A shoe last glue spraying path automatic generation method based on point cloud data processing

Abstract

The application provides a shoe tree glue spraying path automatic generation method based on point cloud data processing. On the basis of scanning a shoe tree to obtain point cloud data, space motion trajectory point marking and data are obtained after point cloud data preprocessing. Then, an approximate glue spraying attachment space trajectory on the shoe tree is obtained through polynomial interpolation. Then, the orthogonal coordinate system NOA vectors corresponding to the glue spraying attachment space trajectory points on all shoe trees are sequentially solved. The mechanical arm end glue spraying space trajectory after the glue spraying trajectory NOA vector direction is offset by a certain distance is solved. The mechanical arm end pose matrix is obtained according to the orthogonal coordinate system NOA vector and the mechanical arm end glue spraying space trajectory. Finally, the inverse kinematics mathematical model is established according to the robot D-H parameters, and the shoe tree glue spraying motion trajectory is obtained by solving the mechanical arm end pose matrix.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of shoe tree manufacturing, and particularly relates to a shoe tree glue spraying path automatic generation method based on point cloud data processing. BACKGROUND

[0002] Traditional shoemaking process relies heavily on manual operation. Gluing is the most important link in the shoemaking process, which not only involves the quality and production efficiency of shoes, but also has a great negative impact on the health of shoemakers. Therefore, it is urgent to use an intelligent glue spraying technology of an industrial robot to replace the traditional manual gluing process. At present, although the shoemaking industry has an intelligent glue spraying technology of an industrial robot, due to the rapid change of shoe models and the need for manual learning (usually using a teach pendant and manual operation judgment) of the motion trajectory of the intelligent glue spraying of the industrial robot, it is time-consuming and labor-intensive, and it is difficult for workers to get started, which is difficult to meet the development needs of the industry. The traditional visual scheme is difficult to implement, the robot learning speed is slow, and the industrial camera is easy to attach pollutants, affecting the control precision. SUMMARY

[0003] The difficulty of considering the solution to the above problems lies in how to obtain the data of the dynamic curved surface of the shoe tree and keep the end of the mechanical arm and the shoe tree glue spraying trajectory curve always perpendicular and the glue spraying distance unchanged, so it is necessary to integrate the line searching, distance and orthogonal algorithm into one control algorithm, and finally convert it into the motion posture of the end of the mechanical arm, which involves complex pose space transformation.

[0004] Therefore, the purpose of the present application is to provide a shoe tree glue spraying path automatic generation method based on point cloud data processing, which solves the problem of slow learning speed and low efficiency of the shoe tree glue spraying path of the robot in the existing shoemaking glue spraying technology under the background of rapid change of shoe models.

[0005] The main process of the scheme includes: 1. using a three-dimensional scanner to scan the shoe tree to obtain point cloud data; 2. point cloud data preprocessing; 3. space motion trajectory point marking and data export; 4. polynomial interpolation to obtain an approximate shoe tree glue spraying space trajectory; 5. orthogonal coordinate system NOA vector solving of the glue spraying posture; 6. obtaining the mechanical arm end glue spraying space trajectory after the NOA vector direction of the shoe tree glue spraying trajectory is offset by a certain distance; 7. obtaining the mechanical arm end pose matrix; 8. establishing an inverse kinematics mathematical model according to the robot D-H parameters. The present application can quickly realize the generation of different shoe tree glue spraying motion trajectories, solve the problem of low efficiency and poor universality of the traditional scheme which relies on manual operation, and continuously meet the development needs of the industry.

[0006] The technical scheme specifically adopted by the application to solve the technical problems is:

[0007] The application discloses a shoe tree glue spraying path automatic generation method based on point cloud data processing.

[0008] Further, when the point cloud data of the scanned shoe tree is obtained, a fixed base integrated with the shoe tree is scanned together to provide the relative position relationship between the workpiece coordinate system and the robot base coordinate system.

[0009] Further, the point cloud data preprocessing includes cutting off redundant point cloud data, and then based on the relative position between the known shoe tree base and the robot, the workpiece coordinate system and the origin are set on the fixed base, the X-Y plane of the workpiece coordinate system and the robot base coordinate system are parallel, and the origin of the workpiece coordinate system is arranged at the center of the base geometric feature or a position with known parameters.

