An outer hexagonal bolt assembly control method, system, device and storage medium

Abstract

The application relates to a hexagonal bolt assembly control method, system, device and storage medium, which comprises the following steps: collecting bolt cap image data information of a bolt workpiece, performing image registration processing on the bolt cap image, and solving the symmetric grabbing pose of the current bolt workpiece; based on distance information collected by a laser sensor, solving an installation plane normal vector, and adjusting the posture of the mechanical arm end and the camera through the normal posture estimation result; positioning the threaded hole on the installation plane according to the installation plane image data information, detecting the distance between the bolt and the threaded hole through the laser sensor; setting a torque / rotation angle change rate threshold value in the bolt assembly process based on torque information collected by a torque sensor and mechanical arm end shaft rotation angle information, and if the threshold value is exceeded in the assembly process, the assembly robot rotates out to the initial tightening position along the reverse motion track. Compared with the prior art, the application realizes full-automatic installation, and has the advantages of high efficiency and high accuracy.

Description

Technical Field

[0001] This invention relates to the field of industrial robot technology, and in particular to a method, system, device and storage medium for controlling the assembly of external hexagonal bolts. Background Technology

[0002] Bolts, as the most common spare parts, are widely used in various connection applications, such as flange connections. However, the installation and tightening of bolts are entirely done manually, resulting in low work efficiency and extreme labor intensity for workers. In harsh environments such as dangerous, toxic, harmful, low-temperature, and high-temperature conditions, such as the bolted connections of pressure vessels in nuclear power plants, if bolts become loose, manual tightening becomes extremely inconvenient and unsafe, significantly impacting production efficiency and leading to issues like incorrect or missing bolts, severely affecting the reliability of bolt assembly. Summary of the Invention

[0003] The purpose of this invention is to overcome the defects of the prior art by providing a method, system, equipment and storage medium for controlling the assembly of external hexagonal bolts, which can realize fully automatic installation of external hexagonal bolts and has the advantages of high efficiency and high accuracy.

[0004] The objective of this invention can be achieved through the following technical solutions:

[0005] According to a first aspect of the present invention, a method for controlling the assembly of external hexagonal bolts is provided, the method comprising:

[0006] Collect bolt cap image data of the bolt workpiece, perform image registration processing with the template bolt cap image, and solve the symmetrical grasping pose of the current bolt workpiece;

[0007] Based on the distance information collected by the laser sensor, the normal vector of the mounting plane is calculated, and the attitude of the robotic arm end effector and the camera is adjusted based on the normal attitude estimation results.

[0008] Based on the collected installation plane image data, the threaded holes on the installation plane are located, and the distance between the bolt and the threaded hole is detected by a laser sensor.

[0009] Based on the torque information collected by the torque sensor and the rotation angle information of the end shaft of the robotic arm, a threshold for the rate of change of torque / rotation angle during bolt assembly is set. If the threshold is exceeded during the assembly process, the assembly robot rotates out to the initial tightening position along the reverse motion trajectory.

[0010] Preferably, the bolt cap image data of the bolt workpiece includes 3D point cloud data information and 2D color image information.

[0011] Preferably, the step of acquiring bolt head image data of the bolt workpiece, performing image registration processing between the current bolt head image of the bolt workpiece and the template bolt head image, and solving the symmetrical grasping pose of the current bolt workpiece includes:

[0012] The center position and gripping posture of the template bolt cap image are calibrated. The center coordinates of the largest inscribed circle of the template bolt cap, i.e. the gripping center coordinates, are obtained by traversing all contour edge points in the template bolt cap image.

[0013] The contour in the template bolt cap image is fitted by Hough transform to solve the template bolt cap grasping angle pose information;

[0014] The shooting position and angle are determined, and the image information of the bolt head in the bolt material is collected by the vision detection module fixed on the mechanical gripper. By comparing the spectrum of the current bolt head image with the template bolt head image after processing by fast Fourier transform and polar coordinate transformation, and using the phase correlation method to solve the translation and scaling size of the current bolt head relative to the template bolt head, the rotation angle between the two images is solved by the rotation invariance of the image. Finally, the rotation angle and gripping center coordinates that need to be adjusted for the mechanical gripper to grasp the bolt head are determined, which is the symmetrical gripping posture of the current bolt workpiece.

