Robot tapping method and device

Abstract

The present invention provides a robot tapping method and device, the method comprising: acquiring an image of a workpiece plate, obtaining the coordinates of the center of a circular hole on the workpiece plate according to the image of the workpiece plate; dividing the image of the workpiece plate into N areas according to the coordinates of the center of the circular hole and a preset value, N being a positive integer greater than 1; using a two-dimensional hand-eye calibration method and the divided areas, the robot drives the camera to find multiple holes in the area to take pictures, and each picture-taking process is a single-hole calibration process. The robot tapping method and device of the present application can adapt to the rapid model switching of products with a small number and a large variety. Moreover, the present application improves production efficiency, reduces labor costs, and improves product quality.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent processing, and in particular, relates to a robot tapping method and device. Background Art

[0002] The existing equipment is to manually use flexible tapping machines or hand drills to tap tens of thousands of holes on aluminum plates, which has low production efficiency and is difficult for workers to process. With the continuous increase in production tasks, the continuous increase in staff costs, and the increasingly stringent quality requirements of customers for production, we must upgrade the existing equipment or processing methods to achieve the purpose of improving production efficiency, reducing labor costs, improving product quality, and increasing profits. Summary of the invention

[0003] The embodiments of the present application provide a robot tapping method and device, which improves production efficiency, reduces labor costs, improves product quality, and increases profit and revenue.

[0004] In a first aspect, an embodiment of the present application provides a robot tapping method, comprising:

[0005] Acquire an image of the workpiece plate, and obtain the center coordinates of the circular hole on the workpiece plate according to the image of the workpiece plate;

[0006] The image of the workpiece plate is divided into N regions according to the coordinates of the center of the circular hole and a preset value, where N is a positive integer greater than 1;

[0007] Using the two-dimensional hand-eye calibration method and the divided area, the robot drives the camera to find multiple holes in the area to take pictures. Each photo-taking process is the single-hole calibration process.

[0008] Among them, it also includes:

[0009] Given multiple first coordinates on the drawing, walk in the robot coordinate system or obtain the corresponding multiple second coordinates through visual recognition, and obtain the affine transformation homogeneous matrix by finding the relationship between the first coordinate and the second coordinate;

[0010] According to the affine transformation homogeneous matrix, the actual coordinates of the workpiece plate are converted into the coordinates of the robot coordinate system.

[0011] Among them, the two-dimensional hand-eye calibration method is a 9-point calibration method. The robot drives the camera to find 9 holes in the area to take pictures.

[0012] The drawings are two-dimensional electronic drawings or three-dimensional electronic drawings.

[0013] Here, an image of the workpiece plate is acquired by a camera.

[0014] In a second aspect, the present application provides a robot tapping device, comprising:

[0015] An acquisition unit, used for acquiring an image of the workpiece plate, and obtaining the center coordinates of the circular hole on the workpiece plate according to the image of the workpiece plate;

[0016] A segmentation unit, used for segmenting the image of the workpiece plate into N regions according to the coordinates of the center of the circular hole and a preset value, where N is a positive integer greater than 1;

[0017] The calibration unit is used to use the two-dimensional hand-eye calibration method and the divided area. The robot drives the camera to find multiple holes in the area to take pictures. Each photo-taking process is a single-hole calibration process.

[0018] It also includes the conversion unit:

[0019] Given multiple first coordinates on the drawing, walk in the robot coordinate system or obtain the corresponding multiple second coordinates through visual recognition, and obtain the affine transformation homogeneous matrix by finding the relationship between the first coordinate and the second coordinate;

[0020] According to the affine transformation homogeneous matrix, the actual coordinates of the workpiece plate are converted into the coordinates of the robot coordinate system.

[0021] Among them, the two-dimensional hand-eye calibration method is a 9-point calibration method, and the calibration unit is used for the robot to drive the camera to find 9 holes in the area to take pictures.

[0022] In a third aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above methods when executed by a processor.

