Mechanical arm tool center point and hand-eye joint calibration method and system

Abstract

This application proposes a method and system for joint hand-eye calibration of the tool center point of a robotic arm. The method includes: obtaining a first transformation relationship between the coordinate system of the vision sensor and the flange coordinate system of the robotic arm, wherein the first transformation relationship is obtained through hand-eye calibration; acquiring a first image of the end effector TCP of the robotic arm collected by the vision sensor, and performing feature point recognition on the first image through the end effector TCP recognition model to obtain end effector TCP feature points; obtaining the first coordinates of the end effector TCP in the coordinate system of the vision sensor based on the end effector TCP feature points, the intrinsic parameters of the left camera, the intrinsic parameters of the right camera, and a second transformation relationship between the coordinate systems of the left camera and the right camera; and obtaining the calibration result of the end effector TCP based on the first transformation relationship and the first coordinates, thereby improving the calibration accuracy and the level of calibration automation.

Description

Technical Field

[0001] This application relates to the field of robotic arm calibration technology, and in particular to a method and system for calibrating the center point of a robotic arm tool and the combined hand-eye calibration. Background Technology

[0002] In related technologies, the Tool Center Point (TCP) set in the robotic arm control system is often only a theoretical or design value. Due to assembly, manufacturing tolerances, wear, and differences in clamping position, the TCP deviates from the theoretical position, directly leading to a decrease in the robotic arm's pointing accuracy. In vision-guided robotic systems, the camera's coordinate system and the robotic arm's base coordinate system are not naturally aligned. Without hand-eye calibration, the target position detected by vision cannot be accurately converted into a pose that the robotic arm can execute. If the TCP is not standardized, the transformation matrix obtained from hand-eye calibration will be contaminated by TCP deviation; if the hand-eye calibration is inaccurate, even if the TCP is accurate, systematic errors will occur in workpiece positioning. The coupled errors caused by TCP errors and hand-eye errors can accumulate and amplify to the millimeter or even centimeter level in precision assembly, welding, and grinding tasks. Therefore, TCP calibration and hand-eye calibration are necessary.

[0003] Existing TCP calibration and hand-eye calibration schemes suffer from problems such as the need to improve the accuracy of calibration results, low automation, complex operation, and high cost. Summary of the Invention

[0004] This application provides a method and system for calibrating the center point of a robotic arm tool and using a combined hand-eye approach, to at least partially address one of the technical problems in related technologies. The technical solution disclosed herein is as follows:

[0005] In a first aspect, embodiments of this application propose a method for joint calibration of the tool center point and hand-eye coordination of a robotic arm. The robotic arm has a vision sensor fixed to its end effector, which includes a left camera and a right camera. The method includes the following steps:

[0006] A first transformation relationship is obtained between the coordinate system of the vision sensor and the flange coordinate system of the robotic arm, the first transformation relationship being obtained through hand-eye calibration;

[0007] The first image of the end-effector center point TCP of the robotic arm, acquired by the vision sensor, is used to identify feature points in the first image through the end-effector TCP recognition model to obtain end-effector TCP feature points.

[0008] Based on the terminal TCP feature points, the intrinsic parameters of the left camera, the intrinsic parameters of the right camera, and the second transformation relationship between the coordinate systems of the left camera and the right camera, the first coordinates of the terminal TCP in the visual sensor coordinate system are obtained.

[0009] Based on the first transformation relationship and the first coordinates, the calibration result of the terminal TCP is obtained.

[0010] Secondly, embodiments of this application propose a robotic arm tool center point and hand-eye joint calibration system, wherein a vision sensor is fixed to the end of the robotic arm, the vision sensor including a left camera and a right camera, and the device includes:

[0011] The data acquisition module is used to acquire a first transformation relationship between the coordinate system of the vision sensor and the flange coordinate system of the robotic arm, the first transformation relationship being acquired through hand-eye calibration;

[0012] The feature recognition module is used to acquire a first image of the end-effector center point TCP of the robotic arm collected by the vision sensor, and to perform feature point recognition on the first image through the end-effector TCP recognition model to obtain end-effector TCP feature points.

[0013] The coordinate acquisition module is used to obtain the first coordinates of the terminal TCP in the visual sensor coordinate system based on the terminal TCP feature points, the intrinsic parameters of the left camera, the intrinsic parameters of the right camera, and the second transformation relationship between the coordinate system of the left camera and the coordinate system of the right camera.

[0014] The result output module is used to obtain the calibration result of the terminal TCP based on the first transformation relationship and the first coordinates.

[0015] Thirdly, embodiments of this application provide an electronic device, including: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method described in the first aspect.

[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the method described in the first aspect.

[0017] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect.

[0018] The robotic arm tool center point and hand-eye joint calibration method and system provided in this application ensure stable observation of the end-effector TCP by fixing a vision sensor to the end of the robotic arm. Combined with the end-effector TCP recognition model, high-precision TCP recognition is achieved. The first transformation relationship obtained by hand-eye calibration ensures accurate mapping of spatial coordinates. Combined with high-precision TCP recognition, high-precision positioning of the end-effector TCP of the robotic arm is finally achieved, providing a reliable foundation for subsequent automated operations. It has important engineering application value and promotion significance.

[0019] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0020] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0021] Figure 1 A schematic flowchart illustrating a method for calibrating the center point of a robotic arm tool and combining hand-eye coordination, as provided in an embodiment of this application.

[0022] Figure 2 A block diagram of a robotic arm tool center point and hand-eye joint calibration system provided in this application embodiment;

[0023] Figure 3 This is a block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0024] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0025] The following description, with reference to the accompanying drawings, describes a method, apparatus, and device for calibrating the center point of a robotic arm tool and a hand-eye joint calibration method according to embodiments of this application.

[0026] Figure 1 This is a flowchart illustrating a method for calibrating the center point of a robotic arm tool and a hand-eye joint calibration method provided in an embodiment of this application.

[0027] It should be noted that the execution subject of the robotic arm tool center point and hand-eye joint calibration method in this application embodiment is the robotic arm tool center point and hand-eye joint calibration system in this application embodiment. The robotic arm tool center point and hand-eye joint calibration system can be configured in an electronic device so that the electronic device can perform the robotic arm tool center point and hand-eye joint calibration function.

[0028] like Figure 1 As shown, the robotic arm tool center point and hand-eye joint calibration method includes the following steps:

[0029] Step S101: Obtain the first transformation relationship between the coordinate system of the vision sensor and the flange coordinate system of the robotic arm. The first transformation relationship is obtained through hand-eye calibration.

[0030] In this embodiment, a vision sensor is fixed to the end of the robotic arm, and the vision sensor includes a left camera and a right camera.

[0031] In one example, a vision sensor is fixed to the end of a robotic arm using a camera mounting structure. The camera mounting structure needs to ensure that the end of the robotic arm, TCP, is within the field of view of the vision sensor. To avoid affecting the 3D measurement of the vision sensor, the end TCP is positioned at the edge of the vision sensor's field of view.

[0032] In this embodiment, the first transformation relationship includes a first rotation matrix handeye_trans_r and a first translation matrix handeye_trans_t.

[0033] Step S102: Obtain the first image of the end effector TCP of the robotic arm collected by the vision sensor, and perform feature point recognition on the first image through the end effector TCP recognition model to obtain the end effector TCP feature points.

[0034] The visual sensor includes a left camera and a right camera. The first image includes a first left image and a first right image. The first left image and the first right image are respectively identified by the terminal TCP recognition model to obtain the terminal TCP feature points (u_l, v_l) corresponding to the left image and the terminal TCP feature points (u_r, v_r) corresponding to the right image.

[0035] In some embodiments, after acquiring a first image of the end effector TCP of the robotic arm collected by a vision sensor, the method includes: performing binocular correction on the first image to obtain a corrected first image to improve the accuracy of the calibration.

[0036] In some embodiments, the training method for the terminal TCP identification model includes: acquiring images of the terminal TCP using a visual sensor; and training a deep learning model based on the images of the terminal TCP with labeled TCP terminal locations to obtain the terminal TCP identification model.

[0037] In one example, images of the end TCP are acquired using a visual sensor, and the TCP end positions are manually labeled on the acquired images. A deep learning model is then trained using image samples labeled with TCP end positions to obtain an end TCP recognition model.

[0038] Step S103: Based on the terminal TCP feature points, the intrinsic parameters of the left camera, the intrinsic parameters of the right camera, and the second transformation relationship between the coordinate systems of the left camera and the right camera, the first coordinates of the terminal TCP in the visual sensor coordinate system are obtained.

[0039] In one example, the first coordinate point of the endpoint TCP in the visual sensor coordinate system is obtained by combining the intrinsic and extrinsic parameters of the left and right cameras of the visual sensor using the following formula:

[0040] ;

[0041] ;

[0042]

[0043] Where, instric_matrix_l is the intrinsic parameter matrix of the left camera, instric_matrix_r is the intrinsic parameter matrix of the right camera, "\" represents the inverse of the matrix, normalized_l is the ray representation of the feature points obtained by the left camera (a 3×1 column vector), normalized_r is the ray representation of the feature points obtained by the right camera (a 3×1 column vector), "(1)" represents the first element in the vector, and trans_l_to_r is the transformation matrix between the coordinate system of the left camera and the coordinate system of the right camera.

[0044] This can be understood as follows: since a single camera has no depth, a ray is obtained by multiplying the inverse of the camera's intrinsic matrix by the corresponding end TCP feature point. The ray corresponds to a point in the image. By intersecting the ray from the left camera with the ray from the right camera, a three-dimensional point can be obtained. A system of linear equations is constructed based on two 3×1 column vectors, and finally, the first coordinate point of the end TCP in the visual sensor coordinate system is obtained.

[0045] Step S104: Based on the first transformation relationship and the first coordinate, obtain the calibration result of the terminal TCP.

[0046] In some embodiments, the method for obtaining the calibration result of the terminal TCP based on the first transformation relationship and the first coordinate includes: performing precision compensation on the first coordinate using the precision compensation matrix of the visual sensor to obtain the precision-compensated first coordinate; and obtaining the calibration result of the terminal TCP based on the first transformation relationship and the precision-compensated first coordinate.

[0047] In this embodiment, the first coordinate is compensated for using the accuracy compensation matrix of the visual sensor, resulting in the first coordinate point_correct after accuracy compensation.

[0048]

[0049] Here, compsation represents the precision compensation matrix.

[0050] In other words, multiplying the first coordinate by the accuracy compensation matrix yields the first coordinate after accuracy compensation, which effectively corrects measurement errors caused by the visual sensor operating outside its range and significantly improves calibration accuracy.

[0051] In some embodiments, the method for obtaining the accuracy compensation matrix of the vision sensor includes: obtaining a first coordinate true value, which is the coordinate true value of a calibration plate feature point in the base coordinate system of the robotic arm, the calibration plate feature point being obtained through hand-eye calibration; obtaining a second coordinate, which is the coordinate of the calibration plate feature point captured by the vision sensor within its working range in the base coordinate system of the robotic arm, the working range being the distance between the vision sensor and the end effector TCP; and obtaining the accuracy compensation matrix of the vision sensor based on the first coordinate true value and the second coordinate.

[0052] Furthermore, using the first formula, based on the true value of the first coordinate and the second coordinate, the accuracy compensation matrix `compsation` of the visual sensor is obtained. The first formula is expressed as follows:

[0053] ;

[0054] Where: stand_camera is the true coordinate value of the calibration plate feature point in the robot arm base coordinate system, and camera_set is the coordinate of the calibration plate feature point in the robot arm base coordinate system captured by the vision sensor within its working range.

[0055] In some embodiments, a method for obtaining the calibration result of the terminal TCP based on a first transformation relationship and a first coordinate after precision compensation includes:

[0056] Combining the first transformation relationship, the first coordinate point_correct after accuracy compensation is transformed into the flange coordinate system of the robotic arm, which is the calibration result tcp_res of the end-effector TCP:

[0057]

[0058] In other words, after the accuracy compensation, the first coordinate is multiplied by the rotation matrix, and then a translation matrix is ​​added to obtain the calibration result of the terminal TCP.

[0059] The robotic arm tool center point and hand-eye joint calibration method in this embodiment ensures stable observation of the robotic arm's end-effector TCP by fixing the vision sensor to the end of the robotic arm. Combined with the end-effector TCP recognition model, high-precision TCP recognition is achieved. The first transformation relationship obtained from hand-eye calibration ensures accurate mapping of spatial coordinates. Combined with high-precision TCP recognition, high-precision positioning of the robotic arm's end-effector TCP is finally achieved. The accuracy compensation matrix effectively corrects measurement errors generated outside the working range of the vision sensor, significantly improving calibration accuracy. This provides a reliable foundation for subsequent automated operations and has significant engineering application value and promotional significance.

[0060] To achieve the above embodiments, this application also proposes a robotic arm tool center point and hand-eye joint calibration system, wherein a vision sensor is fixed at the end of the robotic arm, and the vision sensor includes a left camera and a right camera. Figure 2 This is a schematic diagram of a robotic arm tool center point and hand-eye joint calibration system provided in an embodiment of this application. Figure 2 As shown, the robotic arm tool center point and hand-eye joint calibration system may include: a data acquisition module 201, a feature recognition module 202, a coordinate acquisition module 203, and a result output module 204.

[0061] The data acquisition module 201 is used to acquire the first transformation relationship between the coordinate system of the vision sensor and the flange coordinate system of the robotic arm. The first transformation relationship is acquired through hand-eye calibration.

[0062] The feature recognition module 202 is used to acquire the first image of the end-effector TCP of the robotic arm collected by the vision sensor, and to perform feature point recognition on the first image through the end-effector TCP recognition model to obtain end-effector TCP feature points.

[0063] The coordinate acquisition module 203 is used to obtain the first coordinates of the terminal TCP in the visual sensor coordinate system based on the terminal TCP feature points, the intrinsic parameters of the left camera, the intrinsic parameters of the right camera, and the second transformation relationship between the coordinate systems of the left camera and the right camera.

[0064] The result output module 204 is used to obtain the calibration result of the terminal TCP based on the first transformation relationship and the first coordinate.

[0065] Furthermore, in one possible implementation of this application embodiment, the result output module 204 is specifically used for:

[0066] The accuracy compensation matrix of the vision sensor is used to perform accuracy compensation on the first coordinate, and the first coordinate after accuracy compensation is obtained.

[0067] Based on the first transformation relationship and the first coordinate after precision compensation, the calibration result of the terminal TCP is obtained.

[0068] Furthermore, in one possible implementation of this application embodiment, the system further includes a compensation acquisition module 205, used for:

[0069] Obtain the true value of the first coordinate. The true value of the first coordinate is the true value of the coordinate of the feature point of the calibration plate in the base coordinate system of the robot arm. The feature point of the calibration plate is obtained through hand-eye calibration.

[0070] Obtain the second coordinate, which is the coordinate of the calibration board feature point captured by the vision sensor within the working range in the base coordinate system of the robotic arm. The working range is the distance between the vision sensor and the end effector TCP.

[0071] Based on the true value of the first coordinate and the second coordinate, the accuracy compensation matrix of the vision sensor is obtained.

[0072] Furthermore, in one possible implementation of this application embodiment, the compensation acquisition module 205 is specifically used for:

[0073] Using the first formula, based on the true value of the first coordinate and the second coordinate, the accuracy compensation matrix (compsation) of the visual sensor is obtained. The first formula is expressed as follows:

[0074] ;

[0075] Where: stand_camera is the true coordinate value of the calibration plate feature point in the robot arm base coordinate system, camera_set is the coordinate of the calibration plate feature point captured by the vision sensor within the working range in the robot arm base coordinate system, and camera_set' is obtained by remapping camera_set.

[0076] Furthermore, in one possible implementation of this application embodiment, the feature recognition module 202 is further used for:

[0077] The first image is subjected to binocular correction to obtain the corrected first image.

[0078] Furthermore, in one possible implementation of this application embodiment, the first transformation relationship includes a first rotation matrix and a first translation matrix. When the result output module 204 obtains the calibration result of the terminal TCP based on the first transformation relationship and the first coordinates after precision compensation, it is used for:

[0079] The endpoint TCP calibration result tcp_res is obtained using the following formula:

[0080]

[0081] Where handeye_trans_r is the first transformation relationship, handeye_trans_t is the first translation matrix, and point_correct is the first coordinate after precision compensation.

[0082] Furthermore, in one possible implementation of this application embodiment, the system further includes a model training module 206, used for:

[0083] Images are acquired from the terminal TCP using a visual sensor;

[0084] A deep learning model is trained based on images of terminal TCPs with labeled TCP endpoints to obtain a terminal TCP recognition model.

[0085] Furthermore, in one possible implementation of this application embodiment, the end effector TCP of the robotic arm is at the edge of the field of view of the vision sensor.

[0086] It should be noted that the foregoing explanation of the embodiment of the robotic arm tool center point and hand-eye joint calibration method also applies to the robotic arm tool center point and hand-eye joint calibration system of this embodiment, and will not be repeated here.

[0087] The robotic arm tool center point and hand-eye joint calibration system of this embodiment ensures stable observation of the end effector TCP by fixing the vision sensor to the end effector of the robotic arm. Combined with the end effector TCP recognition model, it achieves high-precision TCP recognition. The first transformation relationship obtained by hand-eye calibration ensures accurate mapping of spatial coordinates. Combined with high-precision TCP recognition, it finally achieves high-precision positioning of the end effector TCP of the robotic arm. The accuracy compensation matrix effectively corrects the measurement error generated outside the working range of the vision sensor, significantly improving the calibration accuracy. It provides a reliable foundation for subsequent automated operation and has important engineering application value and promotion significance.

[0088] To implement the above embodiments, this application also proposes an electronic device. Please see [link to relevant documentation]. Figure 3 , Figure 3 This is a schematic diagram of the structure of the electronic device provided in an embodiment of this application. For example... Figure 3 As shown, the electronic device 300 includes: a processor 301, and a memory 302 communicatively connected to the processor 301; the memory 302 stores computer execution instructions; the processor 301 executes the computer execution instructions stored in the memory to implement the method provided in the foregoing embodiments.

[0089] To implement the above embodiments, this application also proposes a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided in the foregoing embodiments.

[0090] To implement the above embodiments, this application also proposes a computer program product, including a computer program that, when executed by a processor, implements the methods provided in the foregoing embodiments.

[0091] In the foregoing descriptions of the embodiments, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0092] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0093] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for calibrating the center point of a robotic arm tool using a combined hand-eye approach, characterized in that, The end effector of the robotic arm is equipped with a vision sensor, which includes a left camera and a right camera. The method includes the following steps: A first transformation relationship is obtained between the coordinate system of the vision sensor and the flange coordinate system of the robotic arm, the first transformation relationship being obtained through hand-eye calibration; The first image of the end-effector center point TCP of the robotic arm, acquired by the vision sensor, is used to identify feature points in the first image through the end-effector TCP recognition model to obtain end-effector TCP feature points. Based on the terminal TCP feature points, the intrinsic parameters of the left camera, the intrinsic parameters of the right camera, and the second transformation relationship between the coordinate systems of the left camera and the right camera, the first coordinates of the terminal TCP in the visual sensor coordinate system are obtained. Based on the first transformation relationship and the first coordinates, the calibration result of the terminal TCP is obtained, including: performing precision compensation on the first coordinates using the precision compensation matrix of the visual sensor to obtain the precision-compensated first coordinates; and obtaining the calibration result of the terminal TCP based on the first transformation relationship and the precision-compensated first coordinates. The method for obtaining the accuracy compensation matrix of the vision sensor includes: obtaining a first coordinate true value, which is the true coordinate value of a calibration plate feature point in the base coordinate system of the robotic arm, wherein the calibration plate feature point is obtained through hand-eye calibration; obtaining a second coordinate, which is the coordinate of the calibration plate feature point in the base coordinate system of the robotic arm as captured by the vision sensor within its working range, wherein the working range is the distance between the vision sensor and the end effector TCP; and obtaining the accuracy compensation matrix `compsation` of the vision sensor based on the first coordinate true value and the second coordinate using a first formula, wherein the first formula is expressed as follows: Where: stand_camera is the true coordinate value of the calibration plate feature point in the robot arm base coordinate system, camera_set is the coordinate of the calibration plate feature point captured by the vision sensor within the working range in the robot arm base coordinate system, and camera_set' is obtained by remapping camera_set.

2. The method according to claim 1, characterized in that, After acquiring the first image of the end effector TCP of the robotic arm collected by the vision sensor, the process includes: The first image is subjected to binocular correction to obtain the corrected first image.

3. The method according to claim 1, characterized in that, The first transformation relationship includes a first rotation matrix and a first translation matrix. The step of obtaining the calibration result of the terminal TCP based on the first transformation relationship and the first coordinates after precision compensation includes: The calibration result tcp_res of the terminal TCP is obtained using the following formula: Where handeye_trans_r is the first transformation relationship, handeye_trans_t is the first translation matrix, and point_correct is the first coordinate after precision compensation.

4. The method according to claim 1, characterized in that, The training method for the terminal TCP identification model includes: Images of the terminal TCP are acquired using the visual sensor; Based on the image of the terminal TCP with labeled TCP endpoints, a deep learning model is trained to obtain a terminal TCP recognition model.

5. The method according to claim 1, characterized in that, The end effector TCP of the robotic arm is located at the edge of the field of view of the vision sensor.

6. A robotic arm tool center point and hand-eye joint calibration system, characterized in that, The end effector of the robotic arm is equipped with a vision sensor, which includes a left camera and a right camera. The system includes: The data acquisition module is used to acquire a first transformation relationship between the coordinate system of the vision sensor and the flange coordinate system of the robotic arm, the first transformation relationship being acquired through hand-eye calibration; The feature recognition module is used to acquire a first image of the end-effector center point TCP of the robotic arm collected by the vision sensor, and to perform feature point recognition on the first image through the end-effector TCP recognition model to obtain end-effector TCP feature points. The coordinate acquisition module is used to obtain the first coordinates of the terminal TCP in the visual sensor coordinate system based on the terminal TCP feature points, the intrinsic parameters of the left camera, the intrinsic parameters of the right camera, and the second transformation relationship between the coordinate systems of the left camera and the right camera. The result output module is used to obtain the calibration result of the terminal TCP based on the first transformation relationship and the first coordinates; wherein, the result output module is specifically used to: perform precision compensation on the first coordinates through the precision compensation matrix of the vision sensor to obtain the precision-compensated first coordinates; and obtain the calibration result of the terminal TCP based on the first transformation relationship and the precision-compensated first coordinates. The system further includes a compensation acquisition module, which is used to: acquire a first coordinate true value, which is the true coordinate value of the calibration plate feature point in the base coordinate system of the robotic arm, wherein the calibration plate feature point is acquired through hand-eye calibration; acquire a second coordinate, which is the coordinate of the calibration plate feature point in the base coordinate system of the robotic arm as captured by the vision sensor within its working range, wherein the working range is the distance between the vision sensor and the end effector TCP; and acquire the accuracy compensation matrix `compsation` of the vision sensor based on the first coordinate true value and the second coordinate using a first formula, wherein the first formula is expressed as follows: Where: stand_camera is the true coordinate value of the calibration plate feature point in the robot arm base coordinate system, camera_set is the coordinate of the calibration plate feature point captured by the vision sensor within the working range in the robot arm base coordinate system, and camera_set' is obtained by remapping camera_set.

7. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-5.

Images