Method and system for automatically generating cleaning trolley path on edge of photovoltaic panel
By constructing the vehicle body coordinate system on the photovoltaic panel, collecting and calibrating the lidar point cloud data, acquiring the panel edge data linear equation, and generating a global path in combination with safe distances, the problem of cleaning the edge collision between the car and the photovoltaic panel in the existing technology is solved, and more accurate and stable path generation is achieved.
Patent Information
- Application Number
- CN202411712645.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-27
- Publication Date
- 2025-02-25
AI Technical Summary
The existing photovoltaic panel cleaning car path generation method is difficult to effectively avoid collision between the cleaning car and the edge of the photovoltaic panel, especially because there are small fluctuations in the lower edge information of the photovoltaic panel calculated by the lidar, resulting in local path fluctuations and lateral fluctuations in the vehicle's walking.
By setting the starting point of cleaning the car on the photovoltaic panel, building the vehicle body coordinate system, collecting lidar point cloud data and calibrating it to the vehicle body coordinate system, linear fitting is performed based on the point cloud data to obtain the linear equation of the panel edge data, combining the safe distance to obtain the path point, building a global path and generating a local frenet path to avoid collision.
It effectively avoids collision between the cleaning car and the edges of the photovoltaic panel, improves the accuracy and stability of path generation, and reduces the lateral fluctuations of the vehicle's walking.
Smart Images
Figure CN119512118A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of local path planning, and in particular to a method and system for automatically generating a path for a cleaning trolley at the edge of a photovoltaic panel. Background Art
[0002] The surface of photovoltaic panels is often cleaned by a cleaning cart. When the cleaning cart cleans the photovoltaic panels, it moves along the center line of the road set on the surface of the photovoltaic panels, or travels along a local path planned by the center line of the road. When setting the center line of the road, the position of each row of photovoltaic panels on the edge of the center line of the road is not taken into consideration, which will cause a collision between the automatically moving cleaning cart and the edge of the photovoltaic panel.
[0003] The existing solution is to generate a new local path based on the bottom edge information of the photovoltaic panel to avoid collision with the edge of the photovoltaic panel, and there is no need to draw a global road network in the area covered by the photovoltaic panel. The disadvantage of this technology is that the bottom edge information of the photovoltaic panel calculated by the lidar will have slight fluctuations, which will cause fluctuations in the local path and lateral fluctuations in the vehicle's movement. There is still the problem of collision between the cleaning car and the edge of the photovoltaic panel. Summary of the invention
[0004] The present invention provides a method and system for automatically generating a path for a cleaning trolley at the edge of a photovoltaic panel, so as to solve the problem that the existing path generation causes the cleaning trolley to collide with the edge of the photovoltaic panel.
[0005] In order to achieve the above object, the present invention is implemented by the following technical solutions: In a first aspect, the present invention provides a method for automatically generating a cleaning trolley path at the edge of a photovoltaic panel, comprising: Step 1: Set the starting point of the cleaning vehicle on the photovoltaic panel to be cleaned, build the vehicle coordinate system based on the starting point, collect the LiDAR point cloud data of the photovoltaic panel to be cleaned, and calibrate the LiDAR point cloud data to the vehicle coordinate system; Step 2: Perform linear fitting based on the laser radar point cloud data to obtain the straight line equation of the panel edge data; Step 3: Based on the starting point coordinates and the panel edge data straight line equation, calibrate the coordinates of several photovoltaic panel edge points, and then combine the safety distance to obtain several path points in the map coordinate system. According to several path points, a global path is constructed, and a local frenet path is constructed based on the global path as the local path of the cleaning car.
[0006] Furthermore, the step 2 specifically includes: clustering and segmenting the edge area of the photovoltaic panel to be cleaned in the lidar point cloud data to obtain a number of clustered point cloud data, and obtaining the straight line equation of the panel edge data based on the clustered point cloud data fitting.
[0007] Furthermore, the method of obtaining the straight line equation of panel edge data based on clustered point cloud data fitting includes: firstly performing plane fitting based on the clustered point cloud data to obtain plane point cloud data, then performing plane projection to remove noise, and selecting edge data in the plane projection to fit and obtain the straight line equation of panel edge data.
[0008] Furthermore, the plane fitting comprises the following steps: Select three points in the clustered point cloud data, calculate the fitting plane, further calculate the distances of all other points to the plane, and mark the points that are less than the error threshold. If the number of marked points exceeds the preset number, the plane is recorded as a valid plane. Repeat the above steps and select the valid plane with the largest number of marked points as the plane fitting result.
[0009] Furthermore, the step of selecting edge data in plane projection to fit and obtain the straight line equation of panel edge data includes the following steps: Select two points in the edge data of the plane projection to fit the straight line, calculate the distance from all points in the edge data to the straight line, and mark the points that are less than the error threshold. If the number of marked points exceeds the preset number, the straight line is recorded as a valid straight line. Repeat the above steps and select the expression equation of the valid straight line with the largest number of marked points as the straight line equation of the panel edge data.