[0023] In a fourth aspect, an embodiment of the present application provides a robot system, comprising any one of the above-mentioned robot tapping devices.

[0024] The robot tapping method and device of the present application embodiment have the following beneficial effects:

[0025] The robot tapping method of the present application includes: acquiring an image of the workpiece plate, and obtaining the coordinates of the center of the circular hole on the workpiece plate according to the image of the workpiece plate; dividing the image of the workpiece plate into N areas according to the coordinates of the center of the circular hole and a preset value, where N is a positive integer greater than 1; using a two-dimensional hand-eye calibration method and the divided areas, the robot drives the camera to find multiple holes in the area to take pictures, and each picture-taking process is a single-hole calibration process. The robot tapping method and device of the present application can adapt to the rapid model switching of products with a small number and a large variety. In addition, the present application improves production efficiency, reduces labor costs, and improves product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1This is a schematic diagram of the process flow of the robot tapping method according to an embodiment of the present application;

[0027] Figure 2 This is a schematic diagram of the structure of the robot tapping device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] The present application is further described below in conjunction with the accompanying drawings and embodiments.

[0029] In the following introduction, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance. The following introduction provides multiple embodiments of the present invention, and different embodiments can be replaced or combined, so this application can also be considered to include all possible combinations of the same and / or different embodiments recorded. Therefore, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then this application should also be considered to include embodiments containing one or more of all other possible combinations of A, B, C, and D, even though the embodiment may not be clearly recorded in the following text.

[0030] The following description provides examples and does not limit the scope, applicability or examples set forth in the claims. Changes may be made to the functions and arrangements of the elements described without departing from the scope of the present application. Various processes or components may be appropriately omitted, substituted or added to each example. For example, the described method may be performed in an order different from the order described, and various steps may be added, omitted or combined. In addition, features described in some examples may be combined in other examples.

[0031] The existing equipment is to manually use flexible tapping machines or hand drills to tap tens of thousands of holes on aluminum plates, which has low production efficiency and is difficult for workers to process. With the continuous increase in production tasks, the continuous increase in staff costs, and the increasingly stringent quality requirements of customers for production, we must upgrade the existing equipment or processing methods to achieve the purpose of improving production efficiency, reducing labor costs, improving product quality, and increasing profits.

[0032] It is imperative to change the production mode after market research and investigation.

[0033] Option 1: Currently, CNC tapping machines are the most commonly used in the market. Advantages of CNC tapping machines: 1. High precision. 2. Fast response. 3. Low speed and high power. 4. Good stability. Disadvantages of CNC tapping machines: 1. The standard model of CNC tapping machines is up to 3 meters (m) M, but the maximum size of the workpiece produced is 9.3mX3.4m. Aluminum plates cannot be adsorbed by magnets, and the clamping is difficult. 2. CNC tapping machines do not have torque protection function, and the taps are easy to break.

[0034] Option 2: Based on the existing workpiece size and processing requirements, the robot automatic tapping system is independently developed. Advantages: 1. The torque protection function is optimized to protect the tap and reduce the chance of tap breakage. 2. The robot has high repetition accuracy, fast response speed, high stability, and strong versatility, and has all the advantages of a CNC tapping machine. 3. The high level of automation is reflected in its unique benign structure and flexible control method, which reduces the operator's workload and has unparalleled advantages over traditional industries.

[0035] The tapping power head of the robot automatic tapping system includes a spindle motor, a lifting synchronous motor, a purge device, a liquid spray device, an intelligent camera, a tapping servo screw mechanism, and a feed synchronous servo screw mechanism. Operation principle: 1. The spindle motor drives the lower tap to tap. During the tapping process, the real-time monitoring of torque ensures that the tap does not run over torque and simulates the human tapping process. 2. During the spindle tapping process, the lifting synchronous motor drives the mechanism to synchronize the spindle lifting. 3. The liquid spray device sprays lubricating fluid during tapping. 4. The purge device blows away the wire scraps after the tapping is completed.