[0010] Further, in the process of obtaining the approximate glue adhesion space trajectory on the shoe tree through polynomial interpolation, no less than four points are inserted between every two derived mark points, so that the approximate smooth glue adhesion trajectory L1 on the shoe tree is obtained.

[0011] Further, the orthogonal coordinate system NOA vector corresponding to the glue adhesion space trajectory point on all shoe trees is specifically solved. The vector N is obtained by the difference between adjacent points, the solving condition of the vector O is that the vector O is perpendicular to the approximate plane through the corresponding point, and the vector A is solved according to the right-hand rule.

[0012] Further, the mechanical arm end glue spraying space trajectory after the glue spraying trajectory NOA vector direction of the shoe tree is offset by a certain distance is specifically solved. The actual mechanical arm end glue spraying space trajectory L2 is obtained by the vector and the glue adhesion space trajectory on the shoe tree. Wherein, DIS is the offset glue spraying distance.

[0013] Further, the solving and obtaining of the mechanical arm end pose matrix is specifically that the obtained pose and attitude matrix are subjected to homogeneous transformation, and the position matrix of the mechanical arm end is obtained by multiplication, as the input of the inverse kinematics mathematical model of the mechanical arm and the corresponding joint rotation angle is solved.

[0014] Further, the inverse kinematics mathematical model is established according to the robot D-H parameters, and the end tool coordinate system is considered.

[0015] An electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and the processor implements the steps of the shoe last glue spraying path automatic generation method based on point cloud data processing as described above when executing the program.

[0016] A non-transitory computer-readable storage medium has a computer program stored thereon, and the computer program implements the steps of the shoe last glue spraying path automatic generation method based on point cloud data processing as described above when executed by a processor.

[0017] Compared with traditional manual teaching or visual methods, the present application and its preferred schemes have the following advantages: the robot glue spraying path learning is obtained through pre-three-dimensional scanning and theoretical calculation, and the method has the advantages of fast learning speed, low difficulty for workers to start, high cost performance, etc. compared with manual or traditional visual methods, and can greatly shorten the learning period of different shoe spraying path learning, and greatly improve the production capacity and enterprise competitiveness of enterprises. BRIEF DESCRIPTION OF DRAWINGS

[0018] The present application will be further described in detail below in combination with the drawings and specific embodiments:

[0019] Figure 1 is a method flowchart of an embodiment of the present application;

[0020] Figure 2 is a physical object schematic diagram of the feature point attached according to an embodiment of the present application;

[0021] Figure 3 is a schematic diagram of the point cloud before and after preprocessing according to an embodiment of the present application;

[0022] Figure 4 is a schematic diagram of the glue spraying path point marking according to an embodiment of the present application;

[0023] Figure 5 is a polynomial interpolation schematic diagram of the glue spraying path according to the simulation test results of an embodiment of the present application;

[0024] Figure 6 is a vector schematic diagram of the trajectory point set according to the simulation test results of an embodiment of the present application;

[0025] Figure 7 is a schematic diagram of the mechanical arm end glue spraying trajectory according to the simulation test results of an embodiment of the present application;

[0026] Figure 8 ​Fig. 1 is a kinematic control schematic diagram of simulation test results of an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the features and advantages of the present application more apparent, the following detailed description is provided, and the detailed description is as follows:

[0028] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present application. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0029] It should be noted that the terms used herein are only for the purpose of describing specific embodiments, and are not intended to limit the exemplary embodiments according to the present application. As used herein, the singular form is intended to include the plural form unless the context clearly indicates otherwise, and it should also be understood that when the terms "comprise" and / or "include" are used in the specification, there is a presence of the features, steps, operations, devices, components and / or combinations thereof.

