Percolation grid dredging method and system, electronic equipment and storage medium

Abstract

The invention provides a percolation grid dredging method and system, electronic equipment and a storage medium, and the method comprises the steps: responding to a target dredging instruction, controlling dredging equipment to move to a target percolation grid, obtaining an image of a target positioning marker corresponding to the target percolation grid, carrying out the image recognition, obtaining a pixel coordinate of the target positioning marker, and carrying out the dredging of the target percolation grid. Based on the pixel coordinates and the physical coordinates of the target positioning marker, the current conversion relation between the camera coordinate system and the coordinate system corresponding to the target positioning marker is determined, and the target positioning marker is positioned according to the current conversion relation, the preset conversion relation between the mechanical arm coordinate system and the camera coordinate system and the preset pose of the mechanical arm in the coordinate system corresponding to the target positioning marker. Determining a target pose of the mechanical arm in the mechanical arm coordinate system so as to control the mechanical arm to drive the dredging mechanism to be inserted into the target percolation grid to execute dredging according to the target pose; the automatic dredging process can be achieved, manual intervention is not needed, the dredging efficiency can be greatly improved, and the labor cost and the safety risk of personnel can be reduced.

Description

Technical Field

[0001] The present application relates to the technical field of garbage disposal, and in particular to a method, system, electronic device and storage medium for clearing a percolation grid. Background Art

[0002] With the rapid development of urbanization, more and more domestic garbage is generated in cities. Garbage incineration is one of the main ways of garbage disposal, and it occupies an important position in urban garbage disposal. In the process of garbage incineration, the heat energy generated by incineration can be used to generate electricity and realize the comprehensive utilization of resources. Usually, there will be a lot of garbage leachate during the garbage stacking process. In order to improve the incineration efficiency of garbage power generation, it is necessary to discharge the garbage leachate first. Generally, a percolation grid is set at the lower part of the side wall of the garbage pool to discharge the garbage leachate through the percolation grid. However, the percolation grid is often blocked due to the large amount of garbage and the mutual stacking and squeezing, which makes the leachate unable to be discharged smoothly.

[0003] At present, the infiltration grid is mainly cleared by manual work. On the one hand, there are many infiltration grids to be cleared, which requires a large amount of manual work and high labor intensity. On the other hand, there are toxic and dangerous gases in the garbage pool and the environment is relatively bad, so manual clearing has certain safety hazards. Summary of the invention

[0004] In view of the shortcomings of the prior art mentioned above, the present application provides a method, system, electronic device and storage medium for clearing the infiltration grid to solve the technical problems of the above-mentioned manual clearing of the infiltration grid, which has large manual workload, high labor intensity and potential safety hazards.

[0005] The present application provides a method for unblocking an infiltration grid, the method being applied to an unblocking device, the unblocking device comprising a mobile body, an image acquisition device and a robotic arm arranged on the mobile body, and an unblocking mechanism arranged at the free end of the robotic arm, the method comprising: in response to a target unblocking instruction, controlling the unblocking device to move to a target infiltration grid, acquiring an image of a target positioning marker corresponding to the target infiltration grid and performing image recognition to obtain pixel coordinates of the target positioning marker; determining a current conversion relationship between a camera coordinate system and a coordinate system corresponding to the target positioning marker based on the pixel coordinates of the target positioning marker and the physical coordinates of the target positioning marker; determining a target posture of the robotic arm in the robotic arm coordinate system according to the current conversion relationship, a preset conversion relationship between the robotic arm coordinate system and the camera coordinate system, and a preset posture of the robotic arm in the coordinate system corresponding to the target positioning marker, so as to control the robotic arm according to the target posture to drive the unblocking mechanism to insert into the target infiltration grid for unblocking.

[0006] In one embodiment of the present application, before obtaining the image of the target positioning marker corresponding to the target infiltration grille, the method includes: controlling the dredging equipment to move in the direction from the standby position to the infiltration grille, and controlling the image acquisition device to perform real-time image acquisition during the movement to obtain the current number of positioning markers; if the current number of positioning markers and the corresponding number of the target positioning marker meet the preset conditions, the dredging equipment is controlled to stop moving, and the image acquisition device is used to acquire the image of the target positioning marker, wherein the information of the target infiltration grille includes the corresponding number of the target positioning marker, and each positioning marker has a corresponding number.

[0007] In one embodiment of the present application, before determining the target posture of the robotic arm in the robotic arm coordinate system, the method includes: obtaining the preset posture of the robotic arm in the coordinate system corresponding to each positioning marker, wherein obtaining the preset posture of the robotic arm in the coordinate system corresponding to a positioning marker includes: teaching the robotic arm so that the robotic arm drives the dredging mechanism to insert the infiltration grid corresponding to the positioning marker, so as to obtain the taught posture of the robotic arm in the robotic arm coordinate system, and obtaining the image of the positioning marker and performing image recognition to obtain the pixel coordinates of the positioning marker, wherein the image of the positioning marker is acquired by the image acquisition device; based on the pixel coordinates of the positioning marker and the physical coordinates of the positioning marker, determining the conversion relationship between the camera coordinate system and the coordinate system corresponding to the positioning marker; according to the taught posture of the robotic arm in the robotic arm coordinate system, the conversion relationship between the camera coordinate system and the coordinate system corresponding to the positioning marker, and the preset conversion relationship, determining the preset posture of the robotic arm in the coordinate system corresponding to the positioning marker.

[0008] In one embodiment of the present application, before determining the target posture of the robotic arm in the robotic arm coordinate system, the method also includes: fixing a calibration plate at the free end of the robotic arm, obtaining different postures of the robotic arm in the robotic arm coordinate system, and acquiring an image of the calibration plate in each posture through the image acquisition device; determining the preset conversion relationship according to the different postures of the robotic arm in the robotic arm coordinate system and the image of the calibration plate in each posture.

[0009] In one embodiment of the present application, the target posture of the robotic arm in the robotic arm coordinate system is determined according to the current conversion relationship, the preset conversion relationship between the robotic arm coordinate system and the camera coordinate system, and the preset posture of the robotic arm in the coordinate system corresponding to the target positioning marker, so as to control the robotic arm according to the target posture to drive the dredging mechanism to insert into the target infiltration grid to perform dredging, including: determining multiple initial postures of the robotic arm in the coordinate system corresponding to the target positioning marker according to the preset posture of the robotic arm in the coordinate system corresponding to the target positioning marker and multiple preset translation vectors; determining each target posture of the robotic arm in the robotic arm coordinate system according to the current conversion relationship, the preset conversion relationship, and each initial posture of the robotic arm in the coordinate system corresponding to the target positioning marker to obtain multiple target postures of the robotic arm in the robotic arm coordinate system; controlling the robotic arm according to each target posture respectively, so that the robotic arm drives the dredging mechanism to insert into different positions of the target infiltration grid to perform dredging.

