Vision-based automated component placement method

Abstract

The application discloses a kind of component automated positioning methods based on vision, comprising: preparation stage, complete at ball head, ball socket paste checkerboard feature point, complete ball socket inner surface ball center fitting and ball socket checkerboard measurement, have been positioned ball head ball socket camera shooting and save respective feature point three-dimensional data, construct camera to laser tracker assembly coordinate system and laser tracker assembly coordinate system to the pose transformation matrix of positioner;Application stage, camera shooting is to be positioned ball head ball socket and save respective feature point three-dimensional data, construct the pose transformation matrix of ball head checkerboard that has been positioned and is to be positioned, complete to be positioned ball socket feature point and the mapping of ball socket inner surface ball center, obtain relative distance under camera coordinate system, solve the moving distance of positioner by the pose transformation matrix of camera to laser tracker assembly coordinate system to positioner.The advantage of the method is to allow ball head component pose change and pose change when camera shooting, realize aircraft component automated rapid positioning.

Description

Technical Field

[0001] This invention relates to the field of aircraft component assembly technology, and in particular to a vision-based automated component placement method. Background Technology

[0002] In the digital assembly of aircraft components, parts are typically transported to a specific station by an Automated Guided Vehicle (AGV) or a traveling crane. Then, operators manually control a control panel to sequentially move multiple positioners, aligning the ball joints on the positioners with the ball joints on the component. Afterwards, the control console lifts the component from the AGV or traveling crane. This process, involving manual movement of multiple positioners, visual observation of the ball joint alignment, and repeated adjustments by the operator, is labor-intensive, time-consuming, impacts the workflow, and involves numerous uncontrollable factors.

[0003] This invention combines the working conditions of aircraft components entering the station, comprehensively considers the changes in posture of the components after entering the station, takes into account the changes in posture during the camera installation and photography process, adopts a vision-based approach to capture the relevant posture changes, calculates the relative distance between the ball head and the ball socket, and automatically controls the locator to complete the placement work, saving manpower and time and simplifying the operation process. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies by providing a vision-based automated component placement method.

[0005] To achieve the above objectives, the present invention provides a vision-based automated component placement method, comprising:

[0006] A checkerboard pattern is installed at the ball head and the ball socket respectively; the data of the inner corner points of the checkerboard pattern at the ball socket is measured by a laser tracker, and the data of the inner spherical surface of the ball socket is collected and fitted with the coordinates of the ball center; the locator is moved to make the ball socket and the ball head fit into position, the feature point data of the checkerboard pattern at the ball socket is measured by a laser tracker, and the camera is used to take pictures at a predetermined position to obtain the three-dimensional coordinate values ​​of the inner corner points of the checkerboard pattern at the ball head and the ball socket, and the first pose transformation matrix from the camera to the laser tracker assembly coordinate system is calculated; the laser tracker target ball is fixed to the locator, its axes are moved and the data of the locator and the laser tracker are recorded, and the second pose transformation matrix from the laser tracker assembly coordinate system to the locator is constructed.

[0007] The camera captures images of the ball head and socket to be positioned, extracting 3D data of the checkerboard feature points at the socket location. Using the data of the ball head to be positioned and the ball head already positioned, a third pose transformation matrix is ​​constructed. The 3D data of the checkerboard feature points at the socket location are then applied to the third pose transformation matrix to obtain the mapped data. Based on the checkerboard corner point data at the socket location, the checkerboard feature point data at the already positioned socket location, and the mapped data, fourth and fifth pose transformation matrices are constructed. These matrices are then applied to the ball center coordinates to calculate the relative displacement. The relative displacement is multiplied sequentially by the first and second pose transformation matrices to obtain the movement command value. This movement command value is then sent to the locator to complete the ball head and socket alignment.

[0008] Furthermore, a checkerboard pattern is installed on the same side of the ball head and the ball socket, and some or all of the inner corner points of the checkerboard pattern are selected as feature points.

