Photovoltaic cleaning robot based on photovoltaic panel walking method and system

Abstract

The application discloses a photovoltaic cleaning robot walking method and system based on a photovoltaic panel. The target grid line is determined based on the yaw angle and multiple grid lines. The grid line parallel to the target grid line is defined as the first grid line. The multiple first grid lines are clustered based on the density-based clustering algorithm to obtain multiple grid line clusters. At least one target grid line cluster is determined based on the screening of the multiple grid line clusters, and the center line in each target grid line cluster is selected. The initial distance between the photovoltaic cleaning robot and the center line is measured and calculated, and the initial distance is used as the reference distance. In the walking process of the photovoltaic cleaning robot, the change between the current distance and the initial distance between the photovoltaic cleaning robot and the center line is collected, and the change is used to trigger the straight line walking or the arc line walking of the photovoltaic cleaning robot. The walking control of the photovoltaic cleaning robot on the photovoltaic panel is realized to adapt to various photovoltaic panel scenes.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of identification of photovoltaic cleaning robots, and particularly relates to a photovoltaic cleaning robot walking method and system based on a photovoltaic panel. BACKGROUND

[0002] With the development of science and technology, the photovoltaic cleaning robot walks on the photovoltaic panel and is above the photovoltaic panel, the photovoltaic cleaning robot sprays water on the photovoltaic panel and cleans the surface of the photovoltaic panel, in the prior art, the photovoltaic cleaning robot walks relative to the photovoltaic panel and walks along a preset path, however, the photovoltaic cleaning robot gradually moves away from the center line on the left side in the actual walking process, and the distance between the photovoltaic cleaning robot and the center line cannot be controlled, which affects the walking control of the photovoltaic cleaning robot on the photovoltaic panel. SUMMARY

[0003] The present application aims to overcome the shortcomings of the prior art, and provides a photovoltaic cleaning robot walking method and system based on a photovoltaic panel, a yaw angle is introduced, and a target grid line is determined based on the yaw angle and a plurality of grid lines to derive a first grid line, a plurality of first grid lines are clustered based on a density-based clustering algorithm to obtain a plurality of grid line clusters, the accuracy of the plurality of grid line clusters is ensured, thereby ensuring the accuracy of the center line in each target grid line cluster, and then the center line and the photovoltaic cleaning robot are interacted in a distance mode, so as to trigger the straight line walking or arc line walking of the photovoltaic cleaning robot based on the change amount, and the walking control of the photovoltaic cleaning robot on the photovoltaic panel is realized to adapt to various photovoltaic panel scenarios.

[0004] To solve the above technical problems, the present application embodiment provides a photovoltaic cleaning robot walking method based on a photovoltaic panel, which is applied to the scenario of the photovoltaic cleaning robot walking on the photovoltaic panel; the photovoltaic cleaning robot walking method based on the photovoltaic panel comprises:

[0005] An edge and a plurality of grid lines are determined based on a gray image of the photovoltaic panel;

[0006] A yaw angle is determined based on at least one grid line in the plurality of grid lines and the posture direction of the photovoltaic cleaning robot;

[0007] A target grid line is determined based on the yaw angle and the plurality of grid lines;

[0008] A grid line parallel to the target grid line is defined as a first grid line, and a plurality of first grid lines are clustered based on a density-based clustering algorithm to obtain a plurality of grid line clusters;

[0009] At least one target grid line cluster is determined based on the screening of the plurality of grid line clusters, and a center line in each target grid line cluster is selected;

[0010] Calculate an initial distance between the photovoltaic cleaning robot and the center line, and take the initial distance as a reference distance;

[0011] In the walking process of the photovoltaic cleaning robot, a change between a current distance between the photovoltaic cleaning robot and the center line and the initial distance is collected, and a straight-line walking or an arc-line walking of the photovoltaic cleaning robot is triggered based on the change.

[0012] Optionally, the gray-scale image of the photovoltaic panel is acquired, and edges and a plurality of grid lines are determined according to the gray-scale image of the photovoltaic panel, and the method comprises:

[0013] The gray-scale image of the photovoltaic panel is acquired;

[0014] The edges are determined based on the gray-scale image of the photovoltaic panel and an EdgeDrawing algorithm, wherein a Sobel operator is introduced in the EdgeDrawing algorithm, a weighted difference of gray-scale values of four fields above, below, left and right of each pixel in the gray-scale image of the photovoltaic panel is calculated based on the Sobel operator, and the edges are determined when the weighted difference reaches an extreme value at the edges;

[0015] The plurality of grid lines are determined based on the edges, a gradient threshold value and an anchor threshold value.

[0016] Optionally, the yaw angle is determined according to at least one grid line in the plurality of grid lines and a posture direction of the photovoltaic cleaning robot, and the method comprises:

[0017] A first coordinate system is constructed by using the photovoltaic cleaning robot, and a second coordinate system is constructed by using at least one grid line in the plurality of grid lines;

[0018] The second coordinate system is compared with the first coordinate system, and an included angle between the second coordinate system and the first coordinate system is determined;

[0019] If the included angle between the second coordinate system and the first coordinate system is an acute angle, the yaw angle is determined based on the included angle between the second coordinate system and the first coordinate system.

[0020] Optionally, the target grid line is determined based on the yaw angle and the plurality of grid lines, and the method comprises:

[0021] A preset angle range meeting a requirement is determined based on the yaw angle and a preset angle error;

[0022] The target grid line is determined according to the plurality of grid lines and the grid line angle range.

[0023] Optionally, the grid line parallel to the target grid line is defined as a first grid line, and a plurality of first grid lines are clustered based on a density-based clustering algorithm to obtain a plurality of grid line clusters, and the method comprises:

[0024] The grid line parallel to the target grid line is defined as the first grid line;

[0025] acquiring a preset maximum distance between the grid lines and a preset minimum number of grid lines required to form a grid line cluster;

[0026] traversing the plurality of first grid lines and determining the plurality of first grid lines having the adjacent relationship according to the plurality of first grid lines and the preset maximum distance between the grid lines;

[0027] defining the number of the plurality of first grid lines having the adjacent relationship;

[0028] if the number is greater than the preset minimum number of grid lines required to form a grid line cluster, merging the plurality of first grid lines having the adjacent relationship into a grid line cluster;

[0029] in all the grid line clusters, checking any grid line in a grid line cluster with any grid line in another grid line cluster;

[0030] if any grid line in a grid line cluster has the adjacent relationship with any grid line in another grid line cluster, merging the grid line cluster and the another grid line cluster.