[0015] Preferably, the step of calculating the normal vector of the mounting plane based on the distance information collected by the laser sensor, and adjusting the attitude of the robotic arm end effector and the camera based on the normal attitude estimation result, includes:

[0016] The host computer controls the robot to move directly above the mounting plane. The robot selects three non-collinear points on the mounting plane and obtains the depth information of these three points by marking them with a laser sensor. The depth information of the three points is then fused with the calibration matrix of the laser sensor's spatial position to obtain the coordinates of the three points in the robot's base coordinate system. The mounting plane is then fitted using the coordinates of the three points in the base coordinate system, and the normal vector of the mounting plane is calculated. The attitude correction angle of the robot's end effector is calculated based on this normal vector, and the attitude of the end effector is adjusted so that the imaging plane of the servo camera is parallel to the normal vector of the mounting plane.

[0017] Preferably, the step of locating the threaded hole on the mounting plane based on the collected mounting plane image data, and detecting the distance of the bolt to the threaded hole using a laser sensor, includes:

[0018] The host computer controls the robot to move directly above the mounting plane. The robot's camera captures the image information of the threaded hole on the mounting plane. After filtering, the threaded hole is located based on its shape. The pose of the threaded hole in the robot's base coordinate system is calculated. The axis of the bolt rod is aligned with the axis of the threaded hole at this time. A laser sensor is used to monitor the distance data of the bolt rod approaching the threaded hole in real time.

[0019] Preferably, the threshold for the rate of change of torque / angle during bolt assembly is set based on the torque information collected by the torque sensor and the rotation angle information of the robotic arm's end effector. If the threshold is exceeded during assembly, the assembly robot rotates out along the reverse motion trajectory to the initial tightening position, including:

[0020] The tightening torque data after the bolt rod enters the threaded hole and the rotation angle data during the bolt assembly process are monitored in real time by a six-dimensional torque sensor and a robotic arm host computer. The rate of change of tightening torque with rotation angle during the assembly process is calculated to determine whether the torque / rotation angle change rate during the assembly process exceeds the set threshold.

[0021] If the torque / rotation angle change rate exceeds the threshold, it is determined that an assembly failure has occurred during the current bolt assembly process. The assembly robot then rotates out along the reverse motion trajectory to the initial tightening position, repositions the threaded hole, and re-performs the assembly operation.

[0022] Preferably, the assembly failure includes crossover, jamming, and slippage during the thread fit process.

[0023] According to a second aspect of the present invention, a multi-sensor-based external hexagonal bolt assembly control system is provided, the system comprising:

[0024] Visual inspection module: Fixed on the robotic arm, used to collect image data of bolt workpieces and threaded holes on the mounting surface;

[0025] Laser ranging module: fixed on the robotic arm, used to collect distance data as the robotic arm clamps the bolts and approaches the mounting plane;

[0026] Torque detection module: Fixed between the robotic arm and the mechanical gripper, used to collect six-dimensional torque data during bolt assembly;

[0027] Actuator module: includes the robotic arm body and mechanical grippers, used to perform gripping and assembly actions;

[0028] Main control module: used to control the acquisition of execution signals, data acquisition, data preprocessing, visual positioning, robot pose adjustment and tightening assembly.

[0029] According to a third aspect of the present invention, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the program to implement any of the methods described above.

[0030] According to a fourth aspect of the invention, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements any of the methods described herein.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] 1) By using image registration, point cloud plane fitting, laser ranging plane fitting and robot control and other related technologies, we can monitor and locate each step of the assembly of hexagonal bolts, thereby realizing the assembly technology of hexagonal bolts completely dominated by robots, and the detection accuracy can be optimized and improved.

