Method and system for calibrating a tool

Abstract

Methods and systems for calibrating a tool are provided. A method for calibrating a tool mounted on a robotic arm includes determining a transformation relationship of a tool coordinate system relative to a calibration board coordinate system, acquiring an image of at least a portion of a calibration board, the calibration board containing identifying visual features and locating visual features, determining a transformation relationship of the calibration board coordinate system relative to a camera coordinate system based on the image, and calculating a transformation relationship of the tool coordinate system relative to the camera coordinate system.

Description

Technical Field

[0001] This disclosure relates to the field of robotics, and more particularly to a method for calibrating a tool, a system for calibrating a tool, and a computer-readable storage medium storing instructions for implementing the method for calibrating the tool. Background Technology

[0002] Robotic arms are the most widely used automated mechanical devices in the field of robotics, and can be found in fields such as industrial manufacturing, medical treatment, entertainment services, military, semiconductor manufacturing, and space exploration.

[0003] In robotic arm applications, hand-eye calibration refers to establishing the coordinate transformation relationship between vision sensors and the robotic arm, and it is a crucial step in industrial automation. The accuracy of the calibration results directly determines the precision of the robotic arm's grasping, assembly, and inspection operations, and is one of the core foundational technologies for ensuring the efficiency of automated industrial production lines. Traditional hand-eye calibration methods heavily rely on the precision of the robotic arm itself, which is very expensive and time-consuming, leading to insufficient calibration accuracy. Furthermore, it typically requires manual collection of multiple sets of vision and robotic arm data under different postures, making the process complex and time-consuming.

[0004] Therefore, there is an urgent need for a hand-eye calibration method that has a simple operation process, whose calibration results do not depend on the accuracy of the robotic arm itself, and can stably achieve high-precision calibration results. Summary of the Invention

[0005] This disclosure aims to overcome the above and / or other problems in the prior art, and provides a method for calibrating a tool, a system for calibrating a tool, and a computer-readable storage medium storing instructions for implementing the method for calibrating the tool. It can significantly simplify the process, improve calibration efficiency, enhance calibration accuracy, is insensitive to the accuracy of the robotic arm itself, has stronger robustness, and has stronger repeatability and portability.

[0006] According to a first aspect of this disclosure, a method for calibrating a tool mounted on a robotic arm is provided, the method comprising: S10: determining a transformation relationship between the tool coordinate system and a calibration plate coordinate system; S20: acquiring an image of at least a portion of the calibration plate, the calibration plate including visual features for identification and visual features for positioning; S30: determining a transformation relationship between the calibration plate coordinate system and a camera coordinate system based on the image; and S40: calculating a transformation relationship between the tool coordinate system and the camera coordinate system.

[0007] Preferably, determining the transformation relationship between the tool coordinate system and the calibration plate coordinate system may include: moving the robotic arm to guide the tool center point to a predetermined position on the calibration plate, and determining the position of the tool center point in the calibration plate coordinate system as the coordinates of the predetermined position.

[0008] Preferably, determining the transformation relationship between the tool coordinate system and the calibration plate coordinate system may include: adjusting the posture of the robotic arm so that the tool is in a predetermined posture relative to the calibration plate coordinate system.

[0009] Preferably, positioning the tool in a predetermined orientation relative to the calibration plate coordinate system may include aligning the Z-axis of the tool coordinate system perpendicularly to the plane of the calibration plate and having the X-axis of the tool coordinate system in the same direction as the X-axis of the calibration plate coordinate system.

[0010] Preferably, the image may contain at least three of the identification visual features and four of the positioning visual features.

[0011] Preferably, the image may include the end of the tool.

[0012] Preferably, the image may not include the end of the tool.

[0013] Preferably, the visual features for identification may include one or more of ArUco encoding, QR codes, and specific patterns, and the visual features for positioning may include one or more of checkerboard patterns, dot arrays, and calibration dot arrays.

[0014] Preferably, the method may include: performing one or more of steps S10 to S30 multiple times, and exponentially weighting the determined transformation relationship between the calibration plate coordinate system and the camera coordinate system.

[0015] Preferably, the method may include: performing one or more of steps S10 to S30 multiple times, and removing the current pose detection result when the change between the current pose detection result and the previous pose detection result exceeds a predetermined threshold.

