A vehicle glue application positioning method, device, electronic device and storage medium

Abstract

The present invention discloses a vehicle gluing positioning method, comprising the following steps: when the vehicle body to be glued moves to the gluing station, determining a preset identification feature and the preset identification feature image coordinates; acquiring the current image of the vehicle body to be glued; identifying each current image of the vehicle body and determining the current identification feature and the current identification feature image coordinates of each current image of the vehicle body; judging whether the current identification feature matches the preset identification feature; if they match, judging whether the current identification feature image coordinates are the same as the preset identification feature image coordinates of the matching preset identification feature; if not, determining the manipulator offset according to the current image identification feature coordinates. The present invention ensures that the manipulator accurately positions during gluing, thereby greatly improving the accuracy and consistency of gluing. The present invention also discloses a device, an electronic device and a computer-readable storage medium for implementing the above method.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial control, and particularly to a vehicle gluing positioning method, device, electronic device and storage medium. Background Art

[0002] In the process of automobile production, the vehicle body is automatically conveyed on the production line through a skid; when the vehicle body reaches the gluing station, the robot will automatically apply glue to it. Due to the error of the conveying system, the vehicle body cannot stop at exactly the same position every time, but the working position of the robotic arm is unchanged. Therefore, the problem of inaccurate gluing position may occur when the robotic arm is working. Summary of the Invention

[0003] In order to solve the above problems existing in the prior art, the present invention provides a vehicle gluing positioning method, device, electronic device and storage medium. The technical problems to be solved by the present invention are realized through the following technical solutions:

[0004] The first aspect of the embodiment of the present invention provides a vehicle gluing positioning method, including the following steps:

[0005] When the vehicle body to be glued moves to the gluing station, obtain the current vehicle model and the current process;

[0006] According to the current vehicle model and the current process, determine the preset identification feature and the corresponding preset identification feature image coordinates;

[0007] Obtain the current vehicle body images of at least three parts of the vehicle body to be glued collected by at least three industrial cameras respectively;

[0008] Identify each of the current vehicle body images, and determine the current identification feature and the corresponding current identification feature image coordinates of each of the current vehicle body images;

[0009] Judge whether the current identification feature matches the preset identification feature;

[0010] If they match, judge whether the current identification feature image coordinates corresponding to the current identification feature are the same as the preset identification feature image coordinates of the matching preset identification feature;

[0011] If not, determine the robotic arm offset according to the current image identification feature coordinates corresponding to multiple different current identification features.

[0012] In an embodiment of the present invention, the method further includes:

[0013] Send a motion instruction to the robotic arm according to the robotic arm offset.

[0014] In one embodiment of the present invention, determining the robotic arm offset according to the current image identification feature coordinates corresponding to a plurality of different current identification features includes:

[0015] Converting the current image identification feature coordinates into the current identification feature camera coordinates in the camera coordinate system;

[0016] Converting the current identification feature camera coordinates into the current identification feature robotic arm coordinates in the robotic arm coordinate system;

[0017] Determining the robotic arm offset according to the preset robotic arm coordinates of the current identification feature and the current identification feature robotic arm coordinates.

[0018] In one embodiment of the present invention, determining the robotic arm offset according to the preset robotic arm coordinates of the current identification feature and the current identification feature robotic arm coordinates includes:

[0019] Determining the average translational deviation of the robotic arm according to the preset robotic arm coordinates of a plurality of the current identification features and the current identification feature robotic arm coordinates;

[0020] Centering the preset robotic arm coordinates of a plurality of the current identification features and the current identification feature robotic arm coordinates respectively to obtain the preset centered coordinates and the current centered coordinates;

[0021] Constructing a covariance matrix according to the preset centered coordinates and the current centered coordinates;

[0022] Performing singular value decomposition on the covariance matrix;

[0023] Calculating the robotic arm rotation deviation matrix according to the singular value decomposition result;

[0024] Converting the robotic arm rotation deviation matrix into the robotic arm rotation Euler angles;

[0025] Determining the robotic arm offset according to the average translational deviation of the robotic arm and the robotic arm rotation Euler angles.

