Tool coordinate system calibration method for a collaborative robot arm

Abstract

The application relates to the field of robot positioning, in particular to a tool coordinate system calibration method of a collaborative robot mechanical arm, which comprises the following steps: changing the pose of the robot, performing plane estimation and definition analysis on calibration board data collected by a camera, accurately obtaining a plurality of groups of 6D poses of the collaborative robot mechanical arm, and obtaining a transformation matrix of the tool coordinate system relative to a base coordinate system based on the 6D poses of the plurality of groups of mechanical arms, so that the accuracy of tool coordinate system calibration can be improved. Moreover, the tool coordinate system of the collaborative robot can be accurately calibrated without using a high-precision three-coordinate instrument, the economic cost of work coordinate system calibration is reduced, and the calibration efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of robot positioning, in particular to a tool coordinate system calibration method of a collaborative robot mechanical arm. BACKGROUND

[0002] A collaborative robot combined with a vision system can well assist humans in completing mechanical work, fully exerting the efficiency of the robot and the precision of the vision. In actual application, due to the limitations of process and mechanical mechanism, a new tool coordinate system is often defined, which is a coordinate system used to define the position of a tool center point (TCP) and the tool attitude.

[0003] The traditional method of calibrating the tool coordinate system is to adjust the different attitudes of the collaborative robot, align the end with the same reference point, and calculate the calibrated tool coordinate system. However, this method is affected by the machining precision of the end structure, subjective factors, etc., resulting in large errors in the newly created tool coordinate system, which cannot be practically applied in some high-precision and high-detection accuracy applications. In order to pursue a higher-precision tool coordinate system, a high-precision three-coordinate instrument is also used for auxiliary calibration, but this instrument is expensive and is often not purchased for use in actual projects.

[0004] Therefore, how to accurately calibrate the tool coordinate system of the collaborative robot mechanical arm is a problem to be solved. SUMMARY

[0005] The present application provides a tool coordinate system calibration method of a collaborative robot mechanical arm, which changes the pose of the robot, performs plane estimation and definition analysis on the calibration plate data collected by the camera, obtains multiple sets of 6D poses of the collaborative robot mechanical arm, and obtains the transformation matrix of the tool coordinate system relative to the base coordinate system based on the multiple sets of 6D poses of the robot, thereby improving the accuracy of tool coordinate system calibration.

[0006] In order to achieve the above purpose, the present application adopts the following technical solutions:

[0007] In a first aspect, the present application provides a tool coordinate system calibration method of a collaborative robot mechanical arm, which comprises:

[0008] Obtaining the positional relationship between the camera and the collaborative robot;

[0009] Establishing a contour feature model of the marker and obtaining multiple marker-equipped calibration plate images;

[0010] Based on the contour feature model, using a contour matching algorithm to determine the position and direction of the marker in the calibration plate image;

[0011] generate a first movement instruction based on the position and direction of the marker in the calibration board image, send the movement instruction to the collaborative robot to make the marker located at the center of the camera, and then send a second movement instruction to make the robot arm move along the optical axis direction of the camera, and send a plurality of shooting instructions to the camera during the movement to obtain a plurality of calibration board images in which the marker has the same position and direction;

[0012] perform clarity evaluation on the plurality of calibration board images in which the marker has the same position and direction, and select a calibration board image with the highest clarity as a pose image;

[0013] obtain the 6D pose of the robot arm when the pose image is shot;

[0014] calibrate the tool coordinate system based on the 6D poses of the plurality of robot arms and in combination with the position relationship.

[0015] In a preferred example of the present application, the calibration of the tool coordinate system based on the 6D poses of the plurality of robot arms and in combination with the position relationship can further be provided as comprising:

[0016] calibrating the tool coordinate system based on the 6D poses of more than four robot arms and in combination with the position relationship.