[0010] In one embodiment of the present application, after dredging is performed, the method includes: acquiring an image of the target infiltration grid and performing image recognition to obtain an infiltration amount category and an infiltration position of the infiltration liquid in the target infiltration grid, wherein the image of the target infiltration grid is acquired by the image acquisition device, and the infiltration amount category includes a large amount of infiltration or a small amount of infiltration; determining the position of the infiltration liquid in the robot arm coordinate system according to the infiltration position and the preset conversion relationship, and determining the position of the dredging mechanism in the robot arm coordinate system based on the target posture and the preset relative position of the robot arm and the dredging mechanism; if the infiltration amount category is a large amount of infiltration, and the position of the infiltration liquid in the robot arm coordinate system successfully matches the position of the dredging mechanism in the robot arm coordinate system, it is determined that the target infiltration grid is dredged successfully; controlling the dredging device to move to a new target infiltration grid to dredge the new target infiltration grid, wherein the target dredging instruction includes information of multiple target infiltration grids; until all target infiltration grids are dredged successfully, controlling the dredging device to move to a standby position.

[0011] In one embodiment of the present application, the dredging device is controlled to move to a standby position, including: controlling the dredging device to move along the infiltration grid to the standby position, and controlling the image acquisition device to perform real-time image acquisition during the movement; if the image of a positioning ring is identified from the real-time acquired image, the dredging device is controlled to stop moving, wherein the standby position is provided with the positioning ring.

[0012] In one embodiment of the present application, the image acquisition device is controlled to perform real-time image acquisition during the movement process to obtain the current number of positioning markers, including: obtaining the currently acquired real-time image and identifying the real-time image; if a target contour area that meets a preset shape is identified from the real-time image, straight line fitting is performed on the edge points in the target contour area, and the angle between all the fitted straight lines is calculated, wherein the positioning marker includes an outer contour, a first line segment and a second line segment, the shape of the outer contour is the preset shape, the first line segment and the second line segment are perpendicular to each other, and the two ends of the first line segment and the two ends of the second line segment are respectively connected to the outer contour; when the angle meets the preset angle range, the current number of positioning markers is increased by one.

[0013] In one embodiment of the present application, a filtration grille dredging system is also provided, the system comprising: a dredging device, comprising a mobile body, an image acquisition device and a robotic arm arranged on the mobile body, and a dredging mechanism arranged at the free end of the robotic arm; a control module, for controlling the dredging device to move to a target filtration grille in response to a target dredging instruction; controlling the robotic arm to drive the dredging mechanism to insert into the target filtration grille to perform dredging according to the target posture of the robotic arm in the robotic arm coordinate system; an information processing module, for acquiring an image of a target positioning marker corresponding to the target filtration grille and performing image recognition to obtain the pixel coordinates of the target positioning marker; determining the current conversion relationship between the camera coordinate system and the coordinate system corresponding to the target positioning marker based on the pixel coordinates of the target positioning marker and the physical coordinates of the target positioning marker; determining the target posture according to the current conversion relationship, the preset conversion relationship between the robotic arm coordinate system and the camera coordinate system, and the preset posture of the robotic arm in the coordinate system corresponding to the target positioning marker.

[0014] In one embodiment of the present application, an electronic device is also provided, which includes: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the electronic device implements the infiltration grid clearing method as described above.

[0015] In one embodiment of the present application, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer executes the infiltration grid dredging method as described above.

[0016] Beneficial effects of the present invention: The present invention provides a method, system, electronic device and storage medium for dredging a percolation grid. The method controls the dredging equipment to move to the target percolation grid indicated by the target dredging instruction, obtains the image of the target positioning marker corresponding to the target percolation grid and identifies the pixel coordinates of the target positioning marker, and determines the current conversion relationship between the camera coordinate system and the coordinate system corresponding to the target positioning marker based on the pixel coordinates and physical coordinates of the target positioning marker, and then determines the target posture of the robotic arm in the robotic arm coordinate system according to the current conversion relationship, the preset conversion relationship between the robotic arm coordinate system and the camera coordinate system, and the preset posture of the robotic arm in the coordinate system corresponding to the target positioning marker, so as to control the robotic arm according to the target posture to drive the dredging mechanism to insert into the target percolation grid for dredging. The entire dredging process is automated without manual intervention, which can greatly improve the dredging efficiency and reduce labor costs, and can also prevent workers from entering dangerous or harsh working environments, reducing safety risks for workers. Moreover, through image acquisition, recognition and coordinate conversion, the target position can be accurately calculated, thereby ensuring that the robotic arm can accurately drive the dredging mechanism to insert the target infiltration grid to perform dredging operations, thereby improving the quality of infiltration grid dredging operations.

[0017] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of an implementation environment of a percolation grid dredging method shown in an exemplary embodiment of the present application;

[0019] Figure 2 is a flow chart of a method for clearing a percolation grid shown in an exemplary embodiment of the present application;

[0020] Figure 3 It is a schematic diagram of dredging the infiltration grid of a garbage pool shown in a specific embodiment of the present application;

[0021] Figure 4 is a schematic diagram of a coordinate system corresponding to a positioning marker shown in a specific embodiment of the present application;

[0022] Figure 5 is a schematic diagram of a positioning ring shown in a specific embodiment of the present application;

[0023] Figure 6 is a block diagram of a percolation grid dredging system shown in an exemplary embodiment of the present application;

[0024] Figure 7 It is a structural schematic diagram of an electronic device shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0025] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0026] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application, and thus the drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed at will, and the component layout may also be more complicated.

[0027] It should be noted that in this application, "first", "second", etc. are only used to distinguish similar objects, and are not used to limit the order or precedence of similar objects. The variations of "including", "having", etc. described above indicate that the scope covered by the subject of the word is not exclusive except for the examples shown by the word.

[0028] It is understood that the various numbers, step numbers, and other reference numerals recorded in this application are distinguished for the convenience of description and are not intended to limit the scope of this application. The size of the reference numerals in this application does not mean the order of execution. The execution order of each process should be determined by its function and internal logic.

[0029] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0030] The embodiments of the present application respectively propose a method for clearing a percolation grid, a system for clearing a percolation grid, an electronic device, a computer-readable storage medium, and a computer program product, and these embodiments will be described in detail below.

[0031] See also Figure 1 , Figure 1 It is a schematic diagram of an implementation environment of a method for clearing a percolation grid shown as an exemplary embodiment of the present application.