[0033] 2) By monitoring torque information during the assembly process through torque sensors, the assembly status is judged based on the feedback information. If an assembly abnormality occurs, the assembly is reversed and reassembled. This not only improves positioning efficiency but also significantly enhances assembly accuracy. Attached Figure Description

[0034] Figure 1 A schematic diagram illustrating the steps of the external hexagonal bolt assembly control method provided in the embodiment;

[0035] Figure 2 This is a calibration diagram of the center position of the template bolt cap provided for an embodiment;

[0036] Figure 3 The template bolt cap gripping pose calibration diagram provided for the embodiment;

[0037] Figure 4 A flowchart of a bolt cap grasping pose estimation method based on Fourier and logarithmic polar coordinate transformation provided for an embodiment;

[0038] Figure 5 Example diagram of fitting the mounting plane and its normal vector provided for the embodiment;

[0039] Figure 6 Flowchart of the improved arc support group threaded hole fitting algorithm provided for the embodiment;

[0040] Figure 7 A flowchart of the algorithm for extracting arc segments is provided for this embodiment;

[0041] Figure 8 A schematic diagram of the fitting of the mounting plane threaded hole provided for the embodiment;

[0042] Figure 9Example diagram of laser sensor depth data variation provided for the embodiment;

[0043] Figure 10 A schematic diagram of the bolt rod-threaded hole mating process control strategy provided for the embodiment;

[0044] Figure 11 This is a schematic diagram of the structure of an external hexagonal bolt assembly control system provided for an embodiment. Detailed Implementation

[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0046] Example

[0047] Reference Figure 1 As shown in the figure, this embodiment demonstrates an actual assembly scenario where a robot assembles external hexagonal bolts, providing a method for controlling the assembly of external hexagonal bolts. This method includes:

[0048] Collect bolt head image data of the bolt workpiece, perform image registration processing between the current bolt head image of the bolt workpiece and the template bolt head image, and solve the precise symmetrical grasping pose of the current bolt workpiece.

[0049] Based on the distance information collected by the laser sensor, the normal vector of the mounting plane is calculated, and the attitude of the robotic arm end effector and the camera is adjusted based on the normal attitude estimation results.

[0050] Based on the collected installation plane image data, the threaded holes on the installation plane are located, and the distance between the bolt and the threaded hole is detected by a laser sensor.

[0051] Based on the torque information collected by the torque sensor and the rotation angle information of the end shaft of the robotic arm, a threshold for the rate of change of torque / rotation angle during bolt assembly is set. If the threshold is exceeded during the assembly process, the assembly robot rotates out to the initial tightening position along the reverse motion trajectory.

[0052] In this embodiment, a follow-up camera mounted on a mechanical gripper is used to acquire image data of the bolt head portion of the bolt workpiece, including 3D point cloud data and color image data.

[0053] The specific implementation process is as follows:

[0054] (1) Control the robotic arm to move above the bolt workpiece feeding mechanism via the host computer;

[0055] (2) Determine the best shooting position and the best shooting angle, specifically using techniques such as hand-eye calibration, and start the robotic arm to take pictures of the bolt head part of the bolt workpiece (the picture data is 3D point cloud data and 2D color image);

[0056] (3) Use image registration technology to calculate the rotation, translation and scaling of the bolt head part of the current bolt workpiece and the bolt head part of the template, so as to calculate the optimal gripping pose of the current bolt workpiece.

[0057] The bolt cap grasping pose estimation algorithm based on Fourier and log-polar coordinate transformation of the servo camera interacts with the control system. By comparing the spectrum images processed by fast Fourier transform and polar coordinate transformation, and using the phase correlation method, the translation and scaling dimensions of the current bolt cap relative to the template bolt cap can be solved. Through the rotation invariance of the image, the rotation angle θ between the two images can be solved. Finally, the rotation angle and grasping center coordinates that the mechanical gripper needs to adjust to grasp the bolt cap are determined. The specific calculation flowchart of the bolt cap grasping pose estimation algorithm based on Fourier and log-polar coordinate transformation is shown in Figure 4.

