Industrial robot base coordinate system and tooling coordinate system fast calibration method and system

Abstract

The application relates to the technical field of visual measurement, in particular to a quick calibration method and system for an industrial robot base coordinate system and a tooling coordinate system, which comprises the following steps: acquiring the coordinates of target feature points in a target coordinate system; in the case that the target is mounted on an end tooling or an end flange of an industrial robot, acquiring target image information and robot pose information under multiple poses of the robot, so as to determine the conversion relationship between the robot base coordinate system and the target coordinate system; acquiring the coordinates of tooling feature points in a tooling coordinate system, and determining the coordinates of the tooling feature points in the robot base coordinate system based on the image information containing the target feature points and the tooling feature points and the aforementioned conversion relationship; and determining the conversion relationship between the robot base coordinate system and the tooling coordinate system according to the coordinates of the tooling feature points in the two coordinate systems. The application can quickly and accurately obtain the conversion relationship between the robot base coordinate system and the tooling coordinate system.

Description

Technical Field

[0001] This application relates to the field of visual measurement technology, and in particular to a rapid calibration method and system for the base coordinate system and tooling coordinate system of an industrial robot. Background Technology

[0002] In industrial robot automation applications, robot trajectory simulation, robot relocation and resetting, tooling replacement, and on-site machining task deployment typically require establishing a coordinate transformation relationship between the industrial robot's base coordinate system and the tooling coordinate system. The industrial robot's base coordinate system describes the spatial reference for robot motion control, while the tooling coordinate system describes the position and orientation of the workpiece, tooling holes, or machining positioning points on the on-site tooling. Since positional and orientation errors may occur during robot installation, tooling installation, relocation and resetting, and on-site assembly, if the transformation relationship between the two cannot be accurately obtained, offline simulation trajectories, workpiece positioning data, or motion trajectories reused before and after relocation will be difficult to maintain consistency with the actual on-site position, thus affecting robot motion accuracy and machining quality. Therefore, accurately and stably calibrating the relationship between the robot's base coordinate system and the tooling coordinate system is of great significance during on-site deployment and repeated calibration of industrial robots.

[0003] Existing calibration methods typically include fixed-point TCP calibration and laser tracker calibration. Fixed-point TCP calibration generally requires pre-determining several known coordinate points in the tooling coordinate system. The operator then manually guides the robot's end effector flange or end tool to the vicinity of these known coordinate points using a teach pendant, controlling the robot's end effector to contact or align with the same coordinate points in different poses. This process collects robot pose data and calculates the relationship between the robot's base coordinate system and the tooling coordinate system. Laser tracker calibration, on the other hand, typically uses external high-precision measuring equipment such as a laser tracker to perform spatial measurements on the robot's end effector or tooling feature points. The coordinate system calibration is then completed by combining the robot's pose data with the coordinates of the tooling feature points.

[0004] However, in actual industrial settings, tooling tables are often equipped with fixtures, positioning components, supports, or other machining auxiliary structures. Some tooling holes or feature points used for calibration may be obstructed, or there may be insufficient surrounding space, making it difficult for the robot end effector to directly reach the corresponding position and achieve stable contact or alignment using the fixed-point TCP calibration method. Even if the robot can reach the corresponding position, manual teaching and multiple contact operations increase calibration time and easily introduce human error, affecting the consistency of repeated calibrations. Although laser tracker calibration methods offer high measurement accuracy, they require high equipment and maintenance costs and specialized operation skills, making them unsuitable for widespread use in scenarios involving frequent relocation, rapid on-site deployment, or repeated calibrations. Therefore, existing technologies for calibrating the robot's base coordinate system and tooling coordinate system still suffer from significant limitations due to tooling structure obstruction or on-site space constraints, cumbersome calibration operations, and low efficiency in repeated calibrations. Thus, how to quickly and accurately obtain the transformation relationship between the industrial robot's base coordinate system and the tooling coordinate system while reducing the reliance on known points in direct contact between the robot end effector and the tooling is a problem that needs to be solved. Summary of the Invention

[0005] This application provides a rapid calibration method and system for the industrial robot base coordinate system and the tooling coordinate system, which can quickly and accurately obtain the transformation relationship between the industrial robot base coordinate system and the tooling coordinate system. This application provides the following technical solution: In a first aspect, this application provides a rapid calibration method for the base coordinate system of an industrial robot and the coordinate system of a tooling, the method comprising: Obtain the coordinates of multiple target feature points in the target coordinate system; When the target is installed on the end tooling or end flange of an industrial robot, target image information and robot pose information are acquired in multiple robot poses. Based on the target image information, the robot pose information, and the coordinates of each target feature point in the target coordinate system, the transformation relationship between the robot base coordinate system and the target coordinate system is determined. The coordinates of multiple tooling feature points on the tooling table in the tooling coordinate system are obtained, and the coordinates of each tooling feature point in the robot base coordinate system are determined based on the image information that simultaneously contains the target feature points and the tooling feature points, as well as the transformation relationship between the robot base coordinate system and the target coordinate system. Based on the coordinates of each tooling feature point in the tooling coordinate system and the coordinates of each tooling feature point in the robot base coordinate system, the transformation relationship between the robot base coordinate system and the tooling coordinate system is determined.

