Personalized plate self-adaptive robot grinding method and system and electronic equipment

Abstract

The invention provides a personalized plate self-adaptive robot grinding method and system and electronic equipment. The personalized plate self-adaptive robot grinding method comprises the steps that a plate model is obtained; the point cloud of the to-be-polished plate is matched with the point cloud of the plate model, the pose of the to-be-polished plate is determined, and a polishing machining track is generated; and sending the polishing processing track to the robot. According to the invention, the manual operation cost can be reduced. According to the method, the point cloud of the to-be-polished plate is matched with the point cloud of the plate model, self-adaptive adjustment of the polishing machining track is achieved, then the polishing machining track is sent to the robot, and manual operation of operators is not needed.

Description

Technical Field

[0001] The present invention relates to the technical field of plate polishing, and in particular to a method, system and electronic equipment for polishing personalized plates using an adaptive robot. Background Art

[0002] In modern manufacturing, the surface processing quality of the board has a significant impact on the product's appearance, service life, and subsequent processing (such as spraying, bonding, etc.). Grinding, as a key process for board surface treatment, directly affects the flatness and smoothness of the board. Currently, common grinding methods in industrial production mainly include traditional mechanical grinding, robot grinding, CNC grinding, and laser scanning-assisted grinding. Although these technologies have been widely used, there are still many limitations in personalized board processing scenarios, making it difficult to meet the needs of high-precision and adaptive grinding.

[0003] Robotic polishing technology. In recent years, with the development of industrial automation technology, polishing systems based on robot control have been applied in the sheet metal processing industry. Such systems usually combine force control sensors and preset trajectories to enable robots to perform automated polishing tasks. Its main advantage is to reduce manual intervention and improve processing consistency. However, this technology still faces the following problems: dependence on preset trajectories and insufficient adaptability: Traditional robotic polishing relies on CAD / CAM preset trajectories, cannot perceive and adjust the polishing path in real time, and has difficulty in handling local minor defects in the sheet metal. Limited level of intelligence: Although force control sensors can adjust the polishing pressure, they lack accurate perception of the surface morphology of the sheet metal, making it difficult to achieve true adaptive polishing. Difficulty in efficiently processing non-standard sheets: For personalized sheets with complex shapes and irregular sizes, the existing robotic polishing system requires additional modeling, a long debugging cycle, and poor adaptability.

[0004] CNC grinding. CNC equipment is capable of performing high-precision CNC grinding. Some companies use laser scanning technology or contact probes to obtain three-dimensional information of the plate surface, and then perform precise grinding based on the modeling data. Although this method has high precision, it still has the following limitations: Expensive equipment and limited application: High-precision CNC equipment is expensive and complex to maintain, making it difficult to promote to small and medium-sized enterprises. Low processing efficiency: CNC systems usually take high precision as their main goal, and the processing speed is relatively slow, making it difficult to meet the needs of high-efficiency production. Lack of adaptive adjustment capabilities: Most CNC grinding solutions rely on preset parameters and cannot be adjusted in real time according to the individual characteristics of the plate, resulting in poor adaptability.

[0005] In summary, the existing plate grinding technology mainly has the following problems:

[0006] Lack of high-precision adaptive capabilities: Most current grinding systems rely on preset trajectories or fixed processing parameters, which makes it difficult to make intelligent adjustments based on the actual surface characteristics of the plate, resulting in limited processing accuracy.

[0007] Personalized processing is difficult: For non-standard plates (such as bent plates, special-shaped plates, etc.), existing technologies require additional modeling or manual intervention, making it difficult to achieve efficient personalized production.

[0008] Insufficient automation and intelligence: Existing robot grinding and CNC systems mainly rely on pre-programming, lack real-time perception and adaptive optimization capabilities, and cannot flexibly respond to subtle changes in the surface of the board.

[0009] Serious environmental pollution problem: Traditional grinding methods easily generate a large amount of dust, posing a threat to the health of operators and the production environment, and it is difficult to meet environmentally friendly production requirements. Summary of the Invention

[0010] In order to overcome the above technical defects, the present invention provides a method, system and electronic equipment for adaptive robot polishing of personalized plates, which can reduce manual operation costs.

[0011] In order to solve the above problems, the present invention is implemented according to the following technical solutions:

[0012] A method for adaptively grinding personalized plates with a robot, comprising the following steps:

[0013] Get the panel model;

[0014] Match the point cloud of the plate to be polished with the point cloud of the plate model to determine the pose of the plate to be polished and generate the polishing trajectory;

[0015] Send grinding trajectory to the robot.

