Automatic shaft hole assembling method, device and equipment and storage medium

Abstract

The invention provides an automatic shaft hole assembling method, device and equipment and a storage medium, and relates to the technical field of robots. In some embodiments of the present disclosure, after a robot controls a mechanical arm to grab a workpiece to an assembly position, on a plane perpendicular to the Z-axis direction, the mechanical arm is controlled to diffuse from inside to outside along the center point of the workpiece at a set step length to search the position of a target mounting hole, and the contact force of each step of movement of the mechanical arm in the Z-axis direction is recorded, the Z-axis direction is a shaft hole assembling direction; under the condition that the contact force in the Z-axis direction in the time window is smaller than a set force threshold value, shaft hole alignment is determined; the mechanical arm is controlled to move towards the target mounting hole position in the Z-axis direction to complete assembling; according to the method, the mechanical arm is controlled to automatically assemble the shaft hole according to the set search track by means of the change of the contact force at the tail end of the mechanical arm, a sample does not need to be obtained, the equipment cost is reduced, and good scene reusability is achieved.

Description

Technical Field

[0001] The present disclosure relates to the field of robotics, and in particular to a method, device, equipment, and storage medium for automatic shaft-hole assembly. Background Art

[0002] With the rapid development of the manufacturing industry, robots have become increasingly integrated into various manufacturing applications, gradually replacing tasks that previously required significant manual effort. Collaborative robotic arms, automated devices that can work alongside humans, are widely used in the manufacturing sector due to their flexibility, safety, and ease of programming.

[0003] As a crucial step in industrial production, the precision and efficiency of assembling shaft holes play a crucial role in product quality and production efficiency. Therefore, this has become a typical application scenario for collaborative robotic arms.

[0004] At present, assembly shaft holes are usually combined with reinforcement learning algorithms to solve the problem of insufficient target recognition and detection accuracy. Reinforcement learning algorithms require a large number of sensor data samples from the actual assembly process. The acquisition of sample data is time-consuming and inefficient, and the scene reusability is poor. In addition, the training process of the reinforcement learning algorithm requires a large amount of computing resources, and the equipment cost is high for assembly operations. Summary of the Invention

[0005] The present disclosure provides a shaft hole automatic assembly method, device, equipment and storage medium to at least solve the problems of long time and low efficiency in existing sample data acquisition, poor scene reusability and high equipment cost.

[0006] The technical solutions disclosed in this disclosure are as follows:

[0007] The present disclosure provides a method for automatically assembling a shaft hole, comprising:

[0008] After the robotic arm grasps the workpiece and reaches the assembly position, the robotic arm is controlled to search for the location of the target mounting hole from the inside outward along the center point of the workpiece with a set step length on a plane perpendicular to the Z-axis direction, and the contact force of each step of the robotic arm in the Z-axis direction is recorded, wherein the Z-axis direction is the shaft-hole assembly direction;

[0009] When the contact forces in the Z-axis direction are all less than the set force threshold within the time window, it is determined that the shaft and hole are aligned;

[0010] The robotic arm is controlled to move toward the target mounting hole along the Z axis to complete the assembly.

[0011] Optionally, before controlling the robotic arm to search for the position of the target mounting hole along the center point of the workpiece with a set step length from inside to outside on a plane perpendicular to the Z-axis direction, the method further includes:

[0012] Obtain the shaft-hole pose image;

[0013] Determining the pose of the workpiece and the pose of the target mounting hole position according to the shaft hole pose image;

[0014] According to the posture of the workpiece and the posture of the target installation hole, the robot arm is controlled to grab the workpiece and move it to the assembly position of the target installation hole.

[0015] Optionally, the method further includes:

[0016] Recording the absolute value of the torque applied to the end of the robotic arm in the X-axis and Y-axis directions for each step of the robotic arm's movement, wherein the X-axis and the Y-axis are mutually perpendicular directions on a plane perpendicular to the Z-axis direction;

[0017] generating an X-axis torque distribution diagram according to the absolute value of the torque applied to the end of the robot arm in the X-axis direction; and

[0018] A Y-axis torque distribution diagram is generated according to the absolute value of the torque applied to the end of the robot arm in the Y-axis direction.

[0019] Optionally, the method further includes:

[0020] If the search side length is greater than the side length threshold, it is determined that the shaft hole is misaligned; wherein the search side length is the side length of a square spiral line formed by the robot arm searching from the inside to the outside along the center point of the workpiece with a set step length;

[0021] Determining a posture correction amount of the target mounting hole position according to the X-axis torque distribution diagram and the Y-axis torque distribution diagram;

[0022] According to the posture correction amount of the target installation hole position, the robot arm is controlled to search for the position of the target installation hole again along the center point of the workpiece with a set step size from the inside to the outside.

[0023] Optionally, determining the posture correction amount of the target mounting hole position according to the X-axis moment distribution diagram and the Y-axis moment distribution diagram includes:

[0024] Performing filtering on the X-axis moment distribution graph and the Y-axis moment distribution graph respectively to obtain a filtered X-axis moment distribution graph and a filtered Y-axis moment distribution graph;

[0025] Normalizing the filtered X-axis moment distribution graph and the filtered Y-axis moment distribution graph to obtain a normalized X-axis moment distribution graph and a normalized Y-axis moment distribution graph;

[0026] superimposing the normalized X-axis moment distribution graph and the normalized Y-axis moment distribution graph to obtain a composite image;

[0027] Traversing the composite image, finding all locations where the center value of the window is greater than the values ​​of other pixels in the window as the maximum value points;

[0028] Calculating the peak intensity of the maximum point according to the height of the maximum point and the trough height;

[0029] The position correction amount of the target mounting hole position is determined according to the peak strength of the maximum point.