[0031] Optionally, the determining at least one target grid line cluster based on the screening of the plurality of grid line clusters and selecting the center line in each target grid line cluster comprises:

[0032] performing a first screening on each grid line cluster, and taking the distance between the two grid lines at the edge as the width of the grid line cluster;

[0033] if the width of the grid line cluster is greater than a preset width threshold, the grid line cluster meets the width requirement;

[0034] performing a second screening on each grid line cluster, and marking a plurality of gray collection points on the center line of each grid line cluster;

[0035] collecting the gray corresponding to each gray collection point, and if the gray is greater than a preset gray threshold, defining the gray collection point as a qualified collection point;

[0036] if the number of the qualified collection points is greater than a preset number threshold, the grid line cluster meets the brightness requirement;

[0037] if the grid line cluster meets both the width requirement and the brightness requirement, the grid line cluster is a target grid line cluster;

[0038] sorting each target grid line cluster, selecting a plurality of target grid line clusters with more qualified collection points, and taking the center line of the plurality of target grid line clusters as the final selected grid line.

[0039] Optionally, the measuring the initial distance between the photovoltaic cleaning robot and the center line, and taking the initial distance as the reference distance comprises:

[0040] when the photovoltaic cleaning robot is in the starting state, collecting the position of the photovoltaic cleaning robot and the position of the center line.

[0041] measuring the initial distance between the photovoltaic cleaning robot and the center line based on the position of the photovoltaic cleaning robot and the position of the center line;

[0042] Alternatively, the change between the current distance and the initial distance between the photovoltaic cleaning robot and the center line is collected during the walking of the photovoltaic cleaning robot, and the walking of the photovoltaic cleaning robot in a straight line or an arc line is triggered based on the change, comprising:

[0043] During the walking of the photovoltaic cleaning robot, the current distance between the photovoltaic cleaning robot and the center line is collected;

[0044] The change is determined based on the current distance and the initial distance between the photovoltaic cleaning robot and the center line;

[0045] If the change is less than the preset amount of straight-line driving, the walking of the photovoltaic cleaning robot in a straight line is triggered;

[0046] If the change is greater than the preset amount of straight-line driving, the walking of the photovoltaic cleaning robot in an arc line is triggered.

[0047] Optionally, the walking method of the photovoltaic cleaning robot based on the photovoltaic panel further comprises:

[0048] The relative position between the center line and the photovoltaic cleaning robot is collected;

[0049] The center line type is defined according to the relative position between the center line and the photovoltaic cleaning robot, and the center line type is a left center line or a right center line;

[0050] If the center line type is a left center line, the distance between the left center line and the photovoltaic cleaning robot is measured;

[0051] The left walking of the photovoltaic cleaning robot is triggered based on the distance between the left center line and the photovoltaic cleaning robot, and the follow-up walking of the photovoltaic cleaning robot is triggered according to the shape of the left center line.

[0052] Optionally, the walking method of the photovoltaic cleaning robot based on the photovoltaic panel further comprises:

[0053] If the center line type is a right center line, the distance between the right center line and the photovoltaic cleaning robot is measured;

[0054] The left distance is derived based on the distance between the right center line and the photovoltaic cleaning robot;

[0055] In the derivation of the left distance, the left distance is defined according to the distance between the right center line and the photovoltaic cleaning robot, the type of the photovoltaic panel driven by the photovoltaic cleaning robot, and the width of the photovoltaic cleaning robot;

[0056] The left side distance triggers the left side of the photovoltaic cleaning robot to walk.

[0057] Optionally, a photovoltaic cleaning robot based on a walking system of a photovoltaic panel, characterized in that the photovoltaic cleaning robot based on the walking system of the photovoltaic panel is applied to the photovoltaic cleaning robot based on the walking method of the photovoltaic panel, and the photovoltaic cleaning robot based on the walking system of the photovoltaic panel comprises:

[0058] An acquisition module is configured to acquire a grayscale image of the photovoltaic panel, and determine edges and a plurality of grid lines based on the grayscale image of the photovoltaic panel;

[0059] A yaw angle module is configured to determine a yaw angle based on at least one grid line of the plurality of grid lines and a posture direction of the photovoltaic cleaning robot;

[0060] A target grid line module is configured to determine a target grid line based on the yaw angle and the plurality of grid lines;

[0061] A clustering module is configured to define a first grid line as a grid line parallel to the target grid line, and cluster a plurality of first grid lines based on a density-based clustering algorithm to obtain a plurality of grid line clusters;

[0062] A selection module is configured to determine at least one target grid line cluster based on screening of the plurality of grid line clusters, and select a center line in each target grid line cluster;

[0063] A distance module is configured to measure an initial distance between the photovoltaic cleaning robot and the center line, and take the initial distance as a reference distance;

[0064] A walking module is configured to collect a change amount between a current distance and the initial distance between the photovoltaic cleaning robot and the center line in a walking process of the photovoltaic cleaning robot, and trigger straight line walking or arc line walking of the photovoltaic cleaning robot based on the change amount.