[0016] As a further improvement of the present invention, the step of matching the point cloud of the plate to be polished with the point cloud of the plate model to determine the posture of the plate to be polished to generate a polishing trajectory includes:

[0017] Generate plate model point cloud based on plate model;

[0018] Obtain the point cloud of the plate to be polished through the camera;

[0019] Match the point cloud of the plate model with the point cloud of the plate to be polished to obtain the translation vector and rotation vector;

[0020] The position of the plate to be polished is obtained based on the translation vector and rotation vector, and the polishing trajectory is generated.

[0021] As a further improvement of the present invention, the step of matching the plate model point cloud with the plate point cloud to be polished includes:

[0022] The point cloud of the plate model is used as the source point cloud, and the point cloud of the plate to be polished is used as the target point cloud;

[0023] Iteratively align the source point cloud to the position of the target point cloud;

[0024] Use the point cloud alignment function to perform registration and store the registration results;

[0025] Output the registration result;

[0026] Extract translation vector and rotation vector from the registration result.

[0027] As a further improvement of the present invention, in the step of continuously iteratively aligning the source point cloud to the position of the target point cloud, if the transformation amount between two consecutive iterations is less than the convergence threshold, it is determined to be converged; if the error is less than the mean square error threshold, the iteration is terminated; if it is converged within the maximum number of iterations, the iteration is forcibly stopped.

[0028] As a further improvement of the present invention, the registration result includes: whether the registration converges, the final mean square error score, and the 4×4 pose transformation matrix;

[0029] The step of extracting the translation vector and the rotation vector from the registration result includes:

[0030] Extract the 3×3 sub-matrix in the upper left corner from the 4×4 pose transformation matrix, which represents the rotation part;

[0031] Assign values ​​to the 3×3 submatrix;

[0032] Generate a quaternion object using a 4×4 pose transformation matrix;

[0033] Extract translation and rotation vectors from quaternion objects and 4×4 pose transformation matrices.

[0034] As a further improvement of the present invention, the present invention further comprises the steps of:

[0035] The camera is installed with the eye outside the hand, and the positional relationship between the camera and the robot is calibrated.

[0036] As a further improvement of the present invention, the present invention further comprises the steps of:

[0037] If further processing is required, the process returns to the step of matching the point cloud of the plate to be polished with the point cloud of the plate model.

[0038] The present invention also provides a personalized plate adaptive robot grinding system for implementing the above-mentioned personalized plate adaptive robot grinding method, comprising:

[0039] The underlying 3D engine module is used to obtain the panel model;

[0040] The point cloud analysis and processing module is used to match the point cloud of the plate to be polished with the point cloud of the plate model to determine the posture of the plate to be polished and generate the polishing trajectory;

[0041] The user interaction module is used to send the grinding trajectory to the robot.

[0042] The present invention also provides an electronic device, which includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by the processor to implement the above-mentioned personalized plate adaptive robot polishing method.

[0043] Compared with the prior art, the beneficial effects of the present invention are as follows: by matching the point cloud of the plate to be polished with the point cloud of the plate model, adaptive adjustment of the polishing trajectory is achieved, and then the polishing trajectory is sent to the robot without the need for manual operation by the operator. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of the method for adaptive robot polishing of personalized plates described in Example 1;

[0045] Figure 2 This is another flow chart of the method for adaptive robot polishing of personalized plates described in Example 1;

[0046] Figure 3 This is a schematic diagram of the point cloud of the panel model described in Example 1;

[0047] Figure 4 This is a schematic diagram of the point cloud of the plate to be polished described in Example 1;

[0048] Figure 5 A schematic diagram of the point cloud of the plate model described in Example 1 and the point cloud of the plate to be polished before matching;

[0049] Figure 6 This is a schematic diagram after matching the schematic diagram of the plate model point cloud described in Example 1 and the schematic diagram of the point cloud of the plate to be polished. DETAILED DESCRIPTION

[0050] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0051] Example 1

[0052] This embodiment provides a personalized plate adaptive robot grinding method, such as Figure 1 and Figure 2 As shown, the steps include:

[0053] S1. Set up the polishing environment. First, calibrate the camera using the eye-out-of-hand system. Communicate with the robot and PLC. Import the panel working model to ensure the accuracy of the processing data. Position the panel to be polished, preparing for subsequent processes.

[0054] S2. Match the point cloud of the plate to be polished with the point cloud of the plate model to determine the pose of the plate to be polished and generate the polishing trajectory:

[0055] S21. Generate the plate model point cloud according to the plate model, such as Figure 3 shown.

[0056] S22, obtain the point cloud of the plate to be polished through the camera, such as Figure 4 shown.

[0057] S23, match the point cloud of the plate model with the point cloud of the plate to be polished to obtain the translation vector and rotation vector. The pose of the plate automatically generated by the software is different from the pose taken by the real camera, and it cannot be guaranteed to be consistent every time, such as Figure 5 Therefore, it is necessary to match the generated plate model point cloud with the actual plate point cloud captured by the camera. The specific steps include the following:

[0058] This embodiment performs point cloud registration (alignment) based on the ICP algorithm (Iterative Closest Point) of the PCL library, and converts the transformation matrix obtained by the registration into the representation form (gp_Trsf and gp_Quaternion) in OpenCASCADE for subsequent use in the geometric modeling system.