[0032] like Figure 1As shown, the implementation environment may include a dredging device 110 and a computer device 120, wherein the dredging device 110 includes a mobile body, an image acquisition device arranged on the mobile body, a mechanical arm with multi-degree-of-freedom motion, and a dredging mechanism arranged at the free end of the mechanical arm, and the image acquisition device may be at least one of a camera, a camera, a scanner, a point cloud radar, etc. The computer device 120 may be at least one of a microcomputer, an embedded computer, a neural network computer, etc., which is not limited here. The computer device 120 may be configured in the dredging device 110, or the computer device 120 may be a computer device independent of the dredging device 110. Of course, the dredging device may also include an image processing device such as an image processor or an image processing chip, which constitutes a visual system with the image acquisition device, or the image processing device is configured in the computer device 120, which constitutes a visual system with the image acquisition device, which is not limited here. The dredging device 110 and the computer device 120 may be used to implement the dredging operation of the infiltration grid.

[0033] Illustratively, the computer device 120 responds to the target dredging instruction, controls the dredging device 110 to move to the target infiltration grid, obtains the image of the target positioning marker corresponding to the target infiltration grid and performs image recognition to obtain the pixel coordinates of the target positioning marker, wherein each infiltration grid is corresponding to a positioning marker, the image of the target positioning marker is acquired by an image acquisition device, and the target dredging instruction includes information of the target infiltration grid; based on the pixel coordinates of the target positioning marker and the physical coordinates of the target positioning marker, determines the current conversion relationship between the camera coordinate system and the coordinate system corresponding to the target positioning marker, wherein each positioning marker has a corresponding coordinate system and physical coordinates; determines the target posture of the robotic arm in the robotic arm coordinate system according to the current conversion relationship, the preset conversion relationship between the robotic arm coordinate system and the camera coordinate system, and the preset posture of the robotic arm in the coordinate system corresponding to the target positioning marker, so as to control the robotic arm according to the target posture to drive the dredging mechanism to insert into the target infiltration grid to perform dredging, wherein the robotic arm has a corresponding preset posture in the coordinate system corresponding to each positioning marker. It can be seen that the technical solution of the embodiment of the present application can realize automation in the entire dredging process without manual intervention, which can not only greatly improve the dredging efficiency and reduce labor costs, but also prevent workers from entering dangerous or harsh working environments, reducing the safety risks of workers. In addition, through image acquisition, recognition and coordinate conversion, the target posture can be accurately calculated, thereby ensuring that the robot arm can accurately drive the dredging mechanism to insert the target infiltration grid to perform the dredging operation, thereby improving the quality of the infiltration grid dredging operation.

[0034] It should be noted that the infiltration grid unclogging method provided in the embodiment of the present application is generally performed by unclogging equipment 110 and computer equipment 120 .

[0035] See also Figure 2 , Figure 2 is a flow chart of a method for clearing a percolation grid as shown in an exemplary embodiment of the present application. The method for clearing a percolation grid can be applied to Figure 1 The implementation environment shown in FIG. 1 is specifically implemented by the unblocking device 110 and the computer device 120 in the implementation environment. It should be understood that the infiltration grid unblocking method can also be applied to other exemplary implementation environments and be specifically implemented by devices in other implementation environments. This embodiment does not limit the implementation environment to which the infiltration grid unblocking method is applicable. Figure 2 As shown, in an exemplary embodiment, the infiltration grid dredging method is applied to a dredging device, and the infiltration grid dredging method at least includes steps S210 to S230, which are described in detail as follows:

[0036] Step S210, in response to the target dredging instruction, control the dredging equipment to move to the target infiltration grid, obtain the image of the target positioning marker corresponding to the target infiltration grid and perform image recognition to obtain the pixel coordinates of the target positioning marker.

[0037] In one embodiment of the present application, the dredging equipment includes a mobile body, an image acquisition device arranged on the mobile body, a robotic arm with multi-degree-of-freedom motion, and a dredging mechanism arranged at the free end of the robotic arm, wherein the mobile body can be a wheeled mobile body such as a mobile cart, or a tracked mobile body, or a tracked mobile body, the image acquisition device can be at least one of a camera, a camera, a scanner, a point cloud radar, etc. Of course, the dredging equipment can also include an image processing device such as an image processor or an image processing chip, which constitutes a visual system with the image acquisition device, the robotic arm can be a 4-axis manipulator, including 4 degrees of freedom of lateral movement (x movement), longitudinal movement (y movement), lifting (z movement) and base rotation, the robotic arm can also be composed of 6 degrees of freedom, and the dredging mechanism can be a dredging rod or a dredging fork, which is not limited here.

[0038] The target dredging instruction can be sent to the computer device through a mobile terminal, or the staff can manually input the target dredging instruction into the computer device. When the computer device receives the target dredging instruction, it can control the dredging equipment to move to the target infiltration grid according to the target dredging instruction, wherein the target dredging instruction includes the information of the target infiltration grid, which is used to identify the target infiltration grid from multiple infiltration grids. When the dredging equipment reaches the location of the target infiltration grid, it can actively obtain the image of the target positioning marker and return it to the computer device, or the dredging equipment can feedback the arrival signal to the computer device, and the computer device will issue a collection instruction after receiving the arrival signal, and then the dredging equipment will respond to the collection instruction to passively obtain the image of the target positioning marker and return it to the computer device, wherein each infiltration grid is provided with a corresponding positioning marker, and the image of the target positioning marker is obtained by an image acquisition device. The positioning marker is used for the dredging equipment to locate the working position during the dredging operation, and it can be installed at a fixed position away from the edge of each infiltration grid, and the plane of the positioning marker must be parallel to the corresponding infiltration grid plane. The positioning marker can be a positioning plate or a positioning graphic, please refer to Figure 3 , Figure 3 FIG. 1 is a schematic diagram of clearing the infiltration grid of a garbage pool according to a specific embodiment of the present application. Figure 3 As shown, the garbage pool includes a plurality of leachate grids (ie, infiltration grids), and each leachate grid is provided with a positioning plate. Schematically, the positioning marker may be circular or square, or other polygonal shapes, which are not limited here.

[0039] The computer device receives the image of the target positioning marker and can locate and identify the target positioning marker in the image of the target positioning marker by means of target detection and other methods to obtain the pixel coordinates of the target positioning marker. Figure 3 The ellipse and cross lines shown are composed of two mutually perpendicular line segments, and the two ends of the two line segments are connected to the ellipse closed line. Accordingly, the pixel coordinates of the positioning marker can include the coordinates of the intersections between the line segments and the coordinates of the intersections of each line segment with the ellipse closed line; of course, the pattern of the positioning marker can also be composed of multiple solid circles, and accordingly, the pixel coordinates of the positioning marker can include the coordinates of the center points of each solid circle, which is not limited here.