[0065] In the embodiment of the present application, by the method in the embodiment of the present application, the gray scale image of the photovoltaic panel is acquired, and the edges and the plurality of grid lines are determined according to the gray scale image of the photovoltaic panel; the yaw angle is determined according to at least one of the plurality of grid lines and the posture direction of the photovoltaic cleaning robot; the target grid line is determined based on the yaw angle and the plurality of grid lines; the grid line parallel to the target grid line is defined as the first grid line, and the plurality of first grid lines are clustered based on the density-based clustering algorithm to obtain a plurality of grid line clusters; at least one target grid line cluster is determined based on the screening of the plurality of grid line clusters, and the center line in each target grid line cluster is selected; the initial distance between the photovoltaic cleaning robot and the center line is measured and calculated, and the initial distance is taken as the reference distance; in the walking process of the photovoltaic cleaning robot, the change quantity between the current distance and the initial distance between the photovoltaic cleaning robot and the center line is collected, and the straight line walking or the arc line walking of the photovoltaic cleaning robot is triggered based on the change quantity, at this time, the yaw angle is introduced, and the target grid line is determined based on the yaw angle and the plurality of grid lines to introduce the first grid line, the plurality of first grid lines are clustered based on the density-based clustering algorithm to obtain a plurality of grid line clusters, the accuracy of the plurality of grid line clusters is ensured, thereby the accuracy of the center line in each target grid line cluster is ensured, and then the distance type interaction between the center line and the photovoltaic cleaning robot is performed, so as to trigger the straight line walking or the arc line walking of the photovoltaic cleaning robot based on the change quantity, and the walking control of the photovoltaic cleaning robot on the photovoltaic panel is realized to adapt to various photovoltaic panel scenes. BRIEF DESCRIPTION OF DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without any creative effort.

[0067] Figure 1 is a flowchart of the walking method of the photovoltaic cleaning robot based on the photovoltaic panel in the embodiment of the present application;

[0068] Figure 2 is a flowchart of S11 in the walking method of the photovoltaic cleaning robot based on the photovoltaic panel in the embodiment of the present application;

[0069] Figure 3 is a flowchart of S12 in the walking method of the photovoltaic cleaning robot based on the photovoltaic panel in the embodiment of the present application;

[0070] Figure 4 is a flowchart of S13 in the walking method of the photovoltaic cleaning robot based on the photovoltaic panel in the embodiment of the present application;

[0071] Figure 5is a flowchart of S14 in the walking method based on the photovoltaic panel of the photovoltaic cleaning robot in the embodiment of the application;

[0072] Figure 6 is a flowchart of S15 in the walking method based on the photovoltaic panel of the photovoltaic cleaning robot in the embodiment of the application;

[0073] Figure 7 is a flowchart of S16 in the walking method based on the photovoltaic panel of the photovoltaic cleaning robot in the embodiment of the application;

[0074] Figure 8 is a flowchart of S17 in the walking method based on the photovoltaic panel of the photovoltaic cleaning robot in the embodiment of the application;

[0075] Figure 9 is a structural composition diagram of the walking system based on the photovoltaic panel of the photovoltaic cleaning robot in the embodiment of the application;

[0076] Figure 10 is a hardware diagram of an electronic device according to an example embodiment. DETAILED DESCRIPTION

[0077] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by a person of ordinary skill in the art without creative labor fall within the protection scope of the application.

[0078] EMBODIMENT

[0079] Please refer to Figures 1 to 7 A walking method based on a photovoltaic panel of a photovoltaic cleaning robot is applied to a scenario in which the photovoltaic cleaning robot walks on the photovoltaic panel. The walking method based on the photovoltaic panel of the photovoltaic cleaning robot comprises the following steps.

[0080] Step S11: An intensity image of the photovoltaic panel is acquired, and edges and a plurality of grid lines are determined according to the intensity image of the photovoltaic panel.

[0081] Step S12: A yaw angle is determined according to at least one grid line of the plurality of grid lines and a posture direction of the photovoltaic cleaning robot.

[0082] Step S13: A target grid line is determined based on the yaw angle and the plurality of grid lines.

[0083] Step S14: A grid line parallel to the target grid line is defined as a first grid line, and a plurality of first grid lines are clustered according to a density-based clustering algorithm to obtain a plurality of grid line clusters.

[0084] Step S15: determining at least one target grid line cluster based on screening of the plurality of grid line clusters, and selecting a center line in each target grid line cluster;

[0085] Step S16: measuring an initial distance between the photovoltaic cleaning robot and the center line, and taking the initial distance as a reference distance;

[0086] Step S17: in the walking process of the photovoltaic cleaning robot, collecting a change amount between a current distance between the photovoltaic cleaning robot and the center line and the initial distance, and triggering straight line walking or arc line walking of the photovoltaic cleaning robot based on the change amount.

[0087] In the embodiment of the present application, by the method in the embodiment of the present application, the gray scale image of the photovoltaic panel is obtained, and the edges and the plurality of grid lines are determined according to the gray scale image of the photovoltaic panel; the yaw angle is determined according to at least one grid line of the plurality of grid lines and the posture direction of the photovoltaic cleaning robot; the target grid line is determined based on the yaw angle and the plurality of grid lines; the grid line parallel to the target grid line is defined as the first grid line, the plurality of first grid lines are clustered according to the density-based clustering algorithm to obtain the plurality of grid line clusters; at least one target grid line cluster is determined based on screening of the plurality of grid line clusters, and the center line in each target grid line cluster is selected; the initial distance between the photovoltaic cleaning robot and the center line is measured, and the initial distance is taken as the reference distance; in the walking process of the photovoltaic cleaning robot, the change amount between the current distance between the photovoltaic cleaning robot and the center line and the initial distance is collected, and the straight line walking or arc line walking of the photovoltaic cleaning robot is triggered based on the change amount. At this time, the yaw angle is introduced, and the target grid line is determined based on the yaw angle and the plurality of grid lines to introduce the first grid line, the plurality of first grid lines are clustered according to the density-based clustering algorithm to obtain the plurality of grid line clusters, the accuracy of the plurality of grid line clusters is ensured, thereby ensuring the accuracy of the center line in each target grid line cluster, and then the distance interaction between the center line and the photovoltaic cleaning robot is performed, so as to trigger the straight line walking or arc line walking of the photovoltaic cleaning robot based on the change amount, and the walking control of the photovoltaic cleaning robot on the photovoltaic panel is realized to adapt to various photovoltaic panel scenes.