[0058] Based on the distance information collected by the laser sensor, the normal vector of the mounting plane is solved by the three-point method, and the attitude of the robotic arm end effector and the camera is adjusted based on the normal attitude estimation results.

[0059] To achieve higher accuracy in the threaded hole images acquired by the follow-up camera and to ensure that the central axis of the bolt shank portion that grips the bolt is aligned with the normal vector direction of the mounting plane, this embodiment calculates the tilt angle of the mounting plane in the world coordinate system and the normal vector of the mounting plane by measuring the depth information of three surface points on the bolt mounting plane. Then, the position of the mounting plane in the world coordinate system is fitted, and the posture of the robot actuator is corrected by the normal vector of the mounting plane.

[0060] Based on the image data of the mounting plane collected by the servo camera, the threaded hole on the mounting plane is located, and the distance of the bolt to the threaded hole is detected by the laser sensor.

[0061] Among them, the servo camera, based on the improved threaded hole positioning algorithm of the arc support group and the polarity interaction of the control system, first performs noise reduction processing on the image using a bilateral filtering algorithm before fitting the image, and extracts the arc segments in the image. The algorithm flowchart is as follows. Figure 6As shown, the arc segments are grouped according to their continuity and concavity / convexity. The groups with larger central angles corresponding to the radians are directly fitted with relevant ellipse parameters, and the center coordinates are extracted as the set of ellipse center parameters on the image. Then, the arc segments are grouped according to their distance from the center. Arc segments in the same group will eventually fit the same elliptical trajectory. The subset of arc segments in the same group is calculated using the least squares method to obtain the initial ellipse parameters. Finally, the initial ellipse parameters are verified according to the properties of the ellipse, and mismatched ellipses are removed. The specific flowchart of the threaded hole positioning algorithm based on the improved arc support group is shown below. Figure 7 As shown.

[0062] Among them, the distance data from the installation plane monitored by the laser sensor is as follows: Figure 8 As shown.

[0063] Based on the torque information collected by the torque sensor and the rotation angle information of the end shaft of the robotic arm, a threshold for the rate of change of torque / rotation angle during bolt assembly is set. If the threshold is exceeded during the assembly process, the assembly robot rotates out to the initial tightening position along the reverse motion trajectory.

[0064] The specific implementation process is as follows: After the bolt shank enters the threaded hole, the torque information during the bolt assembly process is collected by a torque sensor. Combined with the rotation angle information of the mechanical gripper, the value of the torque-rotation angle change rate λ is calculated. The calculation formula is as follows:

[0065]

[0066] In this embodiment, a change rate threshold λ is set. warning To determine whether unexpected situations such as jamming or thread crossover occur during the assembly process, when λ≤λ warning This indicates that the assembly is normal, when λ > λ. warning This indicates an assembly abnormality; it is used when an assembly abnormality occurs. Figure 10 The adjustment strategy shown.

[0067] The hexagonal bolt assembly method provided by this invention enables a robot-led hexagonal bolt assembly process, reducing labor costs. It utilizes image registration, point cloud plane fitting, laser ranging plane fitting, and robot control technologies to monitor and locate each stage of the hexagonal bolt assembly, achieving a fully robot-led hexagonal bolt assembly technology with easily optimized detection accuracy. Compared to existing assembly methods, it offers higher precision and effectively overcomes the drawbacks of high labor intensity and low efficiency in manual assembly, thus improving the quality and reliability of bolt assembly to a certain extent.