[0006] In one specific implementation, before obtaining the coordinates of multiple target feature points in the target coordinate system, the method further includes: The camera is calibrated to obtain its intrinsic parameter matrix and distortion coefficients; Obtain a target with multiple target feature points, wherein the target feature points include reflective coded points, reflective non-coded points, or a combination of reflective coded points and reflective non-coded points; When the target feature points include reflective coding points, the uniqueness of each reflective coding point is determined based on the coding information of the reflective coding points. In the case where the target feature points include reflective non-coded points, the uniqueness of each reflective non-coded point is determined based on the relative distance and relative position between each reflective non-coded point; When the target feature points include a combination of reflective coded points and reflective non-coded points, an affine transformation is performed based on the reflective coded points to determine the relative positions of the reflective non-coded points, and the uniqueness of each reflective non-coded point is determined based on the relative positions of the reflective non-coded points.

[0007] In one specific implementation, obtaining the coordinates of multiple target feature points in the target coordinate system includes: Select three non-collinear target feature points from a plurality of target feature points that have been determined to be unique; take the first target feature point among the three non-collinear target feature points as the origin of the target coordinate system; The direction from the first target feature point to the second target feature point is taken as the X-axis direction of the target coordinate system; the direction perpendicular to the plane formed by the first target feature point, the second target feature point, and the third target feature point is taken as the Z-axis direction of the target coordinate system. The Y-axis direction of the target coordinate system is determined based on the X-axis direction and the Z-axis direction, the target coordinate system is established, and the coordinates of each target feature point in the target coordinate system are determined.

[0008] In one specific implementation, determining the transformation relationship between the robot base coordinate system and the target coordinate system based on the target image information, the robot pose information, and the coordinates of each target feature point in the target coordinate system includes: Based on the target image information and the coordinates of each target feature point in the target coordinate system, the transformation relationship between the target coordinate system and the camera coordinate system under different robot poses is determined. Based on the robot pose information, determine the transformation relationship between different robot poses; Based on the transformation relationship between the target coordinate system and the camera coordinate system, as well as the transformation relationship between different robot poses, the transformation relationship between the robot end-effector coordinate system and the target coordinate system is determined based on the hand-eye calibration model. Based on the robot pose information corresponding to the target robot pose and the transformation relationship between the robot end-effector coordinate system and the target coordinate system, the transformation relationship between the robot base coordinate system and the target coordinate system under the target robot pose is determined.

[0009] In one specific implementation, obtaining the coordinates of multiple tooling feature points on the tooling table in the tooling coordinate system includes: A mechanical structure with tooling feature points is installed at multiple tooling holes on the tooling table, and the coordinates of each tooling hole in the tooling coordinate system are obtained. Based on the parameters of the mechanical structure, determine the positional compensation relationship between each tooling hole and the corresponding tooling feature point; Based on the coordinates of each tooling hole in the tooling coordinate system and the position compensation relationship, the coordinates of each tooling feature point in the tooling coordinate system are determined.

[0010] In one specific implementation, determining the coordinates of each tooling feature point in the robot base coordinate system based on image information simultaneously containing the target feature points and the tooling feature points, and the transformation relationship between the robot base coordinate system and the target coordinate system, includes: The end effector or end flange of the industrial robot is controlled to move to the vicinity of the tooling hole, and multiple sets of image information containing both the target feature points and the tooling feature points are acquired by the camera under different acquisition postures. Based on the image coordinates of each target feature point and each tooling feature point in the multiple sets of image information, the transformation relationship between different camera acquisition postures is determined, and the coordinates of each target feature point and each tooling feature point in the camera coordinate system are determined by the bundle adjustment method and triangulation. Based on the coordinates of each target feature point in the camera coordinate system and the coordinates of each target feature point in the target coordinate system, the transformation relationship between the target coordinate system and the camera coordinate system is determined, and the coordinates of each tooling feature point in the target coordinate system are determined based on the transformation relationship between the target coordinate system and the camera coordinate system. Based on the coordinates of each tooling feature point in the target coordinate system and the transformation relationship between the robot base coordinate system and the target coordinate system, the coordinates of each tooling feature point in the robot base coordinate system are determined.

[0011] In a specific implementation, determining the transformation relationship between the robot base coordinate system and the tooling coordinate system based on the coordinates of each tooling feature point in the tooling coordinate system and the coordinates of each tooling feature point in the robot base coordinate system includes: Obtain the coordinates of all tooling feature points on the tooling table in the robot base coordinate system, and obtain the coordinates of each tooling feature point in the tooling coordinate system; Establish the correspondence between the coordinates of the same tooling feature point in the tooling coordinate system and the coordinates in the robot base coordinate system; Based on the coordinates of each tooling feature point in the tooling coordinate system, the coordinates in the robot base coordinate system, and the corresponding relationship, the transformation relationship between the robot base coordinate system and the tooling coordinate system is solved by rigid body transformation. Based on the transformation relationship between the robot base coordinate system and the tooling coordinate system, the calibration between the robot base coordinate system and the tooling coordinate system is completed.

[0012] Secondly, this application provides a rapid calibration system for the base coordinate system and tooling coordinate system of an industrial robot, which adopts the following technical solution: A rapid calibration system for the base coordinate system and tooling coordinate system of an industrial robot includes: The target coordinate acquisition module is used to acquire the coordinates of multiple target feature points in the target coordinate system. The base-target conversion determination module is used to acquire target image information and robot pose information in multiple robot poses when the target is installed on the end tooling or end flange of an industrial robot, and to determine the conversion relationship between the robot base coordinate system and the target coordinate system based on the target image information, the robot pose information and the coordinates of each target feature point in the target coordinate system. The tooling coordinate determination module is used to acquire the coordinates of multiple tooling feature points on the tooling table in the tooling coordinate system, and determine the coordinates of each tooling feature point in the robot base coordinate system based on image information that simultaneously includes the target feature points and the tooling feature points, as well as the transformation relationship between the robot base coordinate system and the target coordinate system. The tooling calibration determination module is used to determine the transformation relationship between the robot base coordinate system and the tooling coordinate system based on the coordinates of each tooling feature point in the tooling coordinate system and the coordinates of each tooling feature point in the robot base coordinate system.