[0088] Please refer to Figure 2 In step S11, the gray scale image of the photovoltaic panel is obtained, and the edges and the plurality of grid lines are determined according to the gray scale image of the photovoltaic panel;

[0089] In the specific implementation process of the present application, the specific steps can be:

[0090] S111: obtaining the gray scale image of the photovoltaic panel;

[0091] S112: determine the edge based on the gray image of the photovoltaic panel and the EdgeDrawing algorithm, wherein the Sobel operator is introduced in the EdgeDrawing algorithm, the weighted difference of the gray values of the four fields above, below, left and right of each pixel in the gray image of the photovoltaic panel is calculated based on the Sobel operator, and the edge is determined when the extreme value is reached at the edge;

[0092] S113: determine the plurality of grid lines based on the edge, the gradient threshold and the anchor threshold.

[0093] In the embodiment of the present application, the photovoltaic cleaning robot photographs the photovoltaic panel based on the camera and outputs the image of the photovoltaic panel, and the gray image of the photovoltaic panel is formed based on the post-processing of the image of the photovoltaic panel, so as to further control the gray image of the photovoltaic panel.

[0094] The gray image of the photovoltaic panel is associated with the EdgeDrawing algorithm, so as to output the edge based on the gray image of the photovoltaic panel and the EdgeDrawing algorithm, thereby ensuring the accuracy of the edge.

[0095] At this time, the Sobel operator is introduced in the EdgeDrawing algorithm, the weighted difference of the gray values of the four fields above, below, left and right of each pixel in the gray image of the photovoltaic panel is calculated based on the Sobel operator, and the edge is determined when the extreme value is reached at the edge, so as to comprehensively consider the gray values in multiple fields, so as to control the accuracy of the edge under multi-dimensional consideration, and the edge is determined when the extreme value is reached at the edge, thereby further ensuring the accuracy of the edge.

[0096] Further, the edge is associated with the gradient threshold and the anchor threshold, so as to control the edge based on the gradient threshold and the anchor threshold, thereby determining the plurality of grid lines under the influence of the gradient threshold and the anchor threshold, at this time, the gradient threshold and the anchor threshold have the following advantages.

[0097] At this time, the gradient threshold defines the gradient threshold for detecting the edge. In the edge detection process, the gradient value of the pixel point is calculated, and the pixel point with high gradient value is considered as a candidate point of the edge. The higher the gradient threshold, the only pixel point with large gradient is considered as the edge point, which may lead to more strict edge detection result, but some weak edges may be missed. On the contrary, a lower gradient threshold may include more pixel points with small gradient, but it may also cause more noise points to be mistaken as edges.

[0098] The anchor point threshold defines the threshold used in edge detection to determine anchor points. Anchor points refer to pixels that are considered strong edges in edge detection. The higher the anchor point threshold, the fewer pixels that are considered strong edges, which can result in a more strict edge detection result with clearer edge lines, but can also miss some small edges. Conversely, a lower anchor point threshold can include more pixels, but can also introduce noise or non-real edges. The anchor point threshold is like a "standard" in edge detection, which determines which pixels are considered "real edges". When this value is set very high, the algorithm becomes more "picky" and only pixels that are very obviously edges will be selected. But if this value is set very low, the algorithm can consider some pixels that are not real edges as edges, which can introduce more false information. Therefore, the role of the anchor point threshold is to help us find a balance between accuracy and comprehensiveness in order to obtain the edge detection result we need.

[0099] Referring to Figure 3 In step S12, the yaw angle is determined according to at least one of the plurality of grid lines and the posture direction of the photovoltaic cleaning robot.

[0100] In the specific implementation process of the present application, the specific steps can be:

[0101] S121: constructing a first coordinate system with the photovoltaic cleaning robot, and constructing a second coordinate system with at least one of the plurality of grid lines;

[0102] S122: comparing the second coordinate system with the first coordinate system, and determining the included angle between the second coordinate system and the first coordinate system;

[0103] S123: if the included angle between the second coordinate system and the first coordinate system is an acute angle, determining the yaw angle based on the included angle between the second coordinate system and the first coordinate system.

[0104] In the embodiments of the present application, the photovoltaic cleaning robot and the plurality of grid lines are in the same scene, a first coordinate system is constructed with the photovoltaic cleaning robot, and a second coordinate system is constructed with at least one of the plurality of grid lines, so as to compare the first coordinate system with the second coordinate system, thereby realizing comparison between the photovoltaic cleaning robot and at least one of the plurality of grid lines, and facilitating output of the yaw angle.

[0105] At this time, the second coordinate system is compared with the first coordinate system, and the included angle between the second coordinate system and the first coordinate system is determined, so as to determine the included angle, at this time, there are two cases of obtuse angle or acute angle, further, the angle identification is carried out on the included angle, so as to carry out subsequent processing for the obtuse angle, and the accuracy of the yaw angle is guaranteed. Optionally, if the included angle between the second coordinate system and the first coordinate system is an acute angle, the yaw angle is determined based on the included angle between the second coordinate system and the first coordinate system.

[0106] Please refer to Figure 4 In step S13, the target grid line is determined based on the yaw angle and the plurality of grid lines.

[0107] In the specific implementation process of the present application, the specific steps can be:

[0108] S131: determining the required preset angle range based on the yaw angle and the preset angle error;

[0109] S132: determining the target grid line according to the plurality of grid lines and the grid line angle range.

[0110] In the embodiments of the present application, the yaw angle and the preset angle error are introduced, so as to combine the yaw angle and the preset angle error, at this time, the required preset angle range is determined based on the yaw angle and the preset angle error, so as to screen the grid line in the required preset angle range, at this time, the target grid line is determined according to the plurality of grid lines and the grid line angle range, so as to further limit the target grid line and ensure that the target grid line meets the grid line angle range.

[0111] Please refer to Figure 5 S14: the grid line parallel to the target grid line is defined as the first grid line, and the plurality of first grid lines are clustered based on the density-based clustering algorithm to obtain a plurality of grid line clusters.