[0036] The UI (User Interface) of the robot automatic tapping system realizes a simple, natural, friendly and consistent technological interactive design. The host computer operating system accurately collects and monitors the processing data in real time, as well as traceable storage and processing of fault processing data.

[0037] like Figure 1 As shown, the robot tapping method of the present application includes: S101, acquiring an image of a workpiece plate, and obtaining the center coordinates of a circular hole on the workpiece plate according to the image of the workpiece plate; S103, dividing the image of the workpiece plate into N areas according to the center coordinates of the circular hole and a preset value, where N is a positive integer greater than 1; S105, utilizing a two-dimensional hand-eye calibration method and the divided areas, the robot drives the camera to find multiple holes in the area to take pictures, and each picture-taking process is a single-hole calibration process.

[0038] The image of the workpiece plate is obtained by the intelligent camera on the robot. There are multiple circular holes on the workpiece plate, which are holes to be tapped. By analyzing the image of the workpiece plate, the circular holes on the workpiece plate image and the coordinates of the center of the circular holes are determined. The image of the workpiece plate is divided into N areas according to the coordinates of the center of the circular holes and the preset value. The preset value can be set as needed. By dividing the image into N areas, more accurate positioning can be achieved. Because the robot arm has errors, the longer it walks, the greater the error. After dividing the image of the workpiece plate into N small areas, the robot arm's travel distance becomes shorter, the error becomes smaller, and the positioning is more accurate.

[0039] The 2D hand-eye calibration method is a 9-point calibration method. The robot drives the camera to find 9 holes in the area to take pictures. The so-called 2D means that the working plane is limited to one plane. In actual control, after the camera detects the pixel position of the target in the image, it transforms the pixel coordinates of the camera into the spatial coordinate system of the manipulator through the calibrated coordinate transformation matrix, and then calculates how each motor should move according to the manipulator coordinate system, so as to control the manipulator to reach the specified position.

[0040] The 4-point method, 9-point method, and N-point method can all link image coordinates with robot coordinates. Taking into account factors such as debugging difficulty and calibration accuracy, the 9-point method is the most widely used 2D hand-eye calibration in industry, and is often used in industrial application scenarios such as grabbing objects from a fixed plane for assembly.

[0041] The camera knows pixel coordinates, and the robot knows spatial coordinates, so the hand-eye calibration is to obtain the coordinate transformation relationship between the pixel coordinate system and the spatial robot coordinate system. The nine-point calibration directly establishes the coordinate transformation relationship between the camera and the robot. Let the end of the robot walk to these nine points to obtain the coordinates in the robot coordinate system, and at the same time use the camera to identify the nine points to obtain pixel coordinates. In this way, nine sets of corresponding coordinates are obtained.

[0042] The camera is fixed in one place, and then takes pictures to find the target, and controls the robot to grab it. This is called eye-to-hand. Another case is that the camera is fixed on the robot. The calibration process in this case is actually the same as the calibration method of the camera and robot separated, because when the camera takes pictures, the robot will move to the position when the camera is calibrated, and then the camera takes pictures to get the coordinates of the target, and then controls the robot. The calibration process can be treated the same as the calibration of the hand-eye separation system, which is also called eye-in-hand.

[0043] In some embodiments, the robot tapping method of the present application further includes: knowing a plurality of first coordinates on the drawing, walking in the robot coordinate system or obtaining a plurality of corresponding second coordinates through visual recognition, obtaining an affine transformation homogeneous matrix by finding the relationship between the first coordinates and the second coordinates; and converting the actual coordinates of the workpiece plate into the coordinates of the robot coordinate system according to the affine transformation homogeneous matrix. The drawing is, for example, a two-dimensional electronic drawing or a three-dimensional electronic drawing.