[0013] Thirdly, this application provides an electronic device, the device including a processor and a memory; the memory stores a program, the program being loaded and executed by the processor to implement a rapid calibration method for an industrial robot base coordinate system and a tooling coordinate system as described in the first aspect.

[0014] Fourthly, this application provides a computer-readable storage medium storing a program that, when executed by a processor, is used to implement a rapid calibration method for an industrial robot base coordinate system and a tooling coordinate system as described in the first aspect.

[0015] First, the coordinates of multiple target feature points on the target in the target coordinate system are obtained. Then, with the target installed on the end effector or end flange of an industrial robot, the transformation relationship between the robot base coordinate system and the target coordinate system is determined based on the target image information, robot pose information, and the coordinates of the target feature points in the target coordinate system under multiple robot poses. Subsequently, the coordinates of multiple tooling feature points on the tooling table in the tooling coordinate system are obtained. Based on the image information containing both target feature points and tooling feature points and the transformation relationship between the robot base coordinate system and the target coordinate system, the coordinates of each tooling feature point in the robot base coordinate system are determined. Finally, the transformation relationship between the robot base coordinate system and the tooling coordinate system is determined based on the coordinates of each tooling feature point in both the tooling coordinate system and the robot base coordinate system. Therefore, the tooling feature points do not need to rely on direct contact or precise arrival at the robot end effector. Instead, their coordinate representation in the robot's base coordinate system is established through the target coordinate system and image information. This reduces the impact of tooling structure occlusion and on-site space limitations on the calibration process. Furthermore, this application completes calibration by installing a target at the robot end effector, acquiring image information using a camera, and performing coordinate transformation calculations. It eliminates the need for external precision measuring equipment such as laser trackers, and avoids the need for contacting or aligning known points on the tooling table one by one according to the fixed-point TCP calibration method. This reduces the time spent on manual teaching and equipment deployment during on-site calibration, improving calibration efficiency. Moreover, the coordinates of multiple tooling feature points in both the tooling coordinate system and the robot's base coordinate system jointly participate in solving the transformation relationship, improving the stability and accuracy of the transformation relationship between the robot's base coordinate system and the tooling coordinate system, thereby enhancing the consistency of the calibration results.

[0016] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, the preferred embodiments of this application are described in detail below with reference to the accompanying drawings. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating the rapid calibration method for the industrial robot base coordinate system and tooling coordinate system in the embodiments of this application.

[0018] Figure 2 This is a schematic diagram of the target structure in an embodiment of this application.

[0019] Figure 3 This is a schematic diagram illustrating the principle of determining the uniqueness of non-coded points in the embodiments of this application.

[0020] Figure 4 This is a schematic diagram illustrating the principle of establishing the target coordinate system in the embodiments of this application.

[0021] Figure 5 This is a schematic diagram of the coordinate system transformation relationship in the embodiments of this application.

[0022] Figure 6 This is a schematic diagram of the overall process of the rapid calibration method for the industrial robot base coordinate system and tooling coordinate system in the embodiments of this application.

[0023] Figure 7 This is a structural block diagram of a rapid calibration system for the industrial robot base coordinate system and tooling coordinate system in an embodiment of this application.

[0024] Figure 8 This is a block diagram of an electronic device for rapid calibration of the industrial robot's base coordinate system and the tooling coordinate system in the embodiments of this application. Detailed Implementation

[0025] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are used to illustrate this application, but are not intended to limit the scope of this application.

[0026] Optionally, this application uses the rapid calibration method of industrial robot base coordinate system and tooling coordinate system provided in various embodiments in electronic devices as an example for illustration. The electronic device is a terminal or server. The terminal can be a computer, tablet computer, etc. This embodiment does not limit the type of electronic device.

[0027] Reference Figure 1 This is a flowchart illustrating a rapid calibration method for the industrial robot base coordinate system and tooling coordinate system provided in one embodiment of this application. The method includes at least the following steps: Step S101: Obtain the coordinates of multiple target feature points in the target coordinate system.

[0028] In step S101, to obtain target feature points that can be recognized by the camera and have a defined spatial relationship, the camera is first calibrated to determine its intrinsic parameter matrix and distortion coefficients. Then, a target with multiple target feature points is acquired, and the uniqueness of each feature point is determined. Based on the unique identifiability of each feature point, a target coordinate system is established using these multiple feature points, and the coordinates of each feature point in the target coordinate system are calculated. The intrinsic parameter matrix characterizes the internal parameters of the camera imaging model, and the distortion coefficients characterize the distortion parameters during the camera lens imaging process. By calibrating the camera, distortion correction can be performed on the image during target image processing, reducing the impact of image distortion on the target feature point extraction results.

[0029] Specifically, refer to Figure 2 , Figure 2 This is a schematic diagram of the target structure in an embodiment of this application, wherein, Figure 2 Part (a) is a 3D view of the target structure. Figure 2Part (b) is a front view of the target structure. In the figure, 1 represents the reflective coded point and 2 represents the reflective non-coded point. Figure 2 This describes the arrangement of multiple target feature points on a target. The target has multiple target feature points attached to it. The target feature points can be in the form of reflective coded points, reflective non-coded points, or a combination of reflective coded points and reflective non-coded points.