[0112] In the specific implementation process of the present application, the specific steps can be:

[0113] S141: the grid line parallel to the target grid line is defined as the first grid line;

[0114] S142: obtaining the preset maximum distance between the grid lines and the minimum preset number of grid lines required to form a grid line cluster;

[0115] S143: traversing the plurality of first grid lines, and determining the plurality of first grid lines having the adjacent relationship according to the plurality of first grid lines and the preset maximum distance between the grid lines;

[0116] S144: defining the number of the plurality of first grid lines having the adjacent relationship;

[0117] S145: If the number is greater than the preset minimum number of gate lines required to form one gate line cluster, the first gate lines with adjacent relationship are merged into one gate line cluster;

[0118] S146: In all gate line clusters, any gate line in one gate line cluster is viewed with any gate line in another gate line cluster;

[0119] S147: If any gate line in one gate line cluster has adjacent relationship with any gate line in another gate line cluster, the one gate line cluster and the another gate line cluster are merged.

[0120] In the embodiment of the application, the gate line parallel to the target gate line is defined as the first gate line, so that the first gate line is constructed by using the target gate line and the parallel relationship, at this time, the first gate lines are traversed, and the first gate lines with adjacent relationship are determined according to the preset maximum distance between the first gate lines and the gate lines, so as to construct the adjacent relationship based on the first gate lines, thereby defining the number of the first gate lines with adjacent relationship.

[0121] At this time, the number is compared with the preset minimum number of gate lines required to form one gate line cluster, so as to trigger the merging procedure, therefore, if the number is greater than the preset minimum number of gate lines required to form one gate line cluster, the first gate lines with adjacent relationship are merged into one gate line cluster; further, the relationship between any gate line in one gate line cluster and any gate line in another gate line cluster is determined.

[0122] Therefore, in all gate line clusters, any gate line in one gate line cluster is viewed with any gate line in another gate line cluster; if any gate line in one gate line cluster has adjacent relationship with any gate line in another gate line cluster, the one gate line cluster and the another gate line cluster are merged, thereby realizing the further merging of the one gate line cluster and the another gate line cluster, so as to further trigger the merging of the adjacent relationship of the one gate line cluster and the another gate line cluster, and ensuring the accuracy of the target gate line cluster.

[0123] Please refer to Figure 6 , S15: At least one target gate line cluster is determined based on the screening of the plurality of gate line clusters, and the center line in each target gate line cluster is selected.

[0124] In the specific implementation process of the application, the specific steps can be:

[0125] S151: Each gate line cluster is subjected to first screening, and the distance between the two gate lines located at the edge is taken as the width of the gate line cluster;

[0126] S152: If the width of the gate line cluster is greater than the preset width threshold, the gate line cluster meets the width requirement;

[0127] S153: performing second screening on each grid line cluster, and marking a plurality of gray scale collection points on the center line of each grid line cluster;

[0128] S154: collecting the gray scale corresponding to each gray scale collection point, and defining the gray scale collection point as a qualified collection point if the gray scale is greater than a preset gray scale threshold value;

[0129] S155: if the number of qualified collection points is greater than a preset number threshold value, the grid line cluster meets the brightness requirement;

[0130] S156: if the grid line cluster meets both the width requirement and the brightness requirement, the grid line cluster is a target grid line cluster;

[0131] S157: sorting each target grid line cluster, selecting a plurality of target grid line clusters with more qualified collection points, and taking the center line of the plurality of target grid line clusters as the finally selected grid line.

[0132] In the embodiments of the present application, each grid line cluster is screened multiple times. At this time, the first screening and the second screening are performed on each grid line cluster. Therefore, the distance between the two grid lines located at the edge is taken as the width of the grid line cluster in order to introduce the width of the grid line cluster. If the width of the grid line cluster is greater than a preset width threshold value, the grid line cluster meets the width requirement, thereby ensuring the initial review based on the width requirement.

[0133] Further, the second screening is performed on each grid line cluster, and a plurality of gray scale collection points are marked on the center line of each grid line cluster. The gray scale corresponding to each gray scale collection point is collected. If the gray scale is greater than a preset gray scale threshold value, the gray scale collection point is defined as a qualified collection point. If the number of qualified collection points is greater than a preset number threshold value, the grid line cluster meets the brightness requirement, thereby ensuring the secondary review based on the brightness requirement.

[0134] Therefore, if the grid line cluster meets both the width requirement and the brightness requirement, the grid line cluster is a target grid line cluster. Each target grid line cluster is sorted, and a plurality of target grid line clusters with more qualified collection points are selected. The center line of the plurality of target grid line clusters is taken as the finally selected grid line, thereby controlling multiple dimensions based on the width requirement and the brightness requirement, and further ensuring the finally selected grid line. In order to define the finally selected grid line as the center line in each target grid line cluster.

[0135] Please refer to Figure 7 , S16: measuring the initial distance between the photovoltaic cleaning robot and the center line, and taking the initial distance as the reference distance.

[0136] In the specific implementation process of the present application, the specific steps can be:

[0137] S161: collecting the position of the photovoltaic cleaning robot and the position of the center line when the photovoltaic cleaning robot is in the starting state;

[0138] S162: calculating the initial distance between the photovoltaic cleaning robot and the center line based on the position of the photovoltaic cleaning robot and the position of the center line.

[0139] In the embodiment of the present application, the photovoltaic cleaning robot enters the photovoltaic panel, the position of the photovoltaic cleaning robot and the position of the center line are collected when the photovoltaic cleaning robot is adjusted from the closed state to the starting state, at this time, the position of the photovoltaic cleaning robot is the initial position of the photovoltaic cleaning robot relative to the photovoltaic panel, and the initial distance between the photovoltaic cleaning robot and the center line is calculated based on the position of the photovoltaic cleaning robot and the position of the center line.

[0140] At this time, the initial distance is taken as the reference distance, and the subsequent trigger adjustment is performed according to the floating of the initial distance, so as to control the movement of the photovoltaic cleaning robot relative to the center line, thereby ensuring the walking condition of the photovoltaic cleaning robot on the photovoltaic panel.

[0141] Please refer to Figure 8 , S17: collecting the change amount between the current distance of the photovoltaic cleaning robot and the center line and the initial distance during the walking process of the photovoltaic cleaning robot, and triggering the straight line walking or the arc line walking of the photovoltaic cleaning robot based on the change amount.

