape and a preset point cloud clustering algorithm;

[0032] The line fitting module is used to perform line fitting on the point clouds of different contour parts after clustering using a preset line fitting algorithm.

[0033] The centerline calculation module is used to determine the base station outline based on the fitted straight line, and to calculate the base station centerline based on the determined base station outline.

[0034] As an improvement to the above solution, the device further includes an optimization module for:

[0035] If the current position of the sweeping machine is less than the real-time distance between the latest base station centerline and the sweeping machine is less than a preset threshold, then if not, the sweeping machine is controlled to move closer to the base station centerline and the point cloud is reacquired. The reacquired point cloud is then registered, interpolated at equal intervals, clustered and fitted with straight lines to update the base station centerline until the current position of the sweeping machine is less than the threshold.

[0036] When the real-time distance is less than the threshold, the latest base station centerline is taken as the accurate base station centerline.

[0037] Preferably, the point cloud registration module is specifically used for:

[0038] Using the pre-acquired base station location as the center, a circular filtering area is planned with a preset filtering radius. This circular filtering area is used to filter the laser point cloud acquired by the sweeping robot, and the laser point cloud within the circular filtering area is stored as the original point cloud. The filtering radius is not less than the radius of the base station.

[0039] The original point cloud is registered to match the actual point cloud that corresponds to the outline shape of the base station.

[0040] As a preferred embodiment, the point cloud interpolation module is specifically used for:

[0041] Calculate the distance between two adjacent points in the actual point cloud;

[0042] When the distance between two adjacent points is not less than a preset value, interpolation is performed between the two points at equal intervals.

[0043] Preferably, the clustering module is specifically used for:

[0044] The Kmeans point cloud clustering algorithm is used to divide the base station point cloud into two side parts and one bottom part according to the U-shaped base station outline shape, and preliminary clustering is performed to obtain the point cloud around the two side parts and the bottom part.

[0045] The Gaussian mixture clustering algorithm is used to perform precise clustering on the initially clustered point cloud, resulting in the left side point cloud, right side point cloud, and bottom side point cloud after clustering.

[0046] Furthermore, the line fitting module is specifically used for:

[0047] The RANSAC line fitting algorithm is used to fit the left side line corresponding to the left side point cloud, the right side line corresponding to the right side point cloud, and the bottom side line corresponding to the bottom side point cloud.

[0048] Furthermore, the centerline calculation module is specifically used for:

[0049] The left side line, the right side line, and the bottom line are used as the outline of the base station;

[0050] Calculate the center line of symmetry of the two side lines based on the left side line and the right side line;

[0051] Draw a straight line passing through the midpoint of the straight line at the bottom edge, with the same slope as the center line of symmetry, and use it as the center line of the base station.

[0052] This invention also provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a centerline detection method for a sweeping robot base station as described in any of the above embodiments.

[0053] This invention also provides a computer-readable storage medium, which includes a stored computer program, wherein the computer program, when running, controls the device where the computer-readable storage medium is located to execute a sweeping robot base station centerline detection method as described in any of the above embodiments.

[0054] This invention provides a method, apparatus, device, and storage medium for detecting the centerline of a robot vacuum cleaner's base station. The method involves registering a point cloud acquired by the robot vacuum cleaner with a preset base station outline shape to obtain a registered actual point cloud; performing equidistant interpolation on the actual point cloud to obtain an interpolated base station cloud; clustering the base station cloud into different outline parts based on the base station outline shape and a preset point cloud clustering algorithm; applying a preset straight line fitting algorithm to the point clouds of the different clustered outline parts using straight lines; determining the base station outline based on the fitted straight lines; and calculating the base station centerline based on the determined base station outline. This method can accurately detect the base station centerline, ensuring the accuracy of the robot vacuum cleaner's route back to the base station. Attached Figure Description

[0055] Figure 1 This is a flowchart illustrating a method for detecting the centerline of a robot vacuum cleaner base station according to an embodiment of the present invention;

[0056] Figure 2 This is a flowchart illustrating a method for detecting the centerline of a sweeping robot base station according to another embodiment of the present invention;

