Calibration plate, hand-eye calibration data acquisition method of mechanical arm and hand-eye calibration method

Abstract

The application discloses a calibration plate, a hand-eye calibration data collection method of a mechanical arm and a hand-eye calibration method. The calibration plate is provided with a checkerboard pattern and a directional mark pattern. The directional mark pattern is arranged at the outer side of the checkerboard pattern at intervals and is used as a directional reference for identification when the mechanical arm is calibrated. The application sets the directional mark pattern at the outer side of the checkerboard pattern of the calibration plate, so that the calibration plate is directional. Therefore, the calibration plate with any checkerboard pattern can be used for the hand-eye calibration of the mechanical arm.

Description

Technical Field

[0001] This invention relates to the field of robotic arms, and particularly to a calibration plate, a method for acquiring hand-eye calibration data for robotic arms, and a hand-eye calibration method. Background Technology

[0002] In recent years, with the rapid development of science and technology, robotic arm products have been continuously updated and iterated, and have been widely used in many fields such as medical care, education, and industry.

[0003] During operation, robotic arms typically need to perform visual positioning of the target object to determine its location within the workspace, facilitating subsequent operations such as grasping and welding. When the robotic arm works in conjunction with a camera, a coordinate system calibration is required to establish a relationship between the camera (i.e., the robotic arm's eye) and the robotic arm's (i.e., the robotic arm's hand) coordinate systems; this is known as robotic arm hand-eye calibration.

[0004] Hand-eye calibration of a robotic arm requires a calibration plate. Currently, this typically involves moving the robotic arm to confirm several photo points, ensuring the calibration plate is within the camera's field of view during the photo capture. The robotic arm's position information is recorded at each photo point, and the calibration plate information is collected by taking a photo. Then, based on the acquired sets of robotic arm position information and calibration plate information, hand-eye calibration between the robotic arm and the camera is performed. Figure 1 As shown, existing calibration plates are typically grid patterns; however, as Figure 2 As shown, some calibration plates have a grid pattern that is symmetrical about the center, which cannot guarantee the unique correspondence between the angle of the calibration plate and the actual rotation posture during the hand-eye calibration of the robotic arm, and therefore cannot be used for hand-eye calibration of the robotic arm. Summary of the Invention

[0005] The main objective of this invention is to provide a calibration plate that addresses the technical problems mentioned in the background section.

[0006] To achieve the above objectives, the present invention proposes a calibration board, wherein the calibration board has a checkerboard pattern and an orientation mark pattern, the orientation mark pattern being spaced apart on the outer side of the checkerboard pattern, and the orientation mark pattern being used as an orientation reference for identification.

[0007] In this case, the colors of the squares in the directional sign pattern are different from those in the checkerboard pattern; and / or,

[0008] The shapes of the squares in the directional sign pattern are different from those in the checkerboard pattern; and / or,

[0009] The squares of the directional sign pattern are different in size from those of the checkerboard pattern; and / or,

[0010] The directional signage pattern contains an identification code.

[0011] The directional sign is located on one side of the checkerboard pattern and adjacent to one corner of the checkerboard pattern.

[0012] The directional sign pattern may include one or more elements.

[0013] This invention also proposes a method for acquiring hand-eye calibration data of a robotic arm, the method comprising:

[0014] Establish a world coordinate system based on the calibration plate, and obtain the world coordinates of all corner points of the checkerboard pattern on the calibration plate in the world coordinate system. The calibration plate is the one described above.

[0015] Acquire images of the calibration board, which contain a checkerboard pattern and orientation marker patterns;

[0016] Extract all corner points and orientation markers of the checkerboard pattern in the image of the calibration board, and match all corner points of the checkerboard pattern in the image of the calibration board with all corner points of the checkerboard pattern in the calibration board according to the orientation markers;

[0017] Based on the corresponding results, each corner point of the checkerboard pattern in the calibration board image is matched one-to-one with the world coordinates of each corner point of the checkerboard pattern in the world coordinate system.