[0026] A second aspect of the embodiments of the present invention provides a vehicle gluing positioning device, including:

[0027] A first acquisition module, configured to acquire the current vehicle model and the current process when the vehicle body to be glued moves to the gluing station;

[0028] A first determination module, configured to determine the preset identification features and the corresponding preset identification feature image coordinates according to the current vehicle model and the current process;

[0029] A second acquisition module, configured to acquire the current images of at least three parts of the vehicle body to be glued collected by at least three industrial cameras;

[0030] A second determination module, configured to identify each current image of the vehicle body, and determine the current identification feature and the corresponding current identification feature image coordinates of each current image of the vehicle body;

[0031] A matching module, configured to determine whether the current identification feature matches the preset identification feature;

[0032] A judgment module, configured to, if a match is found, determine whether the current identification feature image coordinates corresponding to the current identification feature are the same as the preset identification feature image coordinates of the matched preset identification feature;

[0033] A calculation module, configured to, if not, determine the manipulator offset according to the current image identification feature coordinates corresponding to multiple different current identification features.

[0034] In an embodiment of the present invention, it further includes: a sending module, configured to send a motion instruction to the manipulator according to the manipulator offset.

[0035] In an embodiment of the present invention, the determining the manipulator offset according to the current image identification feature coordinates corresponding to multiple different current identification features includes:

[0036] Converting the current image identification feature coordinates into current identification feature camera coordinates in the camera coordinate system;

[0037] Converting the current identification feature camera coordinates into current identification feature manipulator coordinates in the manipulator coordinate system;

[0038] Determining the manipulator offset according to the preset manipulator coordinates of the current identification feature and the current identification feature manipulator coordinates.

[0039] In an embodiment of the present invention, it includes: the determining the manipulator offset according to the preset manipulator coordinates of the current identification feature and the current identification feature manipulator coordinates includes:

[0040] Determining the average translational deviation of the manipulator according to the preset manipulator coordinates of multiple current identification features and the current identification feature manipulator coordinates;

[0041] Centering the preset manipulator coordinates of multiple current identification features and the current identification feature manipulator coordinates respectively to obtain preset centered coordinates and current centered coordinates;

[0042] Constructing a covariance matrix according to the preset centered coordinates and the current centered coordinates;

[0043] Performing singular value decomposition on the covariance matrix;

[0044] Calculate the robotic arm rotation deviation matrix based on the singular value decomposition result;

[0045] Convert the robotic arm rotation deviation matrix into the robotic arm rotation Euler angles;

[0046] Determine the robotic arm offset based on the average translational deviation of the robotic arm and the robotic arm rotation Euler angles.

[0047] The third aspect of the embodiments of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements a vehicle gluing positioning method provided in the first aspect of the embodiments of the present invention.

[0048] The fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements a vehicle gluing positioning method provided in the first aspect of the embodiments of the present invention.

[0049] Advantages of the present invention:

[0050] In the present invention, the coordinates of the current image identification features are determined by the method of image recognition for the marked identification features on multiple vehicle bodies, so as to obtain the robotic arm offset between the current position and the preset working position of the robotic arm. After calculating the robotic arm offset, the control system will adjust the position of the robotic arm so that it can accurately align with the current position of the vehicle body. This dynamic adjustment mechanism ensures that the robotic arm is accurately positioned during gluing, thereby greatly improving the accuracy and consistency of gluing.

[0051] Other identification features and advantages of the present invention will be described in the subsequent specification, and part of them will be obvious from the specification, or understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in the written specification, claims, and drawings.

[0052] The following further describes the technical solutions of the present invention in detail through the drawings and embodiments. Description of the Drawings

[0053] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0054] Figure 1 is a schematic flowchart of a vehicle gluing positioning method provided by an embodiment of the present invention;

[0055] Figure 2 is a block diagram of a vehicle gluing positioning device provided by an embodiment of the present invention. Specific Embodiments

[0056] The following further describes the present invention in detail with reference to specific embodiments, but the embodiments of the present invention are not limited thereto.