[0016] According to a second aspect of this disclosure, a system for calibrating a tool is provided, the system comprising: a tool mounted on a robotic arm; a calibration plate including visual features for identification and visual features for positioning; a camera; and a processing unit configured to: determine a pose transformation relationship between the tool coordinate system and the calibration plate coordinate system; acquire an image of at least a portion of the calibration plate using the camera; determine a pose transformation relationship between the calibration plate coordinate system and the camera coordinate system based on the image; and calculate a pose transformation relationship between the tool coordinate system and the camera coordinate system.

[0017] According to a third aspect of this disclosure, a computer-readable storage medium is provided having instructions stored thereon that, when executed, cause a processor to perform the method described in any one of the preceding claims. Attached Figure Description

[0018] Therefore, in order to understand the above-described features of this case in detail, a more detailed description of this case can be made by referring to the embodiments, and a more specific description of the disclosure as briefly described above can be made by referring to the embodiments, some embodiments of which are illustrated in the accompanying drawings. However, it should be noted that the drawings only illustrate exemplary embodiments and should not be considered as limiting its scope, and other equivalent embodiments are permissible.

[0019] Figure 1 A calibration board is shown in the calibration process of a tool according to one embodiment of the present disclosure.

[0020] Figure 2 A schematic diagram of an apparatus for calibrating a tool is shown according to an embodiment of the present disclosure.

[0021] Figure 3 A flowchart of a method for calibrating a tool according to an embodiment of the present disclosure is shown.

[0022] Figure 4 A flowchart illustrating the transformation relationship between the coordinate system of the determination tool and the coordinate system of the calibration plate according to an embodiment of the present disclosure is shown.

[0023] Figure 5 A flowchart illustrating the transformation relationship between the calibration board coordinate system and the camera coordinate system according to an embodiment of the present disclosure is shown.

[0024] Figure 6 An example is shown of an interface that overlays the recognition results onto an image.

[0025] Figure 7 A schematic diagram of a system for calibrating tools according to an embodiment of the present disclosure is shown.

[0026] In the accompanying drawings, similar components and / or features may have the same reference numerals. Furthermore, components of the same type may be distinguished by a letter following the reference numeral, which may differentiate between similar components and / or features. If only the first numerical reference numeral is used in the description, the description applies to any similar component and / or feature having the same first numerical reference numeral, regardless of the letter. Detailed Implementation

[0027] The present disclosure will now be described in detail with reference to the accompanying drawings and specific embodiments. These embodiments are implemented based on the technical solution of the present disclosure, and detailed implementation methods and specific operating procedures are provided. However, the scope of protection of the present disclosure is not limited to the following embodiments.

[0028] Secondly, this disclosure is described in detail with reference to the schematic diagrams. When detailing the embodiments of this disclosure, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not according to general proportions. Furthermore, the schematic diagrams shown are merely examples and should not limit the scope of protection of this disclosure. In addition, actual fabrication should include three-dimensional spatial dimensions of length, width, and depth.

[0029] References to "an embodiment," "an embodiment," "an exemplary embodiment," etc., in the specification indicate that the described embodiment may include a specific feature, structure, or characteristic; however, not every embodiment necessarily includes that specific feature, structure, or characteristic. Furthermore, such phrases do not necessarily refer to the same embodiment. Additionally, when a specific feature, structure, or characteristic is described in connection with an embodiment, it is believed that the influence of such feature, structure, or characteristic on such feature, structure, or characteristic in conjunction with other embodiments, whether explicitly described or not, is within the knowledge of those skilled in the art.

[0030] For ease of description, spatial relative terms such as “below,” “under,” “down,” “above,” “up,” etc., may be used herein to describe the relationship of one element or feature relative to another element or feature as shown in the figure. It should be understood that spatial relative terms are intended to include different orientations of the device used or operated in addition to those shown in the figure. For example, if the device in the figure were flipped, an element described as “below” or “under” other elements or features would be oriented as “above” other elements or features.

