Photovoltaic sweeper positioning method and system, computer equipment and storage medium

Abstract

The invention relates to a photovoltaic sweeper positioning method and system, computer equipment and a storage medium. The method comprises the following steps: collecting at least one frame of point cloud information of the photovoltaic sweeper in a current working scene by using a laser radar; noise filtering is performed based on the point cloud information, and the point cloud information of the region of interest is extracted; acquiring plane parameters of a plane where the reflective sticker is located, and performing plane filtering on the point cloud information of the region of interest to obtain point cloud information of a target region; wherein the target area point cloud information comprises multiple clusters of point clouds, and each cluster of point clouds corresponds to one reflective sticker; calculating the center of mass of each cluster of point clouds, and creating an original point under a laser radar coordinate system based on the actual position of each reflective sticker; and the mass centers are matched with the original points, the conversion relation between the mass centers and the original points is obtained through extraction, and the position of the photovoltaic sweeper in the laser radar coordinate system is obtained based on the conversion relation. By adopting the method, accurate positioning of the photovoltaic sweeper can be realized.

Description

Technical Field

[0001] This application relates to the technical field of photovoltaic robots, and particularly to a positioning method, system, computer device, and storage medium for a photovoltaic sweeper. Background Art

[0002] With the global emphasis on renewable energy, photovoltaic power generation, as a clean and sustainable energy form, is rapidly popularizing. The development of intelligent and automated photovoltaic modules has made a positive contribution to the wide application and sustainable development of renewable energy.

[0003] To ensure the efficient operation of photovoltaic modules during long-term use, regular cleaning and maintenance work are crucial. However, traditional cleaning methods usually rely on manual operation, with low efficiency and uncertainty, making it difficult to meet the maintenance requirements of large-scale photovoltaic power generation systems. Summary of the Invention

[0004] Based on this, in view of the above technical problems, it is necessary to provide a positioning method, system, computer device, and storage medium for a photovoltaic sweeper that can adaptively locate the position of the photovoltaic sweeper, improve the positioning accuracy of the sweeper, and achieve automated cleaning and maintenance of large-scale photovoltaic power generation systems.

[0005] In a first aspect, this application provides a positioning method for a photovoltaic sweeper, on which at least one group of reflective stickers is arranged. The method includes:

[0006] Using a lidar to collect at least one frame of point cloud information of the photovoltaic sweeper in the current working scenario;

[0007] Based on the point cloud information, perform noise filtering to extract the point cloud information of the region of interest;

[0008] Obtain the plane parameters of the plane where the reflective sticker is located, perform plane filtering on the point cloud information of the region of interest, and extract the point cloud information of the target region; wherein, the point cloud information of the target region includes multiple clusters of point clouds, and each cluster of point clouds corresponds to one reflective sticker;

[0009] Calculate the centroid of each cluster of point clouds, and based on the actual positions of the reflective stickers, create the original points in the lidar coordinate system;

[0010] Match the centroid with the original point to obtain the conversion relationship between each centroid and each original point, and based on the conversion relationship, obtain the position of the photovoltaic sweeper in the lidar coordinate system.

[0011] In one embodiment, obtaining the plane parameters of the plane where the reflective sticker is located and performing plane filtering on the point cloud information of the region of interest to extract the target region point cloud information includes:

[0012] Obtain the plane parameters of the plane where the reflective sticker is located;

[0013] Obtain the point coordinates of each point cloud in the point cloud information of the region of interest;

[0014] According to the plane parameters, calculate the distance from each point cloud to the plane where the reflective sticker is located. If the distance is less than zero, delete it; otherwise, retain it to obtain the plane point cloud information of the plane where the reflective sticker is located;

[0015] Extract the target region point cloud information according to the plane point cloud information.

[0016] In one embodiment, extracting the target region point cloud information according to the plane point cloud information includes:

[0017] Calculate the intensity information of each point cloud in the plane point cloud information, and determine whether the intensity information of each point cloud is greater than a set threshold. If it is less, delete it; otherwise, retain it to extract the target region point cloud information.

[0018] In one embodiment, calculating the centroid of each cluster of the point clouds includes:

[0019] Obtain the point coordinates of each point cloud in each cluster of the point clouds. The point coordinates include the first axis coordinate parameter, the second axis coordinate parameter, and the third axis coordinate parameter;

[0020] Calculate the average value of the first axis coordinate parameters, the average value of the second axis coordinate parameters, and the average value of the third axis coordinate parameters of all the point clouds in each cluster of the point clouds to obtain the centroid of each cluster of the point clouds.