[0057] As Figure 1 shown, a vehicle gluing positioning method provided in the first aspect of the embodiment of the present invention includes the following steps:

[0058] Step 11, when the vehicle body to be glued moves to the gluing station, obtain the current vehicle model and the current process.

[0059] Step 12, according to the current vehicle model and the current process, determine the preset identification feature and the corresponding preset identification feature image coordinates.

[0060] Step 13, obtain the current vehicle body images of at least three parts of the vehicle body collected by at least three industrial cameras respectively.

[0061] Step 14, identify each current vehicle body image, and determine the current identification feature and the corresponding current identification feature image coordinates of each current vehicle body image.

[0062] Step 15, determine whether the current identification feature matches the preset identification feature.

[0063] Step 16, if they match, determine whether the current identification feature image coordinates corresponding to the current identification feature are the same as the preset identification feature image coordinates of the matched preset identification feature.

[0064] Step 17, if not, determine the robotic arm offset according to the current image identification feature coordinates corresponding to multiple different current identification features.

[0065] In the present invention, the current image identification feature coordinates are determined by the method of image recognition of the marked identification features on multiple vehicle bodies, so as to obtain the robotic arm offset between the current position and the preset working position of the robotic arm. After calculating the robotic arm offset, the control system will adjust the position of the robotic arm so that it can accurately align with the current gluing position of the vehicle body. Each time the vehicle body to be glued is transported to the station, the offset is calculated before starting gluing. This dynamic adjustment mechanism ensures that the robotic arm is accurately positioned each time during gluing, thus greatly improving the accuracy and consistency of gluing.

[0066] A vehicle gluing positioning method provided in the second aspect of the embodiment of the present invention includes the following steps:

[0067] Step 21, when the vehicle body to be glued moves to the gluing station, obtain the current vehicle model and the current process.

[0068] When the vehicle body to be glued is conveyed to the gluing station, the PLC control system will obtain the current vehicle model information and the current process. The current vehicle model can be obtained according to the information set during initialization or according to the vehicle model identification of the vehicle body to be glued. The vehicle model identification can be obtained by scanning the vehicle model identification code on the vehicle body to be glued; the current process can be obtained according to the process information of the previous vehicle body that has completed gluing. The current process can be the same as or different from the process of the previous vehicle body that has completed gluing.

[0069] Step 22: Determine the preset identification features and the corresponding preset identification feature image coordinates according to the current vehicle model and the current process.

[0070] In this step, after obtaining the current vehicle model and the current process, the information of the corresponding preset identification features can be found in the preset database to obtain the corresponding preset identification features and the preset identification feature image coordinates. Here, the preset identification features can be one or more. The identification features can be holes, but other features such as corners and edges can also be utilized.

[0071] Step 23: Obtain the current vehicle body images of at least three parts of the vehicle body to be glued collected by at least three industrial cameras respectively. Each industrial camera collects one part of the vehicle body, and each industrial camera collects different parts of the vehicle body. In this embodiment, four industrial cameras are taken as an example to collect the current vehicle body images of four different parts. Each current vehicle body image includes at least one identification feature. The preset identification features are obtained by pre-collecting standard images through industrial cameras for feature extraction. The standard images are the images collected when the vehicle body to be glued is in the ideal working condition at the standard position at the gluing station. The coordinates of the identification features in the images are the coordinates at the standard position, that is, the preset identification feature image coordinates.

[0072] Step 24: Identify each current vehicle body image and determine the current identification features and the corresponding current identification feature image coordinates of each current vehicle body image.

[0073] In this step, image recognition is performed on the current vehicle body image to obtain one or more current identification features and the current identification feature image coordinates corresponding to each current identification feature.

[0074] Step 25: Match the current identification features with the preset identification features and determine whether the current identification features match the preset identification features.