[0010] Furthermore, in step 3, the coordinates of several photovoltaic panel edge points are calibrated based on the starting point coordinates of the starting point combined with the straight line equation of the panel edge data, including: according to the starting point coordinates of the starting point, the coordinates of several panel edge points are selected by incrementally taking values on the straight line equation of the panel edge data according to a predetermined incremental value.
[0011] Furthermore, the acquiring of a plurality of path points in a map coordinate system in combination with the safety distance includes: adjusting the coordinates of the edge points of the photovoltaic panel in combination with the safety distance, and then converting them into the map coordinate system to acquire a plurality of path points.
[0012] Furthermore, adjusting the coordinates of the edge points of the photovoltaic panel in combination with the safety distance includes: converting the coordinates of the edge points of the photovoltaic panel from the vehicle body coordinate system to the frent coordinate system, and then adjusting the D coordinates of the coordinates of all the edge points of the photovoltaic panel in combination with the safety distance.
[0013] In a second aspect, the present invention also provides a system for automatically generating local paths based on the edges of photovoltaic panels, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above methods when executing the computer program.
[0014] Beneficial effects: The present invention provides a method and system for automatically generating a cleaning cart path based on the edge of a photovoltaic panel. The method adjusts the future driving trajectory of the cleaning cart by adjusting the coordinates of the edge of the photovoltaic panel in the vehicle coordinate system and the relative position of the vehicle body, thereby avoiding collision between the cleaning cart and the edge of the photovoltaic panel. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] Figure 1 A flow chart of a method for automatically generating a cleaning trolley path at the edge of a photovoltaic panel according to an embodiment of the present invention; Figure 2 It is a schematic diagram of laser radar point cloud data calibrated to a vehicle body coordinate system in an embodiment of the present invention; Figure 3 A schematic diagram of obtaining a plane point cloud by performing plane fitting on clustered point cloud data in an embodiment of the present invention. DETAILED DESCRIPTION
[0016] The technical solution of the present invention is described clearly and completely below. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0017] Unless otherwise defined, the technical terms or scientific terms used in the present invention shall have the usual meanings understood by persons with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, words such as "one" or "one" do not indicate quantity restrictions, but indicate the existence of at least one. Words such as "connect" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship also changes accordingly.
[0018] See also Figure 1 The embodiment of the present application provides a method for automatically generating a cleaning trolley path at the edge of a photovoltaic panel, comprising: Step 1: Set the starting point of the cleaning vehicle on the photovoltaic panel to be cleaned, build the vehicle coordinate system based on the starting point, collect the LiDAR point cloud data of the photovoltaic panel to be cleaned, and calibrate the LiDAR point cloud data to the vehicle coordinate system; See also Figure 2 ,exist Figure 2 The figure shows the laser radar point cloud data calibrated to the vehicle coordinate system.
[0019] Step 2: Perform linear fitting based on the lidar point cloud data to obtain the straight line equation of the panel edge data; Specifically, clustering and segmenting are performed on the edge areas of the photovoltaic panels to be cleaned in the laser radar point cloud data to obtain a number of clustered point cloud data; See also Figure 3 , select three points in the clustered point cloud data, calculate the fitting plane, further calculate the distances from all other points to the plane, and mark the points that are less than the error threshold. If the number of marked points exceeds the preset number, the plane is recorded as a valid plane, and the calculation process of the valid plane is repeated. The valid plane with the largest number of marked points is selected as the plane fitting result; Based on the plane fitting results, the plane point cloud data is obtained, and then the plane projection is performed to remove noise. Two points are selected in the edge data of the plane projection to fit the straight line. The distance from all points in the edge data to the straight line is calculated, and the points within 5 cm are marked. If there are more than 3 marked points, the straight line is recorded as a valid straight line, and the calculation process of the valid straight line is repeated. The expression equation of the valid straight line with the largest number of marked points is selected as the straight line equation. The noise effect is eliminated through plane fitting, and the noise effect is further eliminated by combining plane projection, making the obtained straight line equation more accurate.
[0020] Step 3: Based on the starting point coordinates and the panel edge data straight line equation, calibrate the coordinates of several photovoltaic panel edge points, and then combine the safety distance to obtain several path points in the map coordinate system. According to several path points, a global path is constructed, and a local frenet path is constructed based on the global path as the local path of the cleaning car.
[0021] In this embodiment, according to the starting point coordinates of the starting point, the coordinates of several panel edge points are selected on the straight line equation according to the predetermined incremental value, the coordinates of the photovoltaic panel edge points are converted from the vehicle body coordinate system to the frent coordinate system, and then the D coordinates of the coordinates of all photovoltaic panel edge points are adjusted in combination with the safety distance, and then converted to the map coordinate system to obtain several path points, a global path is constructed according to the several path points, and a local frenet path is constructed based on the global path as the local path of the cleaning car.