[0021] In one embodiment, creating the original points in the lidar coordinate system based on the actual positions of the reflective stickers includes:

[0022] Taking the position of the lidar as the origin and corresponding to the actual positions of the reflective stickers, sequentially establish a plurality of the original points.

[0023] In one embodiment, the conversion relationship includes an offset relationship and a rotation relationship about an axis; matching the centroid with the original point, extracting the conversion relationship between each centroid and each original point, and obtaining the position of the photovoltaic sweeper in the lidar coordinate system based on the conversion relationship includes:

[0024] Matching the center of mass with the original point to obtain the offset relationship and rotation relationship around the axis of each reflective sticker in the laser radar coordinate system;

[0025] The rotational relationship around the axis includes rotational relationships around the first axis, around the second axis, and around the third axis respectively;

[0026] The position of the photovoltaic sweeper in the laser radar coordinate system is generated according to the offset relationship and the axis rotation relationship.

[0027] In one embodiment, filtering noise based on the point cloud information to extract point cloud information of the region of interest includes:

[0028] Filtering the point cloud information using a straight-through filter to extract an initial region of interest;

[0029] Set the filter radius and filter points of the radius filter;

[0030] The radius filter is used to perform noise filtering on the initial region of interest to extract point cloud information of the region of interest.

[0031] In a second aspect, the present application further provides a photovoltaic sweeper positioning system, the system comprising:

[0032] An information collection module, configured to use a laser radar to collect at least one frame of point cloud information of the photovoltaic sweeper in a current working scene;

[0033] A noise filtering module is used to filter the point cloud information to extract the point cloud information of the area of interest;

[0034] a target extraction module, configured to obtain the plane parameters of the plane where the reflective tape is located, perform plane filtering on the point cloud information of the region of interest, and extract the point cloud information of the target region; wherein the point cloud information of the target region includes multiple clusters of point clouds, each cluster of the point clouds corresponding to one reflective tape;

[0035] A centroid extraction module is used to calculate the centroid of the point cloud of each cluster and create an original point in the laser radar coordinate system based on the actual position of each reflective sticker;

[0036] A matching conversion module is used to match the centroid with the original point to obtain a conversion relationship between each centroid and each original point, and obtain the position of the photovoltaic sweeper in the laser radar coordinate system based on the conversion relationship.

[0037] In a third aspect, the present application also provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the content described in the first aspect above is implemented.

[0038] In a fourth aspect, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the content described in the first aspect above is implemented.

[0039] The above-mentioned positioning method, system, computer device and storage medium of the photovoltaic sweeper collect at least one frame of point cloud information of the photovoltaic sweeper in the current working scenario by using a lidar; filter out noise points based on the point cloud information, and extract the point cloud information of the region of interest; obtain the plane parameters of the plane where the reflective sticker is located, perform plane filtering on the point cloud information of the region of interest, and extract the point cloud information of the target region; wherein, the point cloud information of the target region includes multiple clusters of point clouds, and each cluster of point clouds corresponds to one of the reflective stickers; calculate the centroid of each cluster of point clouds, and create an original point in the lidar coordinate system based on the actual positions of the reflective stickers; match the centroid with the original point to obtain the conversion relationship between each centroid and each original point, and obtain the position of the photovoltaic sweeper in the lidar coordinate system based on the conversion relationship, reducing the dependence on manual intervention, reducing the labor cost, realizing the precise positioning of the photovoltaic sweeper, ensuring that the cleaning process is more efficient and accurate, and having strong environmental adaptability, capable of ensuring the stable and precise positioning of the sweeper under different conditions such as strong light, weak light, and dust, providing a reliable guarantee for the maintenance of the photovoltaic system. Description of the Drawings

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0041] Figure 1 It is an application environment diagram of the positioning method of the photovoltaic sweeper in an embodiment;

[0042] Figure 2 It is a flowchart of the positioning method of the photovoltaic sweeper in an embodiment;

[0043] Figure 3 It is a flowchart of the step of extracting the point cloud information of the target region in an embodiment;

[0044] Figure 4Schematic flowchart of the step of calculating the centroid of each cluster of point clouds in an embodiment;

[0045] Figure 5 Schematic flowchart of obtaining the position of the photovoltaic sweeper in the lidar coordinate system in an embodiment;

[0046] Figure 6 Schematic diagram of sorting and color partitioning of point cloud information in a target area in an embodiment;

[0047] Figure 7 Schematic diagram of the centroid and the original points in an embodiment;

[0048] Figure 8 Structural block diagram of a photovoltaic sweeper positioning system in an embodiment;