[0057] Figure 3 This is a schematic diagram of a laser point cloud provided in an embodiment of the present invention;

[0058] Figure 4 This is a schematic diagram of the structure of a centerline detection device for a sweeping machine base station provided in an embodiment of the present invention;

[0059] Figure 5 This is a schematic diagram of the structure of a terminal device provided in an embodiment of the present invention. Detailed Implementation

[0060] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0061] This invention provides a method for detecting the centerline of a robot vacuum cleaner base station, see [link / reference]. Figure 1 The diagram shown is a flowchart illustrating a method for detecting the centerline of a robot vacuum cleaner base station according to an embodiment of the present invention. The method includes steps S1 to S5:

[0062] S1, Register the point cloud acquired by the sweeping machine according to the preset base station outline shape to obtain the registered actual point cloud;

[0063] S2, perform equidistant interpolation on the actual point cloud to obtain the interpolated base point cloud;

[0064] S3, based on the base station outline shape and a preset point cloud clustering algorithm, the base station cloud is clustered into different outline parts;

[0065] S4, a preset straight line fitting algorithm is used to perform straight line fitting on the point clouds of different contour parts after clustering.

[0066] S5. Determine the base station outline based on the fitted straight line, and calculate the base station centerline based on the determined base station outline.

[0067] In the specific implementation of this embodiment, when performing base station centerline detection, it is first necessary to obtain laser point cloud images around the sweeping robot base station. The sweeping robot obtains the corresponding point cloud images through the configured lidar.

[0068] When centerline detection is required, the point cloud information of the base station contained in the acquired point cloud image needs to be extracted first to reduce the amount of laser point cloud data that needs to be processed during centerline detection. The point cloud registration method is used to obtain the actual point cloud after registration with the outline shape of the base station. The actual point cloud contains the point cloud information of the base station, which is used for subsequent base station centerline detection.

[0069] Equidistant interpolation is performed on the registered actual point cloud to ensure that the point cloud is evenly distributed, thus avoiding clustering bias caused by the unevenness of the actual point cloud.

[0070] The base station's point cloud is clustered using a point cloud clustering algorithm based on the base station's outline shape. During the clustering process, the base station's outline shape needs to be referenced for clustering. The point cloud of different outline parts in the base station is clustered according to the base station's outline shape. For example, the base station's outline shape may be square, U-shaped, or other shapes. The clustering results will be different depending on the characteristics of different shapes.

[0071] Line fitting is performed on the point clouds clustered into different contour parts to obtain the fitted lines. Since the base station contour is a straight line, when performing base station centerline detection, it is necessary to fit the corresponding straight line as the base station contour, and then determine the base station centerline based on the fitted straight line.

[0072] By performing registration, isometric interpolation, cluster analysis, and line fitting on the acquired point cloud, the base station outline is determined. Based on the base station outline, geometric calculations are performed to accurately detect the base station centerline, ensuring the accuracy of the sweeping robot's route back to the base station.

[0073] In another embodiment provided by the present invention, the method further includes:

[0074] If the current position of the sweeping machine is less than the real-time distance between the latest base station centerline and the sweeping machine is less than a preset threshold, then if not, the sweeping machine is controlled to move closer to the base station centerline and the point cloud is reacquired. The reacquired point cloud is then registered, interpolated at equal intervals, clustered and fitted with straight lines to update the base station centerline until the current position of the sweeping machine is less than the threshold.

[0075] When the real-time distance is less than the threshold, the latest base station centerline is taken as the accurate base station centerline.

[0076] In the specific implementation of this embodiment, please refer to Figure 2 This is a flowchart illustrating a method for detecting the centerline of a sweeping machine base station according to another embodiment of the present invention.

[0077] The following steps need to be performed when conducting centerline detection:

[0078] S201, acquire point cloud and configure point cloud, that is, register the point cloud acquired by the sweeping machine according to the preset base station outline shape to obtain the registered actual point cloud;

[0079] S202, perform equidistant interpolation, that is, perform equidistant interpolation on the registered actual point cloud to obtain the interpolated base point cloud;

[0080] S203, perform cluster analysis, that is, use a preset point cloud clustering algorithm to perform cluster analysis on the interpolated base station cloud according to the base station outline, and divide the base station cloud into different outline parts;

[0081] S204, perform line fitting, that is, use a preset line fitting algorithm to fit the line containing the point cloud of different contour parts.