[0142] In the specific implementation process of the present application, the specific steps can be:

[0143] S171: collecting the current distance of the photovoltaic cleaning robot and the center line during the walking process of the photovoltaic cleaning robot;

[0144] S172: determining the change amount based on the current distance of the photovoltaic cleaning robot and the center line and the initial distance;

[0145] S173: if the change amount is less than the preset amount of straight line driving, triggering the straight line walking of the photovoltaic cleaning robot;

[0146] S174: if the change amount is greater than the preset amount of straight line driving, triggering the arc line walking of the photovoltaic cleaning robot.

[0147] In the embodiment of the present application, the current distance of the photovoltaic cleaning robot and the center line is collected during the walking process of the photovoltaic cleaning robot, so as to compare the current distance of the photovoltaic cleaning robot and the center line with the initial distance, thereby determining the change amount based on the current distance of the photovoltaic cleaning robot and the center line and the initial distance, so as to trigger the straight line walking or the arc line walking of the photovoltaic cleaning robot according to the change amount.

[0148] At this time, the change amount is compared with the straight driving preset amount, if the change amount is less than the straight driving preset amount, the straight walking of the photovoltaic cleaning robot is triggered, if the change amount is greater than the straight driving preset amount, the arc walking of the photovoltaic cleaning robot is triggered.

[0149] The walking method of the photovoltaic cleaning robot based on the photovoltaic panel further comprises: collecting the relative position between the center line and the photovoltaic cleaning robot; defining the center line type according to the relative position between the center line and the photovoltaic cleaning robot, the center line type being a left center line or a right center line; if the center line type is the left center line, calculating the distance between the left center line and the photovoltaic cleaning robot; triggering the left walking of the photovoltaic cleaning robot based on the distance between the left center line and the photovoltaic cleaning robot, and triggering the follow-up walking of the photovoltaic cleaning robot according to the shape of the left center line.

[0150] The walking method of the photovoltaic cleaning robot based on the photovoltaic panel further comprises: if the center line type is the right center line, calculating the distance between the right center line and the photovoltaic cleaning robot; triggering the derivation of the left distance based on the distance between the right center line and the photovoltaic cleaning robot; in the derivation of the left distance, defining the left distance according to the distance between the right center line and the photovoltaic cleaning robot, the type of the photovoltaic panel driven by the photovoltaic cleaning robot, and the width of the photovoltaic cleaning robot; triggering the left walking of the photovoltaic cleaning robot according to the left distance.

[0151] In the embodiment of the present application, by the method in the embodiment of the present application, the gray scale diagram of the photovoltaic panel is acquired, and the edges and the plurality of grid lines are determined according to the gray scale diagram of the photovoltaic panel; the yaw angle is determined according to at least one of the plurality of grid lines and the posture direction of the photovoltaic cleaning robot; the target grid line is determined based on the yaw angle and the plurality of grid lines; the grid line parallel to the target grid line is defined as the first grid line, and the plurality of first grid lines are clustered according to the density-based clustering algorithm to obtain a plurality of grid line clusters; at least one target grid line cluster is determined based on the screening of the plurality of grid line clusters, and the center line in each target grid line cluster is selected; the initial distance between the photovoltaic cleaning robot and the center line is measured and calculated, and the initial distance is taken as the reference distance; in the walking process of the photovoltaic cleaning robot, the change quantity between the current distance and the initial distance of the photovoltaic cleaning robot and the center line is collected, and the straight line walking or the arc line walking of the photovoltaic cleaning robot is triggered based on the change quantity, at this time, the yaw angle is introduced, and the target grid line is determined based on the yaw angle and the plurality of grid lines to lead out the first grid line, the plurality of first grid lines are clustered according to the density-based clustering algorithm to obtain a plurality of grid line clusters, the accuracy of the plurality of grid line clusters is ensured, thereby the accuracy of the center line in each target grid line cluster is ensured, and then the distance type interaction between the center line and the photovoltaic cleaning robot is carried out, so as to trigger the straight line walking or the arc line walking of the photovoltaic cleaning robot based on the change quantity, and the walking control of the photovoltaic cleaning robot on the photovoltaic panel is realized to adapt to various photovoltaic panel scenes.

[0152] Embodiment

[0153] Please refer to Figure 9 , Figure 9 is the structural composition schematic diagram of the photovoltaic cleaning robot walking system based on the photovoltaic panel in the embodiment of the present application.

[0154] As Figure 9 shown, a photovoltaic cleaning robot walking system based on a photovoltaic panel includes:

[0155] The acquisition module 21 is configured to acquire a gray scale diagram of the photovoltaic panel, and determine edges and a plurality of grid lines according to the gray scale diagram of the photovoltaic panel.

[0156] The yaw angle module 22 is configured to determine a yaw angle according to at least one of the plurality of grid lines and the posture direction of the photovoltaic cleaning robot.

[0157] The target grid line module 23 is configured to determine a target grid line based on the yaw angle and the plurality of grid lines.

[0158] The clustering module 24 is configured to define a grid line parallel to the target grid line as a first grid line, and cluster a plurality of first grid lines according to a density-based clustering algorithm to obtain a plurality of grid line clusters.

[0159] The selecting module 25 is configured to determine at least one target gate line cluster based on the screening of the plurality of gate line clusters, and select a center line in each target gate line cluster;

[0160] The distance module 26 is configured to measure an initial distance between the photovoltaic cleaning robot and the center line, and take the initial distance as a reference distance;

[0161] The walking module 27 is configured to collect a change amount between a current distance between the photovoltaic cleaning robot and the center line and the initial distance during the walking of the photovoltaic cleaning robot, and trigger the photovoltaic cleaning robot to walk in a straight line or an arc line based on the change amount.

[0162] Embodiments

[0163] Please refer to Figure 10 , the electronic device 40 according to the embodiments of the present application will be described below with reference to Figure 10 . Figure 10 The electronic device 40 shown is merely an example, and should not limit the function and use range of the embodiments of the present application.

[0164] As shown in Figure 10 , the electronic device 40 is in the form of a general computing device. The components of the electronic device 40 can include, but are not limited to, the at least one processing unit 41 described above, the at least one storage unit 42 described above, and a bus 43 connecting different system components, including the storage unit 42 and the processing unit 41.