[0075] In this step, search for the features that match the current identification features among the preset identification features. If a matching preset identification feature is found, the matching is successful. If the matching is not successful, the industrial camera re-collects the current vehicle body image.

[0076] Step 26, if there is a match, determine whether the current identification feature image coordinates corresponding to the current identification feature are the same as the preset identification feature image coordinates of the matched preset identification feature.

[0077] In this step, if the match is successful, it is necessary to determine whether the preset identification feature image coordinates of the matched preset identification feature are the same as the current identification feature image coordinates. If they are the same, it means that the current position of the vehicle body to be glued is the standard position and the gluing operation can be directly carried out. If they are not the same, it means that the current position of the vehicle body to be glued has shifted, and it is necessary to continue calculating the offset amount so that the robotic arm moves to the shifted position for gluing. Then, the relative position of the robotic arm and the vehicle body to be glued remains unchanged, and the gluing position is accurate.

[0078] Here, four industrial cameras capture multiple current images of the vehicle body, so that multiple current identification features can be obtained. Through the collaborative work of multiple cameras, the system can obtain richer and more comprehensive feature information, avoiding information loss or errors that may be caused by a single perspective. Calculating the offset amount based on the coordinates of multiple current identification features can balance errors and make the calculated offset amount more accurate.

[0079] Step 27, if they are not the same, determine the robotic arm offset amount according to the current image identification feature coordinates corresponding to multiple different current identification features.

[0080] The specific steps of Step 27 include Step 271 - Step 273:

[0081] Step 271, convert the multiple current image identification feature coordinates into multiple current identification feature camera coordinates in the camera coordinate system.

[0082] In this step, the image coordinates ( u , v ) are converted into the camera coordinate system ( Xc , Yc , Zc ) by the formula:

[0083]

[0084]

[0085] Among them, ( u , v ) are the pixel coordinates in the image coordinate system, ( u 0, v 0) is the principal point of the image (usually the center of the image), fx and fy are the focal lengths of the camera (in pixels), Zc is the depth of the object in the camera coordinate system (usually obtained through a depth camera or triangulation).

[0086] Substitute the feature coordinates of each current image identifier into the formula to calculate the current identifier feature camera coordinates in the camera coordinate system.

[0087] Step 272: Convert the multiple current identifier feature camera coordinates into multiple current identifier feature robot arm coordinates in the robot arm coordinate system.

[0088] In this step, the camera coordinate system ( Xc , Yc , Zc ) is converted into the six-degree-of-freedom robot arm coordinate system ( Xr , Yr , Zr ) using the following formula:

[0089]

[0090] where Tc is the homogeneous transformation matrix from the camera coordinate system to the robot arm coordinate system, which includes the rotation matrix R and the translation vector t :

[0091]

[0092] The rotation matrix represents the rotation of the camera coordinate system relative to the robot arm coordinate system, and

[0093] The rotation matrix R and the translation vector t are usually calculated through Hand-Eye Calibration.

[0094] Step 273: Determine the robot arm offset based on the multiple preset robot arm coordinates of the current identifier features and the multiple current identifier feature robot arm coordinates.

[0095] The specific steps of Step 273 include Steps A1 - A7:

[0096] Step A1: Determine the average translational deviation of the robot arm based on the multiple preset robot arm coordinates of the current identifier features and the current identifier feature robot arm coordinates.

[0097] In this step, the current identifier feature robot arm coordinates are P i =( x i , y i , z i ) ( i= 1, 2, …, n , n ≥ 3). n is the number of current identification features, and the preset robot arm coordinates of multiple current identification features are denoted as P i ′ = ( x i ′, y i ′, z i ′).

[0098] The calculation formula for the average translational deviation of the robot arm is as follows:

[0099] )

[0100] )

[0101] )

[0102] The average translational deviation of the robot arm .