[0030] Optionally, the superimposing the normalized X-axis moment distribution graph and the normalized Y-axis moment distribution graph to obtain a composite image includes:

[0031] Superimposing the normalized X-axis moment distribution graph and the normalized Y-axis moment distribution graph to obtain a superimposed image;

[0032] Traversing the stacked image using a set window, and calculating the variance and mean of each set window to obtain a variance distribution map and a mean distribution map;

[0033] performing normalization operations on the variance distribution graph and the mean distribution graph respectively to obtain a normalized variance distribution graph and a normalized mean distribution graph;

[0034] The normalized variance distribution map and the normalized mean distribution map are superimposed to obtain a composite image.

[0035] Optionally, determining the posture correction amount of the target mounting hole position according to the peak strength of the maximum point includes:

[0036] Select two maximum points with the highest peaks from the maximum points whose peak intensities are greater than the peak intensities threshold;

[0037] Determine the hole offset according to the two maximum value points;

[0038] A position correction amount of the target mounting hole position is determined based on the hole offset.

[0039] Optionally, controlling the robotic arm to move toward the target mounting hole along the Z-axis to complete the assembly includes:

[0040] Determining a joint space offset of the robotic arm based on an actual velocity, an actual acceleration, an expected velocity, and an expected acceleration of a distal end of the robotic arm;

[0041] According to the joint space offset, the robotic arm is controlled to move toward the target installation hole position in the Z-axis direction to complete the assembly.

[0042] The present disclosure also provides an automatic shaft hole assembly device, comprising:

[0043] A search module is configured to control the robotic arm to grasp the workpiece and arrive at the assembly position, and then control the robotic arm to search for the position of the target mounting hole from the inside outward along the center point of the workpiece with a set step length on a plane perpendicular to the Z-axis direction, and record the contact force of each step of the robotic arm in the Z-axis direction, wherein the Z-axis direction is the shaft-hole assembly direction;

[0044] a determination module, configured to determine shaft-hole alignment when the contact forces in the Z-axis direction are all less than a set force threshold within a time window;

[0045] The assembly module is used to control the robot arm to move toward the target installation hole position along the Z axis to complete the assembly.

[0046] Optionally, the search module may be further configured to: before controlling the robotic arm to search for the position of the target mounting hole along the center point of the workpiece with a set step length from the inside outward on a plane perpendicular to the Z-axis direction;

[0047] Obtain the shaft-hole pose image;

[0048] Determining the pose of the workpiece and the pose of the target mounting hole position according to the shaft hole pose image;

[0049] According to the posture of the workpiece and the posture of the target installation hole, the robot arm is controlled to grab the workpiece and move it to the assembly position of the target installation hole.

[0050] Optionally, the search module may also be used to:

[0051] Recording the absolute value of the torque applied to the end of the robotic arm in the X-axis and Y-axis directions for each step of the robotic arm's movement, wherein the X-axis and the Y-axis are mutually perpendicular directions on a plane perpendicular to the Z-axis direction;

[0052] generating an X-axis torque distribution diagram according to the absolute value of the torque applied to the end of the robot arm in the X-axis direction; and

[0053] A Y-axis torque distribution diagram is generated according to the absolute value of the torque applied to the end of the robot arm in the Y-axis direction.

[0054] Optionally, the search module may also be used to:

[0055] If the search side length is greater than the side length threshold, it is determined that the shaft hole is misaligned; wherein the search side length is the side length of a square spiral line formed by the robot arm searching from the inside to the outside along the center point of the workpiece with a set step length;

[0056] Determining a posture correction amount of the target mounting hole position according to the X-axis torque distribution diagram and the Y-axis torque distribution diagram;

[0057] According to the posture correction amount of the target installation hole position, the robot arm is controlled to search for the position of the target installation hole again along the center point of the workpiece with a set step size from the inside to the outside.

[0058] Optionally, when determining the posture correction amount of the target mounting hole position according to the X-axis moment distribution diagram and the Y-axis moment distribution diagram, the search module is configured to:

[0059] Performing filtering on the X-axis moment distribution graph and the Y-axis moment distribution graph respectively to obtain a filtered X-axis moment distribution graph and a filtered Y-axis moment distribution graph;

[0060] Normalizing the filtered X-axis moment distribution graph and the filtered Y-axis moment distribution graph to obtain a normalized X-axis moment distribution graph and a normalized Y-axis moment distribution graph;

[0061] superimposing the normalized X-axis moment distribution graph and the normalized Y-axis moment distribution graph to obtain a composite image;

[0062] Traversing the composite image, finding all locations where the center value of the window is greater than the values ​​of other pixels in the window as the maximum value points;

[0063] Calculating the peak intensity of the maximum point according to the height of the maximum point and the trough height;

[0064] The position correction amount of the target mounting hole position is determined according to the peak strength of the maximum point.

[0065] Optionally, when the search module performs superposition processing on the normalized X-axis moment distribution graph and the normalized Y-axis moment distribution graph to obtain a composite image, it is configured to:

[0066] Superimposing the normalized X-axis moment distribution graph and the normalized Y-axis moment distribution graph to obtain a superimposed image;

[0067] Traversing the stacked image using a set window, and calculating the variance and mean of each set window to obtain a variance distribution map and a mean distribution map;

[0068] performing normalization operations on the variance distribution graph and the mean distribution graph respectively to obtain a normalized variance distribution graph and a normalized mean distribution graph;

[0069] The normalized variance distribution map and the normalized mean distribution map are superimposed to obtain a composite image.

[0070] Optionally, when determining the posture correction amount of the target mounting hole position according to the peak strength of the maximum point, the search module is configured to:

[0071] Select two maximum points with the highest peaks from the maximum points whose peak intensities are greater than the peak intensities threshold;

[0072] Determine the hole offset according to the two maximum value points;

[0073] A position correction amount of the target mounting hole position is determined based on the hole offset.

[0074] Optionally, when controlling the robotic arm to move toward the target mounting hole position in the Z-axis direction to complete assembly, the search module is configured to:

[0075] Determining a joint space offset of the robotic arm based on an actual velocity, an actual acceleration, an expected velocity, and an expected acceleration of a distal end of the robotic arm;

[0076] According to the joint space offset, the robotic arm is controlled to move toward the target installation hole position in the Z-axis direction to complete the assembly.

