A pose conversion method, apparatus, device, and storage medium

Abstract

This application provides a pose conversion method, apparatus, device, and storage medium, relating to the field of robotics. The specific implementation involves: acquiring the pose of an object to be grasped by a robotic arm in the camera coordinate system of a target camera, as the visual positioning pose; acquiring the corrected hand-eye calibration result and corrected DH parameters of the robotic arm; wherein the corrected hand-eye calibration result and corrected DH parameters are obtained by jointly correcting the pre-calibrated hand-eye calibration result and initial DH parameters based on the target image of the calibration board and the reprojection result of the calibration board projected onto the image plane of the target image; and performing pose conversion on the visual positioning pose based on the corrected hand-eye calibration result, corrected DH parameters, and the initial DH parameters to obtain the actual grasping pose of the object. Therefore, this solution can improve the grasping accuracy of the robotic arm.

Description

Technical Field

[0001] This application relates to the field of robotics, and in particular to a pose conversion method, apparatus, device, and storage medium. Background Technology

[0002] With the continuous improvement of industrial automation, the solution of using vision-guided robotic arms to perform object grasping has received widespread attention. Vision-guided robotic arm grasping involves using a camera to acquire the visual positioning and pose of the object to be grasped in the camera coordinate system. Based on the hand-eye calibration results obtained through calibration—that is, the transformation relationship from the camera coordinate system to the robotic arm's base coordinate system—the pose of the object to be grasped is transformed from the camera coordinate system to the base coordinate system. Then, the end effector of the robotic arm is controlled to move to the object's pose in the base coordinate system to perform the grasping action.

[0003] In practical applications, due to manufacturing errors in the robotic arm itself, or wear and tear from repeated use, the actual Denavit-Hartenberg (DH) parameters of the robotic arm may differ from the initial DH parameters at the factory. Since hand-eye calibration results are generated based on these initial DH parameters, the resulting object pose conversion using these calibration results leads to low grasping accuracy. The DH parameters are those in the Denavit-Hartenberg (DH) kinematic model, a method for representing robot kinematics and modeling coordinate systems proposed by Denavit and Hartenberg, which has become the standard method for kinematic modeling of robots.

[0004] Therefore, improving the grasping accuracy of robotic arms has become an urgent technical problem to be solved. Summary of the Invention

[0005] The purpose of this application is to provide a pose conversion method, apparatus, device, and storage medium to improve the grasping accuracy of a robotic arm. The specific technical solution is as follows:

[0006] In a first aspect, embodiments of this application provide a pose transformation method, the method comprising:

[0007] The pose of the object to be grasped by the robotic arm in the camera coordinate system of the target camera is obtained as the visual positioning pose.

[0008] The corrected hand-eye calibration result and corrected DH parameters of the robotic arm are obtained; wherein, the corrected hand-eye calibration result and corrected DH parameters are obtained by jointly correcting the pre-calibrated hand-eye calibration result and the initial DH parameters based on the target image of the calibration plate and the reprojection result of the image plane of the calibration plate projected onto the target image; the target image is the image captured by the target camera when the calibration plate is located at the end effector of the robotic arm;

[0009] Based on the corrected hand-eye calibration results, the corrected DH parameters, and the initial DH parameters, the visual positioning pose is transformed to obtain the actual grasping pose of the object.

[0010] Optionally, the method of jointly correcting the pre-calibrated hand-eye calibration results and the initial DH parameters based on the target image of the calibration board and the reprojection result of the calibration board projected onto the image plane of the target image includes:

[0011] For the reference point of the calibration board, a first expression for the reprojection coordinates of the reference point is constructed; wherein, the first expression is a function expression based on the hand-eye calibration result of the robotic arm and the DH parameter; the reprojection coordinates of the reference point are the reprojection result of the reference point projected onto the image plane of the target image;

[0012] Based on the error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression, the pre-calibrated hand-eye calibration results and the initial DH parameters are jointly corrected; wherein, the image coordinates corresponding to the reference point are the image coordinates of the reference point in the target image.

[0013] Optionally, the step of jointly correcting the pre-calibrated hand-eye calibration results and the initial DH parameters based on the error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression includes:

[0014] Based on the error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression, a joint optimization function is constructed; wherein, the joint optimization function is used to find the hand-eye calibration result of the robotic arm and the DH parameter when the error is minimized;

[0015] By adjusting the hand-eye calibration results and DH parameters contained in the first expression of the joint optimization function, the joint optimization function is solved to obtain the corrected hand-eye calibration results and DH parameters.

[0016] Wherein, the initial value of the hand-eye calibration result contained in the first expression is the pre-calibrated hand-eye calibration result.

[0017] Optionally, the step of performing pose transformation on the visual positioning pose based on the corrected hand-eye calibration results, the corrected DH parameters, and the initial DH parameters to obtain the actual grasping pose of the object includes:

[0018] Based on the corrected hand-eye calibration results, the visual positioning pose is converted into a grasping pose in the corrected base coordinate system; wherein, the corrected base coordinate system is the base coordinate system of the robotic arm under the corrected DH parameters;

[0019] Based on the corrected DH parameters, inverse kinematics calculation is performed on the grasping pose in the corrected base coordinate system to obtain the joint variables;

[0020] Based on the calculated joint variables and the initial DH parameters, the forward kinematics solution is calculated to obtain the actual grasping pose of the object.

[0021] Optionally, the first expression is:

[0022]

[0023] Where K is the intrinsic parameter of the target camera, and D is the distortion coefficient of the target camera; P board The reference point is defined as its physical coordinate in the calibration plate coordinate system of the calibration plate. is the transformation matrix from the calibration plate coordinate system to the end effector's end effector coordinate system; g() is the forward kinematics function, L is the link length parameter of the robotic arm, and θ is the zero-position offset of the robotic arm. The joint angle of the robotic arm; The hand-eye calibration results for the robotic arm.