[0040] In a specific embodiment of the present application, Figure 3Taking the corresponding positioning plate of the leachate grille shown as an example, the contour edge can be extracted by the Canny algorithm, and the position of the corresponding positioning plate of the target leachate grille can be detected by performing ellipse fitting on the edge points. The ellipse area is set as ROI, and the edge points in the area are fitted with straight lines. The cross line is identified by calculating the angle between the straight lines. The center point of the cross line and the four intersection points of the cross line and the ellipse line are calculated by the equation of the ellipse and the equation of the cross line, and the pixel coordinates corresponding to these points are determined as the pixel coordinates of the target positioning marker.

[0041] In one embodiment of the present application, before obtaining an image of a target positioning marker corresponding to a target infiltration grid, the method includes: controlling the dredging equipment to move in a direction from a standby position to the infiltration grid, and controlling an image acquisition device to perform real-time image acquisition during the movement to obtain the current number of positioning markers; if the current number of positioning markers and the corresponding number of the target positioning marker meet preset conditions, controlling the dredging equipment to stop moving, and performing image acquisition of the target positioning marker through the image acquisition device to obtain an image of the target positioning marker, wherein the information of the target infiltration grid includes the corresponding number of the target positioning marker, and each positioning marker has a corresponding number.

[0042] In this embodiment, when there is no dredging operation, the dredging device can be preliminarily stopped at a position such as Figure 3 In the standby position shown, when the computer device receives the target dredging instruction, it can send a moving instruction to the dredging device to move the dredging device from the standby position to the infiltration grid. At the same time, the computer device controls the image acquisition device in the dredging device to be in an on state to collect images in real time during the movement of the dredging device. The initial value of the current number of positioning markers is 0. When the image acquisition device collects an image of a positioning marker, the current number of positioning markers is increased by one until the current number of positioning markers and the corresponding number of the target positioning marker meet the preset conditions, indicating that the dredging device has reached the location of the target infiltration grid. At this time, the computer device can control the dredging device to stop moving, and control the image acquisition device to collect images of the target positioning marker corresponding to the target infiltration grid, thereby obtaining an image of the target positioning marker.

[0043] Illustratively, if the numbering of the positioning markers starts from 0, the corresponding preset condition may be that the current number of positioning markers is greater than the corresponding number of the target positioning marker, and the difference between the two is equal to 1; if the numbering of the positioning markers starts from 1, the corresponding preset condition may be that the current number of positioning markers is the same as the corresponding number of the target positioning marker.

[0044] In one embodiment of the present application, during the movement, the image acquisition device is controlled to perform real-time image acquisition to obtain the current number of positioning markers, including: obtaining the currently acquired real-time image and identifying the real-time image; if a target contour area that meets a preset shape is identified from the real-time image, straight line fitting is performed on the edge points in the target contour area, and the angles between all the fitted straight lines are calculated, wherein the positioning marker includes an outer contour, a first line segment and a second line segment, the shape of the outer contour is a preset shape, the first line segment and the second line segment are perpendicular to each other, and both ends of the first line segment and the second line segment are respectively connected to the outer contour; when the angle meets the preset angle range, the current number of positioning markers is increased by one.

[0045] In this embodiment, the preset shape may be a polygon or an ellipse, which is not limited here. Figure 3 As shown, the positioning marker includes an outer contour of an ellipse, a first line segment and a second line segment, the first line segment and the second line segment are perpendicular to each other to form a cross line, and the two ends of the first line segment and the two ends of the second line segment are respectively connected to the outer contour of the ellipse. The preset angle range can be (87°, 93°), or other angle ranges, which are not limited here. Specifically, after using a visual system such as an image acquisition device to collect an image of the positioning marker, the contour edge can be extracted by the Canny algorithm, and the edge points can be fitted with an ellipse to detect the position of the positioning marker. The ellipse area is set as ROI, and the edge points in the area are fitted with a straight line. The angle between the straight lines is calculated for all the fitted straight lines. If the angle range is greater than 87 degrees and less than 93 degrees, it is judged to be a cross line formed by the first line segment and the second line segment, indicating that a certain infiltration grid has been reached, and the current number of positioning markers is increased by one.

[0046] Step S220, based on the pixel coordinates of the target positioning marker and the physical coordinates of the target positioning marker, determine the current conversion relationship between the camera coordinate system and the coordinate system corresponding to the target positioning marker.

[0047] In one embodiment of the present application, since the relative position of the dredging equipment and the infiltration grid is not fixed, correspondingly, the conversion relationship between the camera coordinate system and the coordinate system corresponding to the positioning marker is also not fixed. Therefore, the conversion relationship between the current camera coordinate system and the coordinate system corresponding to the target positioning marker can be dynamically determined based on the pixel coordinates of the target positioning marker in the image of the target positioning marker and the physical coordinates of the target positioning marker in the coordinate system corresponding to the target positioning marker.

[0048] Each positioning marker has a corresponding coordinate system and physical coordinates, and the physical coordinates of the positioning marker are determined based on the coordinate system corresponding to the positioning marker. Figure 4 , Figure 4is a schematic diagram of a coordinate system corresponding to a positioning marker according to a specific embodiment of the present application, such as Figure 4 As shown, a coordinate system corresponding to the positioning marker is established in advance with the center point of the crosshairs of the positioning marker as the origin, the horizontal left as the positive direction of the X-axis, and the vertical downward as the positive direction of the Y-axis, and based on the coordinate system corresponding to the positioning marker, the physical coordinates of the center point of the crosshairs and the physical coordinates of the four intersection points of the crosshairs and the ellipse are determined as the physical coordinates of the positioning marker.

[0049] In schematic form, based on the pixel coordinates of the target positioning marker and the physical coordinates of the target positioning marker, the current transformation matrix between the camera coordinate system and the coordinate system corresponding to the target positioning marker can be obtained by using the PnP perspective change as the current transformation relationship.

[0050] Step S230, determines the target posture of the robotic arm in the robotic arm coordinate system according to the current conversion relationship, the preset conversion relationship between the robotic arm coordinate system and the camera coordinate system, and the preset posture of the robotic arm in the coordinate system corresponding to the target positioning marker, so as to control the robotic arm according to the target posture to drive the dredging mechanism to insert into the target infiltration grid to perform dredging.

[0051] In one embodiment of the present application, Figure 3 As shown, the robot arm coordinate system is a coordinate system established with the robot arm base as the origin. Since the image acquisition device and the robot arm are fixedly arranged on the mobile body, the relative position between the two is fixed, and accordingly, the conversion relationship between the camera coordinate system and the robot arm coordinate system is also fixed. Therefore, the conversion matrix between the robot arm coordinate system and the camera coordinate system can be determined in advance by calibration as a preset conversion relationship.