[0009] Furthermore, the coordinates of the center of the sphere on the inner surface of the sphere-socket are fitted using the least squares method.

[0010] Furthermore, the step of taking a picture at a predetermined position using a camera to obtain the three-dimensional coordinates of the corner points of the checkerboard pattern at the already positioned ball head and socket includes:

[0011] The camera is controlled by the console to reach the predetermined position and take a picture, obtaining 2D RGB and depth map data of the ball head and nest already in place; 2D floating-point data of the corner points of the checkerboard at the ball head in place are obtained by detecting the 2D RGB image using OpenCV library functions; the area where the ball head and checkerboard are located is masked in the 2D RGB image, and the 2D floating-point data of the corner points of the checkerboard at the ball head in place are obtained; combining the pixel data of the 2D RGB image and the depth map data, the 3D data of the corner points of the checkerboard at the ball head in place are obtained by using a 2D linear interpolation method.

[0012] Further, the calculation of the first pose transformation matrix from camera to laser tracker includes:

[0013] The 3D data of the corner points of the checkerboard at the already positioned fodder and the feature point data of the checkerboard at the already positioned fodder are decentered to construct a covariance matrix. Singular value decomposition is performed on the covariance matrix, and the first pose transformation matrix is ​​calculated by combining the decomposed left and right singular vector matrices. The pose transformation matrix includes a rotation matrix and a translation matrix.

[0014] Furthermore, the target ball of the laser tracker is mounted on the positioner, and the positioner is moved sequentially along its axes by the control console. The coordinate data of the positioner and the measurement data of the laser tracker are recorded respectively, and the second pose transformation matrix from the laser tracker assembly coordinate system to the positioner is constructed.

[0015] Furthermore, the construction of fourth and fifth pose transformation matrices based on the checkerboard corner point data at the sphere's nest, the feature point data of the checkerboard at the already positioned sphere's nest, and the mapped data, and the application of the fourth and fifth pose transformation matrices to the sphere's center coordinates to calculate relative displacement, includes:

[0016] Based on the corner point data of the checkerboard at the ball's nest, the feature point data of the checkerboard at the ball's nest that has been positioned, and the 3D data of the feature point of the checkerboard at the ball's nest after mapping, a fourth pose transformation matrix and a fifth pose transformation matrix are constructed respectively. The ball center coordinates are mapped by applying the fourth pose transformation matrix and the fifth pose transformation matrix respectively, and their difference is calculated to obtain the relative displacement.

[0017] To achieve the above objectives, the present invention also provides a vision-based automated component placement device, including one or more processors for implementing the vision-based automated component placement method described above.

[0018] To achieve the above objectives, the present invention also provides an electronic device, including a memory and a processor, wherein the memory is coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the above-described vision-based automated component placement method.

[0019] To achieve the above objectives, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-described vision-based automated component placement method.

[0020] Compared with the prior art, the beneficial effects of the present invention are:

[0021] Once the AGV or traveling crane transports a component to its designated location, the component does not need to be in a precise position or orientation. This invention eliminates the influence of the component's initial orientation change through internal matrix transformation. Similarly, during camera installation or when its associated actuator moves the camera to a designated location, the camera does not need a precise position or orientation; this invention eliminates the influence of the camera's initial orientation. In application, this invention only requires the console to control the actuator to move the camera to the designated location, the console to control the camera to take a picture, and the console to complete the relevant calculations and output the 3D position command for the locator, which is then sent to the locator to ensure the ball joint and socket are properly aligned. No manual intervention is required, saving time and simplifying the process. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below:

[0023] Figure 1 This is a flowchart of the present invention;

[0024] Figure 2This is a schematic diagram illustrating the operation of the present invention;

[0025] Figure 3 This is a schematic diagram of the ball head and the feature points of the adhesive chessboard grid in this invention;