[0018] The step of extracting all corner points and orientation markers of the checkerboard pattern in the calibration board image, and matching all corner points of the checkerboard pattern in the calibration board image with all corner points of the checkerboard pattern in the calibration board based on the orientation markers, includes:

[0019] Based on the positional relationship between the corner points of the checkerboard pattern in the calibration board and the orientation marker pattern, all corner points of the checkerboard pattern are sorted according to a preset rule, and then each corner point of the checkerboard pattern in the calibration board image is matched one-to-one with the corner points of the checkerboard pattern in the calibration board.

[0020] This invention also proposes a hand-eye calibration method for a robotic arm, wherein the robotic arm is equipped with a vision camera, and the calibration method includes:

[0021] The robotic arm is controlled to move sequentially to multiple image acquisition points, and the position information of the robotic arm at the multiple image acquisition points is recorded. At each image acquisition point, the hand-eye calibration data of the robotic arm is collected using the hand-eye calibration data collection method described above.

[0022] The intrinsic and extrinsic parameters of the vision camera are calculated based on multiple sets of calibration data, and the hand-eye calibration of the robotic arm is performed by combining multiple positional information of the robotic arm.

[0023] The present invention also proposes a hand-eye calibration data acquisition device for a robotic arm, which includes:

[0024] The acquisition module is used to establish a world coordinate system based on the calibration plate and acquire the world coordinates of all corner points of the checkerboard pattern in the calibration plate in the world coordinate system, wherein the calibration plate is the calibration plate described in the foregoing claims;

[0025] The acquisition module is used to acquire images of the calibration board, which contain a checkerboard pattern and orientation marker patterns.

[0026] The mapping module is used to extract all corner points and orientation markers of the checkerboard pattern in the image of the calibration board, and to map all corner points of the checkerboard pattern in the image of the calibration board to all corner points of the checkerboard pattern in the calibration board according to the orientation markers.

[0027] The conversion module is used to map all corner points of the checkerboard pattern in the calibration board image to their world coordinates in the world coordinate system, based on the corresponding results.

[0028] The present invention also proposes a hand-eye calibration system for a robotic arm, the hand-eye calibration system for the robotic arm comprising:

[0029] robotic arm;

[0030] The calibration plate is the calibration plate described in the foregoing claims and is located in the motion space of the robotic arm;

[0031] A vision camera, mounted on the robotic arm, is used to acquire images of the calibration plate.

[0032] The present invention also proposes a control device for a robotic arm, wherein the hand-eye calibration device for the robotic arm includes:

[0033] Memory, used to store computer programs;

[0034] A processor for executing a computer program to implement the hand-eye calibration data acquisition method for a robotic arm as described above, or the hand-eye calibration method for a robotic arm as described above.

[0035] The present invention also proposes a computer storage medium storing a computer program, which, when executed by a processor, implements the hand-eye calibration data acquisition method for a robotic arm as described above, or the hand-eye calibration method for a robotic arm as described above.

[0036] The calibration plate involved in this invention can be used for hand-eye calibration of robotic arms. The calibration plate has a checkerboard pattern and orientation markers. During hand-eye calibration of the robotic arm, the identified orientation markers can be used as a reference for orienting the calibration plate. Specifically, during the hand-eye calibration process, the robotic arm acquires images of the calibration plate through a vision camera. The acquired images of the calibration plate contain the checkerboard pattern and orientation markers. The position of the origin and the x, y, and z axis directions of the calibration plate can be determined based on the identified orientation markers, facilitating further sorting of the corner points of the checkerboard pattern to achieve a one-to-one correspondence between the image coordinates of each corner point and the world coordinates, accurately realizing coordinate transformation and ensuring a unique correspondence between the detected angle of the calibration plate and the actual rotational posture. This invention, by setting orientation markers on the outside of the checkerboard pattern of the calibration plate, gives the calibration plate directionality, allowing calibration plates with any checkerboard pattern to be used for hand-eye calibration of robotic arms. Of course, it can also be used for error correction of robotic arms. Attached Figure Description

[0037] Figure 1 This is a schematic diagram of the structure of a calibration plate in the prior art;

[0038] Figure 2 This is a schematic diagram of another calibration plate in the prior art;

[0039] Figure 3 This is a schematic diagram of the calibration plate structure in one embodiment of the present invention;

[0040] Figure 4 This is a schematic diagram of the calibration plate structure in another embodiment of the present invention;

[0041] Figure 5 This is a schematic diagram of the calibration plate structure in another embodiment of the present invention;