[0052] The robot arm has a corresponding preset posture in the coordinate system corresponding to each positioning marker, which can be predetermined by teaching.

[0053] In one embodiment of the present application, before step S230, the method includes: obtaining a preset posture of the robot arm in a coordinate system corresponding to each positioning marker, wherein obtaining a preset posture of the robot arm in a coordinate system corresponding to a positioning marker includes:

[0054] The robotic arm is taught so that the robotic arm drives the dredging mechanism to insert the infiltration grid corresponding to the positioning marker, so as to obtain the taught posture of the robotic arm in the robotic arm coordinate system, and obtain the image of the positioning marker and perform image recognition to obtain the pixel coordinates of the positioning marker, wherein the image of the positioning marker is acquired by an image acquisition device; based on the pixel coordinates of the positioning marker and the physical coordinates of the positioning marker, the conversion relationship between the camera coordinate system and the coordinate system corresponding to the positioning marker is determined; according to the taught posture of the robotic arm in the robotic arm coordinate system, the conversion relationship between the camera coordinate system and the coordinate system corresponding to the positioning marker, and the preset conversion relationship, the preset posture of the robotic arm in the coordinate system corresponding to the positioning marker is determined.

[0055] In one embodiment of the present application, before step S230, the method also includes: fixing a calibration plate at the free end of the robotic arm, acquiring different postures of the robotic arm in the robotic arm coordinate system, and acquiring an image of the calibration plate at each posture through an image acquisition device; determining a preset conversion relationship according to the different postures of the robotic arm in the robotic arm coordinate system and the image of the calibration plate at each posture.

[0056] In this embodiment, each infiltration grid can be taught for dredging. First, the dredging device is moved to a filtration grid as a teaching position. At the teaching position, the posture of the dredging mechanism of the robot arm inserted into the infiltration grid is taught. The dredging mechanism of the robot arm can be required to be inserted into the middle of the infiltration grid. The extension direction of the dredging mechanism insertion is perpendicular to the plane of the infiltration grid to ensure that the dredging mechanism and the infiltration grid do not collide during the insertion process. The teaching posture of the robot arm at the teaching position in the robot arm coordinate system can be recorded as T e1 (i) can be obtained through the internal sensor of the robot arm and other equipment, where i represents the i-th infiltration grid or positioning marker. Specifically, T e1 (i) is a 4X4 matrix, which contains the rotation vector and translation vector.

[0057] At the teaching position, an image acquisition device or other visual system can be used to capture an image of the positioning marker corresponding to the percolation grid, and the Canny algorithm can be used to extract the contour edge. The edge points are fitted with an ellipse to detect the position of the positioning marker, and the ellipse area is set as ROI. The edge points in the area are fitted with straight lines, and the angles between all the fitted straight lines are calculated. If the angle range is greater than 87 degrees and less than 93 degrees, it is judged to be a cross line. Then, the ellipse equation and the cross equation can be used to calculate the four intersection points of the cross center point and the ellipse, and the pixel coordinates corresponding to these points are determined as the pixel coordinates of the positioning marker. Since the physical coordinates and pixel coordinates of the positioning marker are known, the PnP perspective change can be used to obtain the transformation matrix between the camera coordinate system at the teaching position and the coordinate system corresponding to the positioning marker, which can be recorded as As the conversion relationship between the camera coordinate system and the coordinate system corresponding to the positioning marker, i represents the i-th infiltration grid or positioning marker.

[0058] Schematically, a specific method of pre-determining the conversion matrix between the robot arm coordinate system and the camera coordinate system through calibration as a preset conversion relationship may be to fix the calibration plate to the end of the robot arm, record the position and posture of the robot arm in the robot arm coordinate system, and at the same time, collect and recognize the image of the calibration plate through a visual system such as an image acquisition device. The robot arm moves to the next position and posture, and records the position and posture of the robot arm in the robot arm coordinate system again. At the same time, collect and recognize the image of the calibration plate through a visual system such as an image acquisition device, and repeat the above steps. A total of at least 16 groups of the position and posture of the robot arm in the robot arm coordinate system and the corresponding calibration plate images are recorded and saved. By using the eye-outside-hand calibration, the conversion matrix between the robot arm coordinate system and the camera coordinate system is obtained, which can be recorded as As the preset transformation relationship between the robot coordinate system and the camera coordinate system.

[0059] It can be assumed that in the teaching state at the teaching position, the preset position of the robot arm in the coordinate system corresponding to the positioning marker is recorded as Where i represents the i-th infiltration grid or positioning marker. Therefore, at this teaching position, the teaching position T of the robot arm in the robot arm coordinate system is e1 (i) Conversion relationship between the camera coordinate system and the coordinate system corresponding to the positioning marker Preset conversion relationship And the preset position of the robot arm in the coordinate system corresponding to the positioning marker The relationship between the four is as follows:

[0060]

[0061] Among them, T e1 (i) is the teaching position of the robot arm in the robot arm coordinate system at the teaching position, is the preset position of the robot arm in the coordinate system corresponding to the positioning marker. is the conversion relationship between the camera coordinate system and the coordinate system corresponding to the positioning marker, It is the preset transformation relationship between the robot coordinate system and the camera coordinate system.

[0062] Therefore, the preset position of the robot arm in the coordinate system corresponding to the positioning marker can be obtained according to the following calculation method:

[0063]

[0064] in, is the preset position of the robot arm in the coordinate system corresponding to the positioning marker. is the preset transformation relationship between the robot coordinate system and the camera coordinate system, Te1 (i) -1 is the teaching position T of the robot arm in the robot arm coordinate system at the teaching position e1 The inverse matrix of (i), is the conversion relationship between the camera coordinate system and the coordinate system corresponding to the positioning marker Inverse matrix.

[0065] By analogy, by teaching the dredging of each infiltration grid, the preset position of the robot arm in the coordinate system corresponding to each positioning marker can be obtained.

[0066] Usually, the actual dredging operation position is relative to the teaching position. Since the position of the dredging equipment will change, the relationship between the camera coordinate system and the coordinate system corresponding to the positioning marker will also change accordingly. However, for the infiltration grid corresponding to this position, the position of the dredging mechanism at the end of the robot arm inserted into the infiltration grid must remain unchanged. Therefore, the position of the robot arm in the coordinate system corresponding to the positioning marker remains the preset position during each dredging operation. In addition, since the positions of the camera and the robot base are relatively fixed, the relationship between the robot coordinate system and the camera coordinate system is still the preset conversion relationship. Assume that during the actual dredging operation, the target position of the robot arm in the robot arm coordinate system is denoted as T e2 (m), where m represents the number of the target infiltration grid or the target positioning marker. Therefore, at the actual dredging operation position of the target infiltration grid, the target position T of the manipulator in the manipulator coordinate system is e2 (m), the current transformation relationship between the camera coordinate system and the coordinate system corresponding to the target positioning marker Preset conversion relationship And the preset position of the robot arm in the coordinate system corresponding to the target positioning marker The relationship between the four is as follows:

[0067]

[0068] Among them, T e2 (m) is the target position of the robot arm in the robot arm coordinate system at the actual dredging operation position of the target infiltration grid, The preset position of the robot arm in the coordinate system corresponding to the target positioning marker. is the current transformation relationship between the camera coordinate system and the coordinate system corresponding to the target positioning marker, It is the preset transformation relationship between the robot coordinate system and the camera coordinate system.

