Hinge hole assembly reference determination method and device and electronic equipment

Abstract

The invention relates to the technical field of vehicle assembly, in particular to a hinge hole assembly reference determination method and device and electronic equipment, and the method comprises the steps: obtaining the point cloud data of the upper and lower end faces of a hinge hole; extracting contour edges of the upper and lower end faces of the hinge hole based on clustering processing and plane segmentation of the point cloud data of the upper and lower end faces of the hinge hole, and performing circle fitting on the point cloud data of the contour edges; and identifying circle center coordinates and axis direction vectors of the upper and lower end faces of the hinge hole in a circle fitting result, and determining an assembly reference of the hinge hole according to the circle center coordinates and the axis direction vectors. Therefore, the problem of how to efficiently and accurately determine the assembly reference of the hinge hole in the vehicle door assembly work is solved.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle assembly, and in particular to a method, device and electronic equipment for determining an assembly reference of a hinge hole. Background Art

[0002] The assembly quality of automobile doors has a crucial impact on the vehicle's overall sealing, noise control, and user experience. Traditional door hinge installation mainly relies on manual alignment and mechanical fixture-assisted assembly. However, due to errors in manual operation and processing errors in the body and door components themselves, it is often difficult to ensure high-precision assembly results and cannot meet the needs of mass assembly on automobile production lines.

[0003] Related technologies typically use high-precision automated assembly methods based on point cloud processing to improve the accuracy and efficiency of door installation. However, during hinge installation, the large amount of point cloud data requires complex screening and manual intervention, making the processing time-consuming and accuracy susceptible to noise. This makes it difficult to meet the high-precision requirements of complex assembly environments. Summary of the Invention

[0004] The present application provides a method, device and electronic equipment for determining an assembly datum of a hinge hole, so as to solve the problem of how to efficiently and accurately determine the assembly datum of a hinge hole during vehicle door assembly.

[0005] The first aspect of the present application provides a method for determining the assembly reference of a hinge hole, comprising the following steps: acquiring point cloud data of the upper and lower end faces of the hinge hole; extracting the contour edges of the upper and lower end faces of the hinge hole based on clustering processing and plane segmentation of the point cloud data of the upper and lower end faces of the hinge hole, and performing circle fitting on the point cloud data of the contour edges; identifying the center coordinates and axial direction vectors of the upper and lower end faces of the hinge hole in the circle fitting results, and determining the assembly reference of the hinge hole based on the center coordinates and axial direction vectors.

[0006] Optionally, obtaining point cloud data of the upper and lower end surfaces of the hinge hole includes: starting a three-dimensional scanning device installed at the end of the manipulator; using the three-dimensional scanning device to collect point cloud data of the upper and lower end surfaces of the hinge hole above and below the hinge hole respectively.

[0007] Optionally, before starting the three-dimensional scanning device installed at the end of the manipulator, it also includes: calibrating the manipulator and the end effector to obtain the conversion relationship between the internal coordinate system of the manipulator and the end coordinate system, calibrating the three-dimensional scanning device installed at the end of the manipulator, and establishing a mapping relationship between the three-dimensional scanning device and the internal coordinate system of the manipulator based on the conversion relationship; establishing a global coordinate system of the entire vehicle through the calibration points on the vehicle body and the mapping relationship, and establishing a mapping between the entire vehicle and the manipulator coordinate system based on the global coordinate system of the entire vehicle.

[0008] Optionally, based on clustering processing and plane segmentation of the point cloud data of the upper and lower end faces of the hinge hole, the contour edges of the upper and lower end faces of the hinge hole are extracted, including: clustering processing of the point cloud data of the upper and lower end faces of the hinge hole; plane segmentation of the point cloud data after clustering processing to obtain point cloud data of a target range; traversing the point cloud data of the target range, determining the target neighbor point cloud based on a threshold value of the number of neighbor point clouds of each point cloud, and extracting the contour edges of the upper and lower end faces of the hinge hole based on the target neighbor point cloud.

[0009] Optionally, the point cloud data of the upper and lower end surfaces of the hinge hole are clustered, including: setting a Z-axis coordinate threshold perpendicular to the direction of the three-dimensional scanning device; and clustering the point cloud data of the upper and lower end surfaces of the hinge hole based on the Z-axis coordinate threshold.

[0010] Optionally, plane segmentation is performed on the clustered point cloud data to obtain point cloud data within a target range, including: plane fitting is performed on the clustered point cloud data; a first distance threshold of the fitting plane is set, and point cloud data within the first distance threshold is filtered out from the fitting plane.

[0011] Optionally, circle fitting is performed on the point cloud data of the contour edge, including: setting a threshold for the number of iterations of the fitted circle, a second distance threshold, and a radius threshold; based on the threshold for the number of iterations, the second distance threshold, and the radius threshold, iteratively fitting the point cloud data of the contour edge, and determining the coordinates of the center of the circle according to the iterative fitting result; and calculating the direction vector of the line connecting the centers of the upper and lower end faces according to the coordinates of the center of the circle.

[0012] Optionally, the assembly datum of the hinge hole is determined based on the center coordinates and the axis direction vector, including: calculating the average value of the center coordinates and the average value of the axis direction vector in the circle fitting result; and using the average value of the center coordinates and the average value of the axis direction vector as the assembly datum of the hinge hole.

[0013] The second aspect of the present application provides a hinge hole assembly reference determination device, including: an acquisition module for acquiring point cloud data of the upper and lower end faces of the hinge hole; a processing module for extracting the contour edges of the upper and lower end faces of the hinge hole based on clustering processing and plane segmentation of the point cloud data of the upper and lower end faces of the hinge hole, and performing circle fitting on the point cloud data of the contour edges; a determination module for identifying the center coordinates and axial direction vectors of the upper and lower end faces of the hinge hole in the circle fitting results, and determining the assembly reference of the hinge hole based on the center coordinates and axial direction vectors.

[0014] Optionally, the acquisition module is further used to start a three-dimensional scanning device installed at the end of the manipulator; the three-dimensional scanning device is used to collect point cloud data of the upper and lower end surfaces of the hinge hole above and below the hinge hole respectively.

[0015] Optionally, the hinge hole assembly reference determination device also includes: a calibration module, which is used to calibrate the manipulator and the end effector before starting the three-dimensional scanning device installed at the end of the manipulator to obtain the conversion relationship between the internal coordinate system of the manipulator and the end coordinate system, calibrate the three-dimensional scanning device installed at the end of the manipulator, and establish a mapping relationship between the three-dimensional scanning device and the internal coordinate system of the manipulator based on the conversion relationship; an establishment module, which is used to establish the global coordinate system of the entire vehicle through the calibration points and mapping relationship on the vehicle body, and establish a mapping between the entire vehicle and the manipulator coordinate system according to the global coordinate system of the entire vehicle.

[0016] Optionally, the processing module is further used to perform clustering processing on the point cloud data of the upper and lower end faces of the hinge hole; perform plane segmentation on the clustered point cloud data to obtain point cloud data of the target range; traverse the point cloud data of the target range, determine the target neighbor point cloud based on the threshold of the number of neighbor point clouds of each point cloud, and extract the contour edges of the upper and lower end faces of the hinge hole based on the target neighbor point cloud.

[0017] Optionally, the processing module is further used to set a Z-axis coordinate threshold perpendicular to the direction of the three-dimensional scanning device; and cluster the point cloud data of the upper and lower end surfaces of the hinge hole based on the Z-axis coordinate threshold.

[0018] Optionally, the processing module is further used to set an iteration number threshold, a second distance threshold and a radius threshold for fitting the circle; based on the iteration number threshold, the second distance threshold and the radius threshold, the point cloud data of the contour edge is iteratively fitted, and the center coordinates of the circle are determined according to the iterative fitting results; and the direction vector of the line connecting the centers of the upper and lower end faces is calculated according to the center coordinates.

[0019] Optionally, the determination module is further used to calculate the average value of the circle center coordinates and the average value of the axis direction vector in the circle fitting result; and use the average value of the circle center coordinates and the average value of the axis direction vector as the assembly reference of the hinge hole.

[0020] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein the processor executes the program to implement the hinge hole assembly reference determination method as described in the above embodiment.

[0021] Therefore, this application has the following beneficial effects:

[0022] The embodiment of the present application obtains point cloud data of the upper and lower end faces of the hinge hole, and extracts the contour edges of the upper and lower end faces of the hinge hole based on clustering processing and plane segmentation technology. It can effectively remove irrelevant data and retain the boundary features of the hinge hole, thereby improving the validity of the data, and performing circle fitting on these contour edges to identify the center coordinates and axis direction vectors of the upper and lower end faces of the hinge hole, making the benchmark extraction more reliable and accurate, thereby ensuring higher precision during the assembly process.

[0023] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0025] Figure 1 This is a flow chart of a method for determining an assembly reference of a hinge hole provided in accordance with an embodiment of the present application;

[0026] Figure 2 A detailed flow chart of a method for determining an assembly reference of a hinge hole according to one embodiment of the present application;

[0027] Figure 3 A schematic diagram of a vehicle body end hinge hole and a door end hinge shaft provided according to one embodiment of the present application;

[0028] Figure 4 To provide an angle reference evaluation standard diagram according to one embodiment of the present application;

[0029] Figure 5 To provide a point cloud image after clustering processing according to one embodiment of the present application;

[0030] Figure 6 To provide an edge extraction effect diagram according to one embodiment of the present application;

[0031] Figure 7 A diagram showing the effect of circle fitting according to an embodiment of the present application;

[0032] Figure 8 This is an exemplary diagram of a hinge hole assembly reference determination device according to an embodiment of the present application;

[0033] Figure 9 Schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0034] The following describes in detail embodiments of the present application. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0035] The following describes the hinge hole assembly reference determination method, device and electronic device of the embodiment of the present application with reference to the accompanying drawings. In response to the problems mentioned in the above background technology, the present application provides a hinge hole assembly reference determination method, in which the point cloud data of the upper and lower end faces of the hinge hole are obtained, and the contour edges of the upper and lower end faces of the hinge hole are extracted based on clustering processing and plane segmentation technology. This method can effectively remove irrelevant data and retain the boundary features of the hinge hole, thereby improving the validity of the data. Circular fitting is performed on these contour edges to identify the center coordinates and axial direction vectors of the upper and lower end faces of the hinge hole, making the reference extraction more reliable and accurate, thereby ensuring higher precision during the assembly process.

[0036] Specifically, Figure 1 A schematic flow chart of a method for determining an assembly reference of a hinge hole provided in an embodiment of the present application.

[0037] like Figure 1 As shown, the hinge hole assembly reference determination method includes the following steps:

[0038] In step S101 , point cloud data of the upper and lower end surfaces of the hinge hole are obtained.

[0039] In one embodiment of the present application, obtaining point cloud data of the upper and lower end surfaces of the hinge hole includes: starting a three-dimensional scanning device installed at the end of the manipulator; using the three-dimensional scanning device to collect point cloud data of the upper and lower end surfaces of the hinge hole above and below the hinge hole respectively.

[0040] It is understood that in the embodiment of the present application, after the hinge hole at the vehicle body end is fixed, a 3D scanning device mounted on the end of the manipulator can be used to collect point cloud data of the upper and lower end surfaces of the hinge hole, respectively, directly above and directly below the hinge hole. In this way, complete point cloud data of the hinge hole end surface can be obtained through dual-position acquisition.

[0041] In an embodiment of the present application, before starting the three-dimensional scanning device installed at the end of the manipulator, it also includes: calibrating the manipulator and the end effector to obtain the conversion relationship between the internal coordinate system of the manipulator and the end coordinate system, calibrating the three-dimensional scanning device installed at the end of the manipulator, and establishing a mapping relationship between the three-dimensional scanning device and the internal coordinate system of the manipulator based on the conversion relationship; establishing a global coordinate system of the entire vehicle through the calibration points on the vehicle body and the mapping relationship, and establishing a mapping between the entire vehicle and the manipulator coordinate system based on the global coordinate system of the entire vehicle.

[0042] Specifically, before starting the three-dimensional scanning device installed at the end of the manipulator, the embodiment of the present application can achieve precise positioning of the assembly system through hand-eye calibration technology (the three-dimensional scanning device is at the end of the manipulator). First, the manipulator and the end effector are calibrated to obtain the conversion relationship between the internal coordinate system of the manipulator and the end coordinate system. At the same time, the camera installed at the end of the manipulator is calibrated to establish a mapping between the camera and the manipulator coordinate system. The global coordinate system of the entire vehicle is established through the calibration points on the vehicle body, and the mapping between the entire vehicle and the manipulator coordinate system is achieved to ensure that the spatial position of the assembly point is accurate.

[0043] In step S102 , based on clustering and plane segmentation of the point cloud data of the upper and lower end surfaces of the hinge hole, the contour edges of the upper and lower end surfaces of the hinge hole are extracted, and circle fitting is performed on the point cloud data of the contour edges.

[0044] It can be understood that the embodiment of the present application distinguishes edge points from internal points by calculating the resultant force of each point in its neighborhood, thereby accurately extracting the contour edge of the hinge hole end face.

[0045] In one embodiment of the present application, based on clustering processing and plane segmentation of the point cloud data of the upper and lower end faces of the hinge hole, the contour edges of the upper and lower end faces of the hinge hole are extracted, including: clustering the point cloud data of the upper and lower end faces of the hinge hole; plane segmentation of the point cloud data after clustering processing to obtain point cloud data of a target range; traversing the point cloud data of the target range, determining the target neighbor point cloud based on a threshold value of the number of neighbor point clouds of each point cloud, and extracting the contour edges of the upper and lower end faces of the hinge hole based on the target neighbor point cloud.

[0046] This embodiment of the present application clusters the point cloud data of the upper and lower end faces of the hinge hole, removes background and noise point clouds, and performs plane fitting on the clustered point cloud data. A distance threshold is set to filter out point cloud data whose distance to the fitting plane falls within the threshold range, extracting feature point cloud data of the hinge hole end face and reducing the influence of other interfering point clouds. The method then traverses the point cloud data of the hinge hole end face, sets a threshold for the number of neighboring points for each point, finds the nearest neighbor, and calculates the resultant force of its neighborhood. Edge points and internal points are classified according to the magnitude of the resultant force, thereby extracting the contour edge of the hinge hole end face and accurately identifying the boundary features of the hinge hole.

[0047] Furthermore, the point cloud data of the upper and lower end surfaces of the hinge hole are clustered, including: setting a Z-axis coordinate threshold perpendicular to the direction of the three-dimensional scanning device; and clustering the point cloud data of the upper and lower end surfaces of the hinge hole based on the Z-axis coordinate threshold.

[0048] The embodiment of the present application sets a Z-axis coordinate threshold perpendicular to the direction of the three-dimensional scanning device. Through this threshold, the area where the hinge hole end face is located can be quickly located and extracted, and the point cloud data that meets the conditions can be filtered to retain the valid feature data of the hinge hole end face.

[0049] Furthermore, plane segmentation is performed on the clustered point cloud data to obtain point cloud data within a target range, including: plane fitting is performed on the clustered point cloud data; a first distance threshold of the fitting plane is set, and point cloud data within the first distance threshold is filtered out from the fitting plane.

[0050] Among them, those skilled in the art can set the first distance threshold according to actual conditions, such as setting it to 0.2 mm, without specific limitation.

[0051] In this embodiment of the present application, the plane where the hinge hole end face is located can be accurately fitted using RANSAC, and a first distance threshold can be set to determine which points can be considered to be part of the fitted plane. The first distance threshold directly affects which points will be retained and whether the ultimately extracted point cloud data accurately reflects the true shape of the hinge hole end face. Therefore, by accurately fitting the plane where the hinge hole end face is located and using an appropriate first distance threshold to filter the point cloud, the accuracy of subsequent analysis can be significantly improved.

[0052] In one embodiment of the present application, circle fitting is performed on point cloud data of a contour edge, including: setting a threshold for the number of iterations of the fitting circle, a second distance threshold, and a radius threshold, performing iterative fitting on the point cloud data of the contour edge based on the threshold for the number of iterations, the second distance threshold, and the radius threshold, determining the coordinates of the circle center according to the iterative fitting result; and calculating the direction vector of the line connecting the centers of the upper and lower end faces according to the coordinates of the circle center.

[0053] It is understandable that the embodiment of the present application accurately obtains the center coordinates and axis direction vectors of the upper and lower end faces of the hinge hole by performing circle fitting on the point cloud data of the contour edge. The specific method includes: setting an iteration number threshold, a second distance threshold, and a radius threshold, selecting the best fitting circle through multiple fitting processes, recording its center coordinates, and calculating the direction vector of the line connecting the centers of the upper and lower end faces using the center coordinates as the direction reference of the hinge axis. The iteration number threshold, the second distance threshold, and the radius threshold can be set according to actual conditions without specific limitations. For example, the iteration number threshold is set to 2000 times, the second distance threshold is set to 0.1mm, and the radius threshold is set to 6.5mm.

[0054] In step S103, the center coordinates and axis direction vectors of the upper and lower end surfaces of the hinge hole in the circle fitting result are identified, and the assembly reference of the hinge hole is determined according to the center coordinates and the axis direction vector.

[0055] Building on the above-mentioned examples, the present embodiment intelligently extracts the edges of point cloud data, effectively removing irrelevant data and preserving the boundary features of the hinge hole, thereby improving data validity. RANSAC circle fitting further ensures the precise calculation of the hinge hole end face center coordinates and axis direction vectors, offering excellent noise immunity and stability, making datum extraction more reliable. This significantly improves the accuracy of the hinge hole assembly datum, providing a solid technical foundation for the automation and intelligentization of the door hinge assembly process, reducing the frequency of manual adjustments and error accumulation, and improving production efficiency.

[0056] In one embodiment of the present application, the assembly reference of the hinge hole is determined based on the center coordinates and the axis direction vector, including: calculating the average value of the center coordinates and the average value of the axis direction vector in the circle fitting result; and using the average value of the center coordinates and the average value of the axis direction vector as the assembly reference of the hinge hole.

[0057] In this embodiment, the average value of the center coordinates and axis direction vectors in the fitting results is calculated as the reference coordinates. The deviation value of the center coordinates in each fitting result is obtained, and the maximum deviation and standard deviation in each direction are extracted. At the same time, the angle between the direction vectors is calculated and the maximum value is extracted. These parameters are compared with the accuracy standard to ensure that the hinge hole assembly benchmark meets the accuracy requirements.

[0058] In summary, the hinge hole assembly reference determination method of the embodiment of the present application can significantly improve the accuracy of the assembly reference, while reducing the frequency of manual adjustment and error accumulation, thereby improving production efficiency. Figure 2 As shown, the specific steps include:

[0059] Step 1: Use a 3D scanning device to collect multiple point cloud data of the hinge hole;

[0060] Step 2: Cluster the collected hinge hole end face point cloud data to remove background point clouds and noise point clouds;

[0061] Step 3: After completing the clustering process, the point cloud data needs to be further segmented to extract the plane where the hinge hole end face is located.

[0062] Step 4: The edge extraction technology based on the resultant force method calculates the resultant force of each point in its neighborhood to distinguish edge points from internal points, thereby accurately extracting the contour edge of the hinge hole end face;

[0063] Step 5: Perform circle fitting on the extracted edge point cloud data to accurately obtain the center coordinates of the upper and lower end faces of the hinge hole, and determine the axis direction vector by connecting the center points of the upper and lower end faces;

[0064] Step 6: Obtain the deviation value and maximum angle of the fitting circle center coordinates through multiple acquisitions and calculations, compare them with the preset accuracy requirements, and determine whether the accuracy of the assembly benchmark meets the requirements.

[0065] The following describes in detail the hinge hole assembly benchmark determination method of the embodiment of the present application with reference to specific examples. Before performing benchmark extraction, the embodiment of the present application can obtain the benchmark evaluation standard of the end face center three-dimensional coordinates and angle based on the workpiece drawings of the vehicle body end hinge hole and the door end hinge shaft, providing a judgment standard for subsequent benchmark evaluation, such as Figure 3 Secondly, the embodiment of the present application uses a 3D scanning device to collect point cloud data multiple times, processes the collected point cloud data, and extracts the required benchmark indicators. A calibration plate is used to perform hand-eye calibration on the 3D scanning device, so that the 3D coordinates obtained by subsequent fitting are relative to the coordinate system of the robot base, facilitating the normalization of the coordinate system.

[0066] Before hand-eye calibration, the 3D scanning device is first calibrated with internal parameters. The imaging characteristics of the device are recorded using a calibration plate to obtain the device's internal parameter matrix. The internal parameter matrix can be expressed as:

[0067]

[0068] Among them, f x and f y is the focal length, c x and c y The main point coordinates.

[0069] Fix the calibration plate at a known position and keep it stationary relative to the robot base coordinate system. Operate the end of the manipulator carrying the 3D scanning device to accurately shoot the calibration plate and record the position coordinates of the 20 feature points on the calibration plate: P = (P1, P2, ..., P 24 ), the position coordinates of all feature points relative to the robot base coordinate system are known to be Q = (Q1, Q2, ..., Q 24 ), then the corresponding relationship between P and Q is:

[0070] Q=AXP

[0071] Where A is the transformation matrix of the manipulator end relative to the robot base, and X is the transformation matrix of the 3D scanning device relative to the manipulator end.

[0072] The manipulator end is manipulated to transform its position and obtain the new coordinates of the feature points as U=(U1,U2,...,U 24 ), then the corresponding relationship between the new coordinates U and Q is:

[0073] Q=BXU

[0074] Where B is the new transformation matrix of the manipulator end relative to the robot base,

[0075] AXP=BXU

[0076] X, the transformation matrix of the 3D scanning device relative to the end of the manipulator, can be solved to complete the entire hand-eye calibration process.

[0077] Furthermore, the embodiment of the present application can obtain the benchmark evaluation standard of the three-dimensional coordinates of the end face center and the angle of the shaft hole axial vector through the workpiece drawings of the body end hinge hole and the door end hinge shaft and the shaft hole assembly relationship, such as Figure 4 As shown. The mating hole diameter tolerance range for the body-end hinge hole is 10.13mm-10.19mm, the mating hole height tolerance range is 15.9mm-16.1mm, and the hole end face center positioning accuracy requirement is a diameter tolerance of φ0.4mm. The offset relative to the reference position must be within the circle diameter of 0.4mm. The mating shaft diameter tolerance range for the door-end hinge shaft is 9.98mm-10mm, and the mating shaft height tolerance range is 19.3mm-19.7mm. Based on this shaft-hole assembly relationship and the tolerance range of the workpiece fit, the mating hole diameter D of the body-end hinge hole is set to 10.13mm, and the mating shaft diameter d of the door-end hinge shaft is set to 10mm to ensure a high-precision assembly reference fit. Therefore, the deviation evaluation benchmark calculation result is 0.065mm, that is, the maximum spatial position deviation of the fitting circle center coordinate is 0.065mm.

[0078] According to the shaft-hole assembly relationship, the included angle between the axis direction vectors is calculated as the evaluation benchmark, and the matching hole height h is taken as 16.1mm, such as Figure 5 As shown in the figure, the evaluation benchmark is the maximum vector angle value that can be used to complete the assembly of the shaft-hole fit. The calculation formula of the angle evaluation benchmark α is as follows:

[0079]

[0080] According to this formula, the value of the angle evaluation benchmark α is 0.4584°.

[0081] Use the calibrated 3D scanning equipment to collect point cloud data multiple times, process the collected point cloud data, and extract the required benchmark indicators, such as Figure 5 First, the end-arm of the robot carrying the 3D scanning device is controlled to move the device to preset positions 1 and 2 above and below the hinge hole, respectively, to completely cover the point cloud features of the hinge hole.

[0082] The point cloud data is clustered and filtered, and the z-coordinate threshold range perpendicular to the direction of the 3D scanning device is set to 273mm-277mm. Each cluster group is checked. If there are points in the group that meet the z-coordinate range, the group is retained; otherwise, the group is eliminated to complete the filtering of environmental background and noise.

[0083] The RANSAC plane segmentation method was applied to extract the feature point cloud of the hinge hole end face. The fitting distance threshold was set to 0.2 mm. Based on this threshold, points in the point cloud close to the fitting plane were selected as end face feature points, thereby achieving RANSAC plane segmentation.

[0084] Take the points on the end face as a mechanical model and traverse all the points on the end face. Set the threshold of the number of neighbor points to 7 and the resultant force threshold to 5, find the nearest neighbor point of each point, and calculate the resultant force F of each point in its own neighborhood. sum , the calculation formula is as follows:

[0085]

[0086] Among them, P0 is the three-dimensional coordinate of each calculation point, P i The three-dimensional coordinates of the i-th neighbor point of the calculation point.

[0087] All points are classified according to the resultant force threshold, and points greater than the resultant force threshold are regarded as edge points to realize the edge extraction of point cloud data based on the resultant force method. Figure 6 shown.

[0088] Perform RANSAC circle fitting on the extracted edge point cloud data, set the number of fitting iterations to 2000, the distance threshold to 0.1mm, and the radius threshold to 6.5mm, randomly select three points in the edge point cloud data to complete the circle fitting, filter the size of the fitted circle according to the radius threshold, retain the fitting circle with a radius less than the threshold, record the number of inner points of each successfully fitted circle according to the distance threshold, loop fitting until the number of fitting iterations is reached, select the fitting circle with the most inner points as the best fitting circle, record its center coordinates, and use the line connecting the center coordinates of the upper and lower end faces as the axis direction vector of the hinge hole at the vehicle body end, record the data and retain the vehicle, such as Figure 7 shown.

[0089] Calculate the average value of the fitting coordinates of the upper and lower end faces of the hole as the reference coordinates Calculate the deviation value (Δx i ,Δy i ,Δz i ), get the maximum deviation value Δx max , Δy max , Δz max and the maximum value of the total deviation δ maxAnd the maximum angle β between two adjacent fittings max , the specific calculation formula is as follows:

[0090]

[0091] Where N is the number of data collection and fitting.

[0092] According to the deviation evaluation benchmark requirement of 0.065mm and the angle evaluation benchmark requirement of 0.4854°, when the fitting index is smaller than the benchmark requirement, it is determined that the hinge hole assembly benchmark accuracy is high and meets the assembly requirements.

[0093] According to the hinge hole assembly reference determination method proposed in the embodiment of the present application, by acquiring the point cloud data of the upper and lower end faces of the hinge hole and extracting the contour edges of the upper and lower end faces of the hinge hole based on clustering processing and plane segmentation technology, irrelevant data can be effectively removed and the boundary features of the hinge hole can be retained, thereby improving the validity of the data, and circular fitting is performed on these contour edges to identify the center coordinates and axial direction vectors of the upper and lower end faces of the hinge hole, making the reference extraction more reliable and accurate, thereby ensuring higher precision during the assembly process.

[0094] Next, the hinge hole assembly reference determination device proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0095] Figure 8 It is a block diagram of a hinge hole assembly reference determination device according to an embodiment of the present application.

[0096] like Figure 8 As shown, the hinge hole assembly reference determination device 10 includes: an acquisition module 101 , a processing module 102 and a determination module 103 .

[0097] Among them, the acquisition module 101 is used to obtain the point cloud data of the upper and lower end faces of the hinge hole; the processing module 102 is used to extract the contour edges of the upper and lower end faces of the hinge hole based on the clustering processing and plane segmentation of the point cloud data of the upper and lower end faces of the hinge hole, and perform circle fitting on the point cloud data of the contour edges; the determination module 103 is used to identify the center coordinates and axial direction vectors of the upper and lower end faces of the hinge hole in the circle fitting results, and determine the assembly reference of the hinge hole according to the center coordinates and axial direction vector.

[0098] In one embodiment of the present application, the acquisition module 101 is further used to start a three-dimensional scanning device installed at the end of the manipulator; the three-dimensional scanning device is used to collect point cloud data of the upper and lower end surfaces of the hinge hole above and below the hinge hole respectively.

[0099] In one embodiment of the present application, the hinge hole assembly reference determination device 10 also includes: a calibration module, which is used to calibrate the manipulator and the end effector before starting the three-dimensional scanning device installed at the end of the manipulator to obtain the conversion relationship between the internal coordinate system of the manipulator and the end coordinate system, calibrate the three-dimensional scanning device installed at the end of the manipulator, and establish a mapping relationship between the three-dimensional scanning device and the internal coordinate system of the manipulator based on the conversion relationship; an establishment module, which is used to establish the global coordinate system of the entire vehicle through the calibration points and mapping relationship on the vehicle body, and establish a mapping between the entire vehicle and the manipulator coordinate system according to the global coordinate system of the entire vehicle.

[0100] In one embodiment of the present application, the processing module 102 is further used to perform clustering processing on the point cloud data of the upper and lower end faces of the hinge hole; perform plane segmentation on the clustered point cloud data to obtain point cloud data of the target range; traverse the point cloud data of the target range, determine the target neighbor point cloud based on the threshold of the number of neighbor point clouds of each point cloud, and extract the contour edges of the upper and lower end faces of the hinge hole based on the target neighbor point cloud.

[0101] In one embodiment of the present application, the processing module 102 is further used to set a Z-axis coordinate threshold perpendicular to the direction of the three-dimensional scanning device; and cluster the point cloud data of the upper and lower end surfaces of the hinge hole based on the Z-axis coordinate threshold.

[0102] In one embodiment of the present application, the processing module 102 is further used to set an iteration number threshold, a second distance threshold, and a radius threshold for fitting a circle; based on the iteration number threshold, the second distance threshold, and the radius threshold, the point cloud data of the contour edge is iteratively fitted, and the center coordinates of the circle are determined according to the iterative fitting results; and the direction vector of the line connecting the centers of the upper and lower end faces is calculated according to the center coordinates.

[0103] In one embodiment of the present application, the determination module 103 is further used to calculate the average value of the center coordinates and the average value of the axis direction vector in the circle fitting result; and use the average value of the center coordinates and the average value of the axis direction vector as the assembly reference of the hinge hole.

[0104] It should be noted that the aforementioned explanation of the embodiment of the hinge hole assembly reference determination method is also applicable to the hinge hole assembly reference determination device of this embodiment, and will not be repeated here.

[0105] According to the hinge hole assembly reference determination device proposed in the embodiment of the present application, by acquiring the point cloud data of the upper and lower end faces of the hinge hole and extracting the contour edges of the upper and lower end faces of the hinge hole based on clustering processing and plane segmentation technology, it can effectively remove irrelevant data and retain the boundary features of the hinge hole, thereby improving the validity of the data, and performing circle fitting on these contour edges to identify the center coordinates and axial direction vectors of the upper and lower end faces of the hinge hole, making the reference extraction more reliable and accurate, thereby ensuring higher precision during the assembly process.

[0106] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0107] A memory 901 , a processor 902 , and a computer program stored in the memory 901 and executable on the processor 902 .

[0108] When the processor 902 executes the program, the hinge hole assembly reference determination method provided in the above embodiment is implemented.

[0109] Furthermore, the electronic device further includes:

[0110] The communication interface 903 is used for communication between the memory 901 and the processor 902 .

[0111] The memory 901 is used to store computer programs that can be run on the processor 902 .

[0112] The memory 901 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0113] If the memory 901, the processor 902, and the communication interface 903 are implemented independently, the communication interface 903, the memory 901, and the processor 902 can be connected to each other via a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 9 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0114] Optionally, in a specific implementation, if the memory 901, the processor 902 and the communication interface 903 are integrated on a chip, the memory 901, the processor 902 and the communication interface 903 can communicate with each other through an internal interface.

[0115] The processor 902 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0116] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0117] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0118] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing a custom logical function or process step, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed in a different order than shown or discussed, including performing functions in a substantially simultaneous manner or in a reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0119] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, the steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement the method: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array, a field programmable gate array, etc.

[0120] A person skilled in the art may understand that all or part of the steps carried out in the method for implementing the above-mentioned embodiment may be completed by instructing the relevant hardware through a program, and the above-mentioned program may be stored in a computer-readable storage medium, which, when executed, includes one of the steps of the method embodiment or a combination thereof.

[0121] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for determining the assembly reference of a hinge hole, characterized in that: The following steps are involved: Obtain point cloud data of the upper and lower end surfaces of the hinge hole; Based on clustering processing and plane segmentation of the point cloud data of the upper and lower end surfaces of the hinge hole, the contour edges of the upper and lower end surfaces of the hinge hole are extracted, and circle fitting is performed on the point cloud data of the contour edges; The center coordinates and axis direction vectors of the upper and lower end surfaces of the hinge hole are identified in the circle fitting result, and the assembly reference of the hinge hole is determined according to the center coordinates and axis direction vectors.

2. The hinge hole assembly reference determination method according to claim 1, characterized in that: The step of obtaining point cloud data of the upper and lower end surfaces of the hinge hole includes: Start the three-dimensional scanning device installed at the end of the robot; The three-dimensional scanning device is used to collect point cloud data of the upper and lower end surfaces of the hinge hole respectively above and below the hinge hole.

3. The hinge hole assembly reference determination method according to claim 2, characterized in that: Before starting the 3D scanning device installed at the end of the robot, it also includes: Calibrate the manipulator and end effector to obtain a conversion relationship between the manipulator's internal coordinate system and the end effector's coordinate system, calibrate a three-dimensional scanning device mounted on the end effector of the manipulator, and establish a mapping relationship between the three-dimensional scanning device and the manipulator's internal coordinate system based on the conversion relationship; The global coordinate system of the vehicle is established by the calibration points on the vehicle body and the mapping relationship, and the mapping between the vehicle and the manipulator coordinate system is established based on the global coordinate system of the vehicle.

4. The hinge hole assembly reference determination method according to claim 1, characterized in that: The step of extracting the contour edges of the upper and lower end surfaces of the hinge hole based on clustering processing and plane segmentation of the point cloud data of the upper and lower end surfaces of the hinge hole comprises: performing clustering processing on the point cloud data of the upper and lower end surfaces of the hinge hole; Perform plane segmentation on the point cloud data after clustering to obtain point cloud data within the target range; The point cloud data of the target range is traversed, a target neighbor point cloud is determined based on a threshold value of the number of neighbor point clouds of each point cloud, and contour edges of the upper and lower end surfaces of the hinge hole are extracted based on the target neighbor point cloud.

5. The hinge hole assembly reference determination method according to claim 4, characterized in that: The clustering process of the point cloud data of the upper and lower end surfaces of the hinge hole includes: Set the Z-axis coordinate threshold vertical to the 3D scanning device direction; The point cloud data of the upper and lower end surfaces of the hinge hole are clustered based on the Z-axis coordinate threshold.

6. The hinge hole assembly reference determination method according to claim 4, characterized in that: The step of performing plane segmentation on the clustered point cloud data to obtain point cloud data within a target range includes: Perform plane fitting on the point cloud data after clustering; A first distance threshold of the fitting plane is set, and point cloud data within the first distance threshold is filtered out from the fitting plane.

7. The hinge hole assembly reference determination method according to claim 1, characterized in that: The performing circle fitting on the point cloud data of the contour edge includes: Set the iteration number threshold, second distance threshold and radius threshold of the fitted circle; performing iterative fitting on the point cloud data of the contour edge based on the iteration number threshold, the second distance threshold, and the radius threshold, and determining the coordinates of the circle center according to the iterative fitting result; The direction vector of the line connecting the centers of the upper and lower end faces is calculated according to the center coordinates.

8. The hinge hole assembly reference determination method according to claim 1, characterized in that: Determining the assembly reference of the hinge hole according to the center coordinates and the axis direction vector includes: Calculating the average value of the circle center coordinates and the average value of the axis direction vector in the circle fitting result; The average value of the circle center coordinates and the average value of the axis direction vector are used as the assembly reference of the hinge hole.

9. A hinge hole assembly reference determination device, characterized in that: include: An acquisition module is used to obtain point cloud data of the upper and lower end surfaces of the hinge hole; a processing module, configured to extract the contour edges of the upper and lower end surfaces of the hinge hole based on clustering processing and plane segmentation of the point cloud data of the upper and lower end surfaces of the hinge hole, and perform circle fitting on the point cloud data of the contour edges; The determination module is used to identify the center coordinates and axis direction vectors of the upper and lower end surfaces of the hinge hole in the circle fitting result, and determine the assembly reference of the hinge hole according to the center coordinates and axis direction vector.

10. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the hinge hole assembly reference determination method according to any one of claims 1 to 8.

Images