[0068] Reference Figure 11 This embodiment also provides an external hexagonal bolt assembly control system, which includes:

[0069] Visual inspection module: Fixed on the robotic arm, used to collect image data of bolt workpieces and threaded holes on the mounting surface;

[0070] Laser ranging module: fixed on the robotic arm, used to collect distance data as the robotic arm clamps the bolts and approaches the mounting plane;

[0071] Torque detection module: Fixed between the robotic arm and the mechanical gripper, used to collect six-dimensional torque data during bolt assembly;

[0072] Actuator module: includes the robotic arm body and mechanical grippers, used to perform gripping and assembly actions;

[0073] Main control module: used to control the acquisition of execution signals, data acquisition, data preprocessing, visual positioning, robot pose adjustment and tightening assembly.

[0074] The main control module detects the gripping posture of the hexagonal bolt material, calculates the gripping posture of the bolt head, and then collects the distance data from the laser sensor to the mounting plane. Based on this distance data, it controls the camera's visual inspection device to ensure that the camera's imaging plane is parallel to the mounting plane, thereby collecting the coordinate data of the threaded hole on the mounting plane. The main control device can then insert the bolt shank into the threaded hole according to the coordinates of the threaded hole on the mounting plane. The torque detection module monitors the applied torque in real time during the assembly process and monitors and judges the rate of change of tightening torque / tightening angle. If it exceeds the set threshold, the assembly is judged as abnormal, and the mechanical gripper holds the hexagonal bolt and rotates it back to the initial tightening position along the reverse movement trajectory for reassembly.

[0075] By acquiring images of the bolt caps of hexagonal bolts and using image registration technology to determine the gripping pose of the bolt image, the robotic arm is controlled to hold the bolt. Next, images of the threaded holes on the mounting plane are acquired, filtered, and edge information extracted to locate the orientation of the threaded holes on the mounting plane, aligning the central axis of the threaded holes with the central axis of the bolt shank. Finally, torque sensors monitor torque information during assembly, and the assembly status is determined based on feedback. If an assembly abnormality occurs, the bolt is rotated in the opposite direction and reassembled. This process not only improves positioning efficiency but also significantly enhances assembly accuracy, providing a technological foundation for the assembly of hexagonal bolts.

[0076] The electronic device of this invention includes a central processing unit (CPU), which can perform various appropriate actions and processes according to computer program instructions stored in read-only memory (ROM) or loaded from a storage unit into random access memory (RAM). The RAM may also store various programs and data required for device operation. The CPU, ROM, and RAM are interconnected via a bus. Input / output (I / O) interfaces are also connected to the bus.

[0077] Multiple components in the device are connected to the I / O interface, including: input units such as keyboards and mice; output units such as various types of displays and speakers; storage units such as disks and optical discs; and communication units such as network interface cards (NICs), modems, and wireless transceivers. The communication unit allows the device to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0078] The processing unit performs the various methods and processes described above. For example, in some embodiments, the methods may be implemented as computer software programs tangibly contained in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed on the device via ROM and / or a communication unit. When the computer program is loaded into RAM and executed by the CPU, one or more steps of the methods described above may be performed. Alternatively, in other embodiments, the CPU may be configured to execute the methods by any other suitable means (e.g., by means of firmware).

[0079] The functions described above in this document can be performed at least in part by one or more hardware logic components. For example, exemplary types of hardware logic components that can be used, without limitation, include: field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload programmable logic devices (CPLDs), and so on.