[0077] The present disclosure also provides an electronic device, including:

[0078] processor;

[0079] a memory for storing processor-executable instructions;

[0080] The processor is configured to execute instructions to implement each step in the above method.

[0081] The present disclosure also provides a robot, comprising:

[0082] robotic arms and processors;

[0083] a memory for storing processor-executable instructions;

[0084] The processor is configured to execute instructions to implement each step in the above method.

[0085] The embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, each step in the above method is implemented.

[0086] The embodiments of the present disclosure further provide a computer program product, including a computer program / instruction, which implements the steps in the above method when executed by a processor.

[0087] The technical solutions provided by the embodiments of the present disclosure bring at least the following beneficial effects:

[0088] In some embodiments of the present disclosure, after the robot controls the robotic arm to grasp the workpiece and arrive at the assembly position, on a plane perpendicular to the Z-axis direction, the robotic arm is controlled to search for the position of the target mounting hole from the inside to the outside along the center point of the workpiece with a set step size, and the contact force of each step of the robotic arm movement in the Z-axis direction is recorded, wherein the Z-axis direction is the shaft-hole assembly direction; when the contact force in the Z-axis direction within the time window is less than the set force threshold, the shaft-hole alignment is determined; the robotic arm is controlled to move toward the target mounting hole position in the Z-axis direction to complete the assembly; the present disclosure automatically assembles the shaft hole by controlling the robotic arm according to the set search trajectory and with the help of the change in the contact force at the end of the robotic arm. Compared with the existing shaft-hole assembly method that requires the help of reinforcement learning algorithm, it does not require sample acquisition, reduces equipment cost, and has good scenario reusability.

[0089] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute an improper limitation of the present disclosure.

[0091] Figure 1 A schematic flow chart of a shaft hole automatic assembly method provided by an exemplary embodiment of the present disclosure;

[0092] Figure 2 A schematic diagram of a coordinate system definition provided for an exemplary embodiment of the present disclosure;

[0093] Figure 3 A schematic diagram of an XY plane search trajectory provided by an exemplary embodiment of the present disclosure;

[0094] Figure 4 A schematic diagram of a posture correction module provided by an exemplary embodiment of the present disclosure;

[0095] Figure 5 A schematic diagram of posture correction provided for an exemplary embodiment of the present disclosure;

[0096] Figure 6 A schematic structural diagram of an automatic shaft hole assembly device provided by an exemplary embodiment of the present disclosure;

[0097] Figure 7 A schematic structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0098] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0099] It should be noted that the terms "first," "second," and the like in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the numbers used in this manner are interchangeable where appropriate so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure.

[0100] It should be noted that the user information involved in this disclosure includes but is not limited to: user device information and user personal information; the collection, storage, use, processing, transmission, provision and disclosure of user information in this disclosure comply with the relevant laws and regulations and do not violate public order and good morals.

[0101] Collaborative robotic arms are typically equipped with vision systems to identify the position and posture of workpieces, and utilize end-of-line force sensors to further facilitate the positioning and assembly of shaft holes. Despite years of development, collaborative robotic arms continue to struggle with high-precision tasks due to the limited accuracy of their visual perception. This is particularly true when assembling workpieces with multiple shaft holes, requiring additional calibration and algorithm adjustments to ensure accurate and stable assembly.

[0102] At present, assembly shaft holes are usually combined with reinforcement learning algorithms to solve the problem of insufficient target recognition and detection accuracy. Reinforcement learning algorithms require a large number of sensor data samples from the actual assembly process. Sample acquisition is time-consuming and inefficient, and the scene reusability is poor. In addition, the training process of the reinforcement learning algorithm requires a large amount of computing resources, which makes the equipment cost high for assembly operations.

[0103] In response to the above technical problems, in some embodiments of the present disclosure, after the robot controls the robotic arm to grasp the workpiece and arrive at the assembly position, on a plane perpendicular to the Z-axis direction, the robotic arm is controlled to search for the position of the target mounting hole from the inside to the outside along the center point of the workpiece with a set step size, and the contact force of each step of the robotic arm movement in the Z-axis direction is recorded, wherein the Z-axis direction is the shaft-hole assembly direction; when the contact force in the Z-axis direction within the time window is less than the set force threshold, the shaft-hole alignment is determined; the robotic arm is controlled to move toward the target mounting hole position in the Z-axis direction to complete the assembly; the present disclosure controls the robotic arm according to the set search trajectory and performs automatic assembly of the shaft hole with the help of the change in the contact force at the end of the robotic arm. Compared with the existing shaft-hole assembly method that requires the help of reinforcement learning algorithm, it does not require sample acquisition, reduces equipment cost, and has good scenario reusability.

[0104] The technical solutions provided by various embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0105] Figure 1 The following is a flow chart of a method for automatically assembling a shaft hole according to an exemplary embodiment of the present disclosure. Figure 1 As shown, the method includes:

[0106] S101: After the robot arm grasps the workpiece and reaches the assembly position, the robot arm is controlled to search for the location of the target mounting hole from the inside outward along the center point of the workpiece with a set step length on a plane perpendicular to the Z-axis direction, and the contact force of each step of the robot arm in the Z-axis direction is recorded, where the Z-axis direction is the shaft-hole assembly direction;

[0107] S102: If the contact forces in the Z-axis direction are all less than the set force threshold within the time window, then the shaft-hole alignment is determined;

[0108] S103: Control the robotic arm to move toward the target installation hole position in the Z-axis direction to complete the assembly.

[0109] In this embodiment, the executor of the above method is a robot. The present disclosure does not limit the type of robot. The robot disclosed in the present disclosure is a robot equipped with a robotic arm, and the robot automatically assembles the shaft hole with the help of the robotic arm.

