Photovoltaic motor sweeper and control method thereof

Abstract

The invention discloses a photovoltaic motor sweeper and a control method thereof, the photovoltaic motor sweeper comprises a photovoltaic motor sweeper body, a binocular camera and a camera image processing and calculating unit, and the control method comprises the following steps: acquiring an image, calculating three-dimensional information and color information, segmenting a travelable area, calculating a local gradient, and obtaining a travelable route. According to the photovoltaic sweeper disclosed by the invention, based on a binocular camera, obstacles, photovoltaic modules and a travelable area on a sweeping path in the driving direction are segmented through a specific control mode, and the local gradient of a virtual lane is obtained through calculation, so that a travelable route is determined; the automatic sweeping operation that the photovoltaic sweeper automatically bypasses obstacles and abrupt slopes capable of being bypassed is achieved, and compared with an existing control mode and a photovoltaic sweeper, the map building cost and the production and purchase cost of the photovoltaic sweeper are saved.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic driving of photovoltaic sweepers, and in particular to a photovoltaic sweeper capable of dividing a traversable area and detecting and calculating a local slope to form a traversable route, and a control method thereof. Background Art

[0002] With the development of economy, solar energy is widely studied and used as a clean energy, photovoltaic power generation is increasing year by year, and the photovoltaic power generation industry is getting more and more attention. In the research of photovoltaic power generation system, dust, bird droppings, sand and gravel attached to the surface of photovoltaic modules will affect the normal power generation of photovoltaic power generation system. Existing large-scale photovoltaic power stations generally install photovoltaic sweepers to automatically clean photovoltaic modules, and the automatic cleaning of bright panels is achieved through the cleaning components of the sweeper and the movement of the sweeper.

[0003] The existing autonomous driving technology for photovoltaic cleaning vehicles mainly relies on a map established in advance to locate the position of the cleaning vehicle in the map, and plans the path in advance for autonomous driving (such as a patented path planning and obstacle avoidance method for a photovoltaic power station cleaning robot and a patented control method and system for a photovoltaic cleaning robot). However, the establishment of the entire map of this method requires a lot of time and effort, and it also requires the cooperation of multiple sensors (such as lidar, satellite signal positioning sensors, camera positioning sensors, etc.). The path planning mechanism is complex, and the production cost of photovoltaic cleaning vehicles is high. Summary of the invention

[0004] The present invention provides a photovoltaic sweeper and a control method thereof, which are used to solve the technical problems mentioned in the background technology.

[0005] In order to solve the above technical problems, the technical solution proposed by the present invention is: A photovoltaic sweeper comprises a photovoltaic sweeper body, a binocular camera and a camera image processing and computing unit. The binocular camera is installed on the photovoltaic sweeper body to obtain environmental image information of the direction of the photovoltaic sweeper's driving path; the camera image processing and computing unit is used to process the environmental image information, obtain a drivable route, and send the drivable route to the photovoltaic sweeper body.

[0006] Based on the same technical concept, the present invention also provides a control method for the above-mentioned photovoltaic sweeper, comprising the following steps: S1, obtaining environmental image information in the driving direction through the binocular camera of the photovoltaic sweeper; S2, performing real-time processing on the environmental image information by the camera image processing and calculation unit to obtain three-dimensional point cloud information and color information of the environmental surface in the driving direction, and identifying and separating the drivable area and the non-drivable area based on the three-dimensional point cloud information and color information; S3. Construct a virtual lane in the drivable area and calculate the local slope of the virtual lane; control the action of the photovoltaic sweeper according to the local slope: if the local slope of the virtual lane is greater than the preset maximum climbing limit of the photovoltaic sweeper, reselect the virtual lane in the parallel direction of the virtual lane and calculate the slope of the new virtual lane until the local slope of the new virtual lane is less than or equal to the preset maximum climbing limit of the photovoltaic sweeper. The new virtual lane that meets the above conditions is used as a drivable route, and the photovoltaic sweeper is controlled to travel along the drivable route.

[0007] As a further preferred embodiment of the above technical solution, in S2, the three-dimensional point cloud information and color information of the environmental surface are obtained by the camera image processing calculation unit according to the environmental image information and the binocular vision algorithm.

[0008] As a further preferred embodiment of the above technical solution, in S2, the camera image processing and calculation unit identifies and separates the drivable area and the non-drivable area according to the three-dimensional point cloud information and color information through a deep learning segmentation method or a conventional image area classification segmentation method.

[0009] As a further optimization of the above technical solution, the calculation method of the local slope of the virtual lane in S3 is: take the front position of the photovoltaic sweeper as the positive direction of the x-axis, take the left position of the photovoltaic sweeper perpendicular to the x-axis as the positive direction of the y-axis, and take the vertical upward direction as the positive direction of the z-axis to construct a coordinate system, select the first side-by-side three-dimensional point coordinates visible to the binocular camera of the photovoltaic sweeper as the calculation base point of the current virtual lane and the new virtual lane in the parallel direction, and use the calculation base point coordinates (x0, y, z0) of the current virtual lane to select a three-dimensional point (x0) with a distance δ from the base point in the positive direction of the x-axis. δ1 ,y,z δ1 ), calculate the slope as (z δ1 -z0) / (x δ1 -x0).