[0030] If the target feature points use reflective coded points, the uniqueness of each reflective coded point is determined through the encoding information. Specifically, the acquired target image undergoes distortion correction processing, and the contours of all reflective coded points within the target image are located. Reflective coded points are identified based on the edges corresponding to the found contours, and a unique encoding value is assigned to each reflective coded point by detecting the encoding rings around it. This yields the encoding value and image coordinates corresponding to the reflective coded points in the target image. Since different reflective coded points have different encoding values, the uniqueness of each reflective coded point can be determined based on the encoding information.

[0031] If the target feature points are reflective non-coded points, the uniqueness of each reflective non-coded point is determined by the relative distance and relative position between the feature points. Specifically, the acquired target image is processed to extract multiple reflective non-coded points from the image, and the relative distance and relative position relationship between the reflective non-coded points are determined based on the image position of each reflective non-coded point. Subsequently, the relative distance and relative position relationship between the reflective non-coded points are compared with the parameters determined when designing the target, and the best matching point is calculated, so that each reflective non-coded point corresponds to a specific point on the target, thereby determining the uniqueness of each reflective non-coded point.

[0032] If the target feature points are a combination of reflective coded points and reflective non-coded points, then an affine transformation is performed on the reflective coded points to determine the relative positions of the reflective non-coded points, and the uniqueness of each reflective non-coded point is determined by its relative position. (Refer to...) Figure 3 , Figure 3 This is a schematic diagram illustrating the principle of determining the uniqueness of non-coded points in the embodiments of this application. Figure 3 This describes the process of determining the uniqueness of non-coded reflective points by utilizing the relative positional relationship between them, based on the fact that the correspondence between coded reflective points can be determined through their encoding information. Specifically, firstly, the correspondence between coded reflective points in the target image and those in the target design parameters is determined based on their encoding information. Then, an affine transformation is performed on the coded reflective points with the established correspondences to align the relative positions of the non-coded reflective points with their relative positions in the target design parameters. Finally, the uniqueness of each non-coded reflective point is determined through its relative position.

[0033] After determining the uniqueness of all target feature points on the target, a target coordinate system is established based on these feature points. (Refer to...) Figure 4 , Figure 4 This is a schematic diagram illustrating the principle of establishing the target coordinate system in the embodiments of this application. Figure 4 In this method, the origin and coordinate axis directions of the target coordinate system are determined by three target feature points on the target. In one specific embodiment, three non-collinear target feature points are selected from a plurality of unique target feature points, denoted as P1, P2, and P3. P1 is used as the origin of the target coordinate system, the direction from P1 to P2 is used as the X-axis direction of the target coordinate system, the perpendicular direction of the plane formed by P1, P2, and P3 is used as the Z-axis direction of the target coordinate system, and the cross product of the X-axis and Z-axis directions is used as the Y-axis direction of the target coordinate system. Thus, the target coordinate system is established. Here, P1, P2, and P3 represent the three target feature points selected from the target for establishing the target coordinate system, the direction from P1 to P2 represents the direction from P1 to P2, and the plane formed by P1, P2, and P3 represents the plane jointly determined by P1, P2, and P3.

[0034] After establishing the target coordinate system, the coordinates of all target feature points in the target coordinate system are calculated based on the target design parameters and the positional relationships of each target feature point on the target. Through the above processing, the coordinates of multiple target feature points in the target coordinate system in step S101 are obtained.

[0035] Step S102: When the target is installed on the end tooling or end flange of the industrial robot, acquire the target image information and robot pose information in multiple robot poses, and determine the transformation relationship between the robot base coordinate system and the target coordinate system based on the target image information, robot pose information and the coordinates of each target feature point in the target coordinate system.

[0036] In step S102, based on the coordinates of each target feature point in the target coordinate system obtained in step S101, the target is installed on the end effector or end flange of the industrial robot, and the relative position between the target and the end effector or end flange is kept fixed. By controlling the robot to transform to multiple poses, target image information and robot pose information in multiple robot poses are obtained; then, combined with the coordinates of each target feature point in the target coordinate system, the transformation relationship between the robot base coordinate system and the target coordinate system is determined.

[0037] Reference Figure 5 , Figure 5 This is a schematic diagram of the coordinate system transformation relationship in the embodiments of this application. In the figure, 1 represents the tooling coordinate system, 2 represents the target coordinate system, 3 represents the flange coordinate system, and 4 represents the robot base coordinate system. Figure 5This document illustrates the transformation relationships between the tooling coordinate system, target coordinate system, flange coordinate system, and robot base coordinate system during the calibration process of this application. The following explanation uses the example of a target mounted on the robot's end effector flange. When the target is mounted on the robot's end effector tooling, the relative positions of the target and the end effector tooling remain fixed, and the same coordinate transformation logic is applied.

[0038] Specifically, a target is mounted on the robot's end flange, ensuring a fixed relative position between the target and the end flange. A camera is placed in a fixed position in front of the robot. The camera position is determined by the target size and camera parameters, which can be changed according to the industrial robot's parameters. The camera position must ensure that the target is clearly visible within the camera's field of view regardless of the robot's pose. The robot's end flange is controlled to change to different poses via a teach pendant, acquiring image information of the target in multiple robot poses. Simultaneously, the transformation relationship between the robot's base coordinate system and the robot's end flange coordinate system under corresponding poses is recorded. This transformation relationship is expressed as... Under different robot poses, the corresponding pose values ​​are recorded. .