[0110] In this embodiment, after the robot controls the manipulator to grab the workpiece and arrive at the assembly position, on a plane perpendicular to the Z-axis direction, the manipulator is controlled to diffuse the search for the position of the target mounting hole from the inside out with a set step length along the center point of the workpiece, and record the contact force of each step of the manipulator's movement in the Z-axis direction, wherein the Z-axis direction is the shaft-hole assembly direction; when the contact force in the Z-axis direction within the time window is less than the set force threshold, the shaft-hole alignment is determined; the manipulator is controlled to move toward the target mounting hole position in the Z-axis direction to complete the assembly; the present disclosure controls the manipulator according to the set search trajectory and automatically assembles the shaft hole with the help of the change in the contact force at the end of the manipulator. Compared with the existing shaft hole assembly method that requires the help of reinforcement learning algorithms, there is no need to obtain samples, thereby reducing equipment costs. The present disclosure calculates the adjustment amount based on the prior shaft foot position information. When the shaft hole position distribution changes, only the model parameters need to be modified, and the learning model does not need to be retrained, resulting in good scenario reusability; the present disclosure has low computational overhead, does not require the support of high-power computing equipment, and has low equipment costs.

[0111] Figure 2 A schematic diagram of a coordinate system definition provided for an exemplary embodiment of the present disclosure. In this embodiment, the present disclosure is mainly divided into three stages: near-hole stage, search stage and correction stage. Figure 2 As shown in the figure, the coordinate systems are defined as follows: coordinate system B is fixed on the base of the robot arm; coordinate system P is fixed on the workpiece; coordinate system S is fixed at the center of the target socket.

[0112] 1. Near-pore stage.

[0113] In some embodiments of the present disclosure, an axis hole posture image is acquired; based on the axis hole posture image, the posture of the workpiece and the posture of the target installation hole position are determined; based on the posture of the workpiece and the posture of the target installation hole position, the robotic arm is controlled to grasp the workpiece and move it to the assembly position of the target installation hole position.

[0114] For example, the workpiece pose and the target mounting hole pose are described in the robot base coordinate system B:

[0115] First, the camera equipped on the robotic arm is used to obtain the axis hole pose image in the current environment in real time. The pose of the workpiece in the robotic arm base coordinate system B and the pose of the target installation hole in the robotic arm base coordinate system B are obtained respectively through visual pose estimation.

[0116] Through inverse kinematics, the workpiece pose in the Cartesian space of the robot base coordinate system is calculated into the robotic arm joint space, and the robotic arm is controlled to move to grasp the workpiece and approach the target installation hole. At this point, the workpiece coordinate system P and the target hole coordinate system S should theoretically coincide.

[0117] Due to the influence of visual recognition accuracy and control accuracy, assembly failure will occur when the actual position of the workpiece cannot completely coincide with the target hole position. The following hole search stage is used to solve this problem.

[0118] 2. Hole Searching Stage

[0119] In some embodiments of the present disclosure, after the robotic arm is controlled to grasp the workpiece and reach the assembly position, on a plane perpendicular to the Z-axis direction, the robotic arm is controlled to search for the position of the target mounting hole from the inside to the outside along the center point of the workpiece with a set step length, and the contact force of each step of the robotic arm's movement in each axis direction is recorded, wherein the Z-axis direction is the shaft hole assembly direction.

[0120] The hole search stage adopts force-position hybrid control, and the workpiece motion is described in the target hole coordinate system S:

[0121] In one embodiment, admittance control is used in the Z-axis direction. One possible implementation method is to determine the joint space offset of the robotic arm based on the actual velocity, actual acceleration, desired velocity, and desired acceleration of the robotic arm end; and based on the joint space offset, control the robotic arm to move toward the target mounting hole along the Z-axis to complete the assembly.

[0122] The calculation formula for admittance control is:

[0123]

[0124] Among them, x e Indicates the actual position X of the end of the robot arm and the expected position X in the coordinate system S d The difference between them; Δx represents the position difference, and Δω represents the attitude difference. is x e The first derivative of ; is x e The second derivative of are the actual velocity and acceleration of the end of the robotic arm respectively; are the desired velocity and acceleration of the end of the robot arm, M, K, and B represent the robot inertia matrix, stiffness matrix, and damping matrix, respectively, which are controller parameters. The desired force and torque during the search process are F d =[0,0,f d ,0,0,0], indicating that only the Z direction is expected to be f d N force presses the workpiece; the force and torque in other directions are 0, and the contact force and torque collected by the sensor in real time are F = [f x ,f y ,f z ,τ x ,τ y ,τ z ], the force deviation is F e =Fd -F;

[0125] Iteratively calculate the position offset x in the Cartesian space of the end e , the joint space offset is solved by inverse kinematics to control the motion of the manipulator to achieve admittance control. The formula is as follows:

[0126]

[0127] Where ΔT represents the iteration period.

[0128] In another embodiment, position control is employed on the XY plane, where the XY plane is the aforementioned plane perpendicular to the Z-axis. In one achievable method, the absolute values ​​of the torques applied to the end of the robotic arm in the X-axis and Y-axis directions for each step of the robotic arm's movement are recorded, where the X-axis and Y-axis directions are mutually perpendicular directions on a plane perpendicular to the Z-axis direction. An X-axis torque distribution diagram is generated based on the absolute values ​​of the torques applied to the end of the robotic arm in the X-axis direction, and a Y-axis torque distribution diagram is generated based on the absolute values ​​of the torques applied to the end of the robotic arm in the Y-axis direction. It should be noted that the robotic arm's search trajectory can be a square spiral.

[0129] Figure 3 Schematic diagram of an XY plane search trajectory provided by an exemplary embodiment of the present disclosure. Figure 3 As shown, the center point of the workpiece diffuses from the inside to the outside along the square spiral line, and the step size is set to d step , the side length increases by d each time it runs step After running along the above trajectory, the positions of each step are arranged to form a regular matrix. At each step, the current position and the absolute value of the torque on the end of the robot arm in the X-axis and Y-axis directions collected by the end force sensor are recorded. The X-axis torque distribution diagram and the Y-axis torque distribution diagram can be obtained respectively.