[0044] The process of transforming a rectangle into another rectangle is called affine transformation. The whole process can be carried out in the following three steps: moving the rectangle to the origin, scaling the rectangle to the target size, and moving the rectangle to the target position. Affine transformation is actually the superposition of two other simple transformations: one is linear transformation and the other is translation transformation. A transformation that unifies translation transformation and linear transformation is called "affine transformation". This new transformation is no longer a simple mapping between two linear spaces, but has become a mapping relationship between two affine spaces.

[0045] 4*4 matrix is ​​also generally called homogeneous matrix, which has two main functions: describing translation transformation and describing perspective projection transformation. 3*3 matrix can be used to rotate and scale coordinate system, but it cannot move coordinate system. It needs to shear in 4D space to realize 3D translation (it is easier to understand that 2D translation is realized in 3D space), while 4*4 translation matrix will not affect the rotation and scaling functions, so 4*4 matrix can include the functions of rotating, scaling and translating coordinate system. The w component in 4D vector can "switch" the translation part of 4*4 matrix. Some vectors represent position and should be translated, and some vectors represent direction (such as surface normal vector). In geometric sense, the first type of data is regarded as point and the second type as vector. Homogeneous coordinates are essentially 4D vectors (x, y, z, w). The three-dimensional space at w=1 is defined as a standard 3D space. Any homogeneous coordinate converted to a standard 3D space coordinate point is (x / w, y / w, z / w). If w is 0, (x, y, z, 0) represents the direction of the standard 3D space (x, y, z) rather than the coordinate point.

[0046] The principle of precise positioning of the workpiece plate: refer to the calibration process of the intelligent camera and the manipulator, that is, the coordinate conversion process of the camera's pixel coordinates and the robot's coordinates, to achieve precise positioning of the camera-guided manipulator (single-hole calibration). The workpiece coordinates are read, the entire graphic area is analyzed according to the coordinates of the center of the circle, and the entire graphic is divided into N small areas according to the set value. Given some points (X, Y) in the A coordinate system (such as the drawing coordinates), walk or visually recognize (X', Y') in the B coordinate system (such as the robot coordinate system), and then obtain the affine transformation homogeneous matrix by calculating the relationship from (X, Y) to (X', Y'). Using the 9-point calibration method and the divided area, the robot drives the camera to find 9 holes in the small area to take pictures. Each picture-taking process is the process of single-hole calibration, and finally the actual coordinates of the workpiece are converted into the coordinates of the robot coordinate system.

[0047] The above is the automatic calibration process and principle of the workpiece plate. The calibration process does not require human intervention. In the past, it was necessary to take photos for correction each time, but now it only needs to take 9 photos for each area, which greatly shortens the cycle of hole identification. The above steps corrected the defects of the robot in absolute positioning walking, and the absolute positioning accuracy can reach ±0.2mm.

[0048] The robot tapping method of the present application can adapt to the rapid model switching of products with small quantities and many varieties. The robot tapping method of the present application improves production efficiency, reduces labor costs, improves product quality, and increases profit and revenue.

[0049] like Figure 2 As shown, the robot tapping device of the present application includes: an acquisition unit 201, used to acquire the image of the workpiece plate, and obtain the center coordinates of the circular hole on the workpiece plate according to the image of the workpiece plate; a segmentation unit 202, used to segment the image of the workpiece plate into N areas according to the center coordinates of the circular hole and a preset value, N is a positive integer greater than 1; a calibration unit 203, used to use a two-dimensional hand-eye calibration method and the divided areas, and the robot drives the camera to find multiple holes in the area to take pictures, and each picture-taking process is a single-hole calibration process.

[0050] It also includes a conversion unit: given multiple first coordinates on the drawing, the corresponding multiple second coordinates are obtained by walking in the robot coordinate system or through visual recognition, and the affine transformation homogeneous matrix is ​​obtained by calculating the relationship between the first coordinates and the second coordinates; according to the affine transformation homogeneous matrix, the actual coordinates of the workpiece plate are converted into the coordinates of the robot coordinate system.

[0051] Among them, the two-dimensional hand-eye calibration method is a 9-point calibration method, and the calibration unit is used for the robot to drive the camera to find 9 holes in the area to take pictures.