[0049] Figure 9 Internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0050] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0051] Unless otherwise defined, the technical terms or scientific terms involved in the present application should be of the ordinary meaning understood by those of ordinary skill in the technical field to which the present application belongs. The terms "a", "one", "kind", "the" and the like involved in the present application do not indicate a quantity limitation and may represent a singular or plural number. The terms "including", "comprising", "having" and any variations thereof involved in the present application are intended to cover non-exclusive inclusion; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may further include unlisted steps or units, or may further include other steps or units inherent to these processes, methods, products or devices. The terms "connected", "coupled" and the like involved in the present application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" involved in the present application refers to two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships may exist. For example, "A and / or B" may represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after. The terms "first", "second", "third" and the like involved in the present application are only used to distinguish similar objects and do not represent a specific order for the objects.

[0052] The photovoltaic sweeper positioning method provided by the embodiments of the present application can be applied to, for example, Figure 1 the application environment shown. Among them, the photovoltaic sweeper 102 communicates with the server 104 through a network. At least one group of reflective stickers is arranged on the photovoltaic sweeper 102. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or can be placed in the cloud or other network servers. The lidar 103 and the photovoltaic sweeper are in the same working space and communicate with the server 104 through a network.

[0053] The server 104 uses the lidar 103 to collect at least one frame of point cloud information of the photovoltaic sweeper in the current working scenario; filters out noise from the point cloud information and extracts the point cloud information of the region of interest; obtains the plane parameters of the plane where the reflective sticker is located, filters the point cloud information of the region of interest, and extracts the point cloud information of the target region; wherein, the point cloud information of the target region includes multiple clusters of point clouds, and each cluster of point clouds corresponds to one of the reflective stickers; calculates the centroid of each cluster of point clouds, and based on the actual positions of the reflective stickers, creates the original points in the lidar coordinate system; matches the centroid with the original point to obtain the conversion relationship between each centroid and each original point, and obtains the position of the photovoltaic sweeper in the lidar coordinate system based on the conversion relationship.

[0054] Among them, the server 104 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0055] In an exemplary embodiment, as Figure 2 shown, a photovoltaic sweeper positioning method is provided. Taking the application of this method to the Figure 1 server side as an example, the following steps 201 to step 20 five are included.

[0056] Among them:

[0057] Step 201, use the lidar to collect at least one frame of point cloud information of the photovoltaic sweeper in the current working scenario.

[0058] Specifically, use the lidar to collect one frame of point cloud information of the photovoltaic sweeper in the current working scenario, and perform time integration on one frame of point cloud information to accumulate at least 3-5 frames of point cloud information. Among them, the Pass through filter can be used to limit the scanning range of the lidar to reduce unnecessary point cloud information calculation.

[0059] Step 202, filter out noise based on the point cloud information and extract the point cloud information of the region of interest.

[0060] Specifically, the time-integrated point cloud information is filtered using a PCL pass filter to extract the initial region of interest (ROI). This initial ROI includes the jittering point cloud, which represents noise. The radius filter and the number of filter points are set. The radius filter is used to filter out noise points in the initial ROI and extract the point cloud information.

[0061] Step 203: Obtain the plane parameters of the plane where the reflective sticker is located, perform plane filtering on the point cloud information of the area of interest, and extract the point cloud information of the target area; wherein the point cloud information of the target area includes multiple clusters of point clouds, and each cluster of the point clouds corresponds to one reflective sticker.

[0062] Specifically, to reduce the impact of the ground point cloud scanned by the LiDAR, the plane parameters of the plane where the reflective tape is located are obtained from the point cloud information of the area of interest. The plane parameters are used to perform plane filtering on the point cloud information of the area of interest to extract the point cloud information of the target area, thereby preventing the point cloud behind the plane where the reflective tape is located from filtering the intensity of the reflective tape point cloud.

[0063] Step 204 , calculating the centroid of the point cloud of each cluster, and creating an original point in the laser radar coordinate system based on the actual position of each reflective sticker.

[0064] Among them, each reflective sticker is set with a corresponding number, so the centroid of each cluster of point clouds and each original point are one-to-one corresponding to the number of the reflective sticker.

[0065] Step 205: Match the centroids with the original points to obtain a conversion relationship between each centroid and each original point, and obtain the position of the photovoltaic sweeper in the laser radar coordinate system based on the conversion relationship.