[0069] Therefore, the target position of the robot in the robot coordinate system can be obtained according to the following calculation method:

[0070]

[0071] Among them, T e2 (m) is the target position of the robot arm in the robot arm coordinate system at the actual dredging operation position of the target infiltration grid, is the preset transformation relationship between the robot coordinate system and the camera coordinate system. Preset position of the robot arm in the coordinate system corresponding to the target positioning marker The inverse matrix of The current conversion relationship between the camera coordinate system and the coordinate system corresponding to the target positioning marker The inverse matrix of .

[0072] Specifically, T e2 (m) is a 4X4 matrix that contains the rotation vector and translation vector.

[0073] In one embodiment of the present application, step S230 includes: determining multiple initial postures of the robotic arm in the coordinate system corresponding to the target positioning marker according to a preset posture of the robotic arm in the coordinate system corresponding to the target positioning marker and multiple preset translation vectors; determining each target posture of the robotic arm in the robotic arm coordinate system according to the current transformation relationship, the preset transformation relationship, and each initial posture of the robotic arm in the coordinate system corresponding to the target positioning marker to obtain multiple target postures of the robotic arm in the robotic arm coordinate system; controlling the robotic arm according to each target posture, so that the robotic arm drives the dredging mechanism to insert into different positions of the target infiltration grid to perform dredging.

[0074] In this embodiment, since the width between each railing of the infiltration grid is a fixed value P1, the preset position of the robot arm in the coordinate system corresponding to the target positioning marker can also be used. Add multiple preset translation vectors such as 0*P1, 1*P1, 2*P1, ..., n*P1 to the translation vector in the x direction to obtain multiple initial postures. The preset posture of formula (4) can be replaced with the initial posture, and the current conversion relationship, the preset conversion relationship, and an initial posture are substituted into formula (4) to obtain a target posture of the robot in the robot coordinate system, thereby obtaining multiple target postures of the robot in the robot coordinate system. Then, the robot is controlled according to each target posture to achieve the dredging operation by shifting the current insertion point of the target infiltration grid to the side by n railings.

[0075] In one embodiment of the present application, after step S230, the method includes: acquiring an image of the target infiltration grid and performing image recognition to obtain an infiltration amount category and an infiltration position of the infiltration liquid in the target infiltration grid, wherein the image of the target infiltration grid is acquired by an image acquisition device, and the infiltration amount category includes a large amount of infiltration or a small amount of infiltration; determining the position of the infiltration liquid in the robot arm coordinate system according to the infiltration position and a preset conversion relationship, and determining the position of the dredging mechanism in the robot arm coordinate system based on the target posture, the preset relative position of the robot arm and the dredging mechanism; if the infiltration amount category is a large amount of infiltration, and the position of the infiltration liquid in the robot arm coordinate system successfully matches the position of the dredging mechanism in the robot arm coordinate system, it is determined that the target infiltration grid is dredged successfully; controlling the dredging device to move to a new target infiltration grid to dredge the new target infiltration grid, wherein the target dredging instruction includes information of multiple target infiltration grids; until all target infiltration grids are dredged successfully, controlling the dredging device to move to the standby position.

[0076] In this embodiment, image sample data of the infiltration grid discharging leachate can be obtained in advance, and the leachate in the image sample data can be labeled, specifically including selecting the sample data of leachate discharge through a detection frame, recording the discharge position information of the leachate (i.e., the infiltration position) and the corresponding classification label (i.e., the infiltration amount category), the classification label includes large-scale infiltration and small-scale infiltration, establishing a leachate classification and position detection model based on a deep neural network, and training based on the labeled image sample data to obtain a trained leachate classification and position detection model. Then, the image of the target infiltration grid collected by the visual system such as the image acquisition device is input into the trained infiltration liquid classification and position detection model for image recognition, and the infiltration amount category and infiltration position of the infiltration liquid in the target infiltration grid are obtained. When a large amount of infiltration liquid is detected to be sprayed out, the infiltration amount category of the infiltration liquid in the target infiltration grid is a large amount of infiltration, and the position of the infiltration liquid in the robot arm coordinate system corresponding to the infiltration position is consistent with the position of the dredging mechanism in the robot arm coordinate system corresponding to the target posture of the robot arm in the robot arm coordinate system. It is judged that the current target infiltration grid dredging operation is completed, and the dredging equipment moves to the next target infiltration grid position, and repeats the previous detection positioning and dredging operation. When the dredging operation of all target infiltration grids that need to be dredged is completed, the dredging equipment moves to the standby position.

[0077] In one embodiment of the present application, controlling the dredging equipment to move to a standby position includes: controlling the dredging equipment to move along the infiltration grid to the standby position, and controlling the image acquisition device to perform real-time image acquisition during the movement; if an image of a positioning ring is identified from the real-time acquired image, controlling the dredging equipment to stop moving, wherein the standby position is provided with a positioning ring.

[0078] In this embodiment, the positioning ring is used to position the dredging equipment when it returns to the standby position after the dredging operation is completed. The ratio of the diameter of the large circle to the diameter of the small circle can be preset, and the filling color between the large circle and the small circle can also be preset. Figure 5 , Figure 5 is a schematic diagram of a positioning ring shown in a specific embodiment of the present application, such as Figure 5 As shown, the ratio of the large circle diameter to the small circle diameter of the positioning ring is 2:1, and the area between the large circle and the small circle is filled with black. When all the operations that need to be dredged are completed, the dredging equipment moves to the starting position (i.e., the standby position), and the positioning ring is detected in real time by a visual system such as an image acquisition device. When the ring is detected, it indicates that the dredging equipment has reached the standby position and the dredging equipment stops moving. Schematically, the Canny algorithm can be used to fit all ellipses through the edge points of the image contour edge. When the diameter ratio between the ellipses meets 2:1, and the grayscale value of the area between the ellipses is less than the preset value (thus judging that the area between the ellipses is filled with black), it means that the positioning ring is detected.