[0042] Figure 6 This is a flowchart of a hand-eye calibration data acquisition method for a robotic arm according to an embodiment of the present invention;

[0043] Figure 7 This is a schematic diagram illustrating the establishment of the calibration plate with respect to the world coordinate system in another embodiment of the present invention;

[0044] Figure 8 This is a flowchart of a hand-eye calibration method for a robotic arm according to an embodiment of the present invention;

[0045] Figure 9 This is a block diagram of the hand-eye calibration data acquisition device for a robotic arm according to an embodiment of the present invention;

[0046] Figure 10 This is a schematic diagram of the architecture of the control device for the robotic arm in one embodiment of the present invention. Detailed Implementation

[0047] The solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0049] It should also be noted that when a component is described as "fixed to" or "set on" another component, it can be directly on the other component or there may be an intervening component present. When a component is described as "connected to" another component, it can be directly connected to the other component or there may be an intervening component present.

[0050] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0051] In applications such as machine vision, calibration plates are used to assist in the hand-eye calibration and error correction of robotic arms. The robotic arm uses a vision camera to capture images of a plane with a fixed-spacing pattern array. After calculation by a calibration algorithm, the geometric model of the vision camera is obtained, thus achieving high-precision measurement and reconstruction results. The flat plate with the fixed-spacing pattern array is the calibration plate.

[0052] Reference Figure 3 , Figure 3 This is a schematic diagram of the calibration plate 100 in one embodiment of the present invention:

[0053] The present invention proposes a calibration plate 100, wherein the calibration plate 100 has a checkerboard pattern 110 and an orientation mark pattern 120, the orientation mark pattern 120 being spaced apart on the outer side of the checkerboard pattern 110, and the orientation mark pattern 120 being used as an orientation reference for identification.

[0054] The calibration plate 100 has a checkerboard pattern 110, optionally a black and white alternating square array, where each row and column consists of alternating black and white squares. The calibration plate 100 also has an orientation marker pattern 120, which serves as an orientation reference for identification during the hand-eye calibration process of the robotic arm. To facilitate accurate and rapid identification of the orientation marker pattern 120 in the acquired images of the calibration plate 100, the orientation marker pattern 120 is located outside the checkerboard pattern 110 and spaced apart from it. Optionally, the orientation marker pattern 120 and the checkerboard pattern 110 have different pattern types. The pattern type may include shape, color, size, and style, and is not limited thereto.

[0055] During the hand-eye calibration of the robotic arm, the identified orientation mark pattern 120 can be used as a reference for the orientation of the calibration plate 100. Specifically, during the hand-eye calibration process of the robotic arm, the robotic arm acquires an image of the calibration plate 100 through a vision camera. The acquired image of the calibration plate 100 includes a checkerboard pattern 110 and an orientation mark pattern 120. The position of the origin and the xyz axis direction of the calibration plate 100 can be determined based on the identified orientation mark pattern 120, which facilitates the further sorting of the corner points 111 of the checkerboard pattern 110 to complete the one-to-one correspondence between the image coordinates of the corner points 111 of the checkerboard pattern 110 and the world coordinates, thus ensuring the unique correspondence between the detected angle of the calibration plate 100 and the actual rotation posture.

[0056] The present invention provides the calibration plate 100 with directionality by setting an orientation mark pattern 120 on the outside of the checkerboard pattern 110 of the calibration plate 100. This allows the calibration plate 100, regardless of the checkerboard pattern 110 (provided that the basic requirements for hand-eye calibration are met), to be used for hand-eye calibration of the robotic arm. Of course, it can also be used for error correction of the robotic arm.

[0057] Reference Figures 3 to 5 , Figure 4 This is a schematic diagram of the calibration plate 100 in another embodiment of the present invention. Figure 5 Here is a schematic diagram of the calibration plate 100 in another embodiment of the present invention:

[0058] In some embodiments, the orientation marker pattern 120 may have different colors than the squares of the checkerboard pattern 110. For example, the orientation marker pattern 120 may be set to red, blue, green, or other colors to distinguish it from the black and white squares of the checkerboard pattern 110, thus enabling accurate and rapid identification and improving detection accuracy. Alternatively, the orientation marker pattern 120 may have different shapes than the squares of the checkerboard pattern 110. For example, the orientation marker pattern 120 may be circular, triangular, or other shapes to distinguish it from the squares of the checkerboard pattern 110, thus enabling accurate and rapid identification and improving detection accuracy. Furthermore, the orientation marker pattern 120 may have different sizes than the squares of the checkerboard pattern 110, with the size difference set according to the actual situation. In addition to the above forms, the orientation marker pattern 120 may also include an identification code. This identification code may be a QR code or similar. By setting an identification code, the orientation marker pattern 120 can be accurately and quickly identified, resulting in high detection accuracy.

[0059] In some embodiments, the orientation marker pattern 120 is located on one side of the checkerboard pattern 110 and adjacent to one corner of the checkerboard pattern 110. By placing the orientation marker pattern 120 on one side of the checkerboard pattern 110 and adjacent to one corner of the checkerboard pattern 110 on the calibration plate 100, only one corner point 111 in the checkerboard pattern 110 is closest to it. This allows the corner point 111 closest to the orientation marker pattern 120 to be used as the origin when establishing the world coordinate system, thus facilitating the establishment of the world coordinate system and improving the accuracy of the robotic arm's hand-eye calibration.

[0060] In some embodiments, one or more orientation marker patterns are provided. When multiple orientation marker patterns are provided, the position of the origin of the calibration plate 100 and the xyz axis directions can be determined according to a predetermined rule based on the relative positional relationship between the multiple orientation marker patterns and the checkerboard pattern. For example, two orientation marker patterns are provided, located on the same side of the checkerboard pattern and respectively adjacent to two corners of the checkerboard pattern. The corner point of the checkerboard pattern closest to both orientation marker patterns is taken as the origin. On the plane of the calibration plate, the direction parallel to the line connecting the two orientation marker patterns is taken as the y-axis direction, the direction perpendicular to the line connecting the two orientation marker patterns is taken as the x-axis direction, and the direction perpendicular to the calibration plate 100 is taken as the z-axis direction.

[0061] Reference Figure 6 and Figure 7 , Figure 6 This is a flowchart of a hand-eye calibration data acquisition method for a robotic arm according to an embodiment of the present invention. Figure 7 This is a schematic diagram illustrating the establishment of the calibration plate 100 with respect to the world coordinate system in another embodiment of the present invention:

[0062] This invention also proposes a method for acquiring hand-eye calibration data of a robotic arm, the method comprising:

[0063] Step S100: Establish a world coordinate system based on the calibration plate 100, and obtain the world coordinates of all corner points 111 of the checkerboard pattern 110 in the calibration plate 100 in the world coordinate system, wherein the calibration plate 100 is the calibration plate 100 described in the aforementioned embodiment.

[0064] In this step, such as Figure 7 As shown, the checkerboard pattern 110 of the calibration plate 100 has dimensions of 10Nmm × 8Nmm, with each square measuring Nmm × Nmm. Orientation marker patterns 120 are spaced apart on the outer side of the checkerboard pattern 110, located on one side of the checkerboard pattern 110 and adjacent to one corner thereof. A world coordinate system is established based on the calibration plate 100. Specifically, using the orientation marker patterns 120 on the calibration plate 100 as reference objects, the nearest corner point 111 of the checkerboard pattern 110 to the orientation marker pattern 120 is taken as the origin. On the plane of the calibration plate 100, the horizontal direction is the x-axis, the vertical direction is the y-axis, and the direction perpendicular to the calibration plate 100 is the z-axis, thus establishing a world coordinate system. Figure 7 As shown, all corner points 111 of the checkerboard pattern 110 in the calibration plate 100 are sorted in the order of first along the x-axis of the world coordinate system and then along the y-axis. The coordinates of the first corner point 111 are (0, 0, 0), the coordinates of the second corner point 111 are (N, 0, 0), the coordinates of the third corner point 111 are (2N, 0, 0) and so on. The tenth corner point 111 is located below the first corner point 111, and the coordinates of the tenth corner point 111 are (0, N, 0), the coordinates of the eleventh corner point 111 are (0, 2N, 0) and so on.

[0065] Step S200: Acquire an image of the calibration board 100, wherein the image of the calibration board 100 includes a checkerboard pattern 110 and an orientation marker pattern 120.

[0066] In this step, the image of the calibration plate 100 is acquired by the vision camera on the robotic arm. When acquiring the image of the calibration plate 100, the entire calibration plate 100 is completely within the field of view of the vision camera to ensure that the acquired image of the calibration plate 100 contains the checkerboard pattern 110 and the orientation mark pattern 120.

[0067] Step S300: Extract all corner points 111 of the checkerboard pattern 110 and the orientation mark pattern 120 from the image of the calibration board 100, and match all corner points 111 of the checkerboard pattern 110 in the image of the calibration board 100 with all corner points 111 of the checkerboard pattern 110 in the calibration board 100 according to the orientation mark pattern 120.

[0068] In this step, firstly, all corner points 111 of the checkerboard pattern 110 and the orientation mark pattern 120 in the image of the calibration board 100 are extracted. Then, according to the positional relationship between each corner point 111 of the checkerboard pattern 110 and the orientation mark pattern 120 in the calibration board 100, all corner points 111 of the checkerboard pattern 110 are sorted according to a preset rule, and then each corner point 111 of the checkerboard pattern 110 in the image of the calibration board 100 is matched one-to-one with each corner point 111 of the checkerboard pattern 110 in the calibration board 100.

[0069] Specifically, after extracting all corner points 111 of the checkerboard pattern 110 and the orientation marker pattern 120, the corner point 111 in the checkerboard pattern 110 closest to the orientation marker pattern 120 is determined. This corner point 111 is designated as the first (number 1) corner point 111. The other corner points 111 are then sequentially ordered as corner points 2, 3, ..., following a preset rule, first along the x-axis of the world coordinate system and then along the y-axis. This process completes the sorting of all corner points 111 of the checkerboard pattern 110. Based on the sorted corner points 111 of the checkerboard pattern 110 in the image of the calibration board 100, a one-to-one correspondence is established between the checkerboard pattern 110 and all corner points 111 in the calibration board 100.

[0070] Step S400: Based on the corresponding results, match all corner points 111 of the checkerboard pattern 110 in the image of the calibration plate 100 with the world coordinates of all corner points 111 of the checkerboard pattern 110 in the world coordinate system.

[0071] In this step, the world coordinates of all corner points 111 of the checkerboard pattern 110 in the image of the calibration board 100 are obtained, which are the world coordinates of the corner points 111 with the same index as those in the calibration board 100. For example, in the image of the calibration board 100, the world coordinates of the corner point 111 with index 1 of the checkerboard pattern 110 are the same as the world coordinates (0, 0, 0) of the first corner point 111 in the calibration board 100 determined in the previous step. Therefore, the world coordinates of the corner point 111 with index 1 of the checkerboard pattern 110 in the image of the calibration board 100 are (0, 0, 0). In the image of the calibration board 100, the world coordinates of the corner point 111 with index 2 of the checkerboard pattern 110 are the same as the world coordinates (0, N, 0) of the second corner point 111 in the calibration board 100 determined in the previous step. Therefore, the world coordinates of the corner point 111 of the checkerboard pattern 110 in the image of the calibration board 100 are (0, 0, 0). The world coordinates corresponding to corner point 111 with index 0 and number 2 are (0, N, 0). For example, in the image of the calibration board 100, the world coordinates corresponding to corner point 111 with index 10 of the checkerboard pattern 110 are the world coordinates (N, 0, 0) corresponding to the tenth corner point 111 in the calibration board 100 as determined above. Therefore, the world coordinates corresponding to corner point 111 with index 10 of the checkerboard pattern 110 in the image of the calibration board 100 are (N, 0, 0). This ensures a one-to-one correspondence between any corner point 111 of the checkerboard pattern 110 of the calibration board 100 and its world coordinates in the world coordinate system, achieving accurate coordinate transformation and improving the accuracy of calibration data acquisition.

[0072] Reference Figure 8 , Figure 8 Here is a flowchart of a hand-eye calibration method for a robotic arm according to an embodiment of the present invention:

[0073] This invention also proposes a hand-eye calibration method for a robotic arm, wherein the robotic arm is equipped with a vision camera, and the calibration method includes:

[0074] Step S1000: Control the robotic arm to move sequentially to multiple image acquisition points, record the position information of the robotic arm at multiple image acquisition points, and collect the hand-eye calibration data of the robotic arm at each image acquisition point using the hand-eye calibration data acquisition method of the robotic arm as described above.

[0075] Step S2000: Calculate the intrinsic and extrinsic parameters of the vision camera based on multiple sets of calibration data, and combine them with multiple position information of the robotic arm to perform hand-eye calibration of the robotic arm.

[0076] Among them, the intrinsic parameters of a visual camera are parameters related to the camera's own characteristics, such as the camera's focal length and pixel size; the extrinsic parameters are parameters in the world coordinate system, such as the camera's position and rotation direction.

[0077] Reference Figure 9 , Figure 9 This is a block diagram of the hand-eye calibration data acquisition device for a robotic arm according to an embodiment of the present invention:

[0078] The present invention also proposes a hand-eye calibration data acquisition device for a robotic arm, which includes:

[0079] The acquisition module is used to establish a world coordinate system based on the calibration plate 100 and acquire the world coordinates of all corner points 111 of the checkerboard pattern 110 in the calibration plate 100 in the world coordinate system, wherein the calibration plate 100 is the calibration plate 100 described in the foregoing claims.

[0080] The acquisition module is used to acquire images of the calibration board 100, wherein the images of the calibration board 100 include a checkerboard pattern 110 and an orientation mark pattern 120;

[0081] The mapping module is used to extract all corner points 111 of the checkerboard pattern 110 and the orientation mark pattern 120 in the image of the calibration board 100, and to match all corner points 111 of the checkerboard pattern 110 in the image of the calibration board 100 with all corner points 111 of the checkerboard pattern 110 in the calibration board 100 according to the orientation mark pattern 120.

[0082] The conversion module is used to correspond one-to-one with the world coordinates of all corner points 111 of the checkerboard pattern 110 in the image of the calibration board 100 and the world coordinates of all corner points 111 of the checkerboard pattern 110 in the world coordinate system according to the corresponding results.

[0083] The present invention also proposes a hand-eye calibration system for a robotic arm, the hand-eye calibration system for the robotic arm comprising:

[0084] robotic arm;

[0085] The calibration plate 100 is the calibration plate 100 described as described above, and is located in the motion space of the robotic arm;

[0086] A vision camera, mounted on the robotic arm, is used to acquire images of the calibration plate 100.

[0087] The present invention also proposes a control device for a robotic arm, the control device comprising:

[0088] Memory, used to store computer programs;

[0089] A processor for executing a computer program to implement the hand-eye calibration data acquisition method for a robotic arm as described above, or the hand-eye calibration method for a robotic arm as described above.

[0090] The control device for the robotic arm proposed in this embodiment of the invention can be a robot or a PC. For example... Figure 10 As shown, the control device of the robotic arm may include: a processor 1001, such as a CPU; a network interface 1004; a user interface 1003; a memory 1005; and a communication bus 1002. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit, such as a keyboard. Optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory 1005 may be high-speed RAM or non-volatile memory, such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0091] Those skilled in the art will understand that Figure 10 The control device structure of the robotic arm shown does not constitute a limitation on the control device of the robotic arm. It may include more or fewer parts than shown, or combine certain parts, or have different arrangements of parts.

[0092] like Figure 10 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a control program for the robotic arm.

[0093] exist Figure 10 In the control device of the robotic arm shown, the network interface 1004 is mainly used to connect to the backend server and communicate data with the backend server; the user interface 1003 is mainly used to connect to the client (user end) and communicate data with the client; and the processor 1001 can be used to call the control program of the robotic arm stored in the memory 1005.

[0094] The present invention also proposes a computer storage medium storing a computer program, which, when executed by a processor, implements the hand-eye calibration data acquisition method for a robotic arm as described above, or the hand-eye calibration method for a robotic arm as described above.

[0095] In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or modules may be electrical, mechanical, or other forms.

[0096] The modules described as separate components may or may not be physically separate. Similarly, the components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0097] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0098] If the integrated module is implemented as a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer system (which may be a personal computer, server, or network system, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0099] The above description is only a part or preferred embodiment of the present invention. Neither the text nor the drawings should limit the scope of protection of the present invention. All equivalent structural transformations made using the content of the present invention specification and drawings under the overall concept of the present invention, or direct / indirect applications in other related technical fields, are included within the scope of protection of the present invention.

Claims

1. A method for acquiring hand-eye calibration data for a robotic arm, characterized in that, include: A world coordinate system is established based on the calibration board, and the world coordinates of all corner points of the checkerboard pattern on the calibration board are obtained in the world coordinate system. The calibration board has a checkerboard pattern and an orientation mark pattern. The orientation mark pattern is spaced out on the outside of the checkerboard pattern. The orientation mark pattern has an identification code and is used as an orientation reference for identification. Acquire images of the calibration board; Extract all corner points of the checkerboard pattern and the orientation marker pattern from the image of the calibration board, determine the corner point of the checkerboard pattern that is closest to the orientation marker pattern as the origin and obtain the xyz axis direction, sort the corner points of the checkerboard pattern, and match all corner points of the checkerboard pattern in the image of the calibration board with all corner points of the checkerboard pattern in the calibration board; Based on the corresponding results, all corner points of the checkerboard pattern in the image of the calibration board are matched one-to-one with the world coordinates of all corner points of the checkerboard pattern in the world coordinate system.

2. The hand-eye calibration data acquisition method for a robotic arm according to claim 1, characterized in that, The step of extracting all corner points of the checkerboard pattern and the orientation marker pattern from the image of the calibration board, and matching all corner points of the checkerboard pattern in the image of the calibration board with all corner points of the checkerboard pattern in the calibration board according to the orientation marker pattern, includes: Based on the positional relationship between each corner point of the checkerboard pattern in the calibration board and the orientation marker pattern, all corner points of the checkerboard pattern are sorted according to a preset rule, and then each corner point of the checkerboard pattern in the image of the calibration board is matched one-to-one with each corner point of the checkerboard pattern in the calibration board.

3. A method for hand-eye calibration of a robotic arm, characterized in that, The robotic arm is equipped with a vision camera, and the hand-eye calibration method includes: The robotic arm is controlled to move sequentially to multiple image acquisition points, and the position information of the robotic arm at the multiple image acquisition points is recorded. At each of the image acquisition points, the hand-eye calibration data of the robotic arm is acquired using the hand-eye calibration data acquisition method of the robotic arm as described in any one of claims 1 to 2. The intrinsic and extrinsic parameters of the vision camera are calculated based on multiple sets of calibration data, and the hand-eye calibration of the robotic arm is performed by combining multiple position information of the robotic arm.

4. A hand-eye calibration data acquisition device for a robotic arm, characterized in that, include: The acquisition module is used to establish a world coordinate system based on the calibration board and acquire the world coordinates of all corner points of the checkerboard pattern in the calibration board in the world coordinate system. The calibration board has a checkerboard pattern and an orientation mark pattern. The orientation mark pattern is spaced out on the outside of the checkerboard pattern. The orientation mark pattern has an identification code and is used as an orientation reference for identification. The acquisition module is used to acquire images of the calibration board; The mapping module is used to extract all corner points of the checkerboard pattern and the orientation mark pattern in the image of the calibration board, determine the corner point of the checkerboard pattern that is closest to the orientation mark pattern as the origin and obtain the xyz axis direction, sort the corner points of the checkerboard pattern, and match all corner points of the checkerboard pattern in the image of the calibration board with all corner points of the checkerboard pattern in the calibration board; The conversion module is used to correspond one-to-one with the world coordinates of all corner points of the checkerboard pattern in the calibration board image and the world coordinates of all corner points of the checkerboard pattern in the calibration board in the world coordinate system, based on the corresponding results.

5. A control device for a robotic arm, characterized in that, include: Memory, used to store computer programs; A processor is configured to execute the computer program to implement the hand-eye calibration data acquisition method for a robotic arm as described in any one of claims 1 to 2, or the hand-eye calibration method for a robotic arm as described in claim 3.

6. A computer storage medium, characterized in that, The computer storage medium stores a computer program, which, when executed by a processor, implements the hand-eye calibration data acquisition method for the robotic arm as described in any one of claims 1 to 2, or the hand-eye calibration method for the robotic arm as described in claim 3.

Images