[0022] For example, the X coordinate of the starting point is incremented by 0.4m, the coordinates of 10 panel edge points are selected, and the coordinates of the photovoltaic panel edge points are converted to the frent coordinate system. The d coordinates of all points are 0, and the s coordinates are the accumulation of the distances between each point. Combined with the set safety distance of 1.5m, all s coordinates remain unchanged, and the d coordinates are changed to -1.5. After the modification, the 10 points are converted from the frent coordinate system to the map coordinate system, and a global path is constructed according to several path points. Based on the global path, a local frenet path is constructed as the local path of the cleaning car.
[0023] An embodiment of the present application also provides a system for automatically generating a cleaning cart path at the edge of a photovoltaic panel, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the methods in the above embodiments are implemented.
[0024] The preferred specific embodiments of the present invention are described in detail above. It should be understood that a person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the concept of the present invention on the basis of the prior art should be within the scope of protection determined by the claims.
Claims
1. A method for automatically generating a cleaning trolley path at the edge of a photovoltaic panel, characterized in that: The steps include: Step 1: Set the starting point of the cleaning vehicle on the photovoltaic panel to be cleaned, build the vehicle coordinate system based on the starting point, collect the LiDAR point cloud data of the photovoltaic panel to be cleaned, and calibrate the LiDAR point cloud data to the vehicle coordinate system; Step 2: Perform linear fitting based on the laser radar point cloud data to obtain the straight line equation of the panel edge data; Step 3: Based on the starting point coordinates and the panel edge data straight line equation, calibrate the coordinates of several photovoltaic panel edge points, and then combine the safety distance to obtain several path points in the map coordinate system. According to several path points, a global path is constructed, and a local frenet path is constructed based on the global path as the local path of the cleaning car.
2. The method for automatically generating a cleaning trolley path for the edge of a photovoltaic panel according to claim 1, characterized in that: The step 2 specifically includes: clustering and segmenting the edge area of the photovoltaic panel to be cleaned in the lidar point cloud data to obtain a number of clustered point cloud data, and obtaining the straight line equation of the panel edge data based on the clustered point cloud data fitting.
3. The method for automatically generating a cleaning trolley path for the edge of a photovoltaic panel according to claim 2, characterized in that: The method of obtaining the straight line equation of panel edge data based on clustered point cloud data fitting includes: firstly performing plane fitting based on clustered point cloud data to obtain plane point cloud data, then performing plane projection to remove noise, and selecting edge data in the plane projection to obtain the straight line equation of panel edge data fitting.
4. The method for automatically generating a cleaning trolley path for the edge of a photovoltaic panel according to claim 3, characterized in that: The plane fitting comprises the following steps: Select three points in the clustered point cloud data, calculate the fitting plane, further calculate the distances of all other points to the plane, and mark the points that are less than the error threshold. If the number of marked points exceeds the preset number, the plane is recorded as a valid plane. Repeat the above steps and select the valid plane with the largest number of marked points as the plane fitting result.
5. The method for automatically generating a cleaning trolley path for the edge of a photovoltaic panel according to claim 3, characterized in that: The step of selecting edge data in plane projection to fit and obtain the straight line equation of panel edge data comprises the following steps: Select two points in the edge data of the plane projection to fit the straight line, calculate the distance from all points in the edge data to the straight line, and mark the points that are less than the error threshold. If the number of marked points exceeds the preset number, the straight line is recorded as a valid straight line. Repeat the above steps and select the expression equation of the valid straight line with the largest number of marked points as the straight line equation of the panel edge data.
6. The method for automatically generating a cleaning trolley path for the edge of a photovoltaic panel according to any one of claims 1 to 5, characterized in that: In step 3, the coordinates of several photovoltaic panel edge points are calibrated based on the starting point coordinates of the starting point combined with the panel edge data straight line equation, including: according to the starting point coordinates of the starting point, the coordinates of several panel edge points are selected by incrementally selecting values according to a predetermined incremental value on the panel edge data straight line equation.
7. The method for automatically generating a cleaning trolley path for the edge of a photovoltaic panel according to any one of claims 1 to 5, characterized in that: The acquiring of a plurality of path points in a map coordinate system in combination with a safety distance comprises: adjusting the coordinates of the edge points of the photovoltaic panel in combination with the safety distance, and then converting them into a map coordinate system to acquire a plurality of path points.
8. The method for automatically generating a cleaning trolley path for the photovoltaic panel edge according to claim 7, characterized in that: The adjusting the coordinates of the edge points of the photovoltaic panel in combination with the safety distance includes: converting the coordinates of the edge points of the photovoltaic panel from the vehicle body coordinate system to the frent coordinate system, and then adjusting the D coordinates of the coordinates of all the edge points of the photovoltaic panel in combination with the safety distance.
9. A system for automatically generating a cleaning vehicle path at the edge of a photovoltaic panel, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 8 are implemented.