[0024] Optionally, the joint optimization function is:

[0025]

[0026] Wherein, the reference point takes the value i = 1…n, where n is a positive integer; uv is the image coordinate corresponding to the reference point; K is the intrinsic parameter of the target camera, and D is the distortion coefficient of the target camera; P board The reference point is defined as the physical coordinate of the calibration plate in the calibration plate coordinate system. is the transformation matrix from the calibration plate coordinate system to the end effector's end effector coordinate system; g() is the forward kinematics function, L is the link length parameter of the robotic arm, and θ is the zero-position offset of the robotic arm. The joint angle of the robotic arm; The hand-eye calibration results for the robotic arm.

[0027] Secondly, embodiments of this application provide a pose conversion device, the device comprising:

[0028] The first acquisition module is used to acquire the pose of the object to be grasped by the robotic arm in the camera coordinate system of the target camera, as the visual positioning pose.

[0029] The second acquisition module is used to acquire the corrected hand-eye calibration results and corrected DH parameters of the robotic arm; wherein, the corrected hand-eye calibration results and corrected DH parameters are obtained by jointly correcting the pre-calibrated hand-eye calibration results and the initial DH parameters based on the target image of the calibration plate and the reprojection result of the calibration plate projected onto the image plane of the target image; the target image is the image captured by the target camera when the calibration plate is located at the end effector of the robotic arm;

[0030] The pose conversion module is used to convert the visual positioning pose based on the corrected hand-eye calibration results, the corrected DH parameters, and the initial DH parameters, so as to obtain the actual grasping pose of the object.

[0031] Optionally, the method of jointly correcting the pre-calibrated hand-eye calibration results and the initial DH parameters based on the target image of the calibration board and the reprojection result of the calibration board projected onto the image plane of the target image includes:

[0032] For the reference point of the calibration board, a first expression for the reprojection coordinates of the reference point is constructed; wherein, the first expression is a function expression based on the hand-eye calibration result of the robotic arm and the DH parameter; the reprojection coordinates of the reference point are the reprojection result of the reference point projected onto the image plane of the target image;

[0033] Based on the error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression, the pre-calibrated hand-eye calibration results and the initial DH parameters are jointly corrected; wherein, the image coordinates corresponding to the reference point are the image coordinates of the reference point in the target image.

[0034] Optionally, the step of jointly correcting the pre-calibrated hand-eye calibration results and the initial DH parameters based on the error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression includes:

[0035] Based on the error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression, a joint optimization function is constructed; wherein, the joint optimization function is used to find the hand-eye calibration result of the robotic arm and the DH parameter when the error is minimized;

[0036] By adjusting the hand-eye calibration results and DH parameters contained in the first expression of the joint optimization function, the joint optimization function is solved to obtain the corrected hand-eye calibration results and DH parameters.

[0037] Wherein, the initial value of the hand-eye calibration result contained in the first expression is the pre-calibrated hand-eye calibration result.

[0038] Optionally, the pose conversion module includes:

[0039] The conversion submodule is used to convert the visual positioning pose into a grasping pose in a modified base coordinate system based on the modified hand-eye calibration results; wherein, the modified base coordinate system is the base coordinate system of the robotic arm under the modified DH parameters;

[0040] The inverse kinematics submodule is used to perform inverse kinematics calculations on the grasping pose in the modified base coordinate system based on the modified DH parameters, and to obtain the joint variables.

[0041] The forward kinematics submodule is used to perform forward kinematics calculations based on the calculated joint variables and the initial DH parameters to obtain the actual grasping pose of the object.

[0042] Optionally, the first expression is:

[0043]

[0044] Where K is the intrinsic parameter of the target camera, and D is the distortion coefficient of the target camera; P board The reference point is defined as the physical coordinate of the calibration plate in the calibration plate coordinate system. is the transformation matrix from the calibration plate coordinate system to the end effector's end effector coordinate system; g() is the forward kinematics function, L is the link length parameter of the robotic arm, and θ is the zero-position offset of the robotic arm. The joint angle of the robotic arm; The hand-eye calibration results for the robotic arm.

[0045] Optionally, the joint optimization function is:

[0046]

[0047] Wherein, the reference point takes the value i = 1…n, where n is a positive integer; uv is the image coordinate corresponding to the reference point; K is the intrinsic parameter of the target camera, and D is the distortion coefficient of the target camera; P board The reference point is defined as the physical coordinate of the calibration plate in the calibration plate coordinate system. is the transformation matrix from the calibration plate coordinate system to the end effector's end effector coordinate system; g() is the forward kinematics function, L is the link length parameter of the robotic arm, and θ is the zero-position offset of the robotic arm. The joint angle of the robotic arm; The hand-eye calibration results for the robotic arm.

[0048] Thirdly, embodiments of this application provide an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0049] Memory, used to store computer programs;

[0050] When a processor executes a program stored in memory, it implements the steps of any of the pose conversion methods described above.

[0051] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of any of the pose conversion methods described above.

[0052] Beneficial effects of the embodiments in this application:

[0053] The solution provided in this application, because the corrected hand-eye calibration results and the corrected DH parameters are obtained by jointly correcting the pre-calibrated hand-eye calibration results and the initial DH parameters using the target image of the calibration board and the reprojection result of the image plane of the calibration board projected onto the target image, provides a more accurate set of DH parameters for the robotic arm. Based on the DH parameters before and after correction and the corrected hand-eye calibration results, pose transformation is performed on the visual positioning pose of the object to be grasped. This effectively improves the grasping accuracy even when the absolute accuracy of the robotic arm itself is insufficient, without modifying the current DH parameters of the robotic arm. Therefore, this solution can improve the grasping accuracy of the robotic arm.

[0054] Of course, implementing any product or method of this application does not necessarily require achieving all of the advantages described above at the same time. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other embodiments can be obtained based on these drawings.