[0165] The storage unit stores program code that can be executed by the processing unit 41, so that the processing unit 41 performs the steps described in the "embodiment method" part of the present specification according to various exemplary embodiments of the present application.

[0166] The storage unit 42 can include a readable medium in the form of a volatile storage unit, such as a random access memory (RAM) 421 and / or a cache memory 422, and can further include a read-only memory (ROM) 423.

[0167] The storage unit 42 can also include program / utility 424 having a set of at least one program modules 425, including but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which can include implementation of a network environment or some combination thereof.

[0168] The bus 43 can be one or more of several types of bus structures, including a storage unit bus or storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of a variety of bus structures.

[0169] Electronic device 40 can also communicate with one or more external devices such as a keyboard or a pointing device, a Bluetooth device, etc.; other devices that enable a user to interact with electronic device 40; and / or any devices (e.g., a router, a modem, a peer device or other computing device) that enable electronic device 40 to communicate with one or more other computing devices. Such communication can occur via Input / Output (I / O) interface 44. Still yet, electronic device 40 can communicate with one or more networks, such as a local area network (LAN), a wide area network (WAN), and / or the Internet, through network adapter 45. As Figure 7 illustrated, network adapter 45 can communicate with the other components of electronic device 40 through bus 43. It should be understood that although not shown, other hardware and / or software components could be used in conjunction with electronic device 40. Examples, include, but are not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data archival Figure 7 systems, etc.

[0170] Those skilled in the art will readily observe that the example embodiments described herein can be implemented in a software application, firmware application, circuit, and / or hardware. As such, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.) or network, and includes a number of instructions to make a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) execute the methods according to the embodiments of the present disclosure.

[0171] Those skilled in the art will readily observe that all or part of the methods of the above embodiments can be implemented by programs instructing relevant hardware, and the programs can be stored in a computer readable storage medium, which can include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc. Moreover, the storage medium has computer program instructions stored therein, and when the computer program instructions are executed by a computer, the computer executes the methods according to the above embodiments.

[0172] In addition, the above describes in detail the walking method and system of the photovoltaic cleaning robot based on the photovoltaic panel provided by the embodiment of the present application. The principle and implementation manner of the present application are described by using specific examples in this paper. The above description of the embodiments is only used to help understand the method of the present application and its core idea. Meanwhile, for those skilled in the art, the specific implementation manner and application range will be changed according to the idea of the present application. In summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. A photovoltaic cleaning robot based on the walking method of photovoltaic panels, characterized by, The application is applied to the scene that a photovoltaic cleaning robot walks on a photovoltaic panel; the walking method of the photovoltaic cleaning robot based on the photovoltaic panel comprises the following steps: An image of the photovoltaic panel is acquired, and edges and a plurality of grid lines are determined according to the image of the photovoltaic panel; A yaw angle is determined according to at least one of the plurality of grid lines and the posture direction of the photovoltaic cleaning robot; A target grid line is determined based on the yaw angle and the plurality of grid lines; A grid line parallel to the target grid line is defined as a first grid line, and the plurality of first grid lines are clustered according to a density-based clustering algorithm to obtain a plurality of grid line clusters; At least one target grid line cluster is determined based on the screening of the plurality of grid line clusters, and a center line in each target grid line cluster is selected, comprising: a first screening of each grid line cluster, and a distance between two grid lines located at the edges is taken as a width of the grid line cluster; if the width of the grid line cluster is greater than a preset width threshold, the grid line cluster meets the width requirement; a second screening of each grid line cluster, and a plurality of gray scale collection points are marked on the center line of each grid line cluster; a gray scale corresponding to each gray scale collection point is collected, and if the gray scale is greater than a preset gray scale threshold, the gray scale collection point is defined as a qualified collection point; if the number of qualified collection points is greater than a preset number threshold, the grid line cluster meets the brightness requirement; if the grid line cluster meets both the width requirement and the brightness requirement, the grid line cluster is a target grid line cluster; each target grid line cluster is sorted, and a plurality of target grid line clusters with more qualified collection points are selected, and the center lines of the plurality of target grid line clusters are taken as the finally selected grid lines; An initial distance between the photovoltaic cleaning robot and the center line is measured, and the initial distance is taken as a reference distance; In the walking process of the photovoltaic cleaning robot, a change between a current distance between the photovoltaic cleaning robot and the center line and the initial distance is collected, and a straight line walking or an arc line walking of the photovoltaic cleaning robot is triggered based on the change.

2. The photovoltaic cleaning robot based on the walking method of the photovoltaic panel according to claim 1, characterized in that, The acquisition of the image of the photovoltaic panel and the determination of the edges and the plurality of grid lines according to the image of the photovoltaic panel comprises the following steps: The image of the photovoltaic panel is acquired; The edges are determined based on the image of the photovoltaic panel and an EdgeDrawing algorithm, wherein a Sobel operator is introduced in the EdgeDrawing algorithm, a weighted difference of gray scales of four fields of each pixel in the image of the photovoltaic panel is calculated based on the Sobel operator, and the edges are determined when the weighted difference reaches an extreme value at the edges; The plurality of grid lines are determined based on the edges, a gradient threshold and an anchor threshold.

3. The photovoltaic cleaning robot based on the walking method of the photovoltaic panel according to claim 1, characterized in that, The determination of the yaw angle according to at least one of the plurality of grid lines and the posture direction of the photovoltaic cleaning robot comprises the following steps: A first coordinate system is constructed by the photovoltaic cleaning robot, and a second coordinate system is constructed by at least one of the plurality of grid lines; The second coordinate system is compared with the first coordinate system, and an included angle between the second coordinate system and the first coordinate system is determined; If the included angle between the second coordinate system and the first coordinate system is an acute angle, the yaw angle is determined based on the included angle between the second coordinate system and the first coordinate system.

4. The photovoltaic cleaning robot based on the walking method of the photovoltaic panel according to claim 3, characterized in that, The determination of the target grid line based on the yaw angle and the plurality of grid lines comprises the following steps: A preset angle range meeting the requirement is determined based on the yaw angle and a preset angle error; The target grid line is determined according to the plurality of grid lines and the angle range of the grid lines.