[0026] Figure 4 This is a schematic diagram of the ball socket and the feature points of the adhesive checkerboard pattern in this invention;

[0027] Figure 5 This is a schematic diagram of the feature points of the ball-and-socket checkerboard pattern acquired by a laser tracker in this invention;

[0028] Figure 6 This is a schematic diagram of the structure of the device of the present invention;

[0029] Figure 7 This is a schematic diagram of an electronic device according to the present invention;

[0030] In the attached diagram: 1-Laser tracker, 2-Control console, 3-Positioner, 4-Ball socket, 5-Ball head, 6-Camera, 7-Component mounting bracket, 8-First checkerboard feature point, 9-Second checkerboard feature point, 10-Third checkerboard feature point, 11-Fourth checkerboard feature point. Detailed Implementation

[0031] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0032] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The singular forms “a,” “the,” and “the” used in this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0033] It should be understood that although the terms first, second, third, etc., may be used in this invention to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, first information may also be referred to as second information without departing from the scope of this invention, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to a determination."

[0034] The present invention will be further described below with reference to the accompanying drawings, but the present invention is not limited to these examples.

[0035] like Figure 1 As shown, the present invention provides a vision-based automated component placement method, which includes a preparation stage and an application stage.

[0036] See Figure 2 The schematic diagram shows the working components, including: laser tracker 1, control console 2, locator 3, ball socket 4, ball head 5, camera 6, and component mounting bracket 7.

[0037] During the ground preparation and measurement phase:

[0038] Step 1: Install a checkerboard pattern on the same side of the ball head and the ball socket to facilitate camera shooting, such as... Figure 3 , Figure 4 As shown, the corner points of the chessboard are the 6×6 corner points and the 3×3 corner points.

[0039] It should be noted that a black and white checkerboard pattern should be pasted on the non-working surface near the ball head and socket. Select some or all of the inner corner points of the checkerboard pattern as feature points and paste them on the same side for easy photography. The number of inner corner points of the checkerboard pattern at the ball head and socket should be as different as possible, and their length × width should also be as different as possible for easy detection.

[0040] Step Two: In the waiting position state, use a laser tracker to measure the data of the corner points of the chessboard at the ball's nest, and record the four points of the 3×3 interior corners: the upper left, upper right, lower left, and lower right. Figure 5 Feature point 8 of the first chessboard grid, feature point 9 of the second chessboard grid, feature point 10 of the third chessboard grid, and feature point 11 of the fourth chessboard grid are shown; their respective x, y, z values ​​are recorded. Simultaneously, data on the inner spherical surface of the ball-and-socket joint (the mating surface with the ball head) was collected, with six points evenly distributed, and their x, y, and z values ​​recorded. The coordinates of the sphere's center are determined using the least squares method based on the data from the six points mentioned above. ,point The coordinates are as follows: The coordinates of the sphere's center can be obtained by solving the following equation. .

[0041] ;

[0042] ;

[0043] ;

[0044] in, The equation representing the coordinates of the sphere's center is used to solve for this problem. This represents a 6*4 dimensional matrix constructed from the collected data. The constructed 6*1 dimensional matrix is ​​shown in the upper right corner. This represents the matrix transpose operation.

[0045] Step 3: Move the positioning device via the control panel or console to align the ball socket with the ball head. Use a laser tracker to measure the checkerboard feature point data at the positioned ball socket, such as... Figure 5 The first chessboard feature point 8, the second chessboard feature point 9, the third chessboard feature point 10, and the fourth chessboard feature point 11 are shown. Their x, y, and z values ​​are recorded. The data for the chessboard feature points at the already positioned nests are... The console controls the camera actuator to move the camera to the predetermined position and take a picture, obtaining a 2D RGB image and depth map data of the ball head and socket in place, and obtaining the 3D coordinate values ​​of the corner points of the ball head and socket checkerboard. The first 36 data points are the three-dimensional data of the corner points of the chessboard grid where the ball has already been positioned. The last nine are the three-dimensional data of the corner points of the chessboard grid where the balls have been placed. The specific steps to obtain it are as follows:

[0046] Using the OpenCV library function findChessboardCorners() on a 2D RGB image captured by a camera, retrieve the 2D floating-point data of the 36 interior corner points of the chessboard at the positioned ball head. Calculate the depth value of the first point as an example. First, calculate the values ​​of the four pixels surrounding the first inner corner point: , , , ; Representative to Round down; obtain the corresponding depth map. Four depth data points, fitting :

[0047] ;

[0048] ;

[0049] ;

[0050] in, Represents floating-point numbers Rounding The distance between the latter two, i.e., the decimal part; Represents floating-point numbers Rounding The distance between the latter two is the decimal part.

[0051] In the 2D RGB image, the area where the checkerboard is located at the ball's head is masked, and the 3D data of the 9 inner corner points of the checkerboard at the ball's nest is obtained using the method described above.

[0052] Step 4: Combine the 3D data of the nine corner points of the checkerboard grid at the nine already positioned nests from Step 3. The feature points 8, 9, 10, and 11 of the first, second, and third chessboard squares are extracted in sequence. and renamed Combined with the checkerboard feature point data of the already positioned balls in step three. renamed Calculate the rotation matrix from the camera to the laser tracker. Translation matrix as follows:

[0053] (4.1) Calculate the center of the two sets of data: ; ;

[0054] (4.2) Decentralize the two sets of data: ; ;in, This represents the relative distance between the raw feature point data captured by the camera and the calculated center point. This represents the relative distance from the raw data measured by the laser tracker to the calculated center point;

[0055] (4.3) Construct the covariance matrix: ;

[0056] (4.4) Perform singular value decomposition on the covariance matrix: ;in, Describes a left singular vector matrix. Represents a right singular vector matrix;

[0057] (4.5) Calculate the rotation matrix: If det(R) < 0, perform corrected reflection;

[0058] (4.6) Calculate the translation vector: .

[0059] Step 5: Install the target ball of the laser tracker onto the positioner, and move the positioner to three points on each of its three axes (a total of 9 points) using the control console, while simultaneously recording the positioner's three-coordinate data. Measurement data from laser trackers The rotation matrix from the laser tracker assembly coordinate system to the positioner is constructed using the method in step four. Translation matrix .

[0060] At this point, the preparation phase is complete. We will now proceed with the application phase.

[0061] Step 6: Take a photo of the ball head and rim of the ball to be placed using a camera.

[0062] Step 7: Extract the 3D data of the checkerboard feature points at the ball head to be placed using the method in Step 3. Three-dimensional data of 36 checkerboard feature points at the ball placement positions. There are 9 in total, arranged in order; using the 3D data of the checkerboard feature points at the ball head to be placed. 3D data of the corner points of the chessboard at the already positioned ball head The rotation matrix of the ball head attitude is constructed using the method in step four. Translation matrix The three-dimensional data of the checkerboard feature points at the ball's position to be placed. Apply rotation matrix Translation matrix Obtain the mapped data The details are as follows:

[0063] ;

[0064] in, This represents the three-dimensional data of the first checkerboard feature point at the ball's nest. This represents the 3D data of the first checkerboard feature point at the mapped sphere.

[0065] Step 8: Calculate the corner data of the checkerboard at the ball's nest measured using the laser tracker in Step 2. Compared with the checkerboard feature point data of the ball hole that has been placed in step three The three-dimensional data of the checkerboard feature points at the ball's nest after mapping in step seven. ,according to Figure 5 Four data points were extracted from the first chessboard feature point 8, the second chessboard feature point 9, the third chessboard feature point 10, and the fourth chessboard feature point 11 shown. Construct rotation matrices respectively. Translation matrix Rotation matrix Translation matrix The coordinates of the sphere's center measured by the laser tracker in step two. Apply rotation matrices respectively Translation matrix Rotation matrix Translation matrix , mapped to and And calculate the difference, i.e., the relative displacement. The details are as follows:

[0066] ;

[0067] Step 9: Adjust relative displacement With rotation matrix and rotation matrix The locator movement command value Mr(xr, yr, zr) is obtained by multiplying them sequentially, as follows:

[0068] ;

[0069] Step 10: The console sends the movement command value to the locator to complete the ball head and ball socket coordination.