[0066] In the above photovoltaic cleaning machine positioning method, at least one frame of point cloud information of the photovoltaic cleaning machine in the current working scenario is collected by using a lidar; noise filtering is performed based on the point cloud information, and the point cloud information of the region of interest is extracted; the plane parameters of the plane where the reflective sticker is located are obtained, and plane filtering is performed on the point cloud information of the region of interest to extract the point cloud information of the target region; wherein, the point cloud information of the target region includes multiple clusters of point clouds, and each cluster of point clouds corresponds to one of the reflective stickers; the centroid of each cluster of point clouds is calculated, and based on the actual positions of the reflective stickers, an original point in the lidar coordinate system is created; the centroid is matched with the original point to obtain the conversion relationship between each centroid and each original point, and based on the conversion relationship, the position of the photovoltaic cleaning machine in the lidar coordinate system is obtained, reducing the dependence on manual intervention, lowering the labor cost, realizing the precise positioning of the photovoltaic cleaning machine, ensuring that the cleaning process is more efficient and accurate, and having strong environmental adaptability, capable of ensuring the precise positioning and stable operation of the cleaning machine under different conditions such as strong light, weak light, and dust, providing a reliable guarantee for the maintenance of the photovoltaic system.

[0067] In an exemplary embodiment, as Figure 3 shown, step 203 of obtaining the plane parameters of the plane where the reflective sticker is located, performing plane filtering on the point cloud information of the region of interest, and extracting the point cloud information of the target region specifically includes the following steps 301 to 304. Wherein:

[0068] Step 301, obtaining the plane parameters of the plane where the reflective sticker is located.

[0069] Specifically, the RANSAC algorithm is used to detect the plane parameters of the plane where the reflective sticker is located in the point cloud information of the region of interest.

[0070] Step 302, obtaining the point coordinates of each point cloud in the point cloud information of the region of interest.

[0071] Wherein, the point coordinates include the first axis coordinate parameter, the second axis coordinate parameter, and the third axis coordinate parameter.

[0072] Step 303, calculating the distance from each point cloud to the plane where the reflective sticker is located according to the plane parameters. If the distance is less than zero, it is deleted; otherwise, it is retained to obtain the plane point cloud information of the plane where the reflective sticker is located.

[0073] Specifically, according to the plane parameters and the point coordinates of each point cloud, a plane equation is constructed: ax + by + cz + d = 0, where a, b, c, d are the plane parameters, and x, y, z represent the first axis coordinate, the second axis coordinate, and the third axis coordinate in the point coordinates. Calculate the distance from each point cloud to the plane where the reflective sticker is located:

[0074]

[0075] If the distance is less than zero, delete it; otherwise, keep it to obtain the plane point cloud information of the plane where the reflective sticker is located. By only keeping the point cloud on the front side of the plane where the reflective sticker is located, the interference of the point cloud behind the plane where the reflective sticker is located on the intensity filtering of the reflective sticker point cloud is avoided.

[0076] Step 304: Extract the target area point cloud information according to the plane point cloud information.

[0077] Specifically, calculate the intensity information of each point cloud in the plane point cloud information, determine whether the intensity information of each point cloud is greater than a set threshold. If it is less, delete it; otherwise, keep it, and extract the target area point cloud information.

[0078] Furthermore, in order to improve the accuracy of subsequent positioning, it is necessary to sort the disordered point cloud positions in the target area point cloud information. Divide each cluster of point clouds according to the first axis coordinate parameter and the second axis coordinate parameter of each point cloud in the target area point cloud information. Sort each cluster of divided point clouds in a clockwise or counterclockwise order, and at the same time divide each cluster of point clouds with different intensities by color. Finally, the target area point cloud information is formed into multiple clusters of point clouds, and each cluster of point clouds corresponds to one of the reflective stickers.

[0079] In this embodiment, by using the plane parameters of the plane where the reflective sticker is located, the point cloud information behind the plane where the reflective sticker is located is filtered, and the point cloud information on the front side of the plane where the reflective sticker is located is retained. This not only reduces the influence of the ground point cloud but also avoids the interference of the point cloud behind the plane where the reflective sticker is located on the intensity filtering of the reflective sticker point cloud, improving the accuracy of the point cloud information.

[0080] In an exemplary embodiment, as Figure 4 shown, step 204 calculates the centroid of each cluster of point clouds, which specifically includes the following steps 401 to step 402.

[0081] Step 401: Obtain the point coordinates of each point cloud in each cluster of point clouds, where the point coordinates include the first axis coordinate parameter, the second axis coordinate parameter, and the third axis coordinate parameter.

[0082] Step 402: Calculate the average value of the first axis coordinate parameters, the average value of the second axis coordinate parameters, and the average value of the third axis coordinate parameters of all the point clouds in each cluster of point clouds to obtain the centroid of each cluster of point clouds.