[0079] See also Figure 6 , Figure 6 is a block diagram of a percolation grid dredging system shown in an exemplary embodiment of the present application. The system can be applied to Figure 1 The system can also be applied to other exemplary implementation environments, and this embodiment does not limit the implementation environment to which the system is applied. Figure 6 As shown, the exemplary infiltration grid dredging system includes: a dredging device 110, including a mobile body, an image acquisition device arranged on the mobile body and a multi-degree-of-freedom mechanical arm, and a dredging mechanism arranged at the free end of the mechanical arm; a control module 620, which is used to control the dredging device to move to the target infiltration grid in response to a target dredging instruction, wherein the target dredging instruction includes information about the target infiltration grid; the mechanical arm is controlled according to the target position of the mechanical arm in the mechanical arm coordinate system to drive the dredging mechanism to insert into the target infiltration grid to perform dredging; an information processing module 630, which is used to obtain an image of a target positioning marker corresponding to the target infiltration grid and perform image recognition to obtain a target positioning marker. The pixel coordinates of the marker, wherein a positioning marker is arranged corresponding to each infiltration grid, and the image of the target positioning marker is acquired by an image acquisition device; based on the pixel coordinates of the target positioning marker and the physical coordinates of the target positioning marker, the current conversion relationship between the camera coordinate system and the coordinate system corresponding to the target positioning marker is determined, wherein each positioning marker has a corresponding coordinate system and physical coordinates; the target posture is determined according to the current conversion relationship, the preset conversion relationship between the robot coordinate system and the camera coordinate system, and the preset posture of the robot in the coordinate system corresponding to the target positioning marker, wherein the robot has a corresponding preset posture in the coordinate system corresponding to each positioning marker.

[0080] In this embodiment, the mobile body can be a wheeled mobile body such as a mobile car, or a crawler mobile body, or a track mobile body, the image acquisition device can be at least one of a camera, a camera, a scanner, a point cloud radar, etc., the mechanical arm can be a 4-axis manipulator, including lateral movement (x movement), longitudinal movement (y movement), lifting (z movement) and base rotation 4 degrees of freedom, the mechanical arm can also be composed of 6 degrees of freedom, and the dredging mechanism can be a dredging rod or a dredging fork. The control module 620 can be a control chip or controller such as MCU (Microcontroller Unit) or ECU (Electronic Control Unit), and the information processing module 630 can be a computer device such as a computer, a computing cluster, a microcomputer, an embedded computer, a neural network computer, or a server. Of course, the dredging device 110 can also include an image processing device such as an image processor or an image processing chip, which constitutes a visual system with the image acquisition device, or the image processing device is configured in the information processing module 630, and constitutes a visual system with the image acquisition device, which is not limited here. In addition, the control module 620 and / or the information processing module 630 can be configured in the dredging device 110, or can be independent of the dredging device 110. The control module 620 and / or the information processing module 630 can also be configured in Figure 1 The computer device 120 in the illustrated implementation environment is not limited here either.

[0081] like Figure 3 As shown, the dredging equipment 110 includes a mobile car, a 4-axis manipulator, a visual system and a dredging rod, wherein the mobile car can move forward and backward and turn, the 4-axis manipulator is installed on the mobile car, and has four degrees of freedom of X, Y, Z, and rotation (R), the dredging rod is installed at the end of the 4-axis manipulator, and the visual system is fixedly installed on the mobile car, wherein the visual system includes an image acquisition device and an image processing device such as an image processor or an image processing chip. It should be understood that the mobile car is a specific example of a mobile body, the 4-axis manipulator is a specific example of a mechanical arm, and the dredging rod is a specific example of a dredging mechanism.

[0082] The infiltration screen dredging system can realize the automation of the infiltration screen dredging process in harsh environments such as sewage and explosives, improve the intelligence level of garbage pool infiltration screen operations, greatly improve dredging efficiency, and does not require human intervention, which can effectively reduce labor costs and safety risks for operators.

[0083] It should be noted that the infiltration grid dredging system provided in the above embodiment and the infiltration grid dredging method provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs the operation has been described in detail in the method embodiment, and will not be repeated here. In practical applications, the infiltration grid dredging system provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the system into different functional modules to complete all or part of the functions described above, and this is not limited here.

[0084] This embodiment also provides an electronic device, including: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the electronic device implements the infiltration grid clearing method provided in the above-mentioned embodiments.

[0085] See also Figure 7 , Figure 7 is a schematic diagram of a structure of an electronic device shown in an exemplary embodiment of the present application. It should be noted that: Figure 7 The electronic device 700 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0086] like Figure 7 As shown, the electronic device 700 includes a processor 701, a memory 702 and a communication bus 703; the communication bus 703 is used to connect the processor 701 and the memory 702; the processor 701 is used to execute the computer program stored in the memory 702 to implement one or more methods in the above embodiments.

[0087] This embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer executes the infiltration grid dredging method as described above. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist independently without being assembled into the electronic device.

[0088] This embodiment also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the infiltration grid dredging method provided in each of the above embodiments.

[0089] The electronic device provided in this embodiment includes a processor, a memory, a transceiver and a communication interface. The memory and the communication interface are connected to the processor and the transceiver and complete communication with each other. The memory is used to store computer programs, the communication interface is used to communicate, and the processor and the transceiver are used to run the computer program so that the electronic device executes each step of the above method.

[0090] In this embodiment, the memory may include a random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0091] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0092] The computer-readable storage medium in this embodiment can be understood by ordinary technicians in this field: all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, the execution includes the steps of the above-mentioned method embodiments; and the aforementioned storage medium includes: ROM (read-only memory), RAM (random access memory), magnetic disk or optical disk and other media that can store program codes.

[0093] The above embodiments are merely illustrative of the principles and effects of the present application, and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A method for clearing a percolation grid, characterized in that: The method is applied to a dredging device, which includes a mobile body, an image acquisition device and a mechanical arm arranged on the mobile body, and a dredging mechanism arranged at a free end of the mechanical arm. The method includes: In response to the target dredging instruction, the dredging device is controlled to move to the target infiltration grid, an image of a target positioning marker corresponding to the target infiltration grid is acquired and image recognition is performed to obtain the pixel coordinates of the target positioning marker; Based on the pixel coordinates of the target positioning marker and the physical coordinates of the target positioning marker, determine the current conversion relationship between the camera coordinate system and the coordinate system corresponding to the target positioning marker; According to the current conversion relationship, the preset conversion relationship between the robot arm coordinate system and the camera coordinate system, and the preset posture of the robot arm in the coordinate system corresponding to the target positioning marker, the target posture of the robot arm in the robot arm coordinate system is determined, so as to control the robot arm according to the target posture to drive the dredging mechanism to insert into the target infiltration grid to perform dredging.