[0070] Corresponding to the aforementioned embodiments of the vision-based automated component placement method, the present invention also provides embodiments of a vision-based automated component placement device.

[0071] See Figure 6 The vision-based automated component placement device provided in this embodiment of the invention includes one or more processors for implementing the vision-based automated component placement method in the above embodiment.

[0072] The vision-based automated component placement device of this invention can be applied to any device with data processing capabilities, such as a computer. The device can be implemented in software, hardware, or a combination of both. Taking software implementation as an example, as a logical device, it is formed by the processor of any data processing device loading the corresponding computer program instructions from non-volatile memory into memory for execution. From a hardware perspective, such as... Figure 6 The diagram shown is a hardware structure diagram of any device with data processing capabilities, including the vision-based automated component placement device of this invention. (Except for...) Figure 6 In addition to the processor, memory, network interface, and non-volatile memory shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.

[0073] The specific implementation process of the functions and roles of each unit in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0074] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of the present invention according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0075] Corresponding to the aforementioned embodiments of the vision-based automated component placement method, this application also provides an electronic device, including: one or more processors; a memory for storing one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the vision-based automated component placement method as described above. Figure 7 The diagram shown is a hardware structure diagram of any device with data processing capabilities for the vision-based automated component placement method provided in this application embodiment, except... Figure 7 In addition to the processor, memory, DMA controller, disk, and non-volatile memory shown, any data processing device in the embodiment may also include other hardware depending on the actual function of the data processing device, which will not be described in detail here.

[0076] Corresponding to the aforementioned embodiments of the vision-based automated component placement method, this embodiment of the invention also provides a computer-readable storage medium storing a program thereon, which, when executed by a processor, implements the vision-based automated component placement method described in the above embodiments.

[0077] The computer-readable storage medium can be an internal storage unit of any data processing device described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be any data processing device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data processing device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data processing device, and can also be used to temporarily store data that has been output or will be output.

[0078] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0079] The above embodiments are only used to illustrate the design concept and features of the present invention, and their purpose is to enable those skilled in the art to understand the content of the present invention and implement it accordingly. The protection scope of the present invention is not limited to the above embodiments. Therefore, all equivalent changes or modifications made based on the principles and design ideas disclosed in the present invention are within the protection scope of the present invention.

Claims

1. A vision-based automated component placement method, characterized in that, include: Install checkerboard patterns at the ball head and ball socket; The laser tracker measures the corner points of the checkerboard pattern at the ball's nest location, and simultaneously collects the inner spherical surface data of the nest and fits the ball's center coordinates. The locator is moved to align the nest with the ball's head. The laser tracker measures the feature points of the checkerboard pattern at the nest location, and the camera takes pictures at a predetermined position to obtain the 3D data of the corner points of the checkerboard pattern at the nest location. The first pose transformation matrix from the camera to the laser tracker's assembly coordinate system is calculated. The laser tracker target ball is fixed to the locator, and its axes are moved while the data from the locator and the laser tracker are recorded. The second pose transformation matrix from the laser tracker's assembly coordinate system to the locator is constructed. The camera captures images of the ball head and its socket to be positioned, and extracts the 3D data of the checkerboard feature points at the ball head and its socket. Using the 3D data of the checkerboard feature points at the ball head to be positioned and the 3D data of the inner corner points of the checkerboard at the already positioned ball head, a third pose transformation matrix for the ball head's posture is constructed. The 3D data of the checkerboard feature points at the ball head and its socket are then applied to the third pose transformation matrix to obtain the mapped data. Based on the corner point data of the checkerboard at the ball's nest to be positioned, the feature point data of the checkerboard at the already positioned ball's nest, and the mapped data, the fourth and fifth pose transformation matrices are constructed. The fourth and fifth pose transformation matrices are applied to the ball's center coordinates to calculate the relative displacement. The relative displacement is multiplied by the first and second pose transformation matrices in sequence to obtain the movement command value. The movement command value is sent to the locator to complete the ball head and ball nest alignment.