[0083] Specifically, the average value of the first axis coordinate parameters of all the point clouds in each cluster of point clouds is calculated as:

[0084]

[0085] The average value of the second-axis coordinate parameters of all the point clouds in each cluster of point clouds is:

[0086]

[0087] The average value of the third-axis coordinate parameters of all the point clouds in each cluster of point clouds:

[0088]

[0089] where N represents the number of point clouds included in a cluster of point clouds, and the coordinate of each point cloud is (x i , y i , z i ), and the centroid of a cluster of point clouds is (c x , c y , c z ).

[0090] In this embodiment, by calculating the average value of the coordinate parameters of all the point clouds in each cluster of point clouds, the centroid of each cluster of point clouds is obtained, and the centroid is used to represent the positioning of the corresponding reflective sticker.

[0091] In an exemplary embodiment, the original points in the lidar coordinate system created based on the actual positions of the reflective stickers include: taking the position of the lidar as the origin, corresponding to the actual positions of the reflective stickers, and successively establishing a plurality of the original points.

[0092] Specifically, each reflective sticker is provided with a corresponding number, so the centroid of each cluster of point clouds and each original point are in one-to-one correspondence with the number of the reflective sticker, thereby establishing a plurality of the original points.

[0093] In an exemplary embodiment, the conversion relationship includes an offset relationship and a rotation relationship about an axis. As Figure 5 shown, in step 205, matching the centroid with the original point, extracting the conversion relationship between each centroid and each original point, and obtaining the position of the photovoltaic sweeper in the lidar coordinate system based on the conversion relationship specifically includes the following steps 501 to step 502.

[0094] Step 501, matching the centroid with the original point, and obtaining the offset relationship and the rotation relationship about an axis of each reflective sticker in the lidar coordinate system. Among them, the rotation relationship about an axis includes the rotation relationships about the first axis, the second axis, and the third axis respectively;

[0095] Step 502, generating the position of the photovoltaic sweeper in the lidar coordinate system according to the offset relationship and the rotation relationship about an axis.

[0096] Specifically, the centroid of each cluster point cloud is used as the point to be matched, and each original point is used as the original point to be matched. The SVD algorithm is used for matching to obtain the transformation matrix between each centroid and each original point. The transformation matrix represents the transformation relationship between the centroid and the original point. According to the transformation matrix, the offset relationship and the rotation relationship around the axis of each centroid in the laser radar coordinate system are obtained. According to the offset relationship and the rotation system around the axis, the position of the photovoltaic sweeper in the laser radar coordinate system is generated.

[0097] In this embodiment, the position of the photovoltaic sweeper in the laser radar coordinate system is accurately positioned by obtaining the conversion relationship between the center of mass and the original point.

[0098] In a preferred embodiment, a photovoltaic sweeper positioning method is provided. Two groups (four) of reflective stickers are arranged on the photovoltaic panel plane of the photovoltaic sweeper. According to the different positions of the four reflective stickers, the leftmost reflective sticker is numbered 1, the lower middle one is numbered 2, the right one is numbered 3, and the upper middle one is numbered 4 in a counterclockwise order. The method specifically includes the following steps:

[0099] Step 601: Use the MID360 radar to cumulatively read three frames of point cloud information in ROS format, and convert the point cloud information in ROS format into PCL format.

[0100] In step 602, the time-integrated point cloud information is filtered using a PCL pass filter to extract the initial region of interest. Noise points in the initial region of interest are then filtered using a radius filter to extract the point cloud information for the region of interest. The radius filter has a filter radius of 0.03m and uses 5 filter points. If there are fewer than 5 points within a 0.03m radius of any point cloud, the point cloud is considered noise and filtered.

[0101] Step 603: Detect the plane parameters of the plane where the reflective tape is located in the point cloud information of the region of interest using the RANSAC algorithm. Calculate the distance from each point cloud in the point cloud information of the region of interest to the plane where the reflective tape is located. Filter out the point clouds on the back side of the plane where the reflective tape is located if the calculated distance is negative, thus extracting the plane point cloud information.

[0102] Step 604: Calculate the intensity information of each point cloud in the planar point cloud information, and determine whether the intensity information of each point cloud is greater than a set threshold. If it is less, filter it; otherwise, retain it, and extract the target area point cloud information. Sort the disordered point cloud positions in the target area point cloud information, and divide each cluster of point clouds according to the first axis coordinate parameter x and the second axis coordinate parameter y of each point cloud in the target area point cloud information. For each divided cluster of point clouds, sort them in counterclockwise order, define the rightmost point cloud as point cloud 1, the lower right point cloud as point cloud 2, the left point cloud as point cloud 3, and the upper left point cloud as point cloud 4. At the same time, divide each cluster of point clouds into different colors according to different intensities, and the result is as Figure 6 shown.