[0052] In the present application, the embodiment of the robot tapping device is basically similar to the embodiment of the robot tapping method. For relevant details, please refer to the introduction of the embodiment of the robot tapping method.

[0053] This application also includes graphic visualization operations. Graphics with file attributes in *.step and *.dxf formats can be loaded, and 3D and 2D graphics can be loaded. Double-click a plane in the graphic to automatically index the hole coordinate data on the plane. Between two planes, the robot's process path can be automatically planned. Basic graphics rotation, translation and other operations.

[0054] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present invention can be implemented with the help of software and / or hardware. "Unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, FPGA (Field-Programmable Gate Array), IC (Integrated Circuit), etc.

[0055] The embodiment of the present invention also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, the steps of the above-mentioned robot tapping method are implemented. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), or any type of medium or device suitable for storing instructions and / or data.

[0056] The present application also provides a robot system, which includes any one of the above-mentioned robot tapping devices.

[0057] 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. 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 can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components 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.

[0058] In the embodiments of the present invention, all functional units may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0059] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A robot tapping method, characterized in that: include: Acquire an image of the workpiece plate, and obtain the center coordinates of the circular hole on the workpiece plate according to the image of the workpiece plate; The image of the workpiece plate is divided into N regions according to the coordinates of the center of the circular hole and a preset value, where N is a positive integer greater than 1; Using the 2D hand-eye calibration method and the divided area, the robot drives the camera to find multiple holes in the area to take pictures. Each picture-taking process is the single-hole calibration process. The 2D hand-eye calibration method is a 9-point calibration method. The robot drives the camera to find 9 holes in the area to take pictures. Drawing on the calibration process of the smart camera and the manipulator, that is, the coordinate conversion process of the camera's pixel coordinates and the robot's coordinates, the camera guides the manipulator to accurately position. Also includes: Given multiple first coordinates on the drawing, walk in the robot coordinate system or obtain the corresponding multiple second coordinates through visual recognition, and obtain the affine transformation homogeneous matrix by finding the relationship between the first coordinate and the second coordinate; According to the affine transformation homogeneous matrix, the actual coordinates of the workpiece plate are converted into the coordinates of the robot coordinate system.

2. The robot tapping method according to claim 1, characterized in that: The drawing is a two-dimensional electronic drawing or a three-dimensional electronic drawing.

3. The robot tapping method according to any one of claims 1-2, characterized in that: The image of the workpiece plate is acquired by the camera.

4. A robot tapping device, characterized in that: include: An acquisition unit, used for acquiring an image of the workpiece plate, and obtaining the center coordinates of the circular hole on the workpiece plate according to the image of the workpiece plate; A segmentation unit, used for segmenting the image of the workpiece plate into N regions according to the coordinates of the center of the circular hole and a preset value, where N is a positive integer greater than 1; The calibration unit is used to use the two-dimensional hand-eye calibration method and the divided area. The robot drives the camera to find multiple holes in the area to take pictures. Each photo-taking process is the single-hole calibration process. The two-dimensional hand-eye calibration method is a 9-point calibration method. The calibration unit is used to drive the robot to find 9 holes in the area to take pictures. The calibration process of the smart camera and the manipulator is used for reference, that is, the coordinate conversion process of the camera's pixel coordinates and the robot's coordinates, to achieve precise positioning of the manipulator guided by the camera. Also includes conversion units: Given multiple first coordinates on the drawing, walk in the robot coordinate system or obtain the corresponding multiple second coordinates through visual recognition, and obtain the affine transformation homogeneous matrix by finding the relationship between the first coordinate and the second coordinate; According to the affine transformation homogeneous matrix, the actual coordinates of the workpiece plate are converted into the coordinates of the robot coordinate system.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method described in any one of claims 1 to 3 are implemented.

6. A robot system, characterized in that: The robot system comprises the robot tapping device according to claim 4.

Images