[0103] Step A2: Centralize the preset robot arm coordinates and the robot arm coordinates of the current identification features of multiple current identification features respectively to obtain the preset centralized coordinates and the current centralized coordinates;

[0104] In this step, calculate the center point of the preset robot arm coordinates of multiple current identification features :

[0105]

[0106] Calculate the center point of the robot arm coordinates of multiple current identification features :

[0107]

[0108] Centralize the coordinates to obtain the preset centralized coordinates , and the current centralized coordinates .

[0109] Step A3: Construct a covariance matrix based on the preset centralized coordinates and the current centralized coordinates H .

[0110]

[0111] Step A4: Perform singular value decomposition on the covariance matrix.

[0112]

[0113] Step A5: Calculate the robotic arm rotation deviation matrix based on the singular value decomposition result.

[0114] Robotic arm rotation deviation matrix 。

[0115] Step A6: Convert the robotic arm rotation deviation matrix into the robotic arm rotation Euler angles.

[0116] Step A7: Determine the robotic arm offset based on the average translational deviation of the robotic arm and the robotic arm rotation Euler angles.

[0117] In this step, the calculated average translational deviation of the robotic arm and the rotation Euler angles are the robotic arm offset.

[0118] Step 28: Send a motion command to the robotic arm according to the robotic arm offset.

[0119] In this step, the current coordinates of the robotic arm are calculated based on the preset working coordinates of the robotic arm and the robotic arm offset, and the robotic arm moves to the position of the current coordinates of the robotic arm according to the current coordinates of the robotic arm to start the gluing work.

[0120] In this embodiment, the vision system composed of four industrial cameras will achieve the 3D orientation recognition of various different types of vehicle bodies; for vehicle models with similar dimensions, expansion can be achieved without adding hardware. When the stop position of the vehicle body is within the transmission error range of ±30 mm and the vehicle body is stationary without shaking, the positioning accuracy of the vision system is better than ±1 mm; when one of the cameras in the vision system fails, it can achieve degradation and shield the camera to maintain the operation of 3 cameras. The effective time occupied by the vision system, that is, from the start of the measurement signal sent by the PLC to the measurement orientation correction vector given by the vision system, this measurement process does not exceed 2000 milliseconds; the measurement success rate of the vision system after optimization and stabilization is above 99.9%.

[0121] Preferably, the industrial camera is also equipped with a light source device to supplement light for taking the current image of the vehicle body.

[0122] Furthermore, the vehicle body to be glued is automatically transported on the production line through a skid; when the vehicle body to be glued reaches the gluing station, the vision system will communicate with the external PCL device, and at this time, the vision system will be automatically triggered, and photos will be taken and recognized at 4 different parts fixed at different angles of the vehicle body through the industrial cameras and lights.

[0123] Further, the vision system and the robotic arm system are equipped with standard Ethernet network cards. The vision system controls the lighting / flip cover through the measurement preparation signal given by the PLC master station. The vision system and the robotic arm system are connected in a slave mode, and the communication protocol can be selected. The image processing software used by the vision system has an intuitive and easy-to-operate multi-language user operation interface. The installation distance of the industrial camera is generally 2.5 - 3.5 meters, and it can be adjusted within a range of 200 mm in the up and down, left and right, and front and back directions of the installation point.

[0124] As Figure 2 shown, the third aspect of the embodiment of the present invention provides a vehicle gluing positioning device, including:

[0125] A first acquisition module 31, configured to acquire the current vehicle model and the current process when the vehicle body to be glued moves to the gluing station;

[0126] A first determination module 32, configured to determine a preset identification feature and the corresponding preset identification feature image coordinates according to the current vehicle model and the current process;

[0127] A second acquisition module 33, configured to acquire the current vehicle body images of at least three parts of the vehicle body to be glued respectively collected by at least three industrial cameras;

[0128] A second determination module 34, configured to identify each current vehicle body image and determine the current identification feature and the corresponding current identification feature image coordinates of each current vehicle body image;

[0129] A matching module 35, configured to determine whether the current identification feature matches the preset identification feature;

[0130] A judgment module 36, configured to, if they match, determine whether the current identification feature image coordinates corresponding to the current identification feature are the same as the preset identification feature image coordinates of the matching preset identification feature;

[0131] A calculation module 37, configured to, if not, determine the robotic arm offset according to the current image identification feature coordinates corresponding to multiple different current identification features.