[0103] Step 605: Obtain the point coordinates of each point cloud in each cluster, and calculate the average value of the first axis coordinate parameters, the average value of the second axis coordinate parameters, and the average value of the third axis coordinate parameters of all point clouds in each cluster of point clouds to obtain the centroid of each cluster of point clouds.

[0104] Step 606: Use the SVD algorithm for matching to obtain the transformation matrix between each centroid and each original point. According to this transformation matrix, obtain the offset relationship and the rotation relationship around the axis of the first axis coordinate x, the second axis coordinate y, and the third axis coordinate z of each centroid in the lidar coordinate system. According to the offset relationship and the rotation relationship around the x / y / z axis, generate the position of the photovoltaic sweeper in the lidar coordinate system. As Figure 7 shown, the four points in the upper half of this figure are the centroids of the point clouds of the four reflective sticker positions, and these four are the points to be matched. The four points in the lower half are the four original points created in the MID360 lidar coordinate system, which are the original points for matching.

[0105] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps does not have a strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily have to be executed at the same time, but can be executed at different times. The execution order of these steps or stages does not necessarily have to be sequential, but can be executed alternately or alternately with at least a part of other steps or steps or stages in other steps.

[0106] Based on the same inventive concept, an embodiment of the present application further provides a photovoltaic cleaning machine positioning system for implementing the photovoltaic cleaning machine positioning method involved above. The implementation solutions provided by this device for solving problems are similar to those recorded in the above method. Therefore, the specific limitations in one or more embodiments of the photovoltaic cleaning machine positioning system provided below can refer to the limitations on the photovoltaic cleaning machine positioning method in the above text and will not be repeated here.

[0107] In an exemplary embodiment, as Figure 8 shown, a photovoltaic cleaning machine positioning system is provided, including: an information acquisition module 801, a noise filtering module 802, a target extraction module 803, a centroid extraction module 804, and a matching and conversion module 805, where:

[0108] The information acquisition module 801 is configured to collect at least one frame of point cloud information of the photovoltaic cleaning machine in the current working scenario by using a lidar.

[0109] The noise filtering module 802 is configured to filter noise from the point cloud information and extract the point cloud information of the region of interest.

[0110] The target extraction module 803 is configured to obtain the plane parameters of the plane where the reflective sticker is located, perform plane filtering on the point cloud information of the region of interest, and extract the point cloud information of the target region; wherein, the point cloud information of the target region includes multiple clusters of point clouds, and each cluster of the point clouds corresponds to one of the reflective stickers.

[0111] The centroid extraction module 804 is configured to calculate the centroid of each cluster of the point clouds and create an original point in the lidar coordinate system based on the actual positions of the reflective stickers.

[0112] The matching and conversion module 805 is configured to match the centroid with the original point, obtain the conversion relationship between each centroid and each original point, and obtain the position of the photovoltaic cleaning machine in the lidar coordinate system based on the conversion relationship.

[0113] In one of the embodiments, the target extraction module 803 is further configured to: obtain the plane parameters of the plane where the reflective sticker is located; obtain the point coordinates of each point cloud in the point cloud information of the region of interest; calculate the distance from each point cloud to the plane where the reflective sticker is located according to the plane parameters, and if the distance is less than zero, delete it, otherwise retain it, to obtain the plane point cloud information of the plane where the reflective sticker is located; and extract the point cloud information of the target region according to the plane point cloud information.

[0114] In one embodiment, the target extraction module 803 is further configured to: calculate the intensity information of each point cloud in the planar point cloud information, determine whether the intensity information of each point cloud is greater than a set threshold, if it is less, delete it, otherwise retain it, and extract the target area point cloud information.

[0115] In one embodiment, the centroid extraction module 804 is further configured to: obtain the point coordinates of each point cloud in each cluster, where the point coordinates include a first axis coordinate parameter, a second axis coordinate parameter, and a third axis coordinate parameter; calculate the average value of the first axis coordinate parameters, the average value of the second axis coordinate parameters, and the average value of the third axis coordinate parameters of all the point clouds in each cluster of point clouds to obtain the centroid of each cluster of point clouds.

[0116] In one embodiment, the centroid extraction module 804 is further configured to: take the position of the lidar as the origin, corresponding to the actual position of the retroreflective sticker, and sequentially establish a plurality of the original points.