[0010] As a further optimization of the above technical solution, when the local slope of the current virtual lane is greater than the preset maximum climbing limit of the photovoltaic sweeper, and a new virtual lane is reselected in the parallel direction of the current virtual lane, the calculation base point coordinates (x n ,y n , z n ), select a three-dimensional point (x δn ,y,z δn ), calculate the slope as (z δn -z0) / (x δn -x0).

[0011] As a further preferred embodiment of the above technical solution, the distance δ is set according to the minimum distance of different photovoltaic sweepers' travel slopes.

[0012] As a further optimization of the above technical solution, if the local slopes of the current virtual lane and all parallel virtual lanes in the passable area are greater than the preset maximum climbing limit of the photovoltaic sweeper, it is determined whether the drivable area meets the minimum U-turn area requirement. If so, a U-turn operation is performed, and if not, a reversing operation is performed.

[0013] The present invention has the following beneficial effects: The photovoltaic sweeper of the present invention divides obstacles, photovoltaic modules and drivable areas on the cleaning path in the driving direction based on a binocular camera through a specific control method, and obtains the local slope of the virtual lane through calculation, thereby determining the drivable route, and realizing the photovoltaic sweeper's automatic cleaning operation of automatically bypassing circumventable obstacles and steep slopes. Compared with the existing control method and photovoltaic sweeper, it saves map construction costs and photovoltaic sweeper production and procurement costs.

[0014] The present invention will be further described in detail below with reference to specific implementation modes. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 Schematic diagram of the process of controlling the photovoltaic sweeper of Example 1; Figure 2 This is a schematic diagram of the driving of the photovoltaic sweeper of Example 1; Figure 3 The three-dimensional point cloud information and color information of the environment surface in the driving direction obtained according to the binocular vision algorithm in Example 1; Figure 4 The drivable area and the non-drivable area are separated and obtained in Example 1. DETAILED DESCRIPTION

[0016] The embodiments of the present invention are described in detail below with reference to the accompanying drawings, but the present invention can be implemented in many different ways as defined and covered by the claims.

[0017] Embodiment 1: The photovoltaic sweeper of this embodiment includes a photovoltaic sweeper body, a binocular camera and a camera image processing and computing unit. The binocular camera is installed on the photovoltaic sweeper body to obtain environmental image information in the direction of the photovoltaic sweeper's driving path; the camera image processing and computing unit is used to process the environmental image information, obtain a drivable route, and send the drivable route to the photovoltaic sweeper body.

[0018] like Figure 1 As shown, the control method of the photovoltaic sweeper of this embodiment includes the following steps: S1, obtaining environmental image information in the driving direction through the binocular camera of the photovoltaic sweeper; S2, the environment image information is processed in real time by the camera image processing calculation unit, and the three-dimensional point cloud information and color information of the environment surface in the driving direction are obtained according to the binocular vision algorithm. Figure 3 For example, the environmental image information in the driving direction obtained by the binocular camera is the RGB image on the left. After real-time processing, the point cloud image on the right is obtained according to the binocular vision algorithm. The RGB image corresponds to the point cloud on the right, that is, the ground area segmented by the left RGB image corresponds to the point cloud area on the right. The color value of each 3D point can be rendered as the segmented area of ​​the RGB image. The drivable area and the non-drivable area are identified and separated based on the 3D point cloud information and color information through the deep learning segmentation method (the conventional process in the field of artificial intelligence - data collection, annotation, training of deep learning models, and reasoning to obtain the results). The drivable area is Figure 4 The area outlined by red lines is shown in the figure; S3. Construct a virtual lane in the drivable area (that is, a drivable lane scheme, not a lane constructed on a real virtual engine), calculate the local slope of the virtual lane; control the action of the photovoltaic sweeper according to the local slope: if the local slope of the virtual lane is greater than the preset maximum climbing limit of the photovoltaic sweeper, reselect the virtual lane in the parallel direction of the virtual lane and calculate the slope of the new virtual lane until the local slope of the new virtual lane is less than or equal to the preset maximum climbing limit of the photovoltaic sweeper. The new virtual lane that meets the above conditions is used as a passable route, and the photovoltaic sweeper is controlled to drive along the passable route. Figure 2 As shown in the figure, the calculation method of the local slope of the virtual lane is as follows: the front direction of the photovoltaic sweeper is taken as the positive direction of the x-axis, the left direction of the photovoltaic sweeper perpendicular to the x-axis is taken as the positive direction of the y-axis, and the vertically upward direction is taken as the positive direction of the z-axis to construct a coordinate system, and the coordinates of the first parallel 3D points visible to the binocular camera of the photovoltaic sweeper are selected as the calculation base points of the current virtual lane and the new virtual lane in the parallel direction, and the calculation base point coordinates (x0, y, z0) of the current virtual lane are used to select a 3D point (x0) with a distance δ from the base point in the positive direction of the x-axis. δ1 ,y,z δ1 ), calculate the slope as (z δ1 -z0) / (x δ1 -x0), when the local slope of the current virtual lane is greater than the preset maximum climbing limit of the photovoltaic sweeper, and a new virtual lane is reselected in the parallel direction of the current virtual lane, the calculation base point coordinates (x n ,y n , z n ), select a three-dimensional point (xδn ,y,z δn ), calculate the slope as (z δn -z0) / (x δn -x0). If the local slopes of the current virtual lane and all parallel virtual lanes in the passable area are greater than the preset maximum climbing limit of the photovoltaic sweeper, it is determined whether the drivable area meets the minimum U-turn area requirements (which can be achieved by judging data including turning radius, vehicle length, etc., that is, whether the vehicle can make a U-turn at this position without collision). If so, the U-turn operation is performed, and if not, the reversing operation is performed.