[0082] S205, Calculate the base station centerline. Calculate the base station centerline based on the base station profile composed of straight lines from different contour parts.

[0083] S206, determine whether the real-time distance is less than the preset threshold, that is, calculate the real-time distance between the current position of the sweeping robot and the center line of the base station, and make a judgment;

[0084] If not, proceed to step S207; if yes, proceed to step S208.

[0085] S207, Base station centerline tracking control, that is, controlling the sweeper to move closer to the determined base station centerline, and returning to step S201;

[0086] S208, Determine the precise base station centerline, that is, take the latest base station centerline as the precise base station centerline.

[0087] During the centerline detection process, the sweeping robot cannot initially scan the precise point cloud of the base station outline. Therefore, the centerline of the base station obtained at this time is not accurate enough and has a certain deviation from the real baseline. However, the basic orientation of the centerline determined at this time is near the real base station centerline. As the sweeping robot continuously tracks the centerline detected in real time, it continuously updates the point cloud around it, which contains an increasingly precise point cloud of the base station outline.

[0088] Based on the continuously updated point cloud near the sweeping robot in S205, S201 to S205 are repeated, and the obtained base station centerline gets closer and closer to the real base station centerline, until the distance between the sweeping robot and the calculated base station centerline is less than the preset threshold. At this point, it means that the obtained base station centerline is infinitely close to the real base station centerline, so the base station centerline detection process is exited and the latest base station centerline is taken as the accurate base station centerline; otherwise, the centerline detection process continues.

[0089] By continuously tracking the real-time detected base station centerline, and without directly approximating the actual base station centerline, the accuracy of the obtained base station centerline can be further optimized.

[0090] In another embodiment provided by the present invention, step S1 specifically includes:

[0091] Using the pre-acquired base station location as the center, a circular filtering area is planned with a preset filtering radius. The laser point cloud acquired by the sweeping machine is filtered using the circular filtering area, and the laser point cloud within the circular filtering area is stored as the original point cloud. The filtering radius is not less than the radius of the base station.

[0092] The original point cloud is registered to match the actual point cloud that corresponds to the outline shape of the base station.

[0093] In this specific implementation, the laser radar configured on the sweeping robot scans the approximate location of the base station to obtain laser point clouds in the corresponding direction. (See [link to relevant documentation]). Figure 3 This is a schematic diagram of a laser point cloud provided in an embodiment of the present invention. The initially acquired laser point cloud contains a large amount of irrelevant data, which increases the amount of data required for subsequent centerline detection and increases the difficulty of centerline detection.

[0094] Therefore, this application uses the base station location O as the center and a preset filtering radius r to plan a circular filtering area A, which can encompass the entire base station.

[0095] The pre-acquired base station location is either the base station location stored in the robot vacuum cleaner's database or a rough location of the base station determined through real-time positioning; the filtering radius is set in advance based on the radius of the base station, and the filtering radius is generally set by a magnification factor based on the base station radius to ensure that no base station cloud point data is missed.

[0096] The laser point cloud acquired by the sweeping machine is filtered using a circular filtering area A, and the laser point cloud within the circular filtering area is stored as the original point cloud.

[0097] The original point cloud is registered to match the actual point cloud that corresponds to the outline shape of the base station.

[0098] It should be noted that when performing registration, existing registration schemes can be used to register the point cloud and the base station outline shape to ensure the accuracy of the actual point cloud.

[0099] By defining the filtering region and registering it according to the base station outline shape, the amount of data processed is reduced, the accuracy of the point cloud is improved, and the accuracy of the base station centerline calculated subsequently is increased.

[0100] In another embodiment provided by the present invention, step S2 specifically includes:

[0101] Calculate the distance between two adjacent points in the actual point cloud;

[0102] When the distance between two adjacent points is not less than a preset value, interpolation is performed between the two points at equal intervals.