[0080] The program code used to implement the methods of the present invention can be written in any combination of one or more programming languages. This program code can be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0081] In the context of this invention, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0082] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for controlling the assembly of external hexagonal bolts, characterized in that, The method includes: Collect bolt cap image data of bolt workpiece and perform image registration processing with template bolt cap image to solve the symmetrical grasping pose of current bolt workpiece, including: calibrating the center position and grasping posture of template bolt cap image, and solving the center coordinates of the largest inscribed circle of template bolt cap by traversing all contour edge points in template bolt cap image, i.e., the grasping center coordinates. The contour in the template bolt cap image is fitted by Hough transform to solve the template bolt cap grasping angle pose information; The shooting position and angle are determined, and the image information of the bolt head in the bolt material is collected by the vision detection module fixed on the mechanical gripper. By comparing the spectrum of the current bolt head image with the template bolt head image after processing by fast Fourier transform and polar coordinate transformation, and using the phase correlation method to solve the translation and scaling size of the current bolt head relative to the template bolt head, the rotation angle between the two images is solved by the rotation invariance of the image. Finally, the rotation angle and gripping center coordinates that the mechanical gripper needs to adjust to grip the bolt head are determined, which is the symmetrical gripping posture of the current bolt workpiece. Based on the distance information collected by the laser sensor, the normal vector of the mounting plane is calculated, and the attitude of the robotic arm end effector and the camera is adjusted according to the normal attitude estimation results. This includes: locating the threaded hole on the mounting plane according to the collected image data of the mounting plane, and detecting the distance of the bolt to the threaded hole using the laser sensor; controlling the robot to move directly above the mounting plane using the host computer, controlling the robot's camera to collect the image information of the threaded hole on the mounting plane, locating the threaded hole based on the shape of the threaded hole after filtering, calculating the pose of the threaded hole in the robot's base coordinate system, aligning the axis of the bolt rod with the axis of the threaded hole at this time, and using the laser sensor to monitor the distance data of the bolt rod to the threaded hole in real time. Based on torque information collected by a torque sensor and rotation angle information of the robotic arm's end effector, a threshold for the rate of change of torque / rotation angle during bolt assembly is set. If the threshold is exceeded during assembly, the assembly robot rotates back to the initial tightening position along a reverse motion trajectory, including: The tightening torque data after the bolt rod enters the threaded hole and the rotation angle data during the bolt assembly process are monitored in real time by a six-dimensional torque sensor and a robotic arm host computer. The rate of change of tightening torque with rotation angle during the assembly process is calculated to determine whether the torque / rotation angle change rate during the assembly process exceeds the set threshold. If the torque / rotation angle change rate exceeds the threshold, it is determined that an assembly failure has occurred during the current bolt assembly process. The assembly robot then rotates out along the reverse motion trajectory to the initial tightening position, repositions the threaded hole, and re-performs the assembly operation. The assembly failures include crossover, jamming, and slippage during the thread fit process.

2. The assembly control method for external hexagonal bolts according to claim 1, characterized in that, The bolt cap image data of the bolt workpiece includes 3D point cloud data information and 2D color image information.

3. The assembly control method for external hexagonal bolts according to claim 1, characterized in that, The process involves calculating the normal vector of the mounting plane based on distance information collected by a laser sensor, and then adjusting the attitude of the robotic arm's end effector and the camera using the normal attitude estimation results. This includes: The host computer controls the robot to move directly above the mounting plane. The robot selects three non-collinear points on the mounting plane and obtains the depth information of these three points by marking them with a laser sensor. The depth information of the three points is then fused with the calibration matrix of the laser sensor's spatial position to obtain the coordinates of the three points in the robot's base coordinate system. The mounting plane is then fitted using the coordinates of the three points in the base coordinate system, and the normal vector of the mounting plane is calculated. The attitude correction angle of the robot's end effector is calculated based on this normal vector, and the attitude of the end effector is adjusted so that the imaging plane of the servo camera is parallel to the normal vector of the mounting plane.

4. A system based on the assembly control method for external hexagonal bolts as described in claim 1, characterized in that, The system includes: Visual inspection module: Fixed on the robotic arm, used to collect image data of bolt workpieces and threaded holes on the mounting surface; Laser ranging module: fixed on the robotic arm, used to collect distance data as the robotic arm clamps the bolts and approaches the mounting plane; Torque detection module: Fixed between the robotic arm and the mechanical gripper, used to collect six-dimensional torque data during bolt assembly; Actuator module: includes the robotic arm body and mechanical grippers, used to perform gripping and assembly actions; Main control module: used to control the acquisition of execution signals, data acquisition, data preprocessing, visual positioning, robot pose adjustment and tightening assembly.

5. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 3.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 3.

Images