2. The vision-based automated component placement method according to claim 1, characterized in that, Install a checkerboard pattern on the same side of the ball head and the ball socket, and select some or all of the inner corner points of the checkerboard pattern as feature points.

3. The vision-based automated component placement method according to claim 1, characterized in that, The coordinates of the center of the sphere on the inner surface of the sphere-socket were fitted using the least squares method.

4. The vision-based automated component placement method according to claim 1, characterized in that, The step of taking pictures at predetermined positions using a camera to obtain three-dimensional data of the corner points of the checkerboard grid at the already positioned ball head and nest includes: The camera is controlled by the console to reach the predetermined position and take a picture, obtaining 2D RGB and depth map data of the ball head and nest already in place; 2D floating-point data of the corner points of the checkerboard grid at the ball head is obtained by detecting the 2D RGB image using OpenCV library functions; the area where the ball head and checkerboard grid are located is covered in the 2D RGB image, and 2D floating-point data of the corner points of the checkerboard grid at the nest is obtained; combining the pixel data of the 2D RGB image and the depth map data, 3D data of the corner points of the checkerboard grid at the ball head and nest is obtained by using a 2D linear interpolation method.

5. The vision-based automated component placement method according to claim 1, characterized in that, The calculation of the first pose transformation matrix from camera to laser tracker includes: The 3D data of the corner points of the checkerboard at the already positioned fodder and the feature point data of the checkerboard at the already positioned fodder are decentered to construct a covariance matrix. Singular value decomposition is performed on the covariance matrix, and the first pose transformation matrix is ​​calculated by combining the decomposed left and right singular vector matrices. The pose transformation matrix includes a rotation matrix and a translation matrix.

6. The vision-based automated component placement method according to claim 1, characterized in that, The target ball of the laser tracker is mounted on the positioner. The positioner is moved sequentially along its axes by the control console. The coordinate data of the positioner and the measurement data of the laser tracker are recorded respectively. The second pose transformation matrix from the laser tracker assembly coordinate system to the positioner is constructed.

7. The vision-based automated component placement method according to claim 1, characterized in that, Based on the corner point data of the checkerboard grid at the ball's intended placement location, the feature point data of the checkerboard grid at the already placed ball's placement location, and the mapped data, a fourth and fifth pose transformation matrix are constructed. These fourth and fifth pose transformation matrices are then applied to the ball's center coordinates to calculate the relative displacement, including: Based on the corner point data of the checkerboard at the ball's nest, the feature point data of the checkerboard at the ball's nest that has been positioned, and the 3D data of the feature point of the checkerboard at the ball's nest after mapping, a fourth pose transformation matrix and a fifth pose transformation matrix are constructed respectively. The ball center coordinates are mapped by applying the fourth pose transformation matrix and the fifth pose transformation matrix respectively, and their difference is calculated to obtain the relative displacement.

8. A vision-based automated component placement device, characterized in that, It includes one or more processors for implementing the vision-based automated component placement method according to any one of claims 1-7.

9. An electronic device comprising a memory and a processor, characterized in that, The memory is coupled to the processor; wherein the memory is used to store program data, and the processor is used to execute the program data to implement the vision-based automated component placement method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the vision-based automated component placement method as described in any one of claims 1-7.

Images