[0130] End conditions of the hole search phase:

[0131] 1. If the contact force in the Z-axis direction is less than the set force threshold within the time window, the shaft-hole alignment is determined; the robot arm is controlled to move toward the target installation hole in the Z-axis direction to complete the assembly. z Satisfy f z <f threshold When t is opened, the time window t count , when the time window t is satisfied count Internal z are all less than the set force threshold f threshold When the axis hole is successfully aligned, the XY plane trajectory search is stopped. At this time, the pressure is switched to pressing along the Z axis until the assembly task is completed. It should be noted that the present disclosure does not limit the set force threshold and can be adjusted according to actual conditions.

[0132] 2. If the search side length is greater than the side length threshold, it is determined that the shaft hole is misaligned; the search side length is the side length of the square spiral formed by the robot arm searching from the inside to the outside along the center point of the workpiece with the set step length. side Satisfy d side >d threshold When the hole search phase is considered to be over and the alignment is not successful, d threshold is the set side length threshold. At this point, since the actual posture of the workpiece and the actual posture of the target hole position do not overlap, the two axis feet cannot be aligned with the hole position at the same time, resulting in assembly failure. Stop the search and enter the correction phase. It should be noted that this disclosure does not limit the side length threshold and can be adjusted according to actual conditions.

[0133] 3. Revision Phase

[0134] In some embodiments of the present disclosure, when it is determined that the shaft hole is misaligned, the posture correction value of the target installation hole position is determined based on the X-axis torque distribution diagram and the Y-axis torque distribution diagram; based on the posture correction value of the target installation hole position, the robot arm is controlled to search for the position of the target installation hole from the inside to the outside along the center point of the workpiece with a set step size. In particular, whenever a single shaft foot is aligned with the hole position, the absolute value of the torque in the X-axis direction and the Y-axis direction acting on the end of the robot arm has a significant increase. The correction stage uses the torque distribution diagram obtained in the hole search stage to infer the actual hole position and calculate the posture correction value.

[0135] In some embodiments of the present disclosure, the X-axis torque distribution diagram and the Y-axis torque distribution diagram are filtered respectively to obtain filtered X-axis torque distribution diagram and filtered Y-axis torque distribution diagram; the filtered X-axis torque distribution diagram and the filtered Y-axis torque distribution diagram are normalized to obtain normalized X-axis torque distribution diagram and normalized Y-axis torque distribution diagram; the normalized X-axis torque distribution diagram and the normalized Y-axis torque distribution diagram are superimposed to obtain a composite image; the composite image is traversed to find the position where the center value of all windows is greater than the values ​​of other pixels in the window as the maximum point; the peak strength of the maximum point is calculated based on the height of the maximum point and the trough height; and the posture correction amount of the target mounting hole position is determined based on the peak strength of the maximum point.

[0136] Figure 4 Schematic diagram of a posture correction module provided by an exemplary embodiment of the present disclosure. Figure 4As shown, a 5*5 Gaussian kernel is first used to perform Gaussian low-pass filtering on the X-axis torque distribution graph and the Y-axis torque distribution graph to remove noise and smooth the image, obtaining the filtered X-axis torque distribution graph and the filtered Y-axis torque distribution graph. Each pixel of the filtered image matrix is ​​traversed to find the maximum value max(x) and the minimum value min(x) in the image, and the data is normalized to obtain the normalized X-axis torque distribution graph and the normalized Y-axis torque distribution graph. The formula is as follows:

[0137] x′=(x-min(x)) / (max(x)-min(x)).

[0138] Here, x′ represents the normalized pixel value. Each pixel value in the image is adjusted to the range [0, 1] to remove the dimension and facilitate subsequent operations.

[0139] In some embodiments of the present disclosure, the normalized X-axis torque distribution graph and the normalized Y-axis torque distribution graph are superimposed to obtain a composite image. One achievable method is to superimpose the normalized X-axis torque distribution graph and the normalized Y-axis torque distribution graph to obtain a superimposed image; traverse the superimposed image using a set window and calculate the variance and mean of each set window to obtain a variance distribution graph and a mean distribution graph; normalize the variance distribution graph and the mean distribution graph respectively to obtain a normalized variance distribution graph and a normalized mean distribution graph; and superimpose the normalized variance distribution graph and the normalized mean distribution graph to obtain a composite image.

[0140] Combine Figure 4 After superimposing the two normalized images, a 5x5 sliding window is used to traverse the images. The variance and mean of each window are calculated to obtain the variance distribution map and the mean distribution map. The variance distribution map and the mean distribution map are normalized separately to obtain the normalized variance distribution map and the normalized mean distribution map. The normalized variance distribution map and the normalized mean distribution map are superimposed again to obtain the composite image. The two highest effective peaks in the composite image correspond to the relative offset of the two shaft holes from the image center, which is visually identified as the hole position.

[0141] In some embodiments of the present disclosure, the posture correction amount of the target installation hole position is determined based on the peak strength of the maximum point. One feasible way is to filter out the two maximum points with the highest peaks from the maximum points whose peak strength is greater than the peak strength threshold; determine the hole offset based on the two maximum points; and determine the posture correction amount of the target installation hole position based on the hole offset.

[0142] Combine Figure 4, use a 5*5 sliding window to traverse the above composite image, find all the locations where the window center value is greater than the other pixel values ​​in the window as the maximum point. Traverse the maximum point and calculate its peak intensity P strength , the calculation formula is:

[0143] P strength =min(hh left_base ,hh right_base ,hh up_base ,hh down_base )

[0144] Among them, h represents the height of the maximum point, h left_base , h right_base , h up_base , h down_base They represent the trough heights found along the left, right, up, and down directions. strength >h threshold The two highest peaks among the peaks of h threshold The offsets Δx and Δy of the two peaks M1 and M2 relative to the image center are the offsets of the two holes obtained by visual recognition.