[0017] In a preferred example of the present application, the obtaining of the position relationship between the camera and the collaborative robot can further be provided as comprising:

[0018] obtaining a conversion matrix of the coordinate systems of the camera and the collaborative robot into a world coordinate system.

[0019] In a preferred example of the present application, the clarity evaluation on the plurality of calibration board images in which the marker has the same position and direction can further be provided as comprising:

[0020] performing clarity evaluation on the plurality of calibration board images in which the marker has the same position and direction using an edge detection algorithm.

[0021] In a preferred example of the present application, the clarity evaluation on the plurality of calibration board images in which the marker has the same position and direction using an edge detection algorithm can further be provided as comprising:

[0022] evaluating the sharpness of the stripes of a plurality of stripe groups in each quadrant of the plurality of calibration board images in which the marker has the same position and direction using an edge detection algorithm.

[0023] In a preferred example of the present application, the method can further comprise:

[0024] In combination with the sharpness, a variance value of the stripe width within each stripe group of the calibration plate image is calculated;

[0025] The definition is evaluated according to the variance value and the sharpness of the stripe.

[0026] In a second aspect, the application provides a tool coordinate system calibration device of a collaborative robot arm, the device comprising:

[0027] A position acquisition module is configured to acquire a position relationship between a camera and the collaborative robot;

[0028] A contour recognition module is configured to establish a contour feature model of a marker, acquire multiple marker-equipped calibration plate images, and determine the position and direction of the marker in the calibration plate images based on the contour feature model and using a contour matching algorithm;

[0029] A definition evaluation module is configured to generate a first movement instruction based on the position and direction in the calibration plate image, send the movement instruction to the collaborative robot, make the marker located at the center of the camera, then send a second movement instruction to make the mechanical arm move along the optical axis direction of the camera, send multiple shooting instructions to the camera during the movement, and obtain multiple calibration plate images with the same position and direction of the marker; and perform definition evaluation on the multiple calibration plate images with the same position and direction of the marker, and select a calibration plate image with the highest definition as a pose image.

[0030] A path planning module is configured to plan a path of an end effector based on the first six-dimensional coordinate and the second six-dimensional coordinate, and obtain a rotation angle and a rotation direction of a wrist joint by using an inverse kinematics algorithm, wherein the rotation direction is a clockwise direction or an anticlockwise direction.

[0031] A calibration module is configured to acquire a 6D pose of the mechanical arm when the pose image is shot, and calibrate a tool coordinate system based on multiple 6D poses of the mechanical arm and in combination with the position relationship.

[0032] In a third aspect, the application provides a computer device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the tool coordinate system calibration method of the collaborative robot arm according to any one of the above aspects when executing the computer program.

[0033] In a fourth aspect, the application provides a computer readable storage medium, wherein the computer readable storage medium stores a program, and the program is executable by a processor to implement the tool coordinate system calibration method of the collaborative robot arm according to any one of the above aspects.

[0034] In a fifth aspect, the present application provides a computer program product comprising computer instructions which, when executed by a processor, implement the steps of the tool coordinate system calibration method of the collaborative robot arm according to any one of the above aspects.

[0035] Compared with the prior art, the technical solutions provided by the embodiments of the present application have at least the following beneficial effects:

[0036] The tool coordinate system calibration method of the collaborative robot arm provided by the present application can accurately obtain a plurality of sets of 6D poses of the collaborative robot arm by changing the pose of the robot, performing plane estimation and definition analysis on the calibration board data collected by the camera, and obtaining the transformation matrix of the tool coordinate system relative to the base coordinate system based on the plurality of sets of 6D poses of the robot arm, thereby improving the accuracy of tool coordinate system calibration. Moreover, the tool coordinate system of the collaborative robot can be accurately calibrated without using a high-precision three-coordinate instrument, thereby not only reducing the economic cost of work coordinate system calibration, but also improving the efficiency of calibration. BRIEF DESCRIPTION OF DRAWINGS

[0037] Figure 1 A flowchart of a tool coordinate system calibration method of a collaborative robot arm according to an embodiment of the present application.