[0030] An embodiment of the present application is a shoe last glue spraying path automatic generation method based on point cloud data processing, comprising the following steps:

[0031] Step S1: scanning the shoe last to obtain point cloud data using a three-dimensional scanner;

[0032] Step S2: point cloud data preprocessing;

[0033] Step S3: marking and data exporting of spatial motion trajectory points in point cloud processing software;

[0034] Step S4: obtaining approximate glue spraying attachment spatial trajectories on the shoe last through polynomial interpolation;

[0035] Step S5: solving the vectors corresponding to the glue spraying attachment spatial trajectory points on all shoe lasts;

[0036] Step S6: solving the glue spraying spatial trajectory of the end of the mechanical arm;

[0037] Step S7: solving the end pose matrix of the mechanical arm;

[0038] Step S8: establishing an inverse kinematics mathematical model according to the robot D-H parameters and importing the pose matrix for solving;

[0039] As a preferred scheme of the present embodiment, in step S1, a high-precision feature point visual stitching method is adopted, and feature points need to be attached to the scanned area, and it should be noted that in order to facilitate subsequent coordinate transformation, the fixed base of the shoe last also needs to be scanned.

[0040] As a preferred scheme of the embodiment, in step S2, the point cloud preprocessing can be performed in a reverse engineering software similar to Geomagic studio, and the main operation steps include:

[0041] Step S21: Excess point cloud data is cut off. Too much point cloud data will affect the running speed of the subsequent search algorithm.

[0042] Step S22: Set the X-Y plane of the workpiece coordinate system on the shoe tree fixed base, and make it parallel to the X-Y plane of the robot base coordinate system. At the same time, set the origin of the workpiece coordinate system at the center of the base geometric feature or a position with known parameters.

[0043] As a preferred scheme of the embodiment, in step S3, according to the actual glue spraying process requirements, manually mark the trajectory and export data in the point cloud processing software, and the number of marking points should not be less than 36.

[0044] As a preferred scheme of the embodiment, in step S4, in order to obtain a smoother glue spraying trajectory curve, perform polynomial interpolation processing on the exported data, and insert not less than 4 points between every two exported marking points, and finally obtain the glue adhesion trajectory L1.

[0045] As a preferred scheme of the embodiment, in step S5, after interpolation, the position of each trajectory point O i is the coordinate origin of the i-th point, is the vector of the corresponding point, and further, search for the nearest point B i offset by 1-3 cm in the vertical positive direction (the offset distance and direction can be determined according to the actual situation) in the point cloud data. i then can be obtained according to the condition that it is perpendicular to and . And can be obtained according to the right-hand rule through and . It should be noted that the normal vector obtained by calculation may be opposite in direction, and the direction needs to be unified through the program.

[0046] As a preferred scheme of the embodiment, in step S6, on the premise that the shoe tree glue adhesion trajectory obtained in step S4 and obtained in step S5 are obtained, the movement trajectory of the robot spray head at a certain distance from the shoe tree can be calculated, and the calculation formula is where DIS is the offset glue spraying distance.

[0047] In a preferred embodiment, in step S7, the fourth-order pose matrix of the robotic arm's end effector is obtained from the position matrix obtained in step S6 and the position matrix obtained in step S5. The product of vector matrices after homogeneous transformation.

[0048] As a preferred embodiment, in step S8, mathematical modeling is performed with reference to the robot's DH parameters and end-effector parameters, and then the pose matrix obtained in step S7 is passed to the mathematical model for inverse kinematics solution.

[0049] Reference Figure 1 The following is a specific example of automatically generating shoe last glue spraying paths based on point cloud data processing, including the following steps:

[0050] Step S1: Apply feature points to the shoe last, such as... Figure 2 As shown, the original point cloud data obtained by the 3D scanner is as follows: Figure 3 As shown on the left, the shoe last is fixed to a rectangular thin plate base, which is also scanned. Its significance lies in providing the relative positional relationship between the workpiece coordinate system and the robot base coordinate system.

[0051] Step S2: After the point cloud data obtained in step S1 is processed in the reverse engineering software Geomagic Studio, the resulting point cloud data is as follows: Figure 3 As shown on the right, its coordinate origin is set at the rectangular geometric center of the bottom surface of the fixed base. The XY plane of the point cloud data coincides with the bottom surface of the base, and the Z-axis direction is perpendicular to the bottom surface and upwards.

[0052] Step S3: Mark the spatial motion trajectory points in the software, such as... Figure 4 As shown in Pt1-Pt36; these points need to be marked in sequence according to the actual glue spraying trajectory; workers familiar with the process can mark them, the difficulty of getting started is very low, and no professional knowledge is required; the glue spraying trajectory obtained by this marking is very simple, convenient and efficient, and can effectively replace traditional visual and manual methods.