[0145] Figure 5 A posture correction diagram is provided for an exemplary embodiment of the present disclosure. According to the hole offset, the posture correction amount of the target installation hole position is determined, wherein the posture correction amount includes: correction displacement amount and correction rotation amount. Figure 5 As shown in the figure, the positions of the two holes obtained by visual recognition are represented as points A and B in the coordinate system S according to the workpiece size and the coordinate system S. The actual positions of the two holes can be calculated as A' and B' according to the offset of the two holes, and the corrected displacement d = [d x ,d y ] and the corrected rotation amount ω.

[0146] After obtaining the correction value, the description of the S coordinate system in the B coordinate system is updated, and the robotic arm is controlled to re-enter the hole search stage until the hole search end condition is met, successfully completing the shaft hole assembly task.

[0147] Figure 6 Schematic diagram of the structure of an automatic shaft hole assembly device 60 provided by an exemplary embodiment of the present disclosure. Figure 6 As shown, the shaft hole automatic assembly device 60 includes: a search module 61, a determination module 62 and an assembly module 63.

[0148] The search module 61 is used to control the robot arm to grasp the workpiece and reach the assembly position. Then, on a plane perpendicular to the Z-axis direction, the robot arm is controlled to search for the location of the target mounting hole from the inside outward at a set step length along the center point of the workpiece, and the contact force of each step of the robot arm in the Z-axis direction is recorded. The Z-axis direction is the assembly direction of the shaft hole.

[0149] a determination module 62 for determining shaft-hole alignment when the contact forces in the Z-axis direction within the time window are all less than a set force threshold;

[0150] The assembly module 63 is used to control the robot arm to move toward the target installation hole position in the Z-axis direction to complete the assembly.

[0151] Optionally, the search module 61 may be further configured to: before controlling the robot arm to search for the position of the target mounting hole along the center point of the workpiece with a set step length from the inside out on a plane perpendicular to the Z-axis direction;

[0152] Obtain the shaft-hole pose image;

[0153] Determine the pose of the workpiece and the pose of the target installation hole according to the shaft hole pose image;

[0154] According to the posture of the workpiece and the posture of the target installation hole, the robot arm is controlled to grab the workpiece and move it to the assembly position of the target installation hole.

[0155] Optionally, the search module 61 may also be used to:

[0156] Record the absolute value of the torque applied to the end of the robotic arm in the X-axis and Y-axis directions for each step of the robotic arm's movement, where the X-axis and Y-axis directions are perpendicular to each other on a plane perpendicular to the Z-axis direction;

[0157] generating an X-axis torque distribution diagram according to the absolute value of the torque applied to the end of the robot arm in the X-axis direction; and

[0158] According to the absolute value of the torque applied to the end of the robot arm in the Y-axis direction, a Y-axis torque distribution diagram is generated.

[0159] Optionally, the search module 61 may also be used to:

[0160] If the search side length is greater than the side length threshold, the shaft hole is determined to be misaligned; wherein the search side length is the side length of the square spiral formed by the robot arm searching from the inside to the outside along the center point of the workpiece with a set step length;

[0161] Determine the pose correction of the target mounting hole position based on the X-axis moment distribution diagram and the Y-axis moment distribution diagram;

[0162] According to the posture correction of the target installation hole position, the robot arm is controlled to search for the position of the target installation hole from the inside to the outside along the center point of the workpiece with a set step size.

[0163] Optionally, when determining the posture correction amount of the target mounting hole position according to the X-axis moment distribution diagram and the Y-axis moment distribution diagram, the search module 61 is configured to:

[0164] Performing filtering on the X-axis moment distribution diagram and the Y-axis moment distribution diagram respectively to obtain a filtered X-axis moment distribution diagram and a filtered Y-axis moment distribution diagram;

[0165] Normalizing the filtered X-axis moment distribution graph and the filtered Y-axis moment distribution graph to obtain a normalized X-axis moment distribution graph and a normalized Y-axis moment distribution graph;

[0166] The normalized X-axis moment distribution diagram and the normalized Y-axis moment distribution diagram are superimposed to obtain a composite image;

[0167] Traverse the composite image and find the position where the center value of all windows is greater than the value of other pixels in the window as the maximum point;

[0168] Calculate the peak intensity of the maximum point based on the height of the maximum point and the height of the trough;

[0169] According to the peak strength of the maximum point, the posture correction amount of the target installation hole position is determined.

[0170] Optionally, when the search module 61 performs superposition processing on the normalized X-axis moment distribution diagram and the normalized Y-axis moment distribution diagram to obtain a composite image, it is configured to:

[0171] The normalized X-axis moment distribution diagram and the normalized Y-axis moment distribution diagram are superimposed to obtain a superimposed image;

[0172] The set window is used to traverse the superimposed image, and the variance and mean of each set window are calculated to obtain the variance distribution map and the mean distribution map;

[0173] Normalizing the variance distribution graph and the mean distribution graph respectively to obtain a normalized variance distribution graph and a normalized mean distribution graph;

[0174] The normalized variance distribution map and the normalized mean distribution map are superimposed to obtain a composite image.

[0175] Optionally, when determining the posture correction amount of the target mounting hole position according to the peak strength of the maximum point, the search module 61 is configured to:

[0176] Select the two maximum points with the highest peaks from the maximum points whose peak intensity is greater than the peak intensity threshold;

[0177] According to the two maximum points, the hole offset is determined;

[0178] According to the hole offset, the pose correction of the target installation hole position is determined.

[0179] Optionally, when controlling the robot arm to move toward the target installation hole position in the Z-axis direction to complete the assembly, the search module 61 is configured to:

[0180] Determine the joint space offset of the manipulator based on the actual velocity, actual acceleration, expected velocity, and expected acceleration of the end of the manipulator;

[0181] According to the joint space offset, the robot arm is controlled to move toward the target installation hole in the Z-axis direction to complete the assembly.