[0103] In the specific implementation of this embodiment, the actual point cloud obtained after filtering and matching may have uneven point distribution, which may lead to deviations in subsequent clustering analysis.

[0104] Therefore, before performing cluster analysis, it is necessary to calculate the distance between two adjacent points in the actual point cloud. The method for determining two adjacent points is to determine two adjacent points in sequence along the direction of the base station outline based on the registered point cloud.

[0105] When the distance between two adjacent points is not less than a preset value, perform equal-interval interpolation between the two points;

[0106] No action is taken when the distance between two adjacent points is less than a preset value;

[0107] By interpolating between two points that are too far apart, the distribution of the base station cloud is ensured to be uniform, thus improving the accuracy of cluster analysis.

[0108] In another embodiment provided by the present invention, step S3 specifically includes:

[0109] The Kmeans point cloud clustering algorithm is used to divide the base station point cloud into two side parts and one bottom part according to the U-shaped base station outline shape, and preliminary clustering is performed to obtain the point cloud around the two side parts and the bottom part.

[0110] The Gaussian mixture clustering algorithm is used to perform precise clustering on the initially clustered point cloud, resulting in the left side point cloud, right side point cloud, and bottom side point cloud after clustering.

[0111] In this specific implementation, the base station outline of the sweeping robot is "U" shaped. The base station cloud is divided into two side parts and one bottom part. Based on the interpolated base station cloud, the Kmeans point cloud clustering algorithm is used to initially cluster the base station cloud into 3 types of point clouds. The 3 types of point clouds are the point clouds near the two sides and the bottom of the base station, respectively.

[0112] The Gaussian Mixture Model (GMM) clustering algorithm is used to perform precise clustering on the initially clustered point cloud, thereby accurately clustering the three segments of point cloud corresponding to the two sides and one bottom edge of the base station into one class, resulting in the clustered left side point cloud, right side point cloud, and bottom edge point cloud.

[0113] It should be noted that the clustering result is determined based on the base station outline shape. Using base stations with different outline shapes, different outline parts are divided, and the base station cloud is clustered into different point cloud parts. For example, a base station with a square base station outline shape will be clustered into cluster parts of the four sides. This embodiment discloses the U-shaped base station outline shape commonly used in the prior art to facilitate the sweeping robot to return to the base station. In other embodiments, base stations with other outline shapes are used, and the working process is similar, which will not be described in detail here.

[0114] Cluster analysis is used to determine the point cloud of different parts of the base station outline, which facilitates subsequent fitting of the outline of different parts based on straight line fitting, so as to determine the centerline of the base station.

[0115] In another embodiment provided by the present invention, step S4 specifically includes:

[0116] The RANSAC line fitting algorithm is used to fit the left side line corresponding to the left side point cloud, the right side line corresponding to the right side point cloud, and the bottom side line corresponding to the bottom side point cloud.

[0117] In this specific implementation, based on the left side point cloud, right side point cloud and bottom side point cloud obtained in the above embodiments, the RANSAC straight line fitting algorithm is used to fit the left side straight line L corresponding to the left side point cloud, the right side straight line R corresponding to the right side point cloud and the bottom side straight line H corresponding to the bottom side point cloud, respectively, to obtain different contour parts of the base station.

[0118] Linear fitting can accurately determine different contour parts of a base station, so that the accurate base station centerline can be determined through geometric calculations.

[0119] In another embodiment provided by the present invention, step S5 specifically includes:

[0120] The left side line, the right side line, and the bottom line are used as the outline of the base station;

[0121] Calculate the center line of symmetry of the two side lines based on the left side line and the right side line;

[0122] Draw a straight line passing through the midpoint of the straight line at the bottom edge, with the same slope as the center line of symmetry, and use it as the center line of the base station.

[0123] In this specific implementation, the corresponding base station centerline can be calculated based on the obtained left side line L, right side line R, and bottom line H. The calculation method is as follows:

[0124] First, calculate the center line S of symmetry between the two lines based on the left side line L and the right side line R. Then, determine the midpoint I of the bottom line H. Based on the midpoint I and the center line S, obtain a base station center line J that passes through the midpoint I and maintains the same slope as the center line S by translating the center line S.