[0053] Step S4: Obtain the approximate adhesive adhesion spatial trajectory on the shoe last through polynomial interpolation, as shown below. Figure 4 As shown by the red line in the image; the more interpolation points there are, the closer the curve is to the theoretical glue spraying curve; to improve accuracy, the point closest to the interpolation point can be searched in the point cloud and used to replace the interpolation point, but the amount of computation will increase significantly.

[0054] Step S5: Solve for all trajectory points corresponding to Vectors Figure 6 As shown; each The vector corresponds to the robot's motion posture at the corresponding point. To prevent errors in inverse kinematics calculations, it is not converted to RPY posture angles here. This step is to ensure that the robotic arm's glue-spraying actuator remains perpendicular to the glue-spraying area of ​​the shoe last. The specific calculation steps are as follows:

[0055] Step S51: The coordinate systems are mutually perpendicular. Composed of three unit vectors, the vectors can be calculated first.

[0056] For each trajectory point O i Let the origin of the coordinate system be the i-th point. For the corresponding points Vectors, we can obtain Vector N i It is the direction of movement of the robot's end effector;

[0057] Step S52: Further, search for points in all point cloud data that are far from O i The nearest point B after offsetting a fixed distance in the Z direction. i The search distance and direction can be determined based on the actual situation; it is worth noting the vector. and They are not perpendicular to each other, therefore Cannot replace and It can be found and It was then obtained using the right-hand rule;

[0058] Step S53: Further, calculate the vector sum vector Unit vectors that are perpendicular It is worth noting that the vector obtained in the first calculation The direction can be either positive or negative, and all signs need to be uniformly adjusted to be the same, taking a point enclosed in the trajectory as a reference point;

[0059] Step S54: Further, since the vector to be obtained... and Since they are not perpendicular, it is necessary to find the relationship with the vector. and Unit vectors that are perpendicular After obtaining the three vectors, it is necessary to... Perform homogeneous transformations on vector matrices;

[0060] Step S6: Apply adhesive to the track as follows Figure 7 The thin black line in the image, after being offset by a certain distance, shows the spatial trajectory of the adhesive spraying at the end of the robotic arm. Figure 7 The thick black line in the middle; such as Figure 7As shown, different offset distances of the robot end spraying glue movement track can be obtained according to different DIS settings (DIS=5, DIS=10, and DIS=20) under the same coordinate scale. The operation formula is where DIS is the offset spraying glue distance, L1 is the spraying glue attachment track, and finally all the track points (X, Y, Z) in L2 are converted into a four-order position matrix through homogeneous transformation;

[0061] Step S7: The four-order position matrix of the robot end is obtained by multiplying the position matrix obtained in step S6 and the attitude matrix obtained in step S5;

[0062] Step S8: A mathematical model is established according to the robot D-H parameters and the tool coordinate parameters, and then inverse kinematics is solved. There are eight sets of solutions for the six-axis robot, and the correct set of solutions needs to be selected according to the actual conditions. The 6-axis robot motion control simulation of the finally obtained spraying glue path automatic generation method is as shown in Figure 8

[0063] Based on the same inventive concept, the application further provides a computer device, which comprises one or more processors and a memory for storing one or more computer programs; the program comprises program instructions, and the processor is configured to execute the program instructions stored in the memory. The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is configured to implement one or more instructions, and is specifically configured to load and execute one or more instructions in the computer storage medium to implement the above method.

[0064] ​It should be further explained that based on the same inventive concept, the present application also provides a computer storage medium, which stores a computer program, and the computer program is run by a processor to execute the above method. The storage medium can adopt any combination of one or more computer readable media. The computer readable medium can be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may, for example, but is not limited to, an electrical, magnetic, optical, electrical, magnetic, infrared, or semiconductor system, device or component, or any combination of the above. More specific examples (non-exhaustive list) of the computer readable storage medium include: electrical connections with one or more conductive wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present application, the computer readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device or component.

[0065] It should be noted that unless otherwise defined, technical or scientific terms used in the present application should be understood as their ordinary meaning to those skilled in the art to which the present application belongs. The "first", "second" and similar words used in the present application do not represent any order, quantity or importance, but are only used to distinguish different components. "Include" or "contain" and similar words mean that the elements or objects before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connected" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to represent relative positional relationships, and when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0066] The above is only the preferred embodiment of the present application, and does not limit other forms of the present application. Any skilled person in the art can modify or change the above disclosed technical content into equivalent embodiments with equivalent changes. However, any simple modification, equivalent change and modification of the above embodiments made according to the technical essence of the present application without departing from the technical solution content of the present application still belongs to the protection scope of the present application.