[0038] Figure 2 A calibration board diagram of a tool coordinate system calibration method of a collaborative robot arm according to an embodiment of the present application.

[0039] Figure 3 A structural diagram of a tool coordinate system calibration device of a collaborative robot arm according to an embodiment of the present application. DETAILED DESCRIPTION

[0040] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0041] In an embodiment of the present application, a tool coordinate system calibration method of a collaborative robot arm is provided. As shown in Figure 1 The method comprises the following steps:

[0042] S100: Obtain the positional relationship between the camera and the collaborative robot;

[0043] Specifically, the camera is fixed on the robotic arm of the collaborative robot. After determining the positional relationship between the camera and the collaborative robot through hand-eye calibration, this positional relationship is obtained, and the camera coordinate system and the collaborative robot coordinate system are aligned to the world coordinate system.

[0044] In a preferred embodiment, the coordinate systems of the camera and the collaborative robot are converted to the world coordinate system to obtain the transformation matrix between the two coordinate systems.

[0045] S200: Establish the contour feature model of the markers and acquire multiple images of the calibration plate with the markers;

[0046] Specifically, such as Figure 2 As shown, the marker is an irregular ellipse located in the middle of the calibration plate. After establishing the contour feature model of the marker, the pose of the collaborative robot is adjusted so that the robotic arm moves to different positions, allowing the camera to capture images of the calibration plate from different angles. Then, multiple images of the marker at different positions on the calibration plate are obtained.

[0047] S300: Based on the contour feature model, a contour matching algorithm is used to determine the position and orientation of the marker in the calibration plate image;

[0048] Specifically, a contour matching algorithm is used to identify the contours of the markers in each marker image, thereby obtaining the position of the marker center point and the orientation of the marker's planar coordinate system.

[0049] S400: Generate a first movement command based on the position and orientation in the calibration board image, send the movement command to the collaborative robot to make the marker position in the center of the camera, and then send a second movement command to make the robotic arm move along the optical axis of the camera. During the movement, send multiple shooting commands to the camera to obtain multiple calibration board images of the marker with the same position and orientation.

[0050] Specifically, the first movement command is a command to control the movement of the collaborative robot's robotic arm, calculated based on the position and orientation in the calibration plate image. The second movement command is a command to control the collaborative robot's robotic arm to move along the optical axis of the camera. At this point, the marker is already located at the center point of the camera, and moving along the optical axis will not change the position and orientation of the marker. Multiple shooting commands are sent to the camera while the robotic arm moves along the optical axis, resulting in multiple calibration plate images with the marker having the same position and orientation.

[0051] S500: Evaluate the sharpness of the multiple calibration board images with the same position and orientation of the markers, and select the calibration board image with the highest sharpness as the pose image;

[0052] Specifically, the calibration board images are evaluated using a sharpness evaluation algorithm, as shown in Figure 2 The calibration board is divided into four quadrants, and there are multiple groups of stripes.

[0053] In a preferred embodiment, the multiple calibration board images having the same position and direction of the marker are evaluated for sharpness using an edge detection algorithm.

[0054] By using the edge detection algorithm, the accuracy of the sharpness evaluation is improved.

[0055] S600: Obtain the 6D pose of the robot arm when the pose image is taken;

[0056] Specifically, the 6D pose of the robot arm in the teaching software when the pose image is taken is obtained.

[0057] S700: Based on the 6D pose of the multiple robot arms, and in combination with the positional relationship, calibrate the tool coordinate system.

[0058] Specifically, the relative motion between the known robot base coordinate system and the tool coordinate system can be calculated by using the 6D pose data of the multiple robot arms, and the origin position and direction data of the tool coordinate system, to obtain the transformation matrix of the tool coordinate system relative to the robot base coordinate system.