[0019] The above are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited to the above embodiments. For those skilled in the art, improvements and changes obtained without departing from the technical concept of the present invention should also be regarded as the protection scope of the present invention.

[0020] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are illustrative and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A photovoltaic sweeper, characterized in that: It includes a photovoltaic sweeper body, a binocular camera and a camera image processing and computing unit. The binocular camera is installed on the photovoltaic sweeper body to obtain environmental image information in the direction of the photovoltaic sweeper's driving path; the camera image processing and computing unit is used to process the environmental image information, obtain a passable route, and send the passable route to the photovoltaic sweeper body.

2. A control method for a photovoltaic sweeper according to claim 1, characterized in that: The following steps are involved: S1, obtaining environmental image information in the driving direction through the binocular camera of the photovoltaic sweeper; S2, performing real-time processing on the environmental image information by the camera image processing and calculation unit to obtain three-dimensional point cloud information and color information of the environmental surface in the driving direction, and identifying and separating the drivable area and the non-drivable area based on the three-dimensional point cloud information and color information; S3. Construct a virtual lane in the drivable area and calculate the local slope of the virtual lane; control the action of the photovoltaic sweeper according to the local slope: if the local slope of the virtual lane is greater than the preset maximum climbing limit of the photovoltaic sweeper, reselect the virtual lane in the parallel direction of the virtual lane and calculate the slope of the new virtual lane until the local slope of the new virtual lane is less than or equal to the preset maximum climbing limit of the photovoltaic sweeper. The new virtual lane that meets the above conditions is used as a drivable route, and the photovoltaic sweeper is controlled to travel along the drivable route.

3. The control method according to claim 2, characterized in that: In S2, the three-dimensional point cloud information and color information of the environment surface are obtained by the camera image processing calculation unit according to the environment image information and the binocular vision algorithm.

4. The control method according to claim 2, characterized in that: In S2, the camera image processing calculation unit identifies and separates the drivable area and the non-drivable area according to the three-dimensional point cloud information and color information through a deep learning segmentation method or a conventional image area classification segmentation method.

5. The control method according to any one of claims 2 to 4, characterized in that: The calculation method of the local slope of the virtual lane in S3 is as follows: the front direction of the photovoltaic sweeper is taken as the positive direction of the x-axis, the left direction of the photovoltaic sweeper perpendicular to the x-axis is taken as the positive direction of the y-axis, and the vertically upward direction is taken as the positive direction of the z-axis to construct a coordinate system, select the first parallel three-dimensional point coordinates visible to the binocular camera of the photovoltaic sweeper as the calculation base point of the current virtual lane and the new virtual lane in the parallel direction, and select the three-dimensional point (x0, y0, z0) with a distance δ from the base point in the positive direction of the x-axis with the calculation base point coordinates (x0, y0, z0) of the current virtual lane. δ1 ,y,z δ1 ), calculate the slope as (z δ1 -z0) / (x δ1 -x0).

6. The control method according to claim 5, characterized in that: When the local slope of the current virtual lane is greater than the preset maximum climbing limit of the photovoltaic sweeper, and a new virtual lane is reselected in the parallel direction of the current virtual lane, the calculation base point coordinates (x n ,y n , z n ), select a three-dimensional point (x δn ,y,z δn ), calculate the slope as (z δn -z0) / (x δn -x0).

7. The control method according to claim 6, characterized in that: The distance δ is set according to the minimum distance of different photovoltaic sweepers' travel slopes.

8. The control method according to any one of claims 2 to 4, characterized in that: If the local slopes of the current virtual lane and all parallel virtual lanes in the drivable area are greater than the preset maximum climbing limit of the photovoltaic sweeper, it is determined whether the drivable area meets the minimum U-turn area requirement. If so, a U-turn operation is performed; if not, a reversing operation is performed.

Images