[0031] Unless otherwise defined, the technical or scientific terms used in the claims and description shall have the ordinary meaning understood by one of ordinary skill in the art to which this disclosure pertains. The terms “first,” “second,” and similar terms used in this patent application description and claims do not indicate any order, quantity, or importance, but are merely used to distinguish different components. The terms “an” or “a” and similar terms do not indicate a quantity limitation, but rather indicate the presence of at least one. The terms “comprising” or “including” and similar terms mean that the element or object preceding “comprising” or “including” encompasses the element or object listed following “comprising” or “including” and its equivalents, and do not exclude other elements or objects. The terms “connected” or “linked” and similar terms are not limited to physical or mechanical connections, nor are they limited to direct or indirect connections.

[0032] Unless otherwise specified, all embodiments and preferred embodiments mentioned herein can be combined to form new technical solutions. Similarly, unless otherwise specified, all technical features and preferred features mentioned herein can be combined to form new technical solutions.

[0033] As used in this disclosure, the term "hand-eye calibration" can be interpreted as determining the transformation relationship between the coordinate system of the end effector (e.g., tool) of a robotic arm and the coordinate system of the vision sensor (e.g., camera coordinate system).

[0034] As used in this disclosure, the term "hand-eye calibration matrix" can be interpreted as a matrix representing the transformation relationship between the coordinate system of the robotic arm's end effector and the coordinate system of the vision sensor, which includes attitude information and position information.

[0035] Precise calibration of the Tool Center Point (TCP) is crucial for ensuring the accuracy of the robotic arm's end effector. TCP represents the relative pose of the tool end effector to its mounting position relative to the robotic arm's end effector, and its accuracy directly impacts the final precision of processes such as welding, painting, and assembly. TCP calibration essentially involves establishing a rigid transformation relationship between the coordinate system of the robotic arm's end effector (e.g., the tool) and the coordinate system of the robotic arm's base, and then substituting the result into the robotic arm's kinematic model.

[0036] Current hand-eye calibration methods can be broadly categorized into two types: The first type is calibration plate-based methods, which typically use calibration plates in the form of Aruco codes (square reference marks designed specifically for machine vision, similar to simplified QR codes), checkerboard patterns, or dot arrays as calibration references. By controlling the vision sensor and the robotic arm to complete multiple sets of coordinated movements, the corresponding data of visual feature points and robotic arm poses under different postures are collected, and then the hand-eye calibration matrix is ​​obtained. The second type is calibration methods based on geometric features, which do not require additional calibration plates and directly utilize existing fixed geometric features (such as edges, holes, etc.) in the workpiece to be processed or the robotic arm environment as calibration references.

[0037] However, both of the aforementioned existing hand-eye calibration methods have significant technical drawbacks. For calibration plate-based methods, the calibration process requires manual operation of the robotic arm to repeatedly adjust its posture, ensuring the camera at the end of the arm observes the calibration plate fixed to the worktable, and acquiring the robotic arm's pose data and corresponding images at each posture. To ensure observability and numerical stability, ten to dozens of samples are often required. This process is time-consuming, complex, demands high operator skill, has poor consistency, and heavily relies on the robotic arm's inherent accuracy. As for geometric feature-based calibration methods, their calibration process is highly dependent on specific pre-existing geometric features in the work environment, making them unsuitable for general work environments without corresponding features, resulting in a significantly limited application scope and insufficient versatility.

[0038] Therefore, this disclosure aims to provide a method for calibrating tools that has a simple operation process and can reliably achieve high-precision calibration.

[0039] Figure 1 A calibration board used in the calibration process of a tool according to an embodiment of this disclosure is shown. The calibration board may include identification visual features (e.g., ArUco codes, QR codes, specific pattern codes, etc.) and location visual features (e.g., checkerboard, dot array, calibration dot array, etc.). As a preferred example, the calibration board may be a ChArUco hybrid calibration board, which includes ArUco-coded markers as identification visual features and precise corner points of the checkerboard as location visual features, combining robust identification and high-precision location characteristics. The basic structure of the ChArUco hybrid calibration board is to embed an ArUco code with a unique identification code in each square of a standard checkerboard pattern. This design allows the calibration board to combine the advantages of ArUco coded markers and checkerboard patterns: the checkerboard pattern provides a large number of regularly arranged internal corner points that can be used for sub-pixel level precise positioning to achieve high-precision measurement; while the ArUco markers provide identification capabilities and anti-interference characteristics, enabling rapid and reliable detection and identification of the markers and their codes even under complex imaging conditions such as partial occlusion, uneven lighting, or non-frontal view.