[0039] During the acquisition of target image information, it is necessary to ensure that the target feature points on the target are unobstructed and that the image information is clear and distinguishable. In one specific embodiment, in order to calibrate the transformation relationship between the target coordinate system and the robot end flange coordinate system, at least three sets of target image data under different robot poses are collected; the redundant data obtained in actual operation can be used to optimize the accuracy and robustness of the calibration results.

[0040] After obtaining target image information under different robot poses, feature points are extracted and matched from the target images. Since step S101 has already determined the uniqueness of each target feature point and obtained the coordinates of each target feature point in the target coordinate system, the target feature points identified in the target image can be mapped to the target feature point coordinates in the target coordinate system. A camera coordinate system is established based on the camera pose. Combining the transformation relationship between different robot poses, and using the hand-eye calibration principle, the three-dimensional coordinates of the target feature points on the target under different robot poses in the camera coordinate system are obtained.

[0041] Furthermore, using the three-dimensional coordinates of the target feature points on the target in the camera coordinate system, and the coordinates of the target feature points on the target in the target coordinate system, the transformation relationship between the target coordinate system and the camera coordinate system under different robot poses is solved. This transformation relationship is expressed as follows: Under different robot poses, the corresponding poses are solved separately. .

[0042] Since the transformation relationship between the camera coordinate system and the robot base coordinate system remains unchanged when the camera position is fixed, and the transformation relationship between the robot end flange coordinate system and the target coordinate system remains unchanged when the target and the robot end flange are relatively fixed, the transformation relationship between the robot end flange coordinate system and the target coordinate system can be solved using a hand-eye calibration model by combining the transformation relationships between different robot poses and the transformation relationships between the target coordinate system and the camera coordinate system under different poses. The hand-eye calibration model is expressed as follows: ;in, This represents the relative transformation relationship between the robot's end effector flange coordinate system and different robot poses. This represents the relative transformation relationship between the target coordinate system and the camera coordinate system between different robot poses. This represents the transformation relationship between the robot end-effector coordinate system and the target coordinate system; in the formula... The relative transformation matrix in the hand-eye calibration model, and the robot base coordinate system identifier in the transformation relation subscript. They have different meanings.

[0043] Using the aforementioned hand-eye calibration model, the transformation relationship between the robot's end effector flange coordinate system and the target coordinate system is obtained. This transformation relationship is expressed as follows: The transformation relationship between the robot's end-effector coordinate system and the target coordinate system is obtained. Then, the transformation relationship between the robot base coordinate system and the robot end effector flange coordinate system under the target robot pose is combined. The transformation relationship between the robot's base coordinate system and the target coordinate system under the target robot's pose is solved using the following formula: ; Thus, the transformation relationship between the robot's base coordinate system and the target coordinate system in step S102 is determined.

[0044] Step S103: Obtain the coordinates of multiple tooling feature points on the tooling table in the tooling coordinate system, and determine the coordinates of each tooling feature point in the robot base coordinate system based on the image information that simultaneously contains target feature points and tooling feature points and the transformation relationship between the robot base coordinate system and the target coordinate system.

[0045] In step S103, based on the transformation relationship between the robot base coordinate system and the target coordinate system determined in step S102, the coordinates of multiple tooling feature points on the tooling table in the tooling coordinate system are first acquired; then the camera is enabled to simultaneously observe the target feature points on the target and the tooling feature points on the tooling table, and image information containing both target feature points and tooling feature points is acquired; then the coordinates of the tooling feature points in the target coordinate system are determined based on the image information, and the coordinates of each tooling feature point in the robot base coordinate system are determined using the transformation relationship between the robot base coordinate system and the target coordinate system.

[0046] Specifically, the tooling table has multiple tooling holes, and mechanical structures with tooling feature points are installed at each of these holes. The three-dimensional coordinates of the tooling holes in the tooling coordinate system are known. In practice, the tooling holes can also have known three-dimensional coordinates in the world coordinate system, and these coordinates are used to determine the coordinates of the tooling feature points in the tooling coordinate system, provided the relationship between the tooling coordinate system and the world coordinate system is determined. Since the tooling feature points are located on the mechanical structures installed at the tooling holes, there may be positional offsets between the tooling holes and the tooling feature points caused by the dimensions of the mechanical structure, the installation position, or the attachment position of the feature points. Therefore, the positional compensation relationship between the tooling holes and the corresponding tooling feature points is determined based on the parameters of the mechanical structure. Based on the coordinates of the tooling holes in the tooling coordinate system and this positional compensation relationship, the coordinates of the corresponding tooling feature points in the tooling coordinate system can be determined.

[0047] After determining the coordinates of the tooling feature points in the tooling coordinate system, the end effector or end flange of the industrial robot is moved near the tooling hole using a teach pendant, enabling the camera to simultaneously observe both the target feature points on the target and the tooling feature points at the tooling hole. Subsequently, the camera acquires multiple sets of image information at different acquisition postures, each set containing both target and tooling feature points. During the acquisition process, both target and tooling feature points should be within the camera's field of view, and the feature points in the images should be clearly and stably identified and extracted.

[0048] After obtaining multiple sets of image information under different camera acquisition postures, the transformation relationship between different camera acquisition postures is solved by utilizing the image coordinates of target feature points and tooling feature points under different camera acquisition postures, combined with the principles of multi-view geometry. Specifically, a camera coordinate system is established based on the first camera acquisition posture, and the transformation relationship between different camera acquisition postures and the spatial position of feature points are optimized using bundle adjustment based on the image coordinates of each target feature point and each tooling feature point in different images. Subsequently, triangulation is performed using the optimized transformation relationship between different camera acquisition postures to calculate the coordinates of the target feature points and tooling feature points in the camera coordinate system. Through the above processing, the two-dimensional image coordinates in multiple sets of images can be converted into three-dimensional coordinates in the camera coordinate system.