5. The photovoltaic cleaning robot based on the walking method of the photovoltaic panel according to claim 1, characterized in that, The gate line parallel to the target gate line is defined as a first gate line, and the plurality of first gate lines are clustered according to a density-based clustering algorithm to obtain a plurality of gate line clusters, including: The gate line parallel to the target gate line is defined as a first gate line; Obtaining a preset maximum distance between the gate lines and a minimum preset number of gate lines required to form a gate line cluster; Iterating through the plurality of first gate lines, and determining a plurality of first gate lines having an adjacent relationship according to the plurality of first gate lines and the preset maximum distance between the gate lines; Defining the number of the plurality of first gate lines having the adjacent relationship; If the number is greater than the minimum preset number of gate lines required to form a gate line cluster, the plurality of first gate lines having the adjacent relationship are merged into a gate line cluster; In all gate line clusters, any gate line in a gate line cluster is viewed with any gate line in another gate line cluster; If any gate line in a gate line cluster has an adjacent relationship with any gate line in another gate line cluster, the gate line cluster and the other gate line cluster are merged.

6. The photovoltaic cleaning robot based on the walking method of the photovoltaic panel according to claim 1, characterized in that, The initial distance between the photovoltaic cleaning robot and the center line is calculated, and the initial distance is taken as a reference distance, including: When the photovoltaic cleaning robot is in a starting state, the position of the photovoltaic cleaning robot and the position of the center line are collected; The initial distance between the photovoltaic cleaning robot and the center line is calculated based on the position of the photovoltaic cleaning robot and the position of the center line; Alternatively, during the walking process of the photovoltaic cleaning robot, the change amount between the current distance of the photovoltaic cleaning robot and the center line and the initial distance is collected, and the change amount is used to trigger the straight-line walking or arc-line walking of the photovoltaic cleaning robot, including: During the walking process of the photovoltaic cleaning robot, the current distance of the photovoltaic cleaning robot and the center line is collected; The change amount is determined based on the current distance of the photovoltaic cleaning robot and the center line and the initial distance; If the change amount is less than a preset amount of straight-line driving, the straight-line walking of the photovoltaic cleaning robot is triggered; If the change amount is greater than the preset amount of straight-line driving, the arc-line walking of the photovoltaic cleaning robot is triggered.

7. The photovoltaic cleaning robot based on the walking method of the photovoltaic panel according to claim 1, characterized in that, The walking method of the photovoltaic cleaning robot based on the photovoltaic panel further includes: Collecting the relative position between the center line and the photovoltaic cleaning robot; Defining the center line type according to the relative position between the center line and the photovoltaic cleaning robot, the center line type being a left center line or a right center line; If the center line type is a left center line, the distance between the left center line and the photovoltaic cleaning robot is calculated; Based on the distance between the left center line and the photovoltaic cleaning robot, the left-side walking of the photovoltaic cleaning robot is triggered, and according to the shape of the left center line, the follow-up walking of the photovoltaic cleaning robot is triggered.

8. Photovoltaic cleaning robot based on a method of walking of a photovoltaic panel according to claim 7, characterized in that, The walking method of the photovoltaic cleaning robot based on the photovoltaic panel further includes: If the center line type is a right center line, the distance between the right center line and the photovoltaic cleaning robot is calculated; Based on the distance between the right center line and the photovoltaic cleaning robot, the left-side distance derivation is triggered; In the left-side distance derivation, the left-side distance is defined according to the distance between the right center line and the photovoltaic cleaning robot, the type of the photovoltaic panel driven by the photovoltaic cleaning robot, and the width of the photovoltaic cleaning robot; According to the left-side distance, the left-side walking of the photovoltaic cleaning robot is triggered.

9. A photovoltaic cleaning robot based on a walking system of photovoltaic panels, characterized by, The photovoltaic cleaning robot based on the walking system of the photovoltaic panel is applied to the photovoltaic cleaning robot based on the walking method of the photovoltaic panel, and the photovoltaic cleaning robot based on the walking system of the photovoltaic panel comprises: An acquisition module is configured to acquire a grayscale image of the photovoltaic panel and determine edges and a plurality of grid lines based on the grayscale image of the photovoltaic panel; A yaw angle module is configured to determine a yaw angle based on at least one of the plurality of grid lines and a posture direction of the photovoltaic cleaning robot; A target grid line module is configured to determine a target grid line based on the yaw angle and the plurality of grid lines; A clustering module is configured to define a first grid line as a grid line parallel to the target grid line, and perform clustering on a plurality of first grid lines based on a density-based clustering algorithm to obtain a plurality of grid line clusters; A selection module is configured to determine at least one target grid line cluster based on screening of the plurality of grid line clusters, and select a center line in each target grid line cluster, including: performing a first screening on each grid line cluster, and taking a distance between two grid lines located at the edges as a width of the grid line cluster; if the width of the grid line cluster is greater than a preset width threshold, the grid line cluster meets a width requirement; performing a second screening on each grid line cluster, and marking a plurality of grayscale acquisition points on the center line of each grid line cluster; acquiring a grayscale corresponding to each grayscale acquisition point, and defining the grayscale acquisition point as a qualified acquisition point if the grayscale is greater than a preset grayscale threshold; if the number of qualified acquisition points is greater than a preset number threshold, the grid line cluster meets a brightness requirement; if the grid line cluster meets both the width requirement and the brightness requirement, the grid line cluster is a target grid line cluster; sorting each target grid line cluster, and selecting a plurality of target grid line clusters with more qualified acquisition points, and taking the center lines of the plurality of target grid line clusters as the finally selected grid lines; A distance module is configured to measure an initial distance between the photovoltaic cleaning robot and the center line, and take the initial distance as a reference distance; A walking module is configured to, in a walking process of the photovoltaic cleaning robot, acquire a change amount between a current distance between the photovoltaic cleaning robot and the center line and the initial distance, and trigger straight-line walking or arc-line walking of the photovoltaic cleaning robot based on the change amount.

Images