[0040] Figure 2 A schematic diagram of an apparatus 200 for calibrating a tool according to an embodiment of the present disclosure is shown. The apparatus 200 includes a robotic arm 201 and a tool 203 mounted on the robotic arm 201. The apparatus 200 also includes a reference... Figure 1The described device includes a ChArUco hybrid calibration plate 210. Furthermore, the apparatus includes a camera 205, which can be mounted on a robotic arm 201. Specifically, the camera 205 can be mounted at the end flange of the robotic arm, and it is not required that the camera can directly observe the tool center point (TCP) end of the robotic arm. The calibration method according to embodiments of this disclosure has good anti-occlusion capabilities, and can still accurately calibrate the position and orientation of the TCP even if the camera can only observe a portion of the ChArUco hybrid calibration plate 210. When the camera can simultaneously observe the TCP end, the alignment of the TCP with the calibration plate can be directly displayed in the camera's field of view, further simplifying the teaching process and improving operational visualization and verification efficiency.

[0041] Figure 3 A flowchart of a method 300 for calibrating a tool according to an embodiment of the present disclosure is shown. In step S10, the transformation relationship between the tool coordinate system and the calibration plate coordinate system is determined, that is, the pose transformation relationship of the tool center point (TCP) relative to the calibration plate is determined. .

[0042] Figure 4 A flowchart illustrating the transformation relationship between the tool coordinate system and the calibration plate coordinate system according to an embodiment of the present disclosure is shown. In step S101, the calibration plate 210 is arranged on the worktable. Specifically, the plane of the calibration plate 210 can be made substantially parallel to the ground, and the origin of the coordinate system of the calibration plate 210 can be made to face upwards. This arrangement facilitates subsequent operations on it by the robotic arm. Those skilled in the art will understand that the calibration plate 210 can be placed in any posture that is conducive to visual recognition. In addition, in order to ensure the accuracy of the pose solution, the calibration plate 210 needs to be placed within the effective field of view of the camera 205. Furthermore, in scenes with strong or highly variable ambient light, the effects of specular reflection or shadows can be avoided by, for example, adding a matte background or using diffuse lighting, thereby improving recognition stability.

[0043] In step S103, the robotic arm 201 is moved to guide the tool center point (TCP) to a predetermined position (in this embodiment, the origin) on the calibration plate 210, and the position of the TCP in the calibration plate coordinate system is determined as the coordinates of that predetermined position. The robotic arm can be moved via manual teaching. To reduce errors from human alignment, a low-speed fine-tuning mode is preferred, allowing the operator to gradually correct the TCP position until the deviation between the TCP and the calibration plate origin is imperceptible to the naked eye. At this point, the TCP and the calibration plate origin can be considered to coincide in spatial position, and the positional relationship between the tool coordinate system and the calibration plate coordinate system can be established. (That is, the positional relationship of TCP relative to the calibration board) is determined as follows: Formula 1. (Formula 1)

[0044] If further calibration of the attitude relationship between the tool and the camera is required, in step S105, the attitude of the robotic arm 201 can be adjusted so that the tool 203 is in a predetermined attitude relative to the calibration plate coordinate system. While keeping the TCP at the origin of the calibration plate unchanged, the attitude of the end effector of the robotic arm can be finely adjusted so that: the normal (i.e., the Z-axis direction) of the tool coordinate system (represented here by the TCP) is parallel to and opposite in direction to the normal (i.e., the Z-axis direction) of the calibration plate coordinate system; that is, the TCP points perpendicularly to the calibration plate plane with its Z-axis direction; the X-axis direction of the tool coordinate system is parallel to and in the same direction as the X-axis direction of the calibration plate coordinate system; and the Y-axis direction of the tool coordinate system is parallel to and opposite in direction to the Y-axis direction of the calibration plate coordinate system. Thus, the rotational relationship of the tool coordinate system relative to the calibration plate coordinate system can be determined. (That is, the attitude relationship of TCP relative to the calibration board) is determined as follows: Formula 2. (Formula 2)