2. The method for clearing the infiltration grid according to claim 1, characterized in that: Before acquiring an image of a target positioning marker corresponding to a target infiltration grid, the method includes: Controlling the dredging device to move from the standby position to the infiltration grid, and controlling the image acquisition device to perform real-time image acquisition during the movement to obtain the current number of positioning markers; If the current number of positioning markers and the corresponding numbers of the target positioning markers meet the preset conditions, the dredging equipment is controlled to stop moving, and the image of the target positioning marker is captured by the image acquisition device to obtain an image of the target positioning marker, wherein the information of the target infiltration grid includes the corresponding numbers of the target positioning markers, and each positioning marker has a corresponding number.

3. The method for clearing the infiltration grid according to claim 1, characterized in that: Before determining the target posture of the robotic arm in the robotic arm coordinate system, the method includes: Obtaining the preset posture of the robot arm in the coordinate system corresponding to each positioning marker, wherein obtaining the preset posture of the robot arm in the coordinate system corresponding to a positioning marker includes: Teaching the robotic arm so that the robotic arm drives the dredging mechanism to insert into the percolation grid corresponding to the positioning marker, so as to obtain the teaching posture of the robotic arm in the robotic arm coordinate system, and obtain the image of the positioning marker and perform image recognition to obtain the pixel coordinates of the positioning marker, wherein the image of the positioning marker is acquired by the image acquisition device; Determine the conversion relationship between the camera coordinate system and the coordinate system corresponding to the positioning marker based on the pixel coordinates of the positioning marker and the physical coordinates of the positioning marker; According to the taught posture of the robotic arm in the robotic arm coordinate system, the conversion relationship between the camera coordinate system and the coordinate system corresponding to the positioning marker, and the preset conversion relationship, the preset posture of the robotic arm in the coordinate system corresponding to the positioning marker is determined.

4. The method for clearing a percolation grid according to any one of claims 1 to 3, characterized in that: Before determining the target posture of the robotic arm in the robotic arm coordinate system, the method further includes: Fixing a calibration plate to the free end of the robotic arm, obtaining different postures of the robotic arm in the robotic arm coordinate system, and acquiring an image of the calibration plate in each posture by the image acquisition device; The preset conversion relationship is determined according to different postures of the robotic arm in the robotic arm coordinate system and the image of the calibration plate in each posture.

5. The method for clearing the infiltration grid according to claim 1, characterized in that: According to the current conversion relationship, the preset conversion relationship between the robot coordinate system and the camera coordinate system, and the preset posture of the robot in the coordinate system corresponding to the target positioning marker, the target posture of the robot in the robot coordinate system is determined, so as to control the robot to drive the dredging mechanism to insert into the target infiltration grid to perform dredging according to the target posture, including: Determine multiple initial postures of the robotic arm in the coordinate system corresponding to the target positioning marker according to a preset posture of the robotic arm in the coordinate system corresponding to the target positioning marker and multiple preset translation vectors; Determine each target posture of the robotic arm in the robotic arm coordinate system according to the current conversion relationship, the preset conversion relationship, and each initial posture of the robotic arm in the coordinate system corresponding to the target positioning marker, so as to obtain multiple target postures of the robotic arm in the robotic arm coordinate system; The mechanical arm is controlled according to each target posture respectively, so that the mechanical arm drives the dredging mechanism to be inserted into different positions of the target infiltration grid to perform dredging.

6. The method for clearing the infiltration grid according to claim 1, characterized in that: After performing the unblocking, the method includes: Acquire an image of the target infiltration grid and perform image recognition to obtain the infiltration amount category and infiltration position of the infiltration liquid in the target infiltration grid, wherein the image of the target infiltration grid is acquired by the image acquisition device, and the infiltration amount category includes a large amount of infiltration or a small amount of infiltration; Determine the position of the leachate in the robot arm coordinate system according to the infiltration position and the preset conversion relationship, and determine the position of the dredging mechanism in the robot arm coordinate system based on the target posture and the preset relative position of the robot arm and the dredging mechanism; If the infiltration amount category is large amount of infiltration, and the position of the infiltration liquid in the robot arm coordinate system successfully matches the position of the dredging mechanism in the robot arm coordinate system, it is determined that the target infiltration grid is successfully dredged; Controlling the dredging device to move to a new target infiltration grid to dredge the new target infiltration grid, wherein the target dredging instruction includes information of a plurality of target infiltration grids; Until all target infiltration grids are successfully dredged, the dredging equipment is controlled to move to the standby position.

7. The method for clearing the infiltration grid according to claim 6, characterized in that: Controlling the dredging device to move to a standby position includes: Controlling the dredging device to move along the infiltration grid to the standby position, and controlling the image acquisition device to perform real-time image acquisition during the movement; If the image of the positioning ring is identified from the real-time collected image, the dredging device is controlled to stop moving, wherein the positioning ring is provided at the standby position.

8. The method for clearing the infiltration grid according to claim 2, characterized in that: During the movement, the image acquisition device is controlled to acquire real-time images to obtain the current number of positioning markers, including: Acquire the currently collected real-time image and identify the real-time image; If a target contour area that meets a preset shape is identified from the real-time image, straight line fitting is performed on the edge points in the target contour area, and the angles between all the straight lines obtained by fitting are calculated, wherein the positioning marker includes an outer contour, a first line segment and a second line segment, the shape of the outer contour is the preset shape, the first line segment and the second line segment are perpendicular to each other, and both ends of the first line segment and the second line segment are respectively connected to the outer contour; When the angle satisfies the preset angle range, the current number of positioning markers is increased by one.

9. A percolation grid dredging system, characterized in that: The system comprises: The dredging device comprises a mobile body, an image acquisition device and a mechanical arm arranged on the mobile body, and a dredging mechanism arranged at the free end of the mechanical arm; A control module, for controlling the dredging device to move to a target infiltration grid in response to a target dredging instruction; controlling the mechanical arm to drive the dredging mechanism to insert into the target infiltration grid to perform dredging according to the target position of the mechanical arm in the mechanical arm coordinate system; An information processing module is used to obtain an image of a target positioning marker corresponding to a target infiltration grid and perform image recognition to obtain pixel coordinates of the target positioning marker; based on the pixel coordinates of the target positioning marker and the physical coordinates of the target positioning marker, determine the current conversion relationship between a camera coordinate system and a coordinate system corresponding to the target positioning marker; and determine the target posture according to the current conversion relationship, a preset conversion relationship between a robotic arm coordinate system and a camera coordinate system, and a preset posture of the robotic arm in the coordinate system corresponding to the target positioning marker.

10. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the electronic device to implement the infiltration grid clearing method as described in any one of claims 1-8.

11. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the infiltration grid clearing method as described in any one of claims 1-8.

Images