[0056] Figure 1 A flowchart illustrating a pose conversion method provided in an embodiment of this application;

[0057] Figure 2 The flowchart illustrates step S103 in the pose conversion method provided in this application embodiment;

[0058] Figure 3 The flowchart illustrates step S102 in the pose conversion method provided in this application embodiment;

[0059] Figure 4 A flowchart illustrating a specific example of the pose conversion method provided in an embodiment of this application;

[0060] Figure 5 This is a schematic diagram of the structure of a pose conversion device provided in an embodiment of this application;

[0061] Figure 6 A block diagram of an electronic device for implementing the pose conversion method provided in the embodiments of this application. Detailed Implementation

[0062] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art based on this application are within the scope of protection of this application.

[0063] Below, we will first introduce a pose conversion method provided by an embodiment of this application.

[0064] The pose conversion method provided in this application can be applied to various electronic devices, such as personal computers, servers, and other devices with data processing capabilities. Furthermore, it is understood that the pose conversion method provided in this application can be implemented through software, hardware, or a combination of both.

[0065] The pose conversion method provided in this application embodiment may include the following steps:

[0066] The pose of the object to be grasped by the robotic arm in the camera coordinate system of the target camera is obtained as the visual positioning pose.

[0067] The corrected hand-eye calibration result and corrected DH parameters of the robotic arm are obtained; wherein, the corrected hand-eye calibration result and corrected DH parameters are obtained by jointly correcting the pre-calibrated hand-eye calibration result and the initial DH parameters based on the target image of the calibration plate and the reprojection result of the image plane of the calibration plate projected onto the target image; the target image is the image captured by the target camera when the calibration plate is located at the end effector of the robotic arm;

[0068] Based on the corrected hand-eye calibration results, the corrected DH parameters, and the initial DH parameters, the visual positioning pose is transformed to obtain the actual grasping pose of the object.

[0069] The solution provided in this application, because the corrected hand-eye calibration results and the corrected DH parameters are obtained by jointly correcting the pre-calibrated hand-eye calibration results and the initial DH parameters using the target image of the calibration board and the reprojection result of the image plane of the calibration board projected onto the target image, provides a more accurate set of DH parameters for the robotic arm. Based on the DH parameters before and after correction and the corrected hand-eye calibration results, pose transformation is performed on the visual positioning pose of the object to be grasped. This effectively improves the grasping accuracy even when the absolute accuracy of the robotic arm itself is insufficient, without modifying the current DH parameters of the robotic arm. Therefore, this solution can improve the grasping accuracy of the robotic arm.

[0070] The pose conversion method provided in the embodiments of this application will be described below with reference to the accompanying drawings.

[0071] like Figure 1 As shown, the pose conversion method provided in this application embodiment may include steps S101-S103:

[0072] S101, Obtain the pose of the object to be grasped by the robotic arm in the camera coordinate system of the target camera, as the visual positioning pose;

[0073] In this embodiment, the target camera is a camera associated with the robotic arm. The robotic arm grasps objects by combining the visual positioning provided by the target camera. For example, the target camera can be mounted on the end of the robotic arm or fixed to a base outside the robotic arm; both are reasonable. It should be noted that different mounting methods of the target camera will result in different calculation formulas for subsequent pose conversion. Therefore, for clarity, this embodiment uses the mounting method of the target camera on a fixed base outside the robotic arm as an example to describe the pose conversion method provided in this embodiment.

[0074] In practical applications, the target camera acquires images of the object to be captured, thereby obtaining the pose of the object in the camera coordinate system. In other words, the target camera is an intelligent camera with built-in pose calculation capabilities. It can process the acquired images of the object, including grayscale conversion, edge detection, and contour extraction, extracting features of the object to be captured, such as corners and edges. Then, using the extracted features, it calculates the position and orientation of the object in the camera coordinate system, thus obtaining the object's pose in that coordinate system.

[0075] S102, Obtain the corrected hand-eye calibration result and corrected DH parameters of the robotic arm; wherein, the corrected hand-eye calibration result and corrected DH parameters are obtained by jointly correcting the pre-calibrated hand-eye calibration result and the initial DH parameters based on the target image of the calibration plate and the reprojection result of the image plane of the calibration plate projected onto the target image; the target image is the image captured by the target camera when the calibration plate is located at the end effector of the robotic arm;

[0076] Understandably, when using a robotic arm in conjunction with vision-based pose positioning for grasping, the pose of the object to be grasped in the camera coordinate system, obtained from the target camera, cannot be used directly. It is necessary to transform the pose of the object in the camera coordinate system to the pose in the robotic arm's base coordinate system, so that the end effector can move to the pose of the object in that base coordinate system to grasp it.

[0077] In practical applications, by utilizing the hand-eye calibration results obtained from the robotic arm, the pose of the object to be grasped can be transformed from the camera coordinate system to the base coordinate system, that is, the visual positioning pose of the object to be grasped is converted into the actual grasping pose. However, due to manufacturing errors of the robotic arm itself, or wear and tear due to increased use, the actual DH parameters of the robotic arm may differ from the initial DH parameters at the factory. Since the hand-eye calibration results are generated based on the initial DH parameters, the grasping accuracy after converting the object's pose using the hand-eye calibration results is ultimately not high. Therefore, before performing pose conversion, the corrected hand-eye calibration results and corrected DH parameters of the robotic arm can be obtained first. These corrected DH parameters are the actual DH parameters of the robotic arm. It should be noted that the DH parameters of the robotic arm can include the link length, joint axis, joint angle zero offset, etc.

[0078] In this embodiment, the corrected hand-eye calibration result and the corrected DH parameters are obtained by jointly correcting the pre-calibrated hand-eye calibration result and the initial DH parameters based on the target image of the calibration board and the reprojection result of the image plane of the calibration board projected onto the target image.

[0079] In practical applications, the end effector of the robotic arm can be controlled to move a calibration plate to a spatial point, and then a target camera can capture an image of the calibration plate as the target image. It is understood that if the actual DH parameters of the robotic arm are the same as the initial DH parameters at the factory, then the reprojection result of the calibration plate onto the image plane of the target image will be the same as the calibration plate in the target image. Therefore, by using the constraint that the reprojection result of the calibration plate is the same as the calibration plate in the target image, the pre-calibrated hand-eye calibration results and the initial DH parameters can be jointly corrected to obtain the corrected hand-eye calibration results and corrected DH parameters of the robotic arm.

[0080] The initial DH parameters can be obtained from the robot arm's factory parameters. The calibration method for this pre-calibrated hand-eye calibration result may include steps A1-A3:

[0081] A1. Acquire an image of the robotic arm's end effector carrying the calibration plate moving to a target spatial point within the workspace, and record the pose of the end effector as the end effector pose; wherein, there are multiple target spatial points; the end effector pose is represented by a transformation matrix.

[0082] A2. For each target spatial point, based on the acquired image of the calibration board, determine the calibration board pose in the camera coordinate system.

[0083] A3. Based on the calibration board pose and end-effector pose corresponding to any two images, construct the homogeneous equation AX = XB.

[0084] Where A is the transformation matrix between the poses of the calibration board corresponding to two target spatial points i and j, which can be expressed by the formula: in, Let j be the pose of the calibration plate in the camera coordinate system corresponding to the target space point j. Let be the camera pose in the coordinate system of the calibration board corresponding to target space point i; B is the transformation matrix between the end poses corresponding to the two target space points i and j, which can be expressed by the formula: in, Let j be the end effector pose in the base coordinate system corresponding to the target space point j. X represents the pose of the robot arm's base in the end-effector coordinate system corresponding to point i in the target space; X represents the hand-eye calibration result, i.e., the pose transformation relationship from the base coordinate system to the camera coordinate system. The hand-eye calibration result can be obtained by solving the system of equations.

[0085] In practical applications, a homogeneous equation AX = XB can be constructed from every two images. This allows us to solve a system of homogeneous equations to obtain X.

[0086] Additionally, it should be noted that, for the sake of clarity in the scheme layout, the method of this joint modification will be introduced in the following text, and will not be repeated here.

[0087] S103, based on the corrected hand-eye calibration results and the corrected DH parameters, as well as the initial DH parameters, perform pose transformation on the visual positioning pose to obtain the actual grasping pose of the object.

[0088] Understandably, after obtaining the corrected hand-eye calibration results and the corrected DH parameters of the robotic arm, considering that users often do not have the authority to adjust the DH parameters of the robotic arm based on the corrected DH parameters, in the case that the DH parameters of the robotic arm cannot be modified, the visual positioning pose can still be transformed based on the corrected hand-eye calibration results and the corrected DH parameters, combined with the initial DH parameters.

[0089] Alternatively, in one implementation, such as Figure 2 As shown, based on the corrected hand-eye calibration results and the corrected DH parameters, as well as the initial DH parameters, the visual positioning pose is transformed to obtain the actual grasping pose of the object, which may include steps S1031-S1033:

[0090] S1031, Based on the corrected hand-eye calibration result, the visual positioning pose is converted into a grasping pose in the corrected base coordinate system; wherein, the corrected base coordinate system is the base coordinate system of the robotic arm under the corrected DH parameters;

[0091] Since the hand-eye calibration result represents the transformation relationship from the camera coordinate system to the robot arm's base coordinate system, and the visual positioning pose is the pose of the object to be grasped in the camera coordinate system, the visual positioning pose can be converted into the grasping pose in the corrected base coordinate system by multiplying the visual positioning pose with the corrected hand-eye calibration result.

[0092] S1032, Based on the corrected DH parameters, the inverse kinematics of the grasping pose in the corrected base coordinate system is calculated to obtain the joint variables;

[0093] Understandably, since inverse kinematics calculation involves calculating joint variables based on the end effector's end-effector pose, and the corrected grasping pose in the base coordinate system is the end-effector pose the robotic arm needs to move to when grasping an object under the corrected DH parameters, inverse kinematics calculation can be performed on the corrected grasping pose in the base coordinate system based on the corrected DH parameters to obtain the joint variables. These joint variables include joint angles.

[0094] S1033, based on the calculated joint variables and the initial DH parameters, perform forward kinematics calculation to obtain the actual grasping pose of the object.

[0095] It is understandable that the corrected hand-eye calibration results and corrected DH parameters are obtained by optimizing the pre-calibrated hand-eye calibration results and initial DH parameters based on the constraint that the reprojection result of the calibration board is the same as that of the calibration board in the target image. Therefore, the joint variables calculated based on the corrected hand-eye calibration results and corrected DH parameters are the actual joint variables of each joint in the grasping pose that the end effector needs to move to when the robotic arm grasps the object. Therefore, compared with directly using the pre-calibrated hand-eye calibration results to perform pose transformation of the visual positioning pose, this embodiment obtains a higher accuracy in the actual grasping pose of the object by performing forward kinematics on the joint variables and the initial DH parameters. Thus, controlling the end effector of the robotic arm to grasp the object based on the actual grasping pose calculated by the forward kinematics can improve the grasping accuracy of the robotic arm.

[0096] The solution provided in this application, because the corrected hand-eye calibration results and the corrected DH parameters are obtained by jointly correcting the pre-calibrated hand-eye calibration results and the initial DH parameters using the target image of the calibration board and the reprojection result of the image plane of the calibration board projected onto the target image, provides a more accurate set of DH parameters for the robotic arm. Based on the DH parameters before and after correction and the corrected hand-eye calibration results, pose transformation is performed on the visual positioning pose of the object to be grasped. This effectively improves the grasping accuracy even when the absolute accuracy of the robotic arm itself is insufficient, without modifying the current DH parameters of the robotic arm. Therefore, this solution can improve the grasping accuracy of the robotic arm.

[0097] Alternatively, in another embodiment of this application, such as Figure 3 As shown, in step S102 above, the method of jointly correcting the pre-calibrated hand-eye calibration result and the initial DH parameters based on the target image of the calibration board and the reprojection result of the calibration board projected onto the image plane of the target image may include steps S1021-S1022:

[0098] S1021, For the reference point of the calibration plate, construct a first expression for the reprojection coordinates of the reference point; wherein, the first expression is a function expression based on the hand-eye calibration result of the robotic arm and the DH parameter; the reprojection coordinates of the reference point are the reprojection result of the reference point projected onto the image plane of the target image;

[0099] For example, the calibration board can be a chessboard calibration board, a circular calibration board, etc. If the calibration board is a chessboard calibration board, the reference point can be a corner point in the calibration board; if the calibration board is a circular calibration board, the reference point can be the center of the circle in the calibration board.

[0100] For example, in one implementation, the first expression could be:

[0101]

[0102] Where K is the intrinsic parameter of the target camera, and D is the distortion coefficient of the target camera; P board The physical coordinates of this reference point in the calibration plate coordinate system of this calibration plate. is the transformation matrix from the calibration plate coordinate system to the end effector's end effector coordinate system; g() is the forward kinematics function, L is the link length parameter of the robotic arm, and θ is the zero-position offset of the robotic arm. This refers to the joint angle of the robotic arm; The hand-eye calibration results for this robotic arm.

[0103] It is understandable that the hand-eye calibration result is a transformation matrix from the base coordinate system to the camera coordinate system, and through... By calculating the forward kinematics, the end effector pose of the robotic arm can be obtained, that is, the pose of the end effector in the base coordinate system. Therefore, through this first expression, the physical coordinates of the reference point in the calibration plate coordinate system of the calibration plate, the end coordinate system, the base coordinate system, the camera coordinate system, and the image plane can be transformed to the coordinates in the image plane of the target image according to the transfer relationship between the calibration plate coordinate system, the end coordinate system, the base coordinate system, the camera coordinate system, and the image plane, thereby obtaining the reprojection coordinates of the reference point.

[0104] S1022, based on the error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression, the pre-calibrated hand-eye calibration results and the initial DH parameters are jointly corrected; wherein, the image coordinates corresponding to the reference point are the image coordinates of the reference point in the target image.

[0105] In this embodiment, the pre-calibrated hand-eye calibration result and the initial DH parameters can be jointly corrected by minimizing the error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression.

[0106] Optionally, in one implementation, based on the error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression, the pre-calibrated hand-eye calibration result and the initial DH parameters are jointly corrected, which may include steps B1-B2:

[0107] B1, based on the error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression, a joint optimization function is constructed; wherein, the joint optimization function is used to find the hand-eye calibration result of the robotic arm and the DH parameter when the error is minimized;

[0108] For example, in one specific implementation, the joint optimization function is:

[0109]

[0110] Wherein, the value of the reference point is i = 1…n, where n is a positive integer; uv is the image coordinate corresponding to the reference point; K is the intrinsic parameter of the target camera; D is the distortion coefficient of the target camera; P board The physical coordinates of this reference point in the calibration plate coordinate system of this calibration plate. is the transformation matrix from the calibration plate coordinate system to the end effector's end effector coordinate system; g() is the forward kinematics function, L is the link length parameter of the robotic arm, and θ is the zero-position offset of the robotic arm. This refers to the joint angle of the robotic arm; The hand-eye calibration results for this robotic arm.

[0111] B2, by adjusting the hand-eye calibration results and DH parameters contained in the first expression of the joint optimization function, the joint optimization function is solved to obtain the corrected hand-eye calibration results and the corrected DH parameters;

[0112] The initial value of the hand-eye calibration result contained in the first expression is the pre-calibrated hand-eye calibration result.

[0113] In this embodiment, the pre-calibrated hand-eye calibration result can be used as the initial value of the hand-eye calibration result included in the first expression. The hand-eye calibration result is then adjusted based on this initial value to find the values ​​of the hand-eye calibration result and DH parameters that minimize the joint optimization function. These values ​​are then used as the corrected hand-eye calibration result and the corrected DH parameters. For example, in practical applications, algorithms such as the Levenberg-Marquardt (Levenberg-Marquardt, iterative extremum) method, gradient descent method, and Newton's method can be used to solve the joint optimization function to obtain the corrected hand-eye calibration result and the corrected DH parameters.

[0114] As can be seen, this scheme can be used to jointly optimize the hand-eye calibration results and DH parameters.

[0115] To better understand the pose transformation method provided in this application, a specific example will be used to introduce the content of this application below.

[0116] In high-precision workpiece gripping applications, gripping accuracy within 0.5mm is required, which places high demands on both visual positioning and the absolute accuracy of industrial robots. However, in practical applications, due to the machining errors of the robotic arm itself, or wear and tear as the robotic arm is used more, its absolute accuracy may not be able to meet the requirements of high-precision gripping.

[0117] To address the issue of large grasping errors caused by insufficient absolute precision of robotic arms, this example proposes a pose transformation method. First, the robotic arm is controlled to rotate and translate within the grasping space, acquiring images of multiple calibration plates and recording the joint variables of the robotic arm. The poses of the calibration plates in the camera coordinate system and the end effector are calculated separately, and then the initial values ​​of the hand-eye calibration results are calculated. Next, the initial values ​​of the hand-eye calibration results and the DH parameters of the robotic arm are jointly optimized to obtain the corrected hand-eye calibration results and DH parameters. Finally, the pose transformation is achieved by combining the corrected hand-eye calibration results, the original robotic arm parameters, and the corrected DH parameters. This example can obtain the pose transformation relationship from the camera to the robotic arm during the hand-eye calibration process and correct the robotic arm's own DH parameters. Then, pose transformation is performed based on the corrected and original DH parameters of the robotic arm, which can effectively improve grasping accuracy and significantly enhance practicality compared to existing solutions.

[0118] like Figure 4 As shown, the specific steps in this example include S401-S405:

[0119] S401 controls the rotation and translation of the robotic arm to acquire images of the calibration plate and record the joint variables of the robotic arm;

[0120] The robotic arm is controlled to carry the calibration plate and translate and rotate within the grasping space. At each point in the space, the camera (corresponding to the target camera mentioned above) is controlled to capture images of the calibration plate and record the joint variables of the robotic arm in the current pose, such as the joint angles of each joint.

[0121] S402, calculate the pose of the calibration plate in the camera coordinate system and the end effector pose of the robotic arm;

[0122] Extract the calibration board feature points (corresponding to the reference points mentioned above) from the image, calculate the pose of each calibration board in the camera coordinate system based on the physical dimensions of the calibration board, and represent it using a transformation matrix. By performing forward kinematics on the robotic arm's own DH parameters, the end effector pose of the calibration plate is obtained, which can be represented by a transformation matrix.

[0123] S403, construct the homogeneous matrix equation system AX=XB, and calculate the initial values ​​of the hand-eye calibration results;

[0124] Based on the calibration board pose and end effector pose corresponding to any two images, construct a system of homogeneous matrix equations AX = XB, where i and j represent any two spatial points; X represents the pose transformation relationship from the robotic arm to the camera, that is, the transformation relationship from the robotic arm's base coordinate system to the camera's coordinate system, expressed by a transformation matrix. Then solve AX = XB to obtain the initial values ​​of the hand-eye calibration results.

[0125] S404, construct a reprojection error function that includes hand-eye calibration results and DH parameters of the robotic arm, and jointly optimize the hand-eye calibration results and DH parameters;

[0126] The hand-eye calibration results and DH parameters are used as variables for joint optimization. The known constraints in the calibration system are the spatial physical coordinates of feature points in the calibration board and the camera intrinsic parameters. A reprojection error function for feature points in the calibration board image is constructed using the path "calibration board -> end effector -> camera -> image plane". The hand-eye calibration results and DH parameters are iteratively solved using a nonlinear optimization method to obtain the corrected hand-eye calibration results and corrected DH parameters. The reprojection error function e is expressed as:

[0127]

[0128] In the formula, uv represents the image coordinates corresponding to the feature points in the calibration plate, K is the intrinsic parameter of the camera, and D is the distortion coefficient of the camera; P board These are the physical coordinates of the feature point in the calibration plate coordinate system of the calibration plate. This is the transformation matrix from the coordinate system of the calibration plate to the coordinate system of the end effector. This is the transformation matrix from the end-effector coordinate system to the robot arm's base coordinate system; This is the transformation matrix from the base coordinate system to the camera coordinate system, representing the hand-eye calibration result of the robotic arm. Wherein, The forward kinematics solution of the robotic arm is used to obtain the DH parameters involved in the kinematics solution, including the link length L, the zero-position offset θ, and the joint angles of each axis. The kinematic formula can be expressed as:

[0129]

[0130] Therefore, the objective function for joint optimization (corresponding to the joint optimization function mentioned above) is constructed as follows:

[0131]

[0132] Among them, the parameters to be optimized are the camera intrinsic parameters K and D, and the hand-eye calibration results. DH parameters L and θ, transformation matrix from calibration plate coordinate system to end coordinate system The known physical quantities include the physical coordinates P of the feature points in the calibration plate. board Joint angles in each pose The image coordinates uv of the feature points in the calibration board. The values ​​of each feature point in the calibration board are i = 1…n, where n is a positive integer. The objective function constructed above is a typical nonlinear optimization problem, which can be solved using algorithms such as the LM method, gradient descent method, and Newton's method.

[0133] S405 performs grasping pose conversion based on the corrected hand-eye calibration results, the original DH parameters, and the corrected DH parameters.

[0134] After hand-eye calibration using this method, corrected hand-eye calibration results and corrected DH parameters are obtained. To achieve high-precision grasping, it is necessary to combine the original DH parameters with the corrected parameters for grasping pose transformation. This involves determining the visual positioning pose of the object to be grasped. First, transform the corrected hand-eye calibration results to the corrected base coordinate system. Then, inverse kinematics is performed based on the corrected DH parameters to obtain the joint variables; finally, forward kinematics is performed using the original DH parameters to obtain the actual grasping pose.

[0135] As can be seen, this solution can obtain both the pose transformation relationship between the camera and the robotic arm and the corrected DH parameters of the robotic arm during the hand-eye calibration process. By performing pose transformation of the object to be grasped based on the DH parameters before and after correction and the hand-eye calibration results, the grasping accuracy can be effectively improved without modifying the current DH parameters of the robotic arm, even when the absolute accuracy of the robotic arm itself is insufficient. Furthermore, it can significantly improve the ease of use in the application process compared to existing solutions.

[0136] Based on the above method embodiments, this application also provides a pose conversion device, such as... Figure 5 As shown, the device includes:

[0137] The first acquisition module 510 is used to acquire the pose of the object to be grasped by the robotic arm in the camera coordinate system of the target camera, as the visual positioning pose.

[0138] The second acquisition module 520 is used to acquire the corrected hand-eye calibration results and corrected DH parameters of the robotic arm; wherein, the corrected hand-eye calibration results and corrected DH parameters are obtained by jointly correcting the pre-calibrated hand-eye calibration results and the initial DH parameters based on the target image of the calibration plate and the reprojection result of the calibration plate projected onto the image plane of the target image; the target image is the image captured by the target camera when the calibration plate is located at the end effector of the robotic arm;

[0139] The pose conversion module 530 is used to convert the visual positioning pose based on the corrected hand-eye calibration results, the corrected DH parameters, and the initial DH parameters, so as to obtain the actual grasping pose of the object.

[0140] Optionally, the method of jointly correcting the pre-calibrated hand-eye calibration results and the initial DH parameters based on the target image of the calibration board and the reprojection result of the calibration board projected onto the image plane of the target image includes:

[0141] For the reference point of the calibration board, a first expression for the reprojection coordinates of the reference point is constructed; wherein, the first expression is a function expression based on the hand-eye calibration result of the robotic arm and the DH parameter; the reprojection coordinates of the reference point are the reprojection result of the reference point projected onto the image plane of the target image;

[0142] Based on the error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression, the pre-calibrated hand-eye calibration results and the initial DH parameters are jointly corrected; wherein, the image coordinates corresponding to the reference point are the image coordinates of the reference point in the target image.

[0143] Optionally, the step of jointly correcting the pre-calibrated hand-eye calibration results and the initial DH parameters based on the error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression includes:

[0144] Based on the error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression, a joint optimization function is constructed; wherein, the joint optimization function is used to find the hand-eye calibration result of the robotic arm and the DH parameter when the error is minimized;

[0145] By adjusting the hand-eye calibration results and DH parameters contained in the first expression of the joint optimization function, the joint optimization function is solved to obtain the corrected hand-eye calibration results and DH parameters.

[0146] Wherein, the initial value of the hand-eye calibration result contained in the first expression is the pre-calibrated hand-eye calibration result.

[0147] Optionally, the pose conversion module includes:

[0148] The conversion submodule is used to convert the visual positioning pose into a grasping pose in a modified base coordinate system based on the modified hand-eye calibration results; wherein, the modified base coordinate system is the base coordinate system of the robotic arm under the modified DH parameters;

[0149] The inverse kinematics submodule is used to perform inverse kinematics calculations on the grasping pose in the modified base coordinate system based on the modified DH parameters, and to obtain the joint variables.

[0150] The forward kinematics submodule is used to perform forward kinematics calculations based on the calculated joint variables and the initial DH parameters to obtain the actual grasping pose of the object.

[0151] Optionally, the first expression is:

[0152]

[0153] Where K is the intrinsic parameter of the target camera, and D is the distortion coefficient of the target camera; P board The reference point is defined as the physical coordinate of the calibration plate in the calibration plate coordinate system. is the transformation matrix from the calibration plate coordinate system to the end effector's end effector coordinate system; g() is the forward kinematics function, L is the link length parameter of the robotic arm, and θ is the zero-position offset of the robotic arm. The joint angle of the robotic arm; The hand-eye calibration results for the robotic arm.

[0154] Optionally, the joint optimization function is:

[0155]

[0156] Wherein, the reference point takes the value i = 1…n, where n is a positive integer; uv is the image coordinate corresponding to the reference point; K is the intrinsic parameter of the target camera, and D is the distortion coefficient of the target camera; P board The reference point is defined as the physical coordinate of the calibration plate in the calibration plate coordinate system. is the transformation matrix from the calibration plate coordinate system to the end effector's end effector coordinate system; g() is the forward kinematics function, L is the link length parameter of the robotic arm, and θ is the zero-position offset of the robotic arm. The joint angle of the robotic arm; The hand-eye calibration results for the robotic arm.

[0157] In the technical solution of this application, the operations of obtaining, storing, using, processing, transmitting, providing and disclosing user personal information are all carried out with the user's authorization.

[0158] This application also provides an electronic device, such as... Figure 6 As shown, it includes:

[0159] Memory 601 is used to store computer programs;

[0160] The processor 602, when executing the program stored in the memory 601, implements any of the pose conversion methods described above.

[0161] Furthermore, the aforementioned electronic device may also include a communication bus and / or a communication interface, with the processor 602, the communication interface, and the memory 601 communicating with each other via the communication bus.

[0162] The communication bus mentioned in the above electronic devices can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0163] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0164] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0165] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0166] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores a computer program that, when executed by a processor, implements the steps of any of the above pose conversion methods.

[0167] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to perform any of the pose conversion methods described above.

[0168] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a solid-state drive (SSD), etc.

[0169] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0170] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the apparatus embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0171] The above description is merely a preferred embodiment of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application are included within the scope of protection of this application.

Claims

1. A pose transformation method, characterized in that, The method includes: The pose of the object to be grasped by the robotic arm in the camera coordinate system of the target camera is obtained as the visual positioning pose. The corrected hand-eye calibration result and corrected DH parameters of the robotic arm are obtained; wherein, the corrected hand-eye calibration result and corrected DH parameters are obtained by jointly correcting the pre-calibrated hand-eye calibration result and the initial DH parameters based on the target image of the calibration plate and the reprojection result of the image plane of the calibration plate projected onto the target image; the target image is the image captured by the target camera when the calibration plate is located at the end effector of the robotic arm; Based on the corrected hand-eye calibration results, the visual positioning pose is converted into a grasping pose in the corrected base coordinate system; wherein, the corrected base coordinate system is the base coordinate system of the robotic arm under the corrected DH parameters; Based on the corrected DH parameters, inverse kinematics calculation is performed on the grasping pose in the corrected base coordinate system to obtain the joint variables; Based on the calculated joint variables and the initial DH parameters, the forward kinematics solution is calculated to obtain the actual grasping pose of the object.

2. The method according to claim 1, characterized in that, The method of jointly correcting the pre-calibrated hand-eye calibration results and the initial DH parameters based on the target image of the calibration board and the reprojection result of the calibration board onto the image plane of the target image includes: For the reference point of the calibration board, a first expression for the reprojection coordinates of the reference point is constructed; wherein, the first expression is a function expression based on the hand-eye calibration result of the robotic arm and the DH parameter; the reprojection coordinates of the reference point are the reprojection result of the reference point projected onto the image plane of the target image; Based on the error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression, the pre-calibrated hand-eye calibration results and the initial DH parameters are jointly corrected; wherein, the image coordinates corresponding to the reference point are the image coordinates of the reference point in the target image.

3. The method according to claim 2, characterized in that, The error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression is used to jointly correct the pre-calibrated hand-eye calibration results and the initial DH parameters, including: Based on the error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression, a joint optimization function is constructed; wherein, the joint optimization function is used to find the hand-eye calibration result of the robotic arm and the DH parameter when the error is minimized; By adjusting the hand-eye calibration results and DH parameters contained in the first expression of the joint optimization function, the joint optimization function is solved to obtain the corrected hand-eye calibration results and DH parameters. Wherein, the initial value of the hand-eye calibration result contained in the first expression is the pre-calibrated hand-eye calibration result.

4. The method according to claim 2, characterized in that, The first expression is: ； Wherein, K is the intrinsic parameter of the target camera, and D is the distortion coefficient of the target camera; The reference point is defined as the physical coordinate of the calibration plate in the calibration plate coordinate system. The transformation matrix from the calibration plate coordinate system to the end effector coordinate system; Let L be the forward kinematics function, and L be the lever length parameter of the robotic arm. This is the zero-position offset of the robotic arm. The joint angle of the robotic arm; The hand-eye calibration results for the robotic arm.

5. The method according to claim 3, characterized in that, The joint optimization function is: ； Wherein, the value of the reference point is i=1…n, where n is a positive integer; uv is the image coordinate corresponding to the reference point; K is the intrinsic parameter of the target camera; and D is the distortion coefficient of the target camera. The reference point is defined as the physical coordinate of the calibration plate in the calibration plate coordinate system. The transformation matrix from the calibration plate coordinate system to the end effector coordinate system; Let L be the forward kinematics function, and L be the lever length parameter of the robotic arm. This is the zero-position offset of the robotic arm. The joint angle of the robotic arm; The hand-eye calibration results for the robotic arm.

6. A pose conversion device, characterized in that, The device includes: The first acquisition module is used to acquire the pose of the object to be grasped by the robotic arm in the camera coordinate system of the target camera, as the visual positioning pose. The second acquisition module is used to acquire the corrected hand-eye calibration results and corrected DH parameters of the robotic arm; wherein, the corrected hand-eye calibration results and corrected DH parameters are obtained by jointly correcting the pre-calibrated hand-eye calibration results and the initial DH parameters based on the target image of the calibration plate and the reprojection result of the calibration plate projected onto the image plane of the target image; the target image is the image captured by the target camera when the calibration plate is located at the end effector of the robotic arm; The pose conversion module is used to convert the visual positioning pose into a grasping pose in a corrected base coordinate system based on the corrected hand-eye calibration results; to perform inverse kinematics calculation on the grasping pose in the corrected base coordinate system based on the corrected DH parameters to obtain the joint variables; and to perform forward kinematics calculation based on the calculated joint variables and the initial DH parameters to obtain the actual grasping pose of the object; wherein, the corrected base coordinate system is the base coordinate system of the robotic arm under the corrected DH parameters.

7. The apparatus according to claim 6, characterized in that, The method of jointly correcting the pre-calibrated hand-eye calibration results and the initial DH parameters based on the target image of the calibration board and the reprojection result of the calibration board onto the image plane of the target image includes: For the reference point of the calibration board, a first expression for the reprojection coordinates of the reference point is constructed; wherein, the first expression is a function expression based on the hand-eye calibration result of the robotic arm and the DH parameter; the reprojection coordinates of the reference point are the reprojection result of the reference point projected onto the image plane of the target image; Based on the error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression, the pre-calibrated hand-eye calibration results and the initial DH parameters are jointly corrected; wherein, the image coordinates corresponding to the reference point are the image coordinates of the reference point in the target image.

8. The apparatus according to claim 7, characterized in that, The error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression is used to jointly correct the pre-calibrated hand-eye calibration results and the initial DH parameters, including: Based on the error between the image coordinates corresponding to the reference point and the reprojection coordinates calculated by the first expression, a joint optimization function is constructed; wherein, the joint optimization function is used to find the hand-eye calibration result of the robotic arm and the DH parameter when the error is minimized; By adjusting the hand-eye calibration results and DH parameters contained in the first expression of the joint optimization function, the joint optimization function is solved to obtain the corrected hand-eye calibration results and DH parameters. Wherein, the initial value of the hand-eye calibration result contained in the first expression is the pre-calibrated hand-eye calibration result.

9. The apparatus according to claim 7, characterized in that, The first expression is: ； Wherein, K is the intrinsic parameter of the target camera, and D is the distortion coefficient of the target camera; The reference point is defined as the physical coordinate of the calibration plate in the calibration plate coordinate system. The transformation matrix from the calibration plate coordinate system to the end effector coordinate system; Let L be the forward kinematics function, and L be the lever length parameter of the robotic arm. This is the zero-position offset of the robotic arm. The joint angle of the robotic arm; The hand-eye calibration results for the robotic arm.

10. The apparatus according to claim 8, characterized in that, The joint optimization function is: ； Wherein, the value of the reference point is i=1…n, where n is a positive integer; uv is the image coordinate corresponding to the reference point; K is the intrinsic parameter of the target camera; and D is the distortion coefficient of the target camera. The reference point is defined as the physical coordinate of the calibration plate in the calibration plate coordinate system. The transformation matrix from the calibration plate coordinate system to the end effector coordinate system; Let L be the forward kinematics function, and L be the lever length parameter of the robotic arm. This is the zero-position offset of the robotic arm. The joint angle of the robotic arm; The hand-eye calibration results for the robotic arm.

11. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the method described in any one of claims 1-5.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method described in any one of claims 1-5.

Images