[0059] In this embodiment, by changing the pose of the robot, the calibration board data collected by the camera is subjected to plane estimation and sharpness analysis, and the 6D pose of the multiple collaborative robot arms is accurately obtained. Based on the 6D pose of the multiple robot arms, the transformation matrix of the tool coordinate system relative to the base coordinate system is obtained, which can improve the accuracy of the tool coordinate system calibration. Moreover, the collaborative robot tool coordinate system can be accurately calibrated without using high-precision three-coordinate instruments, which not only reduces the economic cost of the work coordinate system calibration, but also improves the efficiency of the calibration.

[0060] In some embodiments, the calibration of the tool coordinate system based on the 6D pose of the multiple robot arms and in combination with the positional relationship comprises:

[0061] Calibration of the tool coordinate system based on the 6D pose of more than four robot arms and in combination with the positional relationship.

[0062] In this embodiment, the accuracy of the calibration of the tool coordinate system is improved.

[0063] In some embodiments, the calibration of the tool coordinate system based on the 6D pose of the multiple robot arms and in combination with the positional relationship comprises:

[0064] evaluate sharpness of the stripes in each of the plurality of stripe groups in the plurality of the marker having the same position and orientation calibration board images using an edge detection algorithm.

[0065] In particular implementation, as shown in Figure 2 each of the plurality of stripe groups is a combination of parallel stripes in each of the quadrants, and there are a plurality of stripe groups with different orientations in each of the quadrants.

[0066] In this embodiment, the accuracy of the tool coordinate system of the calibration tool is improved.

[0067] In some embodiments, further comprising:

[0068] In combination with the sharpness, calculate a variance value of the stripe width in each of the stripe groups of the calibration board image;

[0069] According to the variance value and the sharpness of the stripe, evaluate the definition.

[0070] In particular implementation, the definition is a ratio of the variance value and the sharpness.

[0071] In this embodiment, the accuracy of the tool coordinate system of the calibration tool is improved.

[0072] The application also provides a tool coordinate system calibration device of a collaborative robot mechanical arm, please refer to Figure 3 As shown in the figure, the device comprises:

[0073] The position acquisition module 100 is configured to acquire the position relationship between the camera and the collaborative robot;

[0074] The contour recognition module 200 is configured to establish a contour feature model of the marker, acquire a plurality of calibration board images with the marker, and determine the position and orientation of the marker in the calibration board image based on the contour feature model and using a contour matching algorithm.

[0075] The definition evaluation module 300 is configured to generate a first movement instruction based on the position and orientation in the calibration board image, send the movement instruction to the collaborative robot, so that the marker is located at the center of the camera, then send a second movement instruction, so that the mechanical arm moves along the optical axis direction of the camera, and send a plurality of shooting instructions to the camera during the movement, to obtain a plurality of calibration board images with the marker having the same position and orientation; evaluate the definition of the plurality of calibration board images with the marker having the same position and orientation, and select the calibration board image with the highest definition as the pose image.

[0076] The path planning module 400 is configured to plan the path of the end effector based on the first six-dimensional coordinate and the second six-dimensional coordinate, and obtain the rotation angle and rotation direction of the wrist joint by using an inverse kinematics algorithm, wherein the rotation direction is clockwise or counterclockwise.

[0077] The calibration module 500 is configured to obtain the 6D pose of the robot arm when the pose image is captured; and calibrate the tool coordinate system based on the 6D poses of the plurality of robot arms and the positional relationship.

[0078] The functions of each module in the tool coordinate system calibration device of the collaborative robot arm correspond to the steps in the tool coordinate system calibration method of the collaborative robot arm, and the functions and implementation processes will not be repeated here.

[0079] The present application also provides a computer device, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the tool coordinate system calibration method of the collaborative robot arm according to any one of the above embodiments when executing the computer program.