[0045] Therefore, in step S107, the transformation relationship between the tool coordinate system and the calibration board coordinate system (i.e., the pose transformation relationship between the TCP and the calibration board) can be established. The formula is determined as follows: Formula 3. (Formula 3)

[0046] return Figure 3 Next, in step S20, an image of at least a portion of the calibration board 210 is acquired via camera 205. The robotic arm is kept stationary, and the camera's exposure, focal length, white balance, and depth-of-field imaging parameters are set appropriately to ensure that the features on the calibration board are clearly visible without significant blurring, overexposure, or underexposure. The acquired image data can be transmitted in real-time via a communication interface for subsequent recognition and calibration calculations. The image contains at least three recognition visual features and four positioning visual features; that is, in the embodiment using the ChArUco hybrid calibration board 210, it contains three ArUco codes and four checkerboard corner points to ensure the solvability and stability of the pose calculation. The image may or may not contain the tool's end effector. When the calibration board is partially obscured in the camera's field of view, the overall pose of the calibration board can be reconstructed using the recognized visual features, thereby maintaining the stability and continuity of the pose estimation.

[0047] In step S30, based on the acquired image, the transformation relationship between the calibration board coordinate system and the camera coordinate system is determined. . Figure 5 This illustrates the transformation relationship between the calibration board coordinate system and the camera coordinate system according to an embodiment of the present disclosure. The flowchart.

[0048] In step S301, visual feature recognition and localization are performed on the acquired image. The calculation module can call the calibration board recognition algorithm to identify the visual features in the acquired image and locate the visual features in the acquired image. In this embodiment, the ChArUco calibration board recognition algorithm can be called to perform corner detection and ArUco encoding / decoding on the acquired image.

[0049] In step S303, the transformation relationship between the calibration plate coordinate system and the camera coordinate system is determined. Based on the localization and recognition of visual features, the pixel coordinates of the visual features in the acquired image can be calculated, and the three-dimensional coordinates of the visual features in the calibration board coordinate system can be determined. This allows us to obtain the mapping relationship between the calibration board coordinate system and the camera coordinate system, that is, to determine the transformation relationship between the calibration board coordinate system and the camera coordinate system. As shown in Formula 4 below. (Formula 4)

[0050] Here, even if the image acquired by the camera does not include the entire calibration board and TCP, the overall pose of the calibration board can be reconstructed using the visual features for recognition and localization already contained in the image.

[0051] return Figure 3 Preferably, one or more of steps S10 to S30 can be performed multiple times to obtain multiple frames of images, and the transformation relationship between the calibration board coordinate system and the camera coordinate system can be determined based on the multiple frames of images to obtain multiple pose relationship recognition results. Next, preferably, in step S32, data filtering and anomaly removal can be performed. To improve the stability and continuity of the pose data and ultimately ensure calibration accuracy, data post-processing including data filtering and anomaly removal can be performed after obtaining the determination results of the multiple frames of images. The pose relationship results determined based on consecutive multiple frames of images can be filtered (e.g., smoothing filter) to suppress random noise and short-term jitter. Furthermore, when an abnormal frame is detected (e.g., corner mismatch, feature loss, or sudden illumination change), the abnormal frame can be automatically removed or re-acquisition can be triggered to ensure the validity and consistency of the calibration data.

[0052] Data filtering can be a smoothing algorithm based on exponentially weighted low-pass filtering, which updates continuously determined results exponentially, so that the weighted results can smoothly transition between the current frame and historical results, thereby suppressing instantaneous fluctuations caused by changes in illumination, image noise or corner jitter.

[0053] For a single acquired image frame, the pose of the calibration board in the camera coordinate system can be identified based on that image frame. , pose Includes translation part and posture part Orientation Filtering includes the translation portion and posture part Filtering is performed separately, as shown in Equations 5 and 6 below. The translation part uses an exponentially weighted average, while the attitude part uses spherical linear interpolation in quaternion space to ensure the accuracy and smoothness of the rotational interpolation. (Formula 5) (Formula 6)

[0054] in This is the translation vector for the current frame; This is the rotation matrix for the current frame; This is a smoothing coefficient; the smaller its value, the smoother the output, but the slower the response to new data. This represents a spherical linear interpolation function used for attitude smoothing.

