Manipulator test classification control method and system, electronic equipment and readable storage medium

Abstract

The invention relates to the technical field of manipulator control, in particular to a manipulator test classification control method and system, electronic equipment and a readable storage medium. The method comprises the following steps: performing recognition processing on an obtained workpiece image to obtain pose information of a target workpiece; controlling a manipulator to transfer the target workpiece to a test system according to the pose information; determining a test result of the target workpiece based on the test system; and according to the test result, the manipulator is controlled to execute classification operation on the target workpiece. A test link is embedded into control logic of the manipulator to form a closed-loop control system, and the system can adjust classification operation in real time according to a test result, so that intelligent decision making and full-process automation are realized.

Description

Technical Field

[0001] This application relates to the field of robotic arm control technology, and in particular to robotic arm test classification control methods, systems, electronic devices, and readable storage media. Background Technology

[0002] Currently, automated production lines are widely used in industries such as electronics, automotive, and medical devices to improve production efficiency, reduce labor costs, and ensure product consistency. Industrial robots, especially multi-axis manipulators, are key execution units in automated systems. Meanwhile, advancements in computer vision technology have driven the integrated application of vision recognition systems in automated equipment. This enables automated production systems to identify information such as the position, posture, and defects of workpieces, thereby supporting more intelligent and precise operational control.

[0003] Current common automated equipment has initially achieved the linkage between vision systems and robotic arms. For example, Chinese patent CN114750168A discloses a robotic arm control method and system based on machine vision. It acquires image information of the object being executed by the robotic arm through an image acquisition device, obtains the position data of the robotic arm through a position detection device, and then generates instructions to control the robotic arm based on the image information and position data.

[0004] However, in applications involving workpiece handling, these automated systems typically lack the ability to perform functional testing on the workpieces and to perform intelligent classification based on test results. The testing process often relies on manual operation or independent testing equipment, failing to form a closed-loop control with the robotic arm's movements, thus limiting the overall automation level and operational efficiency of the process.

[0005] The above content is only used to help understand the technical solution of this application and does not represent an admission that the above content is prior art. Summary of the Invention

[0006] The main objective of this application is to provide a robot arm testing classification control method, system, electronic device, and readable storage medium, aiming to solve the technical problem that workpiece testing is not forming a closed-loop control with robot arm control.

[0007] To achieve the above objectives, this application proposes a robotic arm test classification control method, which includes: The acquired workpiece image is processed to obtain the pose information of the target workpiece; Based on the pose information, the robot arm is controlled to transfer the target workpiece to the testing system; Based on the testing system, the test results of the target workpiece are determined; Based on the test results, the robot arm is controlled to perform a sorting operation on the target workpiece.

[0008] Optionally, the step of performing recognition processing on the acquired workpiece image to obtain the pose information of the target workpiece includes: Based on edge detection algorithms, fuzzy matching algorithms, and deep learning recognition algorithms, the workpiece image is processed to obtain the pose data and position data of the target workpiece.

[0009] Optionally, the step of controlling the robot to transfer the target workpiece to the testing system based on the pose information includes: Based on the position data of the pose information, the movement trajectory of the robotic arm is determined; and, Based on the posture data of the pose information, the grasping angle of the robotic arm is determined; Based on the movement trajectory and the grasping angle, a grasping action command is generated; The gripping action command is executed to control the robotic arm to grip the target workpiece, move and place the target workpiece into the testing system.

[0010] Optionally, the step of determining the test result of the target workpiece based on the test system includes: Identify the test pose of the target workpiece and determine whether the test pose is correct; If so, execute the test program to obtain the test results of the target workpiece, the test results including qualified, unqualified, and pending re-inspection.

[0011] Optionally, the step of controlling the robotic arm to perform a sorting operation on the target workpiece based on the test results includes: Based on the test results, generate classification action instructions; Execute the classification action instruction, grab the target workpiece, move and place the target workpiece to the target classification area.

[0012] Optionally, after the step of generating classification action instructions based on the test results, the method further includes: Determine the surplus or shortage status of the target classification region; When the surplus / shortage state is full, the execution of the classification action instruction is stopped, and the full signal of the target classification area is output. When the surplus / shortage state is empty, the execution of the classification action instruction continues.

[0013] Optionally, the step of determining the test result of the target workpiece based on the test system includes: The test procedure is executed to perform a conformity test on the target workpiece, and test data and test results are obtained. The conformity test includes electrical performance testing and functional testing. Generate a test record based on the test data; Update the test database based on the test record.

[0014] In addition, to achieve the above object, the present application also proposes a manipulator test classification control system, which includes: A visual recognition module, configured to perform recognition processing on the acquired workpiece image to obtain the pose information of the target workpiece; A manipulator control module, configured to control the manipulator to transfer the target workpiece to the test system according to the pose information; A test control module, configured to determine the test result of the target workpiece based on the test system; A classification decision module, configured to control the manipulator to perform a classification operation on the target workpiece according to the test result.

[0015] In addition, to achieve the above object, the present application also proposes an electronic device, which includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and the computer program is configured to implement the steps of the manipulator test classification control method as described above.

[0016] In addition, to achieve the above object, the present application also proposes a readable storage medium, which is a computer-readable storage medium, and a computer program is stored on the readable storage medium, and when the computer program is executed by a processor, the steps of the manipulator test classification control method as described above are implemented.

[0017] One or more technical solutions proposed by the present application have at least the following technical effects: Obtain the pose information of the target workpiece by recognizing and processing the workpiece image, and control the manipulator to transfer the target workpiece to the test system according to the pose information. Then, the test system tests the target workpiece to determine the qualification of the target workpiece, and further drives the manipulator to classify the target workpiece according to the test result. Through a series of consecutive steps of perception, execution, judgment, and feedback execution, the test link is embedded in the control logic of the manipulator, forming a closed-loop control system. The system can adjust the classification operation in real time according to the test result, thus realizing intelligent decision-making and full-process automation.

[0018] Through the visual recognition module and the manipulator control module, the deep integration of visual recognition and manipulator control is realized, and the grasping accuracy is improved. Combining the test control module and the classification decision module, the classification action is driven by the test result to form a closed-loop control. Through a highly integrated software architecture, the deployment and maintenance are simplified, and the recognition and classification of multiple types of workpieces are supported to meet the requirements of flexible production. In addition, by providing functions of exception handling and data traceability, the reliability of the system is improved. Attached Figure Description

[0019] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart illustrating an embodiment of the robotic arm testing classification control method of this application. Figure 2 This is a flowchart illustrating Embodiment 2 of the robotic arm test classification control method of this application. Figure 3 This is a schematic diagram of the module structure of the robotic arm test classification control system according to an embodiment of this application; Figure 4 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the robotic arm test classification control method in the embodiments of this application.

[0022] The purpose, features, and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0023] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0024] It should be noted that in the description of this application and the appended claims, the terms "first," "second," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0025] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0026] It should be noted that the executing entity in this embodiment can be an electronic device with data processing, network communication and program running functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of realizing the above functions.

[0027] Reference Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the robotic arm test classification control method of this application. In this embodiment, the robotic arm test classification control method includes steps S100 to S400: Step S100: The acquired workpiece image is processed for recognition to obtain the pose information of the target workpiece.

[0028] It should be noted that the target workpiece can be electronic components, circuit boards, or electronic devices, etc. Pose information includes attitude data and position data. Position data refers to the position of the target workpiece in camera coordinates, which can be (x, y, z) coordinates; attitude data refers to the rotation angles around the x, y, and z axes, which can be represented by Euler angles or quaternions.

[0029] Additionally, it should be noted that robotic arms can be multi-axis, especially six-axis robotic arms. Six-axis robotic arms are characterized by high flexibility, a wide range of motion, and the ability to adapt to complex working conditions. They offer significant advantages in automated grasping, assembly, and material handling. In this embodiment, there are no specific limitations on the method of acquiring workpiece images. For example, an industrial camera installed above the workstation can be used to take pictures of the target workpiece to acquire workpiece images. Furthermore, before acquiring workpiece images, it can be detected whether the target workpiece has entered the field of view of the industrial camera, and only after it is determined that the target workpiece has entered the field of view will the industrial camera perform the workpiece image acquisition operation.

[0030] Optionally, the method of recognizing and processing the workpiece image includes using integrated computer vision algorithms to process and analyze the workpiece image. These integrated computer vision algorithms include, but are not limited to, feature matching, contour extraction, and deep learning model inference.

[0031] Understandably, accurate positioning of the workpiece graphic using computer vision algorithms is a prerequisite for a robotic arm to successfully grasp the target workpiece. Without precise positional data, the robotic arm may miss or collide with the workpiece. For asymmetrical or directional workpieces, such as circuit boards and connectors, it is necessary to determine the workpiece's posture to ensure accurate placement into the testing system. Posture data clarifies the angle at which the robotic arm should grasp and place the target workpiece. In other words, pose information is fundamental to obtaining the optimal path that ensures the robotic arm's safe and efficient operation.

[0032] In one feasible implementation, step S100 includes performing recognition processing on the workpiece image based on an edge detection algorithm, a fuzzy matching algorithm, and a deep learning recognition algorithm to obtain the pose data and position data of the target workpiece.

[0033] In the process of recognizing and processing workpiece images, the workpiece images are first preprocessed, then the outline of the target workpiece is located by the edge detection algorithm, the fuzzy matching algorithm is used to achieve preliminary recognition and positioning, and finally, the deep learning recognition algorithm is used to achieve accurate recognition and pose estimation of the target workpiece, thereby obtaining the pose data and position data of the target workpiece.

[0034] The preprocessing steps for the workpiece image include noise reduction and contrast enhancement. Then, an edge detection algorithm identifies points in the workpiece image where pixel brightness changes abruptly to delineate the external contour and key internal features of the target workpiece. This is equivalent to quickly determining "approximately where the workpiece is located in the image" and "what its basic shape is."

[0035] The fuzzy matching algorithm searches and calculates similarity between a preset standard workpiece template image and the currently captured workpiece image to overcome the effects of lighting changes, slight occlusion, and angle deflection, thereby determining the region most similar to the template and obtaining the approximate position (X, Y coordinates) and rotation angle of the target workpiece in the two-dimensional image plane.

[0036] Deep learning recognition algorithms, using deep learning models trained on large amounts of labeled data, such as convolutional neural networks or networks specifically designed for pose estimation, acquire more abstract and deeper features of workpieces. In terms of recognition, deep learning algorithms can distinguish workpieces that are extremely similar in appearance but different in model; in terms of pose estimation, they can directly predict the precise six-degree-of-freedom pose of the target workpiece in three-dimensional space end-to-end from a single or a few images.

[0037] The purpose of this approach is to first narrow down the search area through edge detection and template matching, and then use computationally intensive deep learning recognition algorithms to obtain pose information. This achieves both the speed requirements of production schedules and the accuracy requirements of the task. Furthermore, due to challenges in industrial production environments such as varying lighting, workpiece surface reflections, random positioning, and mutual occlusion, integrated computer vision algorithms ensure stable operation under various non-ideal conditions, thereby improving the reliability and intelligence of the entire automation system.

[0038] Step S200: Based on the pose information, control the robot arm to transfer the target workpiece to the testing system.

[0039] In this embodiment, the pose information is converted into coordinate commands that the robot can understand, driving the robot to move to a designated position and grasp the target workpiece in the correct posture. The grasping action can be achieved by a specific end effector, such as a suction cup or gripper. Then, the robot is driven to smoothly and accurately transport the target workpiece to the designated test position in the testing system, such as a test rack, test table, bed of needles, or RF shielding box, following a predetermined trajectory.

[0040] Understandably, by using the pose information to drive the robot to transfer the target workpiece to the testing system, the traditional manual loading and positioning operations are replaced, allowing the workpiece to automatically and continuously flow from the previous station to the testing station, thus improving overall efficiency.

[0041] In one feasible implementation, step S200 may include steps S210 to S240: Step S210: Determine the movement trajectory of the robotic arm based on the position data of the pose information; and, Step S220: Determine the grasping angle of the robotic arm based on the posture data of the pose information; Step S230: Generate a grasping action command based on the movement trajectory and the grasping angle; Step S240: Execute the gripping action command to control the robotic arm to grip the target workpiece, move and place the target workpiece to the testing system.

[0042] In this embodiment, the position coordinates in the position data are used as the target point, and the movement trajectory of the robot is obtained through a path planning algorithm. The movement trajectory can be a simple straight line from the starting point to the gripping point, or it can be a curve containing multiple critical path points. For example, the movement trajectory can be from the starting point to an approach point higher than the target workpiece and without collision risk; from the approach point, it moves vertically downward to the gripping point to avoid lateral scraping of the workpiece; after gripping, it is first vertically lifted to a safe height, then horizontally moved above the testing system, and finally descends in a straight line again to place the target workpiece onto the testing fixture. This ensures that the robot will not collide with the worktable, surrounding equipment, or the workpiece itself during the movement.

[0043] Optionally, based on the attitude data, inverse kinematics calculations are used to determine the angle that the robot's end effector, such as a suction cup or gripper, needs to be adjusted to ensure it can grip the target workpiece directly, guaranteeing full contact between the end effector and the workpiece surface. By determining the robot's gripping angle using attitude data, the workpiece can be placed in the bin at any angle. Furthermore, a correct gripping attitude provides a prerequisite for adjusting the final posture of the workpiece during subsequent placement.

[0044] The movement trajectory and gripping angle are converted into executable gripping motion commands. Gripping motion commands include, but are not limited to, motion commands for each joint motor; commands that trigger the end effector to move at specific points on the trajectory, such as gripping points, such as clamping commands; and corresponding speed and acceleration parameters.

[0045] When executing the gripping action command, the servo motors of each axis and the end effector are driven to complete the entire operation process as required by the command. The operation process includes, but is not limited to, moving above the workpiece, lowering, gripping, lifting, transferring, lowering to the test position, releasing the workpiece, and returning to the standby position.

[0046] The purpose of this is to transform the abstract pose information obtained from visual perception into precise, reliable, and safe mechanical movements by using a strategy of planning before execution and spatial path before end-effector posture, thus providing material preparation for subsequent functional testing.

[0047] Step S300: Based on the testing system, determine the test results of the target workpiece.

[0048] In this embodiment, after the target workpiece is placed in the test area of ​​the test system, the test system performs corresponding conformity tests according to the type of the target workpiece. For example, for electronic components, its resistance, capacitance, continuity and other electrical parameters are tested; for printed circuit boards (PCBs), in-circuit tester (ICT), flying probe test, or functional circuit test (FCT) is performed to verify whether its circuit connection and overall function are normal; for electronic devices, power-on self-test, performance calibration, communication test, etc. are performed.

[0049] After the test is completed, a clear test result is generated, such as pass / fail, pass / fail, or a detailed quality level classification.

[0050] In one feasible implementation, step S300 may include identifying the test pose of the target workpiece and determining whether the test pose is correct; if so, executing a test program to obtain the test result of the target workpiece, wherein the test result includes qualified, unqualified, or pending re-inspection.

[0051] In this embodiment, after the manipulator places the target workpiece on the test system, the vision system or the vision sensor in the test system is used again to take a snapshot and identify the test pose of the target workpiece. The test pose refers to the final position and orientation of the target workpiece on the test area of the test system. By comparing the test pose with a preset and correct reference pose, it is determined whether the deviation between the two is within the allowable tolerance range to determine whether the test pose is correct.

[0052] It should be noted that for some tests, such as the electrical performance test of a circuit board and the conduction test of a connector, it is required that the probe or interface be accurately aligned with the test point of the target workpiece. Therefore, before executing the test program, it is necessary to determine whether the test pose of the target workpiece is correct to avoid inaccurate testing, misjudgment, or even damage to the workpiece or test equipment caused by misalignment.

[0053] Optionally, after the test pose of the target workpiece is confirmed to be correct, the test program is executed to test the target workpiece. For example, for an electrical performance test, power is supplied to the target workpiece, a test signal is applied, and the output voltage, current, waveform, etc. are measured; for a function test, the functions of the workpiece are triggered, such as making the motor rotate, the screen display, the sensor sense, etc., and its response is detected whether it meets the expectations; for a safety test, an insulation withstand voltage test is carried out, etc.

[0054] Then, based on the obtained test data, it is compared with the preset qualified standard. If all parameters are within the specification range, it is determined to be qualified; if one or more parameters exceed the specification range, it is determined to be unqualified; if the data is in a critical state, or the test process is affected by instantaneous interference and cannot be clearly determined, it is determined to be pending re-inspection. The purpose of achieving objective and consistent automated testing and ensuring the unity of the product quality judgment standard is achieved.

[0055] Furthermore, if the test pose is incorrect, an exception handling is triggered, such as sending an alarm signal or a re-placement signal. Thus, self-check is realized to cope with complex working conditions, and when a deviation occurs, it can self-detect and trigger the processing flow instead of continuing to execute with errors.

[0056] In a feasible implementation manner, step S300 may further include steps S310 to S330: Step S310, execute the test program to perform a qualification test on the target workpiece, obtain test data and the test result, and the qualification test includes an electrical performance test and a functional detection; Step S320, generate a test record based on the test data; Step S330, update the test database based on the test record.

[0057] It should be noted that the purpose of electrical performance testing is to verify the intrinsic quality and parameter consistency of the target workpiece, ensuring that the workpiece meets design specifications and can operate stably under correct electrical conditions. The purpose of functional testing is to verify whether the external behavior and user interaction of the workpiece meet expectations, ensuring that the product not only "connects to electricity" but also "works." Through conformity testing, defective products can be intercepted, improving the overall reliability and safety of products leaving the factory.

[0058] In this embodiment, the test records include, but are not limited to, the identification of the target workpiece (such as a serial number), the test time, the specific values ​​of the pass / fail test, and the final judgment result. When an anomaly occurs in the target workpiece, the production testing process can be quickly traced back using the test records to determine whether it is a batch problem or an isolated phenomenon, and it can also be used for fault analysis.

[0059] Test records are compiled into a test database to form a continuously updated quality data pool. This database allows for real-time analysis of test data, enabling early warnings when test parameters begin to drift or show increased variability, preventing the generation of large batches of defective products. Furthermore, based on the test database, root cause analysis can be performed using historical test data to identify potential correlations between failures and production batches, process parameters, and other data, providing data-driven decision support for process improvement and design optimization.

[0060] Step S400: Based on the test results, control the robot arm to perform a sorting operation on the target workpiece.

[0061] In this embodiment, different classification instructions are generated based on the test results to control the robot arm to perform classification operations on the target workpiece. For example, if the test result is qualified, the robot arm is controlled to move the target workpiece to the "qualified" bin or conveyor belt; if the test result is unqualified, the robot arm is controlled to move the target workpiece to the "unqualified" bin. Furthermore, unqualified products can be classified into different areas according to different failure modes. By directly driving the robot arm's classification actions using the test results, a complete, self-determining feedback loop is formed between "testing" and "execution".

[0062] Specifically, step S400 includes steps S410 to S420: Step S410: Based on the test results, generate classification action instructions; Step S420: Execute the classification action instruction, grab the target workpiece, move and place the target workpiece to the target classification area.

[0063] In this embodiment, test results are correlated with the classification location of the target workpiece to ensure that workpieces of different quality states are separated. For example, qualified products are placed in the qualified area to proceed to the next process or be packaged and stored. Unqualified products are placed in the scrap area or the repair area to prevent them from being mixed with qualified products and to ensure the quality of the finished product. Products awaiting re-inspection are placed in the re-inspection area for further processing to avoid losses due to misjudgment. This not only ensures the consistency and reliability of the final product but also facilitates subsequent maintenance, scrapping, or quality analysis, achieving refined material tracking and management.

[0064] In the technical solution provided in this embodiment, the pose information of the target workpiece is obtained by recognizing and processing the workpiece image, and the robot arm is controlled to transfer the target workpiece to the testing system based on the pose information. The testing system then tests the target workpiece to determine its qualification, and then drives the robot arm to classify the target workpiece based on the test results. By embedding the testing link into the control logic of the robot arm through the coherent steps of perception, execution, decision, and feedback execution, a closed-loop control system is formed. The system can adjust the classification operation in real time according to the test results, thereby realizing intelligent decision-making and full-process automation.

[0065] Based on the first embodiment of this application, a second embodiment of the robotic arm test classification control method of this application is proposed. In this embodiment, content that is the same as or similar to that in the first embodiment described above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 After step S410, steps S411 to S412 are also included: Step S411: Determine the surplus or shortage status of the target classification region; Step S412: When the surplus / shortage state is a full state, stop executing the classification action instruction and output the full signal of the target classification area. When the surplus / shortage state is a vacant state, continue executing the classification action instruction.

[0066] In this embodiment, the robotic arm monitors the current capacity of the target sorting area before or simultaneously with performing the sorting action. The target sorting area is the bin, tray, or area where the target workpieces are placed. A full state means the target sorting area is full and no more workpieces can be added; an empty state means the target sorting area can continue to be added. This embodiment does not impose specific limitations on the method of determining the full state of the target sorting area. For example, a photoelectric sensor installed on the top of the bin can be used to detect whether the stack height has reached the trigger position. Alternatively, a camera in a vision system can be used to analyze the stacking of workpieces in the bin. Alternatively, a weight sensor can be used to determine whether the bin is full by weighing. Alternatively, a counter can be used to count the number of workpieces placed in the bin, and when the number reaches a preset upper limit, it is determined to be full.

[0067] Understandably, if a target workpiece is forcibly placed into an already full bin, it will collide and be crushed with the workpieces already piled up inside, resulting in scratches, crushing, or structural damage. Therefore, if the bin is full, the ongoing sorting operation is immediately stopped, and the robot arm is controlled to stop at a safe position, holding the workpiece and waiting. Simultaneously, a full signal is output, for example, by displaying a pop-up alarm on the screen and / or triggering an audible and visual alarm. The system then enters a waiting state until the bin returns to a empty state, at which point the stop is lifted, and the unfinished sorting operation resumes from the breakpoint.

[0068] In the technical solution provided in this embodiment, the overflow / shortage state of the target sorting area is determined. When the target sorting area is full, the robot's operation is stopped and an alarm is triggered to prevent workpiece damage. The robot's sorting operation resumes when the target sorting area is empty again. This complete unmanned closed loop of automatic operation, automatic detection, automatic alarm, and automatic recovery reