A workpiece processing trajectory generation method, device, equipment and storage medium

Abstract

The present application discloses a method, device, equipment and storage medium for generating a workpiece machining trajectory, the method comprising: slicing a standard point cloud image of a region to be machined to obtain a plurality of point cloud sub-regions; projecting points in a sample point cloud region calculated from the point cloud sub-regions onto a preset cutting plane to obtain a dimension reduction plane; after meshing the dimension reduction plane, counting the number of projected points in each grid to obtain sample statistical features; calculating the correlation based on the sample statistical features and the template statistical features, and selecting the grid corresponding to the largest correlation to determine the feature grid position; calculating the three-dimensional coordinates of the machining trajectory points on the preset cutting plane based on the feature grid position and the cutting plane equation; filtering and interpolating the three-dimensional coordinates of the machining trajectory points to obtain the workpiece machining trajectory. The present application can solve the technical problem that the trajectory generated by the prior art lacks three-dimensional scene information, so the accuracy and reliability are low, resulting in failure to meet actual production needs.

Description

Technical Field

[0001] The present application relates to the technical field of automated workpiece processing, and in particular to a method, device, equipment and storage medium for generating a workpiece processing trajectory. Background Art

[0002] In the process of automated machining of workpieces, machining trajectories determine machining efficiency. Existing machining trajectory determination methods mainly include manual teaching and image-based trajectory generation. The former has a low degree of automation and must be re-taught for different machining workpieces, and the manual operation accuracy is low. The latter currently mainly extracts two-dimensional machining trajectories based on images, and then completes machining operations based on machining trajectories through hand-eye calibration.

[0003] The current two-dimensional processing trajectory generated based on images lacks the three-dimensional information of the object and cannot solve the needs of automatic extraction, processing and detection of the three-dimensional trajectory of the operating object. In other words, the generated trajectory lacks accuracy and reliability and cannot meet actual production needs. Summary of the invention

[0004] The present application provides a workpiece processing trajectory generation method, device, equipment and storage medium, which are used to solve the technical problem that the trajectory generated by the prior art lacks scene three-dimensional information, so the accuracy and reliability are low, resulting in the inability to meet actual production needs.

[0005] In view of this, the first aspect of the present application provides a method for generating a workpiece machining trajectory, comprising:

[0006] Slice the standard point cloud image of the area to be processed to obtain multiple point cloud sub-areas;

[0007] Projecting points in the sample point cloud region calculated according to the point cloud sub-region onto a preset cutting plane to obtain a dimension reduction plane;

[0008] After meshing the dimension reduction plane, the number of projection points in each mesh is counted to obtain sample statistical features;

[0009] Calculate the correlation according to the sample statistical features and the template statistical features, and select the grid corresponding to the largest correlation to determine the feature grid position;

[0010] Calculate the three-dimensional coordinates of the processing trajectory points on the preset cutting plane based on the characteristic grid position and the cutting plane equation;

[0011] The three-dimensional coordinates of the processing trajectory points are filtered and interpolated to obtain the workpiece processing trajectory.

[0012] Preferably, projecting the points in the sample point cloud region calculated according to the point cloud sub-region onto a preset cutting plane to obtain a dimension reduction plane comprises:

[0013] Calculate the sample point cloud area corresponding to the point cloud sub-area according to the preset transformation matrix;

[0014] After calculating the three-dimensional center point of each of the sample point cloud regions, a straight line fitting is performed in combination with the sample point cloud region and the corresponding neighborhood to obtain a direction vector of the straight line;

[0015] Calculating a preset cutting plane corresponding to the sample point cloud area according to the three-dimensional center point and the direction vector of the straight line to obtain a cutting plane equation;

[0016] Based on the cutting plane equation, the points in the sample point cloud area are projected in parallel onto the preset cutting plane to obtain a dimension reduction plane.

[0017] Preferably, after the dimension reduction plane is gridded, the number of projection points in each grid is counted to obtain sample statistical features, including:

[0018] Performing network division on the dimension reduction plane, and establishing a grid coordinate system based on the three-dimensional center point to obtain the two-dimensional point coordinates of each projection point in the dimension reduction plane;

[0019] Count the number of projection points in each grid and get the sample statistical characteristics.

[0020] Preferably, calculating the correlation according to the sample statistical features and the template statistical features, and selecting a grid corresponding to the largest correlation to determine the feature grid position, includes:

[0021] Configuring the template statistical features of the target trajectory of the area to be processed, and determining the characteristic position of the midpoint of the target trajectory in the template;

[0022] Calculating the correlation between the sample statistical features and the template statistical features;

[0023] Determine the feature grid position of the grid corresponding to the maximum correlation according to the template statistical features.

[0024] A second aspect of the present application provides a workpiece machining trajectory generating device, comprising:

[0025] A slicing and partitioning unit is used to slice the standard point cloud image of the area to be processed to obtain multiple point cloud sub-areas;

[0026] A plane projection unit, used for projecting points in the sample point cloud region calculated according to the point cloud sub-region onto a preset cutting plane to obtain a dimension reduction plane;

[0027] A division and statistics unit is used to divide the dimension reduction plane into grids, count the number of projection points in each grid, and obtain sample statistical features;

[0028] A correlation calculation unit, used for calculating the correlation according to the sample statistical features and the template statistical features, and selecting the grid corresponding to the largest correlation to determine the feature grid position;

[0029] A coordinate calculation unit, used for calculating the three-dimensional coordinates of the processing trajectory points on the preset cutting plane based on the characteristic grid position and the cutting plane equation;

[0030] The trajectory generating unit is used to filter and interpolate the three-dimensional coordinates of the processing trajectory points to obtain the workpiece processing trajectory.

[0031] Preferably, the plane projection unit is specifically used for:

[0032] Calculate the sample point cloud area corresponding to the point cloud sub-area according to the preset transformation matrix;

[0033] After calculating the three-dimensional center point of each of the sample point cloud regions, a straight line fitting is performed in combination with the sample point cloud region and the corresponding neighborhood to obtain a direction vector of the straight line;

[0034] Calculating a preset cutting plane corresponding to the sample point cloud area according to the three-dimensional center point and the direction vector of the straight line to obtain a cutting plane equation;

[0035] Based on the cutting plane equation, the points in the sample point cloud area are projected in parallel onto the preset cutting plane to obtain a dimension reduction plane.

[0036] Preferably, the division statistics unit is specifically used for:

[0037] Performing network division on the dimension reduction plane, and establishing a grid coordinate system based on the three-dimensional center point to obtain the two-dimensional point coordinates of each projection point in the dimension reduction plane;

[0038] Count the number of projection points in each grid and get the sample statistical characteristics.

[0039] Preferably, the related calculation unit is specifically used for:

[0040] Configuring the template statistical features of the target trajectory of the area to be processed, and determining the characteristic position of the midpoint of the target trajectory in the template;

[0041] Calculating the correlation between the sample statistical features and the template statistical features;

[0042] Determine the feature grid position of the grid corresponding to the maximum correlation according to the template statistical features.

[0043] A third aspect of the present application provides a workpiece machining trajectory generation device, the device comprising a processor and a memory;

[0044] The memory is used to store program code and transmit the program code to the processor;

[0045] The processor is used to execute the workpiece processing trajectory generation method described in the first aspect according to the instructions in the program code.

[0046] A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store program codes, and the program codes are used to execute the workpiece processing trajectory generation method described in the first aspect.

[0047] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0048] In the present application, a method for generating a workpiece processing trajectory is provided, comprising: slicing a standard point cloud image of an area to be processed to obtain a plurality of point cloud sub-areas; projecting points in a sample point cloud area calculated based on the point cloud sub-areas onto a preset cutting plane to obtain a dimensionality reduction plane; after gridding the dimensionality reduction plane, counting the number of projected points in each grid to obtain sample statistical features; calculating the correlation based on the sample statistical features and the template statistical features, and selecting the grid corresponding to the largest correlation to determine the feature grid position; calculating the three-dimensional coordinates of the processing trajectory points on the preset cutting plane based on the feature grid position and the cutting plane equation; filtering and interpolating the three-dimensional coordinates of the processing trajectory points to obtain the workpiece processing trajectory.

[0049] The workpiece processing trajectory generation method provided by the present application is based on the analysis and processing of the point cloud image of the area to be processed, so that the trajectory contains three-dimensional scene information and can better reflect the positional relationship of the actual object. In order to improve the efficiency of calculation and analysis, the three-dimensional point cloud is projected onto the cutting plane for calculation; it can ensure the accuracy of the generated trajectory and improve the efficiency of trajectory generation. Therefore, the present application can solve the technical problem that the trajectory generated by the prior art lacks three-dimensional scene information, so the accuracy and reliability are low, resulting in the inability to meet actual production needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 A schematic diagram of a process flow of a method for generating a workpiece machining trajectory provided in an embodiment of the present application;

[0051] Figure 2 A schematic diagram of the structure of a workpiece machining trajectory generating device provided in an embodiment of the present application;

[0052] Figure 3 A schematic diagram of the process of projecting a three-dimensional point cloud onto a two-dimensional cutting plane provided in an embodiment of the present application;

[0053] Figure 4 A schematic diagram of a process for determining a grid position based on sample statistical features and template statistical features provided in an embodiment of the present application;

[0054] Figure 5 A schematic diagram of the three-dimensional coordinates of the processing trajectory points provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0056] For easier understanding, see Figure 1 , an embodiment of a workpiece processing trajectory generation method provided by the present application includes:

[0057] Step 101: Slice the standard point cloud image of the area to be processed to obtain multiple point cloud sub-areas.

[0058] It should be noted that after determining the local area where the processing trajectory is located, a standard point cloud image is generated for this area, and then it is sliced ​​to obtain multiple point cloud sub-areas. Assuming that there are n sub-areas, it can be expressed as R 1 ,R 2 ,......,R n In addition, the standard point cloud image of the slicing process of this embodiment is an offline template image. In order to obtain the processing area in the template image, the approximate processing trajectory T is marked on the standard point cloud image, and then T is converted into the processing area R on the standard image through the expansion technology, and preparation is made for the subsequent acquisition of the two-dimensional statistical features of the three-dimensional subspace through projection.

[0059] Step 102: Project the points in the sample point cloud region calculated according to the point cloud sub-region onto a preset cutting plane to obtain a dimension reduction plane.

[0060] Furthermore, step 102 includes:

[0061] Calculate the sample point cloud area corresponding to the point cloud sub-area according to the preset transformation matrix;

[0062] After calculating the three-dimensional center point of each sample point cloud area, a straight line is fitted based on the sample point cloud area and the corresponding neighborhood to obtain the direction vector of the straight line;

[0063] Calculate the preset cutting plane corresponding to the sample point cloud area according to the direction vector of the three-dimensional center point and the straight line, and obtain the cutting plane equation;

[0064] Based on the cutting plane equation, the points in the sample point cloud area are projected parallel to the preset cutting plane to obtain the dimension reduction plane.

[0065] It should be noted that the feature point matching between the standard point cloud image area and the sample image can obtain the corresponding feature point coordinates {(u 0 ,v 0 ),(u 1 ,v 1 )}, thereby the transformation matrix H between the standard image and the sample image can be calculated, that is, the preset transformation matrix. According to the preset transformation matrix H, the corresponding point cloud sub-region of the point standard image can be converted into the sample point cloud region. The specific calculation process is expressed as:

[0066]

[0067]

[0068] The sample point cloud area R' can be obtained 1 ,R' 2 ,......,R' n ,in,

[0069]

[0070] They are point cloud sub-regions R 1 ,R 2 ,......,R n With the sample point cloud area R' 1 ,R' 2 ,......,R' n The homogeneous form of any point in , (x,y) are the coordinates.

[0071] For each sample point cloud area R' k The three-dimensional center point C of the area can be calculated k ; Combined with the sample point cloud area R' k and its neighborhood R' k-i ...R' k+i , where 1≤ki≤k+i≤n, the corresponding point cloud centroid can fit a spatial straight line, and the direction vector of the straight line is expressed as n k ; According to the three-dimensional center point C k and the direction vector n of the line k The point method can be used to calculate the preset cutting plane P corresponding to the sample point cloud area k The equation of the cutting plane F k(x, y, z) = 0, k = 1, 2,..., n:

[0072]

[0073] F k (x, y, z) = m 1 (xa)+m 2 (yb)+m 3 (zc)=0

[0074] Among them, D k To represent the image area R' k corresponding to all three-dimensional points, FindCenter(·) represents the set of three-dimensional center points, Fit3DLine(·) is the spatial straight line fitting function, S(u,v) represents the spatial point represented by the position (u,v) in the three-channel image; (m 1 ,m 2 ,m 3 ) is the cutting plane P k The normal vector of (a, b, c) is the cutting plane P k Go up a little.

[0075] It should be noted that the data reconstructed by the structured light system is Data = {(x, y, z, g) | (x, y, z, g)} = f(u, v), where (u, v)∈N, N is a rectangular subset of a two-dimensional discrete plane, (x, y, z) represents the coordinates of a spatial point, and g represents the grayscale value. The data is stored in a four-channel image. At this time, (u, v) represents the pixel coordinates of the image, and each pixel has four values, namely x, y, z, and g.

[0076] The sample point cloud area R' k The points in the image are projected parallel to the preset cutting plane P. k On the graph, we can set P as the sample point cloud area R' k For a spatial point in the point cloud, the projection point P' corresponding to P on the preset cutting plane can be calculated based on the cutting plane equation:

[0077]

[0078] Among them, t is the parameter of the straight line equation from the space point to the projection point, P .x , P .y , P .z are the axis components of the spatial point P on the x-axis, y-axis and z-axis respectively, P' .x , P' .y , P' .z are the axis components of the projected point P' on the x-axis, y-axis and z-axis respectively. Each sample point cloud area R' kEach point in can be parallel projected according to the above method to obtain the projection point; each sample point cloud area can achieve dimensionality reduction after projection, that is, the three-dimensional point cloud is transformed into a two-dimensional plane. For the specific projection process, please refer to Figure 3 .

[0079] Step 103: After meshing the dimension reduction plane, count the number of projection points in each mesh to obtain sample statistical features.

[0080] Further, step 103 includes:

[0081] Perform network division on the dimension reduction plane, and establish a grid coordinate system based on the three-dimensional center point to obtain the two-dimensional point coordinates of each projection point in the dimension reduction plane;

[0082] Count the number of projection points in each grid and get the sample statistical characteristics.

[0083] It should be noted that the grid is divided into the projection point area on the dimensionality reduction plane, and then the three-dimensional center point C k The grid coordinate system is constructed as the center, then the projection point in each grid on the dimensionality reduction plane can be given a clear two-dimensional point coordinate; the number of projection points in each grid is counted and used as the sample point cloud area R' k The two-dimensional statistical characteristics of the three-dimensional points are the sample statistical characteristics.

[0084] See also Figure 4 , assuming that the three-dimensional center point C k The grid coordinate system constructed for the center includes the r axis and the c axis, and the vector expression in three-dimensional space is W r , W c ; The two-dimensional coordinates of the projection point in the grid coordinate system are (r 0 ,c 0 ), the sample statistical characteristics obtained by counting the number of projection points are expressed as J k (r,c), specifically:

[0085]

[0086] in, is the vector from the origin of the grid coordinate system to the projection point on the cutting plane, σ r , σ c are the quantization intervals of the r and c axes of the grid coordinate system of the cutting plane, Floor(·) is the floor rounding function, and Rect((r 0 ,c 0 ),(r 0 +σ u ,c 0 +σ v)) represents the rectangular area formed by the lower left corner and the upper right corner, and Count(·) is a function of the number of projection points in the statistical area. Based on the above, we can get the sample point cloud area R' k The two-dimensional statistical characteristics of the three-dimensional points in the sample, namely the sample statistical characteristics J k (r,c).

[0087] Step 104: Calculate the correlation according to the sample statistical features and the template statistical features, and select the grid corresponding to the maximum correlation to determine the feature grid position.

[0088] Furthermore, step 104 includes:

[0089] Configure the template statistical features of the target trajectory of the area to be processed, and determine the characteristic position of the midpoint of the target trajectory in the template;

[0090] Calculate the correlation between the sample statistical features and the template statistical features;

[0091] The characteristic grid position of the grid corresponding to the maximum correlation is determined according to the template statistical features.

[0092] Template statistical features are pre-configured and are idealized templates with clear feature positions of trajectory points. They are mainly used for comparative analysis to determine the position of the grid to which the trajectory points belong in the sample statistical features, i.e., the feature grid position A. k Assuming that the statistical feature of the template is J', the processing trajectory points in the template are expressed as A(r 1 ,c 1 ), the origin of the grid coordinate system of the template statistical feature is expressed as B(r 2 ,c 2 ), sample statistical characteristics J k The origin of the grid coordinate system is expressed as C(r 3 ,c 3 ),So:

[0093]

[0094] Among them, MaxRelevance(J k , J') represents the relationship between the origins of the two grid coordinate systems under maximum correlation They are the vector from the origin of the grid coordinate system in the template statistical feature to the processing trajectory point, and the vector from the origin of the grid coordinate system in the sample statistical feature to the feature point to be found. Select the grid with the maximum correlation, and determine the grid position of the sample based on the specific position of the grid in the template statistical feature, that is, the feature grid position. Figure 4 , where point A is a point in the template coordinate system, and the point in the sample located by the maximum correlation matching method that is most relevant to point A is considered to be the feature point A sought in the sample.k ;Right now Figure 4 Point A and A k They are overlapping, one in the template feature and one in the sample feature.

[0095] Step 105: Calculate the three-dimensional coordinates of the processing trajectory points on the preset cutting plane based on the feature grid position and the cutting plane equation.

[0096] See also Figure 5 , if the three-dimensional coordinates of the machining trajectory points are expressed as W k , then the specific calculation process is:

[0097]

[0098] Among them, σ r , σ c are the quantization intervals of the r and c axes of the grid coordinate system of the cutting plane, respectively; are the components of the vector from the origin of the sample statistical feature grid coordinate system to the feature point to be found on the r and c axes of the grid coordinate system, respectively. They are the three-dimensional coordinates W of the machining trajectory points k Components on the x-axis, y-axis, and z-axis.

[0099] Step 106: Filter and interpolate the three-dimensional coordinates of the processing trajectory points to obtain the workpiece processing trajectory.

[0100] There are multiple processing trajectory points, for example, there are n processing trajectory points, and the three-dimensional coordinates W of the n processing trajectory points are k Filtering and difference processing are performed to form a complete processing trajectory, namely the workpiece processing trajectory. The workpiece processing trajectory generation process in this embodiment not only takes into account the three-dimensional information of the scene, ensures the accuracy and reliability of the trajectory, but also improves the efficiency through the cutting plane analysis method.

[0101] The workpiece processing trajectory generation method provided in the embodiment of the present application is based on the analysis and processing of the point cloud image of the area to be processed, so that the trajectory contains three-dimensional scene information and can better reflect the positional relationship of the actual object. In order to improve the efficiency of calculation and analysis, the three-dimensional point cloud is projected onto the cutting plane for calculation; it can ensure the accuracy of the generated trajectory and improve the efficiency of trajectory generation. Therefore, the embodiment of the present application can solve the technical problem that the trajectory generated by the prior art lacks three-dimensional scene information, so the accuracy and reliability are low, resulting in the inability to meet actual production needs.

[0102] For easier understanding, see Figure 2 The present application provides an embodiment of a workpiece processing trajectory generating device, comprising:

[0103] The slicing and partitioning unit 201 is used to slice the standard point cloud image of the area to be processed to obtain multiple point cloud sub-areas;

[0104] A plane projection unit 202, used to project points in the sample point cloud region calculated according to the point cloud sub-region onto a preset cutting plane to obtain a dimension reduction plane;

[0105] A division and statistics unit 203 is used to divide the dimension reduction plane into grids, count the number of projection points in each grid, and obtain sample statistical features;

[0106] A correlation calculation unit 204 is used to calculate the correlation according to the sample statistical features and the template statistical features, and select the grid corresponding to the maximum correlation to determine the characteristic grid position;

[0107] A coordinate calculation unit 205, used to calculate the three-dimensional coordinates of the processing trajectory points on the preset cutting plane based on the characteristic grid position and the cutting plane equation;

[0108] The trajectory generating unit 206 is used to filter and interpolate the three-dimensional coordinates of the processing trajectory points to obtain the workpiece processing trajectory.

[0109] Further, the plane projection unit 202 is specifically used for:

[0110] Calculate the sample point cloud area corresponding to the point cloud sub-area according to the preset transformation matrix;

[0111] After calculating the three-dimensional center point of each sample point cloud area, a straight line is fitted based on the sample point cloud area and the corresponding neighborhood to obtain the direction vector of the straight line;

[0112] Calculate the preset cutting plane corresponding to the sample point cloud area according to the direction vector of the three-dimensional center point and the straight line, and obtain the cutting plane equation;

[0113] Based on the cutting plane equation, the points in the sample point cloud area are projected parallel to the preset cutting plane to obtain the dimension reduction plane.

[0114] Furthermore, the statistical unit 203 is divided to be specifically used for:

[0115] Perform network division on the dimension reduction plane, and establish a grid coordinate system based on the three-dimensional center point to obtain the two-dimensional point coordinates of each projection point in the dimension reduction plane;

[0116] Count the number of projection points in each grid and get the sample statistical characteristics.

[0117] Furthermore, the relevant calculation unit 204 is specifically configured to:

[0118] Configure the template statistical features of the target trajectory of the area to be processed, and determine the characteristic position of the midpoint of the target trajectory in the template;

[0119] Calculate the correlation between the sample statistical features and the template statistical features;

[0120] The characteristic grid position of the grid corresponding to the maximum correlation is determined according to the template statistical features.

[0121] The present application also provides a workpiece processing trajectory generation device, the device comprising a processor and a memory;

[0122] The memory is used to store the program code and transmit the program code to the processor;

[0123] The processor is used to execute the workpiece processing trajectory generation method in the above method embodiment according to the instructions in the program code.

[0124] The present application also provides a computer-readable storage medium, which is used to store program codes, and the program codes are used to execute the workpiece processing trajectory generation method in the above method embodiment.

[0125] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0126] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0128] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for executing all or part of the steps of the method described in each embodiment of the present application through a computer device (which can be a personal computer, a server, or a network device, etc.). The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (full name in English: Read-Only Memory, English abbreviation: ROM), random access memory (full name in English: Random Access Memory, English abbreviation: RAM), disk or optical disk and other media that can store program codes.

[0129] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for generating a workpiece machining trajectory, characterized in that: include: Slice the standard point cloud image of the area to be processed to obtain multiple point cloud sub-areas; Projecting points in the sample point cloud region calculated according to the point cloud sub-region onto a preset cutting plane to obtain a dimension reduction plane; After meshing the dimension reduction plane, the number of projection points in each mesh is counted to obtain sample statistical features; The correlation is calculated based on the sample statistical features and the template statistical features, and the grid corresponding to the largest correlation is selected to determine the characteristic grid position. The template statistical features are pre-configured and are a template of the characteristic position of an idealized trajectory point, which is used for comparative analysis to determine the position of the grid to which the trajectory point belongs in the sample statistical features, that is, the characteristic grid position. The specific calculation and selection process is as follows: Configuring the template statistical features of the target trajectory of the area to be processed, and determining the characteristic position of the midpoint of the target trajectory in the template; Calculating the correlation between the sample statistical features and the template statistical features; Determine the feature grid position of the grid corresponding to the maximum correlation according to the template statistical features; Calculate the three-dimensional coordinates of the processing trajectory points on the preset cutting plane based on the characteristic grid position and the cutting plane equation; The three-dimensional coordinates of the processing trajectory points are filtered and interpolated to obtain the workpiece processing trajectory.