[0055] When filtering is performed, the recognition result of the first frame image is used as the initial filter value. Subsequently, when each frame image is updated, the filtered result of the previous frame is combined with the current recognition result with weights to obtain a continuous and stable pose relationship recognition result.

[0056] For anomaly removal, when the amount of pose change between adjacent frames exceeds a predetermined threshold (e.g., a translational change exceeding approximately 5 mm, or a pose angle change exceeding 2°), the current frame is identified as anomalous data and automatically aligned or resampled.

[0057] In step S40, the transformation relationship between the tool coordinate system and the camera coordinate system is calculated. .

[0058] Since the TCP has been guided to a predetermined position on the calibration board 210, and the three-dimensional position coordinates of this predetermined position on the calibration board 210 in the camera coordinate system can be determined by the ChArUco calibration board recognition algorithm, the displacement of the calibration board relative to the camera can be used as a basis for the determination. Determine the displacement of the TCP relative to the camera In this embodiment, the predetermined position on the calibration plate 210 is the origin, therefore the displacement of the TCP relative to the camera... It can be determined as shown in Formula 7 below. (Formula 7)

[0059] In addition, the ChArUco calibration board recognition algorithm can determine the rotation relationship between the calibration board coordinate system and the camera coordinate system. Therefore, it can be based on the rotation relationship between the tool coordinate system and the calibration plate coordinate system. The rotation relationship between the tool coordinate system and the camera coordinate system can be obtained using the following formula 8. (Formula 8)

[0060] Based on this, the transformation relationship between the tool coordinate system and the camera coordinate system can be calculated, as shown in Formula 9 below. (Formula 9)

[0061] And through the By finding the inverse matrix, we can obtain the required camera-to-TCP hand-eye calibration matrix, as shown in Formula 10 below. (Formula 10)

[0062] Preferably, the feature points and coordinate system orientations identified from the image can be overlaid on the image and displayed on the interface to assist in verifying the recognition effect and the correctness of the posture orientation, such as... Figure 6 As shown.

[0063] After the calibration process is complete, the system can visually verify the calibration results through a software interface. Specifically, the interface can simultaneously display the calibration board coordinate system identified in real time by the visual algorithm, and the tool coordinate system calculated based on the hand-eye calibration matrix obtained in this calibration and projected onto the image. By intuitively comparing the positions and orientations of these two coordinate systems in the image, the operator can verify the accuracy of the previous manual alignment of the "tool and calibration board origin" and evaluate the validity of the final hand-eye calibration results.

[0064] According to embodiments of this disclosure, a computer-readable storage medium is also provided, on which encoded instructions are recorded, which, when executed, implement the method described above for calibrating a tool mounted on a robotic arm according to this disclosure. The computer-readable storage medium may include, but is not limited to: phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, optical disc read-only memory (CD-ROM), optical disc read / write (CD-R / W) drives, digital versatile optical discs (DVDs) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transfer medium, which can be used to store information accessible by a computing device. Hard disk drives, floppy disk drives, digital universal disk (DVD) drives, flash memory drives, and / or solid-state storage devices, etc., are also included.

[0065] According to embodiments of this disclosure, a computer program product is also provided, including a computer program that, when executed, implements the method for calibrating a robotic arm as described above. The computer program product can be implemented using various programming languages, such as C, C++, Java, Python, and JavaScript, to adapt to different development environments and platform requirements.

[0066] According to embodiments of this disclosure, a device for calibrating a tool mounted at a robotic arm mounting location is also provided.

[0067] refer to Figure 7 The document illustrates a system 700 for calibrating a tool mounted at a robotic arm mounting location according to an embodiment of the present disclosure, including... Figure 2 The tool, calibration plate, camera, and processing unit 710 mounted on the robotic arm are shown in the diagram. The control unit 710 can be configured to perform the various steps described above.