[0132] In an embodiment of the present invention, it further includes: a sending module, configured to send a motion instruction to the robotic arm according to the robotic arm offset.

[0133] In an embodiment of the present invention, determining the robotic arm offset according to the current image identification feature coordinates corresponding to multiple different current identification features includes:

[0134] Converting the current image identification feature coordinates into the current identification feature camera coordinates in the camera coordinate system;

[0135] Converting the current identification feature camera coordinates into the current identification feature robotic arm coordinates in the robotic arm coordinate system;

[0136] Based on the preset robotic arm coordinates corresponding to the current identification features and the robotic arm coordinates of the current identification features, determine the robotic arm offset.

[0137] In an embodiment of the present invention, based on the preset robotic arm coordinates corresponding to the current identification features and the robotic arm coordinates of the current identification features, determining the robotic arm offset includes:

[0138] Based on the preset robotic arm coordinates corresponding to multiple current identification features and the robotic arm coordinates of the current identification features, determine the average translational deviation of the robotic arm;

[0139] Centralize the preset robotic arm coordinates corresponding to multiple current identification features and the robotic arm coordinates of the current identification features respectively to obtain the preset centralized coordinates and the current centralized coordinates;

[0140] Construct a covariance matrix based on the preset centralized coordinates and the current centralized coordinates;

[0141] Perform singular value decomposition on the covariance matrix;

[0142] Calculate the robotic arm rotation deviation matrix according to the singular value decomposition result;

[0143] Convert the robotic arm rotation deviation matrix into the robotic arm rotation Euler angles;

[0144] Based on the average translational deviation of the robotic arm and the robotic arm rotation Euler angles, determine the robotic arm offset.

[0145] A fourth aspect of the embodiments of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements a vehicle gluing positioning method provided in the above embodiments of the present invention.

[0146] A fifth aspect of the embodiments of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the steps of a vehicle gluing positioning method provided in the above embodiments of the present invention.

[0147] Wherein, the memory may include a random access memory (Random Access Memory, RAM), and may also include a non-volatile memory (Non-Volatile Memory, NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0148] The above-mentioned processor may be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware systems.

[0149] The method provided by the embodiments of the present invention can be applied to an electronic device. Specifically, the electronic device may be: a desktop computer, a portable computer, a smart mobile terminal, a server, etc. There is no limitation here. Any electronic device that can implement the present invention belongs to the protection scope of the present invention.

[0150] For the device / electronic device embodiments, since they are basically similar to the method embodiments, the description is relatively simple. For the relevant parts, please refer to the partial description of the method embodiments.

[0151] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, and the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0152] These computer program instructions can also be stored in a computer-readable memory that can guide a computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured product including an instruction device, and the instruction device implements the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0153] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the functions specified in one process or a plurality of processes and / or blocks Figure 1 in one block or a plurality of blocks Figure 1 in the steps of the processes.