2. The workpiece machining trajectory generation method according to claim 1, characterized in that: The projecting of points in the sample point cloud region calculated according to the point cloud sub-region onto a preset cutting plane to obtain a dimension reduction plane includes: Calculate the sample point cloud area corresponding to the point cloud sub-area according to the preset transformation matrix; After calculating the three-dimensional center point of each of the sample point cloud regions, a straight line fitting is performed in combination with the sample point cloud region and the corresponding neighborhood to obtain a direction vector of the straight line; Calculating a preset cutting plane corresponding to the sample point cloud area according to the three-dimensional center point and the direction vector of the straight line to obtain a cutting plane equation; Based on the cutting plane equation, the points in the sample point cloud area are projected in parallel onto the preset cutting plane to obtain a dimension reduction plane.

3. The workpiece machining trajectory generation method according to claim 2, characterized in that: After the dimension reduction plane is gridded, the number of projection points in each grid is counted to obtain sample statistical features, including: Performing network division on the dimension reduction plane, and establishing a grid coordinate system based on the three-dimensional center point to obtain the two-dimensional point coordinates of each projection point in the dimension reduction plane; Count the number of projection points in each grid and get the sample statistical characteristics.

4. A workpiece processing trajectory generating device, characterized in that: include: A slicing and partitioning unit is used to slice the standard point cloud image of the area to be processed to obtain multiple point cloud sub-areas; A plane projection unit, used for projecting points in the sample point cloud region calculated according to the point cloud sub-region onto a preset cutting plane to obtain a dimension reduction plane; A division and statistics unit is used to divide the dimension reduction plane into grids, count the number of projection points in each grid, and obtain sample statistical features; A correlation calculation unit is used to calculate the correlation according to the sample statistical features and the template statistical features, and select the grid corresponding to the largest correlation to determine the characteristic grid position. The template statistical feature is pre-configured and is a template of the characteristic position of an idealized trajectory point, which is used for comparative analysis to determine the position of the grid to which the trajectory point belongs in the sample statistical features, that is, the characteristic grid position. The correlation calculation unit is specifically used to: Configuring the template statistical features of the target trajectory of the area to be processed, and determining the characteristic position of the midpoint of the target trajectory in the template; Calculating the correlation between the sample statistical features and the template statistical features; Determine the feature grid position of the grid corresponding to the maximum correlation according to the template statistical features; A coordinate calculation unit, used for calculating the three-dimensional coordinates of the processing trajectory points on the preset cutting plane based on the characteristic grid position and the cutting plane equation; The trajectory generating unit is used to filter and interpolate the three-dimensional coordinates of the processing trajectory points to obtain the workpiece processing trajectory.

5. The workpiece machining trajectory generating device according to claim 4, characterized in that: The plane projection unit is specifically used for: Calculate the sample point cloud area corresponding to the point cloud sub-area according to the preset transformation matrix; After calculating the three-dimensional center point of each of the sample point cloud regions, a straight line fitting is performed in combination with the sample point cloud region and the corresponding neighborhood to obtain a direction vector of the straight line; Calculating a preset cutting plane corresponding to the sample point cloud area according to the three-dimensional center point and the direction vector of the straight line to obtain a cutting plane equation; Based on the cutting plane equation, the points in the sample point cloud area are projected in parallel onto the preset cutting plane to obtain a dimension reduction plane.

6. The workpiece machining trajectory generating device according to claim 5, characterized in that: The division statistics unit is specifically used for: Performing network division on the dimension reduction plane, and establishing a grid coordinate system based on the three-dimensional center point to obtain the two-dimensional point coordinates of each projection point in the dimension reduction plane; Count the number of projection points in each grid and get the sample statistical characteristics.

7. A workpiece processing trajectory generation device, characterized in that: The device comprises a processor and a memory; The memory is used to store program code and transmit the program code to the processor; The processor is used to execute the workpiece processing trajectory generation method described in any one of claims 1 to 3 according to the instructions in the program code.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store program codes, and the program codes are used to execute the workpiece processing trajectory generation method according to any one of claims 1 to 3.

Images