[0059] Initialize the ICP object: use the panel model point cloud as the source point cloud and the point cloud of the plate to be polished as the target point cloud, and move the panel model point cloud to the position of the real point cloud.

[0060] Specify the source point cloud (Source Cloud) and target point cloud (Target Cloud) for registration: the source point cloud is the object to be transformed and aligned; the target point cloud is the reference object and remains stationary; ICP iteratively aligns the source point cloud to the position of the target point cloud.

[0061] Configuring ICP Parameters: To ensure registration effectiveness and efficiency, several key ICP parameters were configured: The Transformation Epsilon (TE) was set to 1e-10, indicating that the ICP algorithm is considered converged when the transformation between two consecutive iterations is less than this value. A smaller TE value results in stricter convergence, but also increases computational time. The Maximum Correspondence Distance (MAX_CORRECT_DISTANCE) was set to 100 (in millimeters). This means that when establishing point pair matching, points greater than 10 centimeters are not considered a matching pair. This parameter effectively eliminates false matches and improves accuracy. The Euclidean Fitness Epsilon (MEF) was set to 0.001, indicating that iterations are terminated early if the error falls below this value. The Maximum Iterations (MAX_IT) was set to 500, indicating that ICP will execute a maximum of 500 iterations and will terminate if convergence fails within this range.

[0062] Perform point cloud matching: Use the point cloud alignment function icp.align() to perform the registration and store the registration result in a new point cloud Cloud_Final, which is the transformed source point cloud that fits the target point cloud as closely as possible.

[0063] Outputs the registration results: whether the registration converges (Boolean value), the final mean square error score (the smaller the score, the better the fit), and a 4×4 pose transformation matrix, which represents the spatial transformation from the source point cloud to the target point cloud, including rotation and translation.

[0064] Extract translation vector and rotation vector from the registration result.

[0065] The 4×4 pose transformation matrix is ​​in OpenCASCADE format: In order to use the point cloud transformation results in the OpenCASCADE geometry system, the program converts the obtained registration transformation matrix into the following two components: gp_Mat (rotation matrix) extracts the 3×3 sub-matrix in the upper left corner from the 4×4 registration transformation matrix, representing the rotation part; it is assigned according to the OpenCASCADE matrix format gp_Mat. gp_Quaternion (quaternion) uses the rotation matrix just constructed to generate a quaternion object; the quaternion representation can describe the rotation information more concisely and stably. gp_Trsf (complete transformation) Finally, the quaternion and the translation vector and rotation vector (the first three components in the last column) extracted from the transformation matrix are passed into gp_Trsf; gp_Trsf is the standard class in OpenCASCADE for describing rigid body transformations (rotation + translation).

[0066] Through the above steps, the pose difference between the source point cloud and the target point cloud is obtained.

[0067] S25. Obtain the position and posture of the plate to be polished based on the translation vector and the rotation vector, and generate a polishing trajectory.

[0068] S3. Send the grinding trajectory to the robot.

[0069] S4. If further processing is required, the process returns to the step of matching the point cloud of the plate to be polished with the point cloud of the plate model.

[0070] In summary, this embodiment has the following beneficial effects: the polishing environment is set up and calibrated using a camera that is outside the hand. By communicating with the robot and PLC, the working model of the plate can be imported to ensure the accuracy of the processing data. The camera obtains the point cloud of the plate to be polished and performs preprocessing (noise removal and smoothing), generates a plate model point cloud based on the plate model, and performs point cloud matching to determine the working posture of the plate, providing accurate information for path planning. Subsequently, the polishing trajectory is adaptively generated and sent to the robot, converted into a program executable by the robot, and the robot automatically performs the polishing operation according to the processing program. Determine whether to continue processing based on the processing results: if necessary, repeat the processing program. If not, end the run.

[0071] This embodiment ensures that the robot can adaptively generate a grinding path according to different plate shapes and sizes, thereby improving the grinding accuracy and efficiency.

[0072] Example 2

[0073] This embodiment provides a personalized plate adaptive robot polishing system, which is used to implement the personalized plate adaptive robot polishing method as in Example 1, including: an underlying three-dimensional engine module, a point cloud analysis and processing module, and a user interaction module, wherein the underlying three-dimensional engine module is used to obtain the plate model; the point cloud analysis and processing module is used to match the point cloud of the plate to be polished with the point cloud of the plate model, determine the posture of the plate to be polished, and generate a polishing processing trajectory; the user interaction module is used to send the polishing processing trajectory to the robot.