[0125] By analyzing the obtained side and bottom straight lines, the accurate centerline of the base station can be determined.

[0126] See Figure 4 This is a schematic diagram of a centerline detection device for a sweeping robot base station provided in an embodiment of the present invention. The device includes:

[0127] The point cloud registration module is used to register the point cloud acquired by the sweeping machine according to the preset base station outline shape, and obtain the registered actual point cloud.

[0128] The point cloud interpolation module is used to perform equidistant interpolation on the actual point cloud to obtain the interpolated base point cloud.

[0129] The clustering module is used to cluster the base station cloud into different contour parts according to the base station contour shape and a preset point cloud clustering algorithm;

[0130] The line fitting module is used to perform line fitting on the point clouds of different contour parts after clustering using a preset line fitting algorithm.

[0131] The centerline calculation module is used to determine the base station outline based on the fitted straight line, and to calculate the base station centerline based on the determined base station outline.

[0132] The sweeper base station centerline detection device provided in this embodiment can perform all the steps and functions of the sweeper base station centerline detection method provided in any of the above embodiments. The specific functions of the device will not be described in detail here.

[0133] See Figure 5This is a schematic diagram of a terminal device provided in an embodiment of the present invention. The terminal device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, such as a centerline detection program for a robotic vacuum cleaner base station. When the processor executes the computer program, it implements the steps in the various embodiments of the above-described method for centerline detection of a robotic vacuum cleaner base station, for example... Figure 1 The steps S1 to S5 are shown. Alternatively, when the processor executes the computer program, it implements the functions of each module in the above-described device embodiments.

[0134] For example, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program in the sweeping robot base station centerline detection device. For example, the computer program can be divided into various modules, the specific functions of which have been described in detail in the sweeping robot base station centerline detection method provided in any of the above embodiments; therefore, the specific functions of this device will not be repeated here.

[0135] The aforementioned centerline detection device for a robotic vacuum cleaner base station can be a computing device such as a desktop computer, laptop, handheld computer, or cloud server. This device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the schematic diagram is merely an example of a robotic vacuum cleaner base station centerline detection device and does not constitute a limitation on such a device. It may include more or fewer components than illustrated, or combine certain components, or use different components. For example, the robotic vacuum cleaner base station centerline detection device may also include input / output devices, network access devices, buses, etc.

[0136] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. This processor is the control center of the sweeping robot base station centerline detection device, connecting all parts of the device via various interfaces and lines.

[0137] The memory can be used to store the computer program and / or modules. The processor implements various functions of the sweeping robot base station centerline detection device by running or executing the computer program and / or modules stored in the memory and calling the data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital card (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0138] If the module integrated into the sweeping robot base station centerline detection device is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately added to or subtracted from the content as required by the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium may not include electrical carrier signals and telecommunication signals.

[0139] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for detecting the centerline of a sweeping robot base station, characterized in that, The method includes: The point cloud acquired by the sweeping robot is registered according to the preset base station outline shape to obtain the registered actual point cloud; The actual point cloud is interpolated at equal intervals to obtain the interpolated base point cloud; Based on the base station outline shape and a preset point cloud clustering algorithm, the base station point cloud is clustered into different outline parts; A preset line fitting algorithm is used to perform line fitting on the point clouds of different contour parts after clustering. The base station outline is determined based on the fitted straight line, and the base station centerline is calculated based on the determined base station outline. The step of clustering the base station cloud into different contour parts based on the base station contour shape and a preset point cloud clustering algorithm specifically includes: The Kmeans point cloud clustering algorithm is used to divide the base station point cloud into two side parts and one bottom part according to the U-shaped base station outline shape, and preliminary clustering is performed to obtain the point cloud around the two side parts and the bottom part. Gaussian mixture clustering algorithm is used to perform precise clustering on the initially clustered point cloud, resulting in the left side point cloud, right side point cloud and bottom side point cloud after clustering; The step of using a preset straight-line fitting algorithm to perform straight-line fitting on the point clouds of different contour parts after clustering specifically includes: The RANSAC line fitting algorithm is used to fit the left side line corresponding to the left side point cloud, the right side line corresponding to the right side point cloud, and the bottom side line corresponding to the bottom side point cloud, respectively. The process of determining the base station profile based on the fitted straight line and calculating the base station centerline based on the determined base station profile specifically includes: The left side line, the right side line, and the bottom line are used as the outline of the base station; Calculate the center line of symmetry of the two side lines based on the left side line and the right side line; Draw a straight line passing through the midpoint of the straight line at the bottom edge, with the same slope as the center line of symmetry, and use it as the center line of the base station.