[0117] In one embodiment, the matching and conversion module 805 is further configured to: match the centroid with the original points, obtain the offset relationship and the axis rotation relationship of each retroreflective sticker in the lidar coordinate system; the axis rotation relationship includes the rotation relationships around the first axis, the second axis, and the third axis respectively; generate the position of the photovoltaic sweeper in the lidar coordinate system according to the offset relationship and the axis rotation relationship.

[0118] In one embodiment, the noise filtering module 802 is further configured to: filter the point cloud information by using a pass-through filter to extract an initial region of interest; set the filtering radius and the number of filtering points of a radius filter; use the radius filter to perform noise filtering on the initial region of interest to extract the point cloud information of the region of interest.

[0119] Each module in the above photovoltaic sweeper positioning system can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0120] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as Figure 9As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store point cloud information. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. The computer program, when executed by the processor, implements a method for positioning a photovoltaic sweeper.

[0121] Those skilled in the art can understand that Figure 9 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0122] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0123] Using a lidar to collect at least one frame of point cloud information of the photovoltaic sweeper in the current working scenario;

[0124] Based on the point cloud information, perform noise filtering to extract the point cloud information of the region of interest;

[0125] Obtain the plane parameters of the plane where the reflective sticker is located, perform plane filtering on the point cloud information of the region of interest, and extract the point cloud information of the target region; wherein, the point cloud information of the target region includes multiple clusters of point clouds, and each cluster of point clouds corresponds to one of the reflective stickers;

[0126] Calculate the centroid of each cluster of point clouds, and based on the actual positions of the reflective stickers, create the original points in the lidar coordinate system;

[0127] Match the centroid with the original point to obtain the conversion relationship between each centroid and each original point, and based on the conversion relationship, obtain the position of the photovoltaic sweeper in the lidar coordinate system.

[0128] In one embodiment, when the processor executes the computer program, the following steps are further implemented: obtaining the plane parameters of the plane where the reflective sticker is located; obtaining the point coordinates of each point cloud in the point cloud information of the region of interest; calculating the distance from each point cloud to the plane where the reflective sticker is located according to the plane parameters, and if the distance is less than zero, deleting it, otherwise retaining it, to obtain the plane point cloud information of the plane where the reflective sticker is located; extracting the point cloud information of the target region according to the plane point cloud information.

[0129] In one embodiment, when the processor executes the computer program, the following steps are further implemented: calculating the intensity information of each point cloud in the plane point cloud information, and determining whether the intensity information of each point cloud is greater than a set threshold, and if it is less than, deleting it, otherwise retaining it, to extract the point cloud information of the target region.

[0130] In one embodiment, when the processor executes the computer program, the following steps are further implemented: obtaining the point coordinates of each point cloud in each cluster of point clouds, where the point coordinates include a first axis coordinate parameter, a second axis coordinate parameter, and a third axis coordinate parameter; calculating the average value of the first axis coordinate parameters, the average value of the second axis coordinate parameters, and the average value of the third axis coordinate parameters of all the point clouds in each cluster of point clouds to obtain the centroid of each cluster of point clouds.

[0131] In one embodiment, when the processor executes the computer program, the following steps are further implemented: taking the position of the lidar as the origin, corresponding to the actual position of the reflective sticker, and sequentially establishing a plurality of the original points.

[0132] In one embodiment, the conversion relationship includes an offset relationship and a rotation relationship about an axis; when the processor executes the computer program, the following steps are further implemented: matching the centroid with the original points to obtain the offset relationship and the rotation relationship about an axis of each reflective sticker in the lidar coordinate system; the rotation relationship about an axis includes the rotation relationships about the first axis, the second axis, and the third axis respectively; generating the position of the photovoltaic cleaning machine in the lidar coordinate system according to the offset relationship and the rotation relationship about an axis.

[0133] In one embodiment, when the processor executes the computer program, the following steps are further implemented: filtering the point cloud information by using a pass-through filter to extract an initial region of interest; setting the filtering radius and the number of filtering points of a radius filter; filtering the noise of the initial region of interest by using the radius filter to extract the point cloud information of the region of interest.

[0134] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the corresponding steps of the photovoltaic cleaning machine positioning method described in the above embodiments are implemented.

[0135] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0136] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in this application.