[0182] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0183] Figure 7 FIG. 1 is a structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure. Figure 7 As shown, the electronic device includes a memory 71 and a processor 72. In addition, the electronic device also includes a power supply component 73 and a communication component 74.

[0184] The memory 71 is used to store computer programs and can be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on the electronic device.

[0185] The memory 71 can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0186] The communication component 74 is used for data transmission with other devices.

[0187] The processor 72 can execute computer instructions stored in the memory 71 to: control the robotic arm to grasp the workpiece and reach the assembly position, and then control the robotic arm to search for the position of the target mounting hole from the inside to the outside along the center point of the workpiece with a set step length on a plane perpendicular to the Z-axis direction, and record the contact force of each step of the robotic arm in the Z-axis direction, wherein the Z-axis direction is the shaft-hole assembly direction; when the contact force in the Z-axis direction within the time window is less than the set force threshold, the shaft-hole alignment is determined; and the robotic arm is controlled to move toward the target mounting hole position in the Z-axis direction to complete the assembly.

[0188] Accordingly, the embodiment of the present disclosure further provides a computer-readable storage medium storing a computer program. When the computer-readable storage medium stores the computer program and the computer program is executed by one or more processors, the one or more processors are caused to execute Figure 1 Each step in the method embodiment.

[0189] Accordingly, the present disclosure also provides a computer program product, which includes a computer program / instruction, and the computer program / instruction is executed by a processor. Figure 1 Each step in the method embodiment.

[0190] above Figure 7 The communication component is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G / LTE, 5G and other mobile communication networks, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0191] above Figure 7 The power supply component in a device provides power to various components of the device in which the power supply component is located. The power supply component may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device in which the power supply component is located.

[0192] The electronic device also includes a display screen and an audio component.

[0193] The display screen includes a screen, which may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0194] The audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC), and when the device where the audio component is located is in an operating mode, such as call mode, recording mode, and voice recognition mode, the microphone is configured to receive external audio signals. The received audio signal can be further stored in a memory or sent via a communication component. In some embodiments, the audio component also includes a speaker for outputting audio signals.

[0195] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0196] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0197] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0198] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0199] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0200] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0201] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0202] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device that includes the element.

[0203] The above are merely specific embodiments of the present disclosure, intended to enable those skilled in the art to understand and implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure is not limited to these embodiments, but is to be construed in the broadest manner consistent with the principles and novel features disclosed herein.

Claims

1. A shaft hole automatic assembly method, characterized in that: include: After the robotic arm grasps the workpiece and reaches the assembly position, the robotic arm is controlled to search for the location of the target mounting hole from the inside outward along the center point of the workpiece with a set step length on a plane perpendicular to the Z-axis direction, and the contact force of each step of the robotic arm in the Z-axis direction is recorded, wherein the Z-axis direction is the shaft-hole assembly direction; When the contact forces in the Z-axis direction are all less than the set force threshold within the time window, it is determined that the shaft and hole are aligned; The robotic arm is controlled to move toward the target mounting hole along the Z axis to complete the assembly.

2. The method according to claim 1, characterized in that Before controlling the robot arm to search for the position of the target mounting hole along the center point of the workpiece with a set step length from inside to outside on a plane perpendicular to the Z-axis direction, the method further includes: Obtain the shaft-hole pose image; Determining the pose of the workpiece and the pose of the target mounting hole position according to the shaft hole pose image; According to the posture of the workpiece and the posture of the target installation hole, the robot arm is controlled to grab the workpiece and move it to the assembly position of the target installation hole.

3. The method according to claim 1, characterized in that The method further comprises: Recording the absolute value of the torque applied to the end of the robotic arm in the X-axis and Y-axis directions for each step of the robotic arm's movement, wherein the X-axis and the Y-axis are mutually perpendicular directions on a plane perpendicular to the Z-axis direction; generating an X-axis torque distribution diagram according to the absolute value of the torque applied to the end of the robot arm in the X-axis direction; and A Y-axis torque distribution diagram is generated according to the absolute value of the torque applied to the end of the robot arm in the Y-axis direction.

4. The method according to claim 3, characterized in that The method further comprises: If the search side length is greater than the side length threshold, it is determined that the shaft hole is misaligned; wherein the search side length is the side length of a square spiral line formed by the robot arm searching from the inside to the outside along the center point of the workpiece with a set step length; Determining a posture correction amount of the target mounting hole position according to the X-axis torque distribution diagram and the Y-axis torque distribution diagram; According to the posture correction amount of the target installation hole position, the robot arm is controlled to search for the position of the target installation hole again along the center point of the workpiece with a set step size from the inside to the outside.

5. The method according to claim 4, characterized in that Determining the posture correction amount of the target mounting hole position according to the X-axis moment distribution diagram and the Y-axis moment distribution diagram includes: Performing filtering on the X-axis moment distribution graph and the Y-axis moment distribution graph respectively to obtain a filtered X-axis moment distribution graph and a filtered Y-axis moment distribution graph; Normalizing the filtered X-axis moment distribution graph and the filtered Y-axis moment distribution graph to obtain a normalized X-axis moment distribution graph and a normalized Y-axis moment distribution graph; superimposing the normalized X-axis moment distribution graph and the normalized Y-axis moment distribution graph to obtain a composite image; Traversing the composite image, finding all locations where the center value of the window is greater than the values ​​of other pixels in the window as the maximum value points; Calculating the peak intensity of the maximum point according to the height of the maximum point and the trough height; The position correction amount of the target mounting hole position is determined according to the peak strength of the maximum point.

6. The method according to claim 5, characterized in that The superimposing process of the normalized X-axis moment distribution diagram and the normalized Y-axis moment distribution diagram to obtain a composite image includes: Superimposing the normalized X-axis moment distribution graph and the normalized Y-axis moment distribution graph to obtain a superimposed image; Traversing the stacked image using a set window, and calculating the variance and mean of each set window to obtain a variance distribution map and a mean distribution map; performing normalization operations on the variance distribution graph and the mean distribution graph respectively to obtain a normalized variance distribution graph and a normalized mean distribution graph; The normalized variance distribution map and the normalized mean distribution map are superimposed to obtain a composite image.