[0049] After obtaining the coordinates of the target feature points in the camera coordinate system, and combining them with the coordinates of the target feature points in the target coordinate system obtained in step S101, the transformation relationship between the target coordinate system and the camera coordinate system is calculated. This transformation relationship is expressed as follows: Determine the transformation relationship between the target coordinate system and the camera coordinate system. Then, by combining the coordinates of the tooling feature points in the camera coordinate system, the coordinates of the tooling feature points in the target coordinate system are obtained. Further, the transformation relationship between the robot base coordinate system and the target coordinate system, already determined in step S102, is utilized. Obtain the coordinates of the tooling feature points in the robot's base coordinate system.

[0050] The image acquisition, transformation relationship calculation between different camera acquisition postures, bundle adjustment optimization, triangulation, target coordinate system transformation, and robot base coordinate system transformation processes are repeated for the tooling feature points at different tooling holes on the tooling table to obtain the coordinates of all tooling feature points on the tooling table in the robot base coordinate system. In a specific embodiment, the number of tooling holes used for positioning on the tooling table is at least three, and the coordinates of these tooling holes in the tooling coordinate system or world coordinate system are known; the tooling feature points need to be clearly and stably identified and extracted within the camera's field of view. When the number of tooling feature points is more than three, redundant data can be further improved in terms of coordinate measurement accuracy through adjustment optimization methods.

[0051] Step S104: Determine the transformation relationship between the robot base coordinate system and the tooling coordinate system based on the coordinates of each tooling feature point in the tooling coordinate system and the coordinates of each tooling feature point in the robot base coordinate system.

[0052] In step S104, through the processing in step S103, the coordinates of all tooling feature points on the tooling table in the robot base coordinate system have been obtained, and the coordinates of each tooling feature point in the tooling coordinate system have been determined. Since the coordinates of the same tooling feature point in the tooling coordinate system and the coordinates in the robot base coordinate system represent the position of the same spatial point in two different coordinate systems, a coordinate correspondence relationship of the same tooling feature point in the two coordinate systems can be established, and the transformation relationship between the robot base coordinate system and the tooling coordinate system can be solved based on this correspondence relationship.

[0053] Specifically, first, the coordinates of all tooling feature points on the tooling table in the robot's base coordinate system are obtained, and then the coordinates of each tooling feature point in the tooling coordinate system are also obtained. Next, the coordinates of the same tooling feature point in the tooling coordinate system are mapped to its coordinates in the robot's base coordinate system, so that each tooling feature point has a set of corresponding coordinate data. This mapping is used to represent the positional correspondence between the same tooling feature point in the tooling coordinate system and the robot's base coordinate system.

[0054] After establishing the above correspondence, the transformation relationship between the robot base coordinate system and the tooling coordinate system is solved by using the coordinates of each tooling feature point in the tooling coordinate system and the coordinates in the robot base coordinate system through rigid body transformation. This transformation relationship is expressed as follows: The transformation relationship between the robot's base coordinate system and the tooling coordinate system is obtained by solving the problem. Complete the calibration between the robot's base coordinate system and the tooling coordinate system.

[0055] In summary, combining Figure 6 The rapid calibration method for the industrial robot base coordinate system and tooling coordinate system provided in this application uses the target coordinate system as an intermediate transition coordinate system in the coordinate transformation process to form a cascaded transformation relationship between the tooling coordinate system, the target coordinate system, and the robot base coordinate system. Specifically, firstly, the coordinates of multiple target feature points on the target in the target coordinate system are obtained; then, with the target installed on the end tooling or end flange of the industrial robot, target image information and robot pose information in multiple robot poses are collected to determine the transformation relationship between the robot base coordinate system and the target coordinate system; subsequently, tooling feature points are set at multiple tooling holes on the tooling table, and the coordinates of each tooling feature point in the tooling coordinate system are obtained. By using image information that simultaneously contains target feature points and tooling feature points, the tooling feature points are transformed from the target coordinate system to the robot base coordinate system; finally, based on the coordinate correspondence of the same batch of tooling feature points in the tooling coordinate system and the robot base coordinate system, the transformation relationship between the robot base coordinate system and the tooling coordinate system is solved through rigid body transformation, thereby completing the calibration.

[0056] Based on the above scheme, the tooling feature points on the tooling table no longer need to be directly contacted or precisely reached by the robot end effector. Instead, the target feature points and tooling feature points are observed simultaneously by a camera, and the spatial position of the tooling feature points is transferred to the robot base coordinate system using the target coordinate system. Therefore, the impact of structural obstructions such as fixtures, positioning parts, and supports on the tooling table, as well as insufficient on-site space, on the calibration process can be reduced, and the dependence of fixed-point TCP contact calibration on manual teaching and end effector contact operations can be reduced. At the same time, this application does not rely on high-cost external precision measurement equipment such as laser trackers. The coordinate relationship can be solved through the target, camera images, multi-pose information, and rigid body transformation, which can reduce the equipment and operation threshold. Under the same tooling and environmental configuration, the robot motion trajectory can also be reused, reducing the manual matching process during repeated calibration, making the calibration process more convenient, universal, and highly repeatable, thereby improving the efficiency and accuracy of obtaining the transformation relationship between the robot base coordinate system and the tooling coordinate system.