[0074] Furthermore, the underlying 3D engine module provides a basic interactive interface for importing and exporting panel models, as well as displaying and manipulating them. Interactive features include a toolbar that provides quick access to common tools such as selection, movement, rotation, and scaling. The menu system includes options for file operations, view control, and settings. Common 3D model file formats are supported, including OBJ, STL, STEP, and IGS.

[0075] The user interaction module adds dedicated interactive buttons to the basic interactive interface for users to operate various functions. An intuitive function area is designed, and commonly used operation buttons (such as import, export, analysis, view switching, etc.) are placed in the appropriate position for users to quickly operate.

[0076] For other implementations of this embodiment, please refer to Example 1, which will not be described in detail here.

[0077] Example 3

[0078] This embodiment provides an electronic device, which includes a processor and a memory. The memory stores at least one instruction, and the at least one instruction is loaded and executed by the processor to implement the personalized plate adaptive robot polishing method of Example 1.

[0079] The processor may be a central processing unit (CPU), 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.

[0080] The memory can be used to store the computer program or module, and the processor implements the various functions of the trajectory planning optimization method by running or executing the computer program or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0081] The above is a detailed introduction to the personalized plate adaptive robot grinding method, system and electronic equipment provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core idea of ​​this application; at the same time, for those skilled in the art, according to the idea of ​​this application, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on this application. The above embodiments are only preferred embodiments cited to fully illustrate the present invention, and the scope of protection of the present invention is not limited thereto. Equivalent substitutions or changes made by those skilled in the art on the basis of the present invention are all within the scope of protection of the present invention.

Claims

1. A personalized plate adaptive robot grinding method, characterized in that: Including steps: Get the panel model; Match the point cloud of the plate to be polished with the point cloud of the plate model to determine the pose of the plate to be polished and generate the polishing trajectory; Send grinding trajectory to the robot.

2. The method for adaptive robot polishing of personalized plates according to claim 1, characterized in that: The step of matching the point cloud of the plate to be polished with the point cloud of the plate model to determine the posture of the plate to be polished to generate a polishing trajectory includes: Generate plate model point cloud based on plate model; Obtain the point cloud of the plate to be polished through the camera; Match the point cloud of the plate model with the point cloud of the plate to be polished to obtain the translation vector and rotation vector; The position of the plate to be polished is obtained based on the translation vector and rotation vector, and the polishing trajectory is generated.

3. The method for adaptive robot polishing of personalized plates according to claim 1, characterized in that: The step of matching the plate model point cloud with the point cloud of the plate to be polished includes: The point cloud of the plate model is used as the source point cloud, and the point cloud of the plate to be polished is used as the target point cloud; Iteratively align the source point cloud to the position of the target point cloud; Use the point cloud alignment function to perform registration and store the registration results; Output the registration result; Extract translation vector and rotation vector from the registration result.

4. The method for adaptive robot polishing of personalized plates according to claim 3, characterized in that: In the step of continuously iteratively aligning the source point cloud to the position of the target point cloud, if the transformation amount between two consecutive iterations is less than the convergence threshold, it is determined to be converged; if the error is less than the mean square error threshold, the iteration is terminated; if convergence is within the maximum number of iterations, the iteration is forcibly stopped.

5. The method for adaptive robot polishing of personalized plates according to claim 4, characterized in that: The registration results include: whether the registration converges, the final mean square error score, and the 4×4 pose transformation matrix; The step of extracting the translation vector and the rotation vector from the registration result includes: Extract the 3×3 sub-matrix in the upper left corner from the 4×4 pose transformation matrix, which represents the rotation part; Assign values ​​to the 3×3 submatrix; Generate a quaternion object using a 4×4 pose transformation matrix; Extract translation and rotation vectors from quaternion objects and 4×4 pose transformation matrices.

6. The method for adaptive robot polishing of personalized plates according to claim 1, characterized in that: Also includes the steps: The camera is installed with the eye outside the hand, and the positional relationship between the camera and the robot is calibrated.

7. The method for adaptive robot polishing of personalized plates according to claim 1, characterized in that: Also includes the steps: If further processing is required, the process returns to the step of matching the point cloud of the plate to be polished with the point cloud of the plate model.

8. A personalized plate adaptive robot grinding system, characterized by: A method for implementing the personalized plate adaptive robot polishing method according to any one of claims 1 to 7, comprising: The underlying 3D engine module is used to obtain the panel model; The point cloud analysis and processing module is used to match the point cloud of the plate to be polished with the point cloud of the plate model to determine the posture of the plate to be polished and generate the polishing trajectory; The user interaction module is used to send the grinding trajectory to the robot.

9. An electronic device, characterized in that: The electronic device includes a processor and a memory, wherein at least one instruction is stored in the memory, and the at least one instruction is loaded and executed by the processor to implement the personalized plate adaptive robot grinding method according to any one of claims 1 to 7.

Images