7. The method according to claim 5, characterized in that Determining the posture correction amount of the target mounting hole position according to the peak strength of the maximum point includes: Select two maximum points with the highest peaks from the maximum points whose peak intensities are greater than the peak intensities threshold; Determine the hole offset according to the two maximum value points; A position correction amount of the target mounting hole position is determined based on the hole offset.

8. The method according to claim 1, characterized in that The controlling the robotic arm to move toward the target mounting hole position in the Z-axis direction to complete the assembly includes: Determining a joint space offset of the robotic arm based on an actual velocity, an actual acceleration, an expected velocity, and an expected acceleration of a distal end of the robotic arm; According to the joint space offset, the robotic arm is controlled to move toward the target installation hole position in the Z-axis direction to complete the assembly.

9. An automatic shaft hole assembly device, characterized in that: include: A search module is configured to control the robotic arm to grasp the workpiece and arrive at the assembly position, and then control the robotic arm to search for the position of the target mounting hole from the inside outward along the center point of the workpiece with a set step length on a plane perpendicular to the Z-axis direction, and record the contact force of each step of the robotic arm in the Z-axis direction, wherein the Z-axis direction is the shaft-hole assembly direction; a determination module, configured to determine shaft-hole alignment when the contact forces in the Z-axis direction are all less than a set force threshold within a time window; The assembly module is used to control the robot arm to move toward the target installation hole position along the Z axis to complete the assembly.

10. The device according to claim 9, characterized in that Before the search module controls the robot arm to search for the position of the target mounting hole from the inside outward along the center point of the workpiece with a set step length on a plane perpendicular to the Z-axis direction, the search module may also be used to: Obtain the shaft-hole pose image; Determining the pose of the workpiece and the pose of the target mounting hole position according to the shaft hole pose image; According to the posture of the workpiece and the posture of the target installation hole, the robot arm is controlled to grab the workpiece and move it to the assembly position of the target installation hole.

11. The device according to claim 9, characterized in that The search module can also be used to: Recording the absolute value of the torque applied to the end of the robotic arm in the X-axis and Y-axis directions for each step of the robotic arm's movement, wherein the X-axis and the Y-axis are mutually perpendicular directions on a plane perpendicular to the Z-axis direction; generating an X-axis torque distribution diagram according to the absolute value of the torque applied to the end of the robot arm in the X-axis direction; and A Y-axis torque distribution diagram is generated according to the absolute value of the torque applied to the end of the robot arm in the Y-axis direction.

12. The device according to claim 11, characterized in that The search module can also be used to: If the search side length is greater than the side length threshold, it is determined that the shaft hole is misaligned; wherein the search side length is the side length of a square spiral line formed by the robot arm searching from the inside to the outside along the center point of the workpiece with a set step length; Determining a posture correction amount of the target mounting hole position according to the X-axis torque distribution diagram and the Y-axis torque distribution diagram; According to the posture correction amount of the target installation hole position, the robot arm is controlled to search for the position of the target installation hole again along the center point of the workpiece with a set step size from the inside to the outside.

13. The device according to claim 12, characterized in that When determining the posture correction amount of the target mounting hole position based on the X-axis moment distribution diagram and the Y-axis moment distribution diagram, the search module is used to: Performing filtering on the X-axis moment distribution graph and the Y-axis moment distribution graph respectively to obtain a filtered X-axis moment distribution graph and a filtered Y-axis moment distribution graph; Normalizing the filtered X-axis moment distribution graph and the filtered Y-axis moment distribution graph to obtain a normalized X-axis moment distribution graph and a normalized Y-axis moment distribution graph; superimposing the normalized X-axis moment distribution graph and the normalized Y-axis moment distribution graph to obtain a composite image; Traversing the composite image, finding all locations where the center value of the window is greater than the values ​​of other pixels in the window as the maximum value points; Calculating the peak intensity of the maximum point according to the height of the maximum point and the trough height; The position correction amount of the target mounting hole position is determined according to the peak strength of the maximum point.

14. The device according to claim 13, characterized in that When the search module performs superposition processing on the normalized X-axis moment distribution graph and the normalized Y-axis moment distribution graph to obtain a composite image, it is used to: Superimposing the normalized X-axis moment distribution graph and the normalized Y-axis moment distribution graph to obtain a superimposed image; Traversing the stacked image using a set window, and calculating the variance and mean of each set window to obtain a variance distribution map and a mean distribution map; performing normalization operations on the variance distribution graph and the mean distribution graph respectively to obtain a normalized variance distribution graph and a normalized mean distribution graph; The normalized variance distribution map and the normalized mean distribution map are superimposed to obtain a composite image.

15. The device according to claim 13, characterized in that When determining the posture correction amount of the target mounting hole position according to the peak strength of the maximum point, the search module is used to: Select two maximum points with the highest peaks from the maximum points whose peak intensities are greater than the peak intensities threshold; Determine the hole offset according to the two maximum value points; A position correction amount of the target mounting hole position is determined based on the hole offset.

16. The device according to claim 9, characterized in that When controlling the robotic arm to move toward the target mounting hole position along the Z-axis to complete assembly, the search module is used to: Determining a joint space offset of the robotic arm based on an actual velocity, an actual acceleration, an expected velocity, and an expected acceleration of a distal end of the robotic arm; According to the joint space offset, the robotic arm is controlled to move toward the target installation hole position in the Z-axis direction to complete the assembly.

17. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute instructions to implement each step in the method according to any one of claims 1 to 8.

18. A robot, characterized in that: include: robotic arms and processors; a memory for storing processor-executable instructions; The processor is configured to execute instructions to implement each step in the method according to any one of claims 1 to 8.

19. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

20. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images