[0137] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A positioning method for a photovoltaic cleaning machine, in which at least one group of reflective stickers is arranged on the photovoltaic cleaning machine, characterized in that, The method includes: Collecting at least one frame of point cloud information of the photovoltaic sweeper in the current working scenario by using a lidar; Performing noise filtering on the point cloud information, and extracting the point cloud information of the region of interest; Obtaining the plane parameters of the plane where the reflective sticker is located, performing plane filtering on the point cloud information of the region of interest, and extracting the point cloud information of the target region; wherein, the point cloud information of the target region includes multiple clusters of point clouds, and each cluster of point clouds corresponds to one of the reflective stickers; Calculating the centroid of each cluster of point clouds, and creating an original point in the lidar coordinate system based on the actual positions of the reflective stickers; Matching the centroid with the original point to obtain the conversion relationship between each centroid and each original point, and obtaining the position of the photovoltaic sweeper in the lidar coordinate system based on the conversion relationship.

2. The photovoltaic cleaning machine positioning method according to claim 1, wherein, The obtaining the plane parameters of the plane where the reflective sticker is located, performing plane filtering on the point cloud information of the region of interest, and extracting the point cloud information of the target region includes: Obtaining the plane parameters of the plane where the reflective sticker is located; Obtaining the point coordinates of each point cloud in the point cloud information of the region of interest; Calculating the distance from each point cloud to the plane where the reflective sticker is located according to the plane parameters, and if the distance is less than zero, deleting it, otherwise retaining it, to obtain the plane point cloud information of the plane where the reflective sticker is located; Extracting the point cloud information of the target region according to the plane point cloud information.

3. The photovoltaic sweeper positioning method according to claim 2, characterized in that, The extracting the point cloud information of the target region according to the plane point cloud information includes: Calculating the intensity information of each point cloud in the plane point cloud information, and determining whether the intensity information of each point cloud is greater than a set threshold. If it is less, deleting it, otherwise retaining it, to extract the point cloud information of the target region.

4. The photovoltaic cleaning machine positioning method according to claim 1, characterized in that, The calculating the centroid of each cluster of point clouds includes: Obtaining the point coordinates of each point cloud in each cluster of point clouds, where the point coordinates include a first axis coordinate parameter, a second axis coordinate parameter, and a third axis coordinate parameter; Calculating the average value of the first axis coordinate parameters, the average value of the second axis coordinate parameters, and the average value of the third axis coordinate parameters of all the point clouds in each cluster of point clouds to obtain the centroid of each cluster of point clouds.

5. The photovoltaic cleaning machine positioning method according to claim 4, wherein The creating an original point in the lidar coordinate system based on the actual positions of the reflective stickers includes: Taking the position of the lidar as the origin, corresponding to the actual positions of the reflective stickers, and sequentially establishing a plurality of the original points.

6. The photovoltaic sweeper positioning method according to claim 5, characterized in that The conversion relationship includes an offset relationship and a rotation relationship around an axis; the matching the centroid with the original point, extracting the conversion relationship between each centroid and each original point, and obtaining the position of the photovoltaic sweeper in the lidar coordinate system based on the conversion relationship includes: Matching the centroid with the original point to obtain the offset relationship and the rotation relationship around an axis of each reflective sticker in the lidar coordinate system; The rotation relationship around an axis includes rotation relationships around the first axis, around the second axis, and around the third axis respectively; Generating the position of the photovoltaic sweeper in the lidar coordinate system according to the offset relationship and the rotation relationship around an axis.

7. The photovoltaic sweeper positioning method according to claim 1, characterized in that The performing noise filtering based on the point cloud information to extract point cloud information of the area of interest includes: Filtering the point cloud information using a straight-through filter to extract an initial region of interest; Set the filter radius and filter points of the radius filter; The radius filter is used to perform noise filtering on the initial region of interest to extract point cloud information of the region of interest.

8. A positioning system for a photovoltaic cleaning machine, on which at least one group of reflective stickers is arranged, characterized in that, The system comprises: An information collection module, configured to use a laser radar to collect at least one frame of point cloud information of the photovoltaic sweeper in a current working scene; A noise filtering module is used to filter the point cloud information to extract the point cloud information of the area of interest; a target extraction module, configured to obtain the plane parameters of the plane where the reflective tape is located, perform plane filtering on the point cloud information of the region of interest, and extract the point cloud information of the target region; wherein the point cloud information of the target region includes multiple clusters of point clouds, each cluster of the point clouds corresponding to one reflective tape; A centroid extraction module is used to calculate the centroid of the point cloud of each cluster and create an original point in the laser radar coordinate system based on the actual position of each reflective sticker; A matching conversion module is used to match the centroid with the original point to obtain a conversion relationship between each centroid and each original point, and obtain the position of the photovoltaic sweeper in the laser radar coordinate system based on the conversion relationship.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images