[0057] Figure 7This is a structural block diagram of a rapid calibration system for an industrial robot base coordinate system and a tooling coordinate system provided in one embodiment of this application. The system includes at least the following modules: The target coordinate acquisition module is used to acquire the coordinates of multiple target feature points in the target coordinate system. The base-target conversion determination module is used to acquire target image information and robot pose information in multiple robot poses when the target is installed on the end tooling or end flange of an industrial robot, and to determine the conversion relationship between the robot base coordinate system and the target coordinate system based on the target image information, robot pose information and the coordinates of each target feature point in the target coordinate system. The tooling coordinate determination module is used to obtain the coordinates of multiple tooling feature points on the tooling table in the tooling coordinate system, and determine the coordinates of each tooling feature point in the robot base coordinate system based on image information that simultaneously contains target feature points and tooling feature points and the transformation relationship between the robot base coordinate system and the target coordinate system. The tooling calibration determination module is used to determine the transformation relationship between the robot base coordinate system and the tooling coordinate system based on the coordinates of each tooling feature point in the tooling coordinate system and the coordinates of each tooling feature point in the robot base coordinate system.

[0058] For relevant details, please refer to the above method implementation examples.

[0059] Figure 8 This is a block diagram of an electronic device provided in one embodiment of this application. The device includes at least a processor 801 and a memory 802.

[0060] The processor 801 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 801 may be implemented using at least one hardware form selected from CPU, DSP, FPGA, and GPU. In this embodiment, the processor 801 is used to execute the data processing steps in the rapid calibration method for the industrial robot's base coordinate system and the tooling coordinate system, including acquiring and processing target image information and tooling feature point image information, identifying and matching target feature points and tooling feature points, solving the transformation relationship between different camera acquisition postures, triangulation calculations, solving the transformation relationship between the target coordinate system and the camera coordinate system, solving the transformation relationship between the robot's base coordinate system and the target coordinate system, and solving the transformation relationship between the robot's base coordinate system and the tooling coordinate system. The processor 801 can also perform coordinate transformation calculations based on the robot's pose information, target feature point coordinates, and tooling feature point coordinates to obtain calibration results.

[0061] The memory 802 may include one or more computer-readable storage media, which may be non-transitory. The memory 802 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices, flash memory devices, etc. In some embodiments, the memory 802 is used to store data such as program instructions, camera intrinsic parameter matrices, distortion coefficients, coordinates of target feature points in the target coordinate system, coordinates of tooling feature points in the tooling coordinate system, robot pose information, image processing results, and coordinate system transformation relationships. The non-transitory computer-readable storage medium in the memory 802 is used to store at least one instruction, which, when executed by the processor 801, implements the rapid calibration method for the industrial robot base coordinate system and tooling coordinate system provided in this application embodiment.

[0062] Optionally, this application also provides a computer-readable storage medium storing a program that is loaded and executed by a processor to implement the rapid calibration method for the industrial robot base coordinate system and tooling coordinate system of the above method embodiments.

[0063] Optionally, this application also provides a computer product including a computer-readable storage medium storing a program, which is loaded and executed by a processor to implement the rapid calibration method for the industrial robot base coordinate system and tooling coordinate system of the above method embodiments.

[0064] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0065] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A rapid calibration method for the base coordinate system and tooling coordinate system of an industrial robot, characterized in that, The method includes: Obtain the coordinates of multiple target feature points in the target coordinate system; When the target is installed on the end tooling or end flange of an industrial robot, target image information and robot pose information are acquired in multiple robot poses. Based on the target image information, the robot pose information, and the coordinates of each target feature point in the target coordinate system, the transformation relationship between the robot base coordinate system and the target coordinate system is determined. The coordinates of multiple tooling feature points on the tooling table in the tooling coordinate system are obtained, and the coordinates of each tooling feature point in the robot base coordinate system are determined based on the image information that simultaneously contains the target feature points and the tooling feature points, as well as the transformation relationship between the robot base coordinate system and the target coordinate system. Based on the coordinates of each tooling feature point in the tooling coordinate system and the coordinates of each tooling feature point in the robot base coordinate system, the transformation relationship between the robot base coordinate system and the tooling coordinate system is determined.

2. The rapid calibration method for the industrial robot base coordinate system and tooling coordinate system according to claim 1, characterized in that, Before obtaining the coordinates of multiple target feature points in the target coordinate system, the process also includes: The camera is calibrated to obtain its intrinsic parameter matrix and distortion coefficients; Obtain a target with multiple target feature points, wherein the target feature points include reflective coded points, reflective non-coded points, or a combination of reflective coded points and reflective non-coded points; When the target feature points include reflective coding points, the uniqueness of each reflective coding point is determined based on the coding information of the reflective coding points. In the case where the target feature points include reflective non-coded points, the uniqueness of each reflective non-coded point is determined based on the relative distance and relative position between each reflective non-coded point; When the target feature points include a combination of reflective coded points and reflective non-coded points, an affine transformation is performed based on the reflective coded points to determine the relative positions of the reflective non-coded points, and the uniqueness of each reflective non-coded point is determined based on the relative positions of the reflective non-coded points.

3. The rapid calibration method for the industrial robot base coordinate system and tooling coordinate system according to claim 2, characterized in that, The step of obtaining the coordinates of multiple target feature points in the target coordinate system includes: Select three non-collinear target feature points from a plurality of target feature points that have been determined to be unique; take the first target feature point among the three non-collinear target feature points as the origin of the target coordinate system; The direction from the first target feature point to the second target feature point is taken as the X-axis direction of the target coordinate system; the direction perpendicular to the plane formed by the first target feature point, the second target feature point, and the third target feature point is taken as the Z-axis direction of the target coordinate system. The Y-axis direction of the target coordinate system is determined based on the X-axis direction and the Z-axis direction, the target coordinate system is established, and the coordinates of each target feature point in the target coordinate system are determined.