[0068] The tool calibration method disclosed herein achieves significant and beneficial technical effects. Firstly, it fundamentally simplifies the operation process and efficiency, eliminating the need for multiple pose data acquisition and processing steps. Calibration can be achieved with only one manual teaching alignment and a single image capture, significantly shortening calibration time, improving efficiency, and facilitating rapid deployment and application in production environments. Secondly, the calibration accuracy is fundamentally freed from dependence on the precision of the robotic arm itself. Since the calibration process does not rely on the geometric parameters or kinematic precision of the robotic arm, its own geometric errors, transmission errors, or absolute positioning errors will not be transmitted to the calibration results. Therefore, even with limited precision of the robotic arm itself, accurate tool-camera pose relationships can still be obtained. Furthermore, this disclosure integrates the anti-occlusion and high-precision recognition characteristics of the ChArUco hybrid calibration board, combined with a pose data filtering and anomaly removal post-processing mechanism, effectively suppressing interference from noise, illumination fluctuations, and other factors, achieving high precision and high repeatability of the calibration results. In addition, the method disclosed herein is simple to implement, has good versatility and portability, and can be widely applied to visual guidance systems and calibration scenarios for robots of different configurations.

[0069] It should be understood that the above description is illustrative and not restrictive. For example, the above embodiments (and / or aspects thereof) can be used in combination with each other. Furthermore, many modifications can be made to adapt particular situations or materials to the teachings of the various embodiments of this disclosure without departing from the scope of this disclosure. While the dimensions and types of materials described herein are used to define parameters of the various embodiments of this disclosure, the embodiments are not intended to be restrictive but are exemplary. Many other embodiments will become apparent to those skilled in the art upon reading the above description. Therefore, the scope of the various embodiments of this disclosure should be determined by reference to the appended claims and the full scope of their equivalents.

Claims

1. A method for calibrating a tool, the tool being mounted on a robotic arm, the method comprising: S10: Determine the transformation relationship between the tool coordinate system and the calibration plate coordinate system; S20: Acquire an image of at least a portion of a calibration board, the calibration board comprising visual features for identification and visual features for localization; S30: Determine the transformation relationship between the calibration board coordinate system and the camera coordinate system based on the image; and S40: Calculate the transformation relationship between the tool coordinate system and the camera coordinate system.

2. The method of claim 1, wherein determining the transformation relationship between the tool coordinate system and the calibration plate coordinate system comprises: The robotic arm is moved to guide the tool center point to a predetermined position on the calibration plate, and the position of the tool center point in the calibration plate coordinate system is determined as the coordinates of the predetermined position.

3. The method of claim 1, wherein determining the transformation relationship between the tool coordinate system and the calibration plate coordinate system includes: Adjust the posture of the robotic arm so that the tool is in a predetermined posture relative to the calibration plate coordinate system.

4. The method of claim 3, wherein positioning the tool in a predetermined orientation relative to the calibration plate coordinate system comprises positioning the Z-axis of the tool coordinate system perpendicular to the plane of the calibration plate and the X-axis of the tool coordinate system having the same direction as the X-axis of the calibration plate coordinate system.

5. The method of claim 1, wherein the image comprises at least three of the recognition visual features and four of the positioning visual features.

6. The method of claim 1, wherein the image includes the end of the tool.

7. The method of claim 1, wherein the image does not include the end of the tool.

8. The method of claim 1, wherein the visual identification feature includes one or more of ArUco encoding, QR code, and specific pattern, and the visual positioning feature includes one or more of checkerboard, dot array, and calibration dot array.

9. The method of claim 1, wherein the method comprises: Perform one or more of steps S10 to S30 multiple times, and apply an exponential weight to the determined transformation relationship between the calibration plate coordinate system and the camera coordinate system.

10. The method of claim 1, wherein the method comprises: Perform one or more of steps S10 to S30 multiple times, and when the change between the current pose detection result and the previous pose detection result exceeds a predetermined threshold, remove the current pose detection result.

11. A system for calibrating a tool, the system comprising: The tool is mounted on the robotic arm; A calibration board, the calibration board comprising visual features for identification and visual features for positioning; camera; as well as A processing unit configured to perform the method as described in any one of claims 1 to 10.

12. A computer-readable storage medium having instructions stored thereon that, when executed, cause a processor to perform the method as described in any one of claims 1 to 10.

Images