[0080] The present application also provides a computer readable storage medium, which stores a program, wherein the computer readable storage medium refers to a carrier storing data, which can include, but is not limited to, floppy disks, optical disks, hard disks, flash memories, USB flash disks, Memory Sticks, and the like, and the computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The working process, working details, and technical effects of the computer readable storage medium provided in the present embodiment can be referred to the above embodiments of the tool coordinate system calibration method of the collaborative robot arm, and will not be repeated here.

[0081] The present application also provides a computer program product, which comprises computer instructions executable by a processor to implement the steps of the tool coordinate system calibration method of the collaborative robot arm according to any one of the above embodiments.

[0082] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, storage, database or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0083] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, however, as long as the combinations of the technical features do not contradict, they should be considered within the scope of the present disclosure. The above embodiments only express several implementation manners of the present application, and the description is specific and detailed, but it should not be considered as a limitation on the scope of the patent. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, some modifications and improvements can be made, which are all within the scope of the present application. Therefore, the scope of the patent protection of the present application should be subject to the appended claims.

Claims

1. A tool coordinate system calibration method for a collaborative robot arm, characterized by, The method comprises the following steps: acquiring the positional relationship between the camera and the collaborative robot; establishing a contour feature model of the marker, and acquiring multiple markered calibration board images; determining the position and direction of the marker in the calibration board images based on the contour feature model and using a contour matching algorithm; generating first movement instructions based on the position and direction in the calibration board images, sending the movement instructions to the collaborative robot to make the marker located at the center of the camera, and then sending second movement instructions to make the mechanical arm move along the optical axis direction of the camera, and sending multiple shooting instructions to the camera during the movement to obtain multiple calibration board images with the same position and direction of the marker; performing clarity evaluation on the multiple calibration board images with the same position and direction of the marker, and selecting the calibration board image with the highest clarity as the pose image; acquiring the 6D pose of the mechanical arm when the pose image is shot; based on the multiple 6D poses of the mechanical arm and in combination with the positional relationship, calibrating the tool coordinate system.

2. The tool coordinate system calibration method of a collaborative robot arm according to claim 1, characterized in that, The calibration of the tool coordinate system based on the multiple 6D poses of the mechanical arm and in combination with the positional relationship comprises: calibrating the tool coordinate system based on the 6D poses of more than four mechanical arms and in combination with the positional relationship.

3. The tool coordinate system calibration method of a collaborative robot arm according to claim 1, wherein, The acquisition of the positional relationship between the camera and the collaborative robot comprises: unifying the coordinate systems of the camera and the collaborative robot to the world coordinate system, and acquiring the conversion matrix of the coordinate systems.

4. The tool coordinate system calibration method of a collaborative robot arm according to claim 1, wherein, The clarity evaluation on the multiple calibration board images with the same position and direction of the marker comprises: using an edge detection algorithm to perform clarity evaluation on the multiple calibration board images with the same position and direction of the marker.

5. The tool coordinate system calibration method of a collaborative robot arm according to claim 4, wherein, The clarity evaluation on the multiple calibration board images with the same position and direction of the marker using the edge detection algorithm comprises: using the edge detection algorithm to evaluate the sharpness of the stripes in the multiple stripe groups in each quadrant of the multiple calibration board images with the same position and direction of the marker.

6. The tool coordinate system calibration method of a collaborative robotic arm according to claim 5, wherein, Further comprising: in combination with the sharpness, calculating the variance value of the stripe width in each stripe group of the calibration board image; evaluating the clarity according to the variance value and the sharpness of the stripes.

7. A computer device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the steps of the tool coordinate system calibration method of the collaborative robot mechanical arm according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a program, wherein the program is executed by the processor to realize the tool coordinate system calibration method of the collaborative robot mechanical arm according to any one of claims 1 to 6.

9. A computer program product comprising computer instructions, characterized in that, The computer instructions are executed by the processor to realize the steps of the tool coordinate system calibration method of the collaborative robot mechanical arm according to any one of claims 1 to 6.

Images