4. The rapid calibration method for the industrial robot base coordinate system and tooling coordinate system according to claim 1, characterized in that, The step of determining the transformation relationship between the robot base coordinate system and the target coordinate system based on the target image information, the robot pose information, and the coordinates of each target feature point in the target coordinate system includes: Based on the target image information and the coordinates of each target feature point in the target coordinate system, the transformation relationship between the target coordinate system and the camera coordinate system under different robot poses is determined. Based on the robot pose information, determine the transformation relationship between different robot poses; Based on the transformation relationship between the target coordinate system and the camera coordinate system, as well as the transformation relationship between different robot poses, the transformation relationship between the robot end-effector coordinate system and the target coordinate system is determined based on the hand-eye calibration model. Based on the robot pose information corresponding to the target robot pose and the transformation relationship between the robot end-effector coordinate system and the target coordinate system, the transformation relationship between the robot base coordinate system and the target coordinate system under the target robot pose is determined.

5. The rapid calibration method for the industrial robot base coordinate system and tooling coordinate system according to claim 1, characterized in that, The step of obtaining the coordinates of multiple tooling feature points on the tooling table in the tooling coordinate system includes: A mechanical structure with tooling feature points is installed at multiple tooling holes on the tooling table, and the coordinates of each tooling hole in the tooling coordinate system are obtained. Based on the parameters of the mechanical structure, determine the positional compensation relationship between each tooling hole and the corresponding tooling feature point; Based on the coordinates of each tooling hole in the tooling coordinate system and the position compensation relationship, the coordinates of each tooling feature point in the tooling coordinate system are determined.

6. The rapid calibration method for the industrial robot base coordinate system and tooling coordinate system according to claim 1, characterized in that, The step of determining the coordinates of each tooling feature point in the robot base coordinate system based on image information simultaneously containing the target feature points and the tooling feature points, and the transformation relationship between the robot base coordinate system and the target coordinate system, includes: The end effector or end flange of the industrial robot is controlled to move to the vicinity of the tooling hole, and multiple sets of image information containing both the target feature points and the tooling feature points are acquired by the camera under different acquisition postures. Based on the image coordinates of each target feature point and each tooling feature point in the multiple sets of image information, the transformation relationship between different camera acquisition postures is determined, and the coordinates of each target feature point and each tooling feature point in the camera coordinate system are determined by the bundle adjustment method and triangulation. Based on the coordinates of each target feature point in the camera coordinate system and the coordinates of each target feature point in the target coordinate system, the transformation relationship between the target coordinate system and the camera coordinate system is determined, and the coordinates of each tooling feature point in the target coordinate system are determined based on the transformation relationship between the target coordinate system and the camera coordinate system. Based on the coordinates of each tooling feature point in the target coordinate system and the transformation relationship between the robot base coordinate system and the target coordinate system, the coordinates of each tooling feature point in the robot base coordinate system are determined.

7. The rapid calibration method for the industrial robot base coordinate system and tooling coordinate system according to claim 1, characterized in that, The step of determining the transformation relationship between the robot base coordinate system and the tooling coordinate system based on the coordinates of each tooling feature point in the tooling coordinate system and the coordinates of each tooling feature point in the robot base coordinate system includes: Obtain the coordinates of all tooling feature points on the tooling table in the robot base coordinate system, and obtain the coordinates of each tooling feature point in the tooling coordinate system; Establish the correspondence between the coordinates of the same tooling feature point in the tooling coordinate system and the coordinates in the robot base coordinate system; Based on the coordinates of each tooling feature point in the tooling coordinate system, the coordinates in the robot base coordinate system, and the corresponding relationship, the transformation relationship between the robot base coordinate system and the tooling coordinate system is solved by rigid body transformation. Based on the transformation relationship between the robot base coordinate system and the tooling coordinate system, the calibration between the robot base coordinate system and the tooling coordinate system is completed.

8. A rapid calibration system for the base coordinate system and tooling coordinate system of an industrial robot, characterized in that, include: The target coordinate acquisition module is used to acquire the coordinates of multiple target feature points in the target coordinate system. The base-target conversion determination module is used to acquire target image information and robot pose information in multiple robot poses when the target is installed on the end tooling or end flange of an industrial robot, and to determine the conversion relationship between the robot base coordinate system and the target coordinate system based on the target image information, the robot pose information and the coordinates of each target feature point in the target coordinate system. The tooling coordinate determination module is used to acquire the coordinates of multiple tooling feature points on the tooling table in the tooling coordinate system, and determine the coordinates of each tooling feature point in the robot base coordinate system based on image information that simultaneously includes the target feature points and the tooling feature points, as well as the transformation relationship between the robot base coordinate system and the target coordinate system. The tooling calibration determination module is used to determine the transformation relationship between the robot base coordinate system and the tooling coordinate system based on the coordinates of each tooling feature point in the tooling coordinate system and the coordinates of each tooling feature point in the robot base coordinate system.

9. An electronic device, characterized in that, The device includes a processor and a memory; the memory stores a program, which is loaded and executed by the processor to implement a rapid calibration method for the base coordinate system and tooling coordinate system of an industrial robot as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a program, which, when executed by a processor, is used to implement a rapid calibration method for the industrial robot base coordinate system and tooling coordinate system as described in any one of claims 1 to 7.

Images