2. The method for detecting the centerline of a sweeping robot base station as described in claim 1, characterized in that, The method further includes: If the current position of the sweeping machine is less than the real-time distance between the latest base station centerline and the sweeping machine is less than a preset threshold, then if not, the sweeping machine is controlled to move closer to the base station centerline and the point cloud is reacquired. The reacquired point cloud is then registered, interpolated at equal intervals, clustered and fitted with straight lines to update the base station centerline until the current position of the sweeping machine is less than the threshold. When the real-time distance is less than the threshold, the latest base station centerline is taken as the accurate base station centerline.

3. The method for detecting the centerline of a sweeping robot base station as described in claim 1 or 2, characterized in that, The process of registering the point cloud acquired by the sweeping machine according to the preset base station outline shape to obtain the registered actual point cloud specifically includes: Using the pre-acquired base station location as the center, a circular filtering area is planned with a preset filtering radius. This circular filtering area is used to filter the laser point cloud acquired by the sweeping robot, and the laser point cloud within the circular filtering area is stored as the original point cloud. The filtering radius is not less than the radius of the base station. The original point cloud is registered to match the actual point cloud that corresponds to the outline shape of the base station.

4. The method for detecting the centerline of a sweeping machine base station as described in claim 1 or 2, characterized in that, The step of performing equidistant interpolation on the actual point cloud to obtain the interpolated base point cloud specifically includes: Calculate the distance between two adjacent points in the actual point cloud; When the distance between two adjacent points is not less than a preset value, interpolation is performed between the two points at equal intervals.

5. A centerline detection device for a sweeper base station, characterized in that, The device includes: The point cloud registration module is used to register the point cloud acquired by the sweeping machine according to the preset base station outline shape, and obtain the registered actual point cloud. The point cloud interpolation module is used to perform equidistant interpolation on the actual point cloud to obtain the interpolated base point cloud. The clustering module is used to cluster the base station cloud into different contour parts based on the base station contour shape and a preset point cloud clustering algorithm; The line fitting module is used to perform line fitting on the point clouds of different contour parts after clustering using a preset line fitting algorithm. The centerline calculation module is used to determine the base station outline based on the fitted straight line, and to calculate the base station centerline based on the determined base station outline. The step of clustering the base station cloud into different contour parts based on the base station contour shape and a preset point cloud clustering algorithm specifically includes: The Kmeans point cloud clustering algorithm is used to divide the base station point cloud into two side parts and one bottom part according to the U-shaped base station outline shape, and preliminary clustering is performed to obtain the point cloud around the two side parts and the bottom part. Gaussian mixture clustering algorithm is used to perform precise clustering on the initially clustered point cloud, resulting in the left side point cloud, right side point cloud and bottom side point cloud after clustering; The step of using a preset straight-line fitting algorithm to perform straight-line fitting on the point clouds of different contour parts after clustering specifically includes: The RANSAC line fitting algorithm is used to fit the left side line corresponding to the left side point cloud, the right side line corresponding to the right side point cloud, and the bottom side line corresponding to the bottom side point cloud, respectively. The process of determining the base station profile based on the fitted straight line and calculating the base station centerline based on the determined base station profile specifically includes: The left side line, the right side line, and the bottom line are used as the outline of the base station; Calculate the center line of symmetry of the two side lines based on the left side line and the right side line; Draw a straight line passing through the midpoint of the straight line at the bottom edge, with the same slope as the center line of symmetry, and use it as the center line of the base station.

6. A terminal device, characterized in that, The system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the centerline detection method for a sweeping robot base station as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the sweeper base station centerline detection method as described in any one of claims 1 to 4.

Images