[0067] The application is not limited to the above best mode, and anyone can derive other various forms of a shoe last glue spraying path automatic generation method based on point cloud data processing under the inspiration of the application. Any equivalent changes and modifications made in the application scope of the application should be included in the scope of the application.

Claims

1. A shoe last glue spraying path automatic generation method based on point cloud data processing, characterized in that: On the basis of scanning the shoe last to obtain point cloud data, the point cloud data is preprocessed to obtain space motion trajectory point labels and data; the approximate glue spraying attachment space trajectory on the shoe last is obtained through polynomial interpolation; then the orthogonal coordinate system NOA vector corresponding to the glue spraying attachment space trajectory point on all shoe lasts is sequentially solved, the mechanical arm end glue spraying space trajectory after the NOA vector direction of the shoe last glue spraying trajectory is offset by a certain distance is solved, the mechanical arm end pose matrix is solved and obtained according to the orthogonal coordinate system NOA vector and the mechanical arm end glue spraying space trajectory; finally, the inverse kinematics mathematical model is established according to the robot D-H parameter, and the mechanical arm end pose matrix is solved and obtained by bringing the mechanical arm end pose matrix into the inverse kinematics mathematical model to obtain the shoe last glue spraying motion trajectory; When the point cloud data is obtained by scanning the shoe last, a fixed base integrated with the shoe last is scanned together to provide the relative position relationship between the workpiece coordinate system and the robot base coordinate system; The point cloud data preprocessing includes cutting off redundant point cloud data, and then based on the relative position of the known shoe last base and the robot, the workpiece coordinate system and the origin are set on the fixed base, the X-Y plane of the workpiece coordinate system and the robot base coordinate system is parallel, and the origin of the workpiece coordinate system is set at the center of the base geometric feature or the position with known parameters; In the process of obtaining the approximate glue-attaching space trajectory on the shoe tree through polynomial interpolation, no less than 4 points are inserted between every two derived mark points to ensure that the approximate smooth glue-attaching trajectory on the shoe tree is obtained ; The orthogonal coordinate system NOA vector corresponding to the glue spraying attachment space trajectory point on all shoe lasts is specifically: The coordinate system is perpendicular to each other , , Three unit vectors, first find the vector , with each trajectory point being the coordinate origin of the i-th point, being the vector of the corresponding point, we get , the vector N i is the direction of motion of the robot's end. Search for the closest point in all point cloud data The closest point after offsetting a fixed distance in the Z direction , After obtaining and , it is obtained by the right-hand rule; Computing with vectors and vectors unit vectors , the first vector directions are adjusted uniformly with a point enclosed in the trajectory as the reference point, all symbols are the same; Find the vector and Unit vectors that are perpendicular After obtaining the three vectors, Perform homogeneous transformations on vector matrices.

2. The method of claim 1, wherein the method is based on point cloud data processing. The mechanical arm end spraying space trajectory after the shoe tree spraying trajectory NOA vector direction is offset by a certain distance is specifically: through the obtained Vector and shoe tree spraying attachment space trajectory to obtain the actual mechanical arm end spraying space trajectory Wherein DIS is the offset spraying distance.

3. The method of claim 1, wherein the method is based on point cloud data processing. The solving and obtaining of the mechanical arm end pose matrix is specifically that the obtained pose and attitude matrix are subjected to homogeneous transformation, and the position matrix of the mechanical arm end is obtained by multiplication, which is input into the inverse kinematics mathematical model of the mechanical arm and the corresponding joint rotation angle is solved.

4. The method of claim 1, wherein the method is based on point cloud data processing. The inverse kinematics mathematical model established according to the robot D-H parameter considers the end tool coordinate system.

5. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the program to realize the steps of the shoe last glue spraying path automatic generation method based on point cloud data processing according to any one of claims 1-4.

6. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the steps of the shoe last glue spraying path automatic generation method based on point cloud data processing according to any one of claims 1-4.

Images