[0154] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A vehicle gluing positioning method, characterized in that: The following steps are involved: When the car body to be glued moves to the gluing station, the current car model and current process are obtained; Determining a preset identification feature and a corresponding preset identification feature image coordinate according to the current vehicle model and the current process; Acquire current images of at least three parts of the vehicle body to be coated with glue, respectively captured by at least three industrial cameras; Identify each of the current images of the vehicle body, and determine the current identification feature of each of the current images of the vehicle body and the corresponding current identification feature image coordinates; Determining whether the current identification feature matches the preset identification feature; If they match, determining whether the current identification feature image coordinates corresponding to the current identification feature are the same as the preset identification feature image coordinates of the matched preset identification feature; If not, determining the robot arm offset according to the current image identification feature coordinates corresponding to the multiple different current identification features; The determining of the robot arm offset according to the current image identification feature coordinates corresponding to the multiple different current identification features includes: Convert the current image identification feature coordinates into the current identification feature camera coordinates in the camera coordinate system; Convert the current identification feature camera coordinates into the current identification feature manipulator arm coordinates in the manipulator arm coordinate system; Determine the offset of the robot arm according to the preset robot arm coordinates of the current identification feature and the robot arm coordinates of the current identification feature; The step of determining the offset of the robot arm according to the preset robot arm coordinates of the current identification feature and the robot arm coordinates of the current identification feature comprises: Determine an average translation deviation of the robot arm according to a plurality of preset robot arm coordinates of the current identification features and the robot arm coordinates of the current identification features; Respectively centering the plurality of current identification feature preset mechanical arm coordinates and the current identification feature mechanical arm coordinates to obtain preset centralized coordinates and current centralized coordinates; Constructing a covariance matrix according to the preset centered coordinates and the current centered coordinates; Performing singular value decomposition on the covariance matrix; Calculate the robot arm rotation deviation matrix according to the singular value decomposition result; Converting the robot arm rotation error matrix into the robot arm rotation Euler angle; The offset of the robotic arm is determined according to the average translation deviation of the robotic arm and the Euler angle of rotation of the robotic arm.

2. The method according to claim 1, characterized in that The method further comprises: A motion instruction is sent to the robotic arm according to the robotic arm offset.

3. A vehicle gluing positioning device, characterized in that: include: The first acquisition module is used to acquire the current vehicle model and current process when the vehicle body to be glued moves to the glue coating station; A first determination module, used to determine a preset identification feature and a corresponding preset identification feature image coordinate according to the current vehicle model and the current process; A second acquisition module is used to acquire current images of the vehicle body to be coated with glue at at least three parts of the vehicle body captured by at least three industrial cameras respectively; A second determination module is used to identify each of the current images of the vehicle body, and determine the current identification feature of each of the current images of the vehicle body and the corresponding current identification feature image coordinates; A matching module, used to determine whether the current identification feature matches the preset identification feature; A judgment module, used for judging whether the image coordinates of the current identification feature corresponding to the current identification feature are the same as the preset identification feature image coordinates of the matched preset identification feature if there is a match; A calculation module, for determining the robot arm offset according to the current image identification feature coordinates corresponding to the multiple different current identification features; The determining of the robot arm offset according to the current image identification feature coordinates corresponding to the multiple different current identification features includes: Convert the current image identification feature coordinates into the current identification feature camera coordinates in the camera coordinate system; Convert the current identification feature camera coordinates into the current identification feature manipulator arm coordinates in the manipulator arm coordinate system; Determine the offset of the robot arm according to the preset robot arm coordinates of the current identification feature and the robot arm coordinates of the current identification feature; The step of determining the offset of the robot arm according to the preset robot arm coordinates of the current identification feature and the robot arm coordinates of the current identification feature comprises: Determine an average translation deviation of the robot arm according to a plurality of preset robot arm coordinates of the current identification features and the robot arm coordinates of the current identification features; Respectively centering the plurality of current identification feature preset mechanical arm coordinates and the current identification feature mechanical arm coordinates to obtain preset centralized coordinates and current centralized coordinates; Constructing a covariance matrix according to the preset centered coordinates and the current centered coordinates; Performing singular value decomposition on the covariance matrix; Calculate the robot arm rotation deviation matrix according to the singular value decomposition result; Converting the robot arm rotation error matrix into the robot arm rotation Euler angle; The offset of the robotic arm is determined according to the average translation deviation of the robotic arm and the Euler angle of rotation of the robotic arm.

4. The device according to claim 3, characterized in that Also includes: A sending module is used to send a motion instruction to the robotic arm according to the offset of the robotic arm.

5. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the vehicle gluing positioning method as described in any one of claims 1 or 2 is implemented.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the vehicle gluing positioning method according to any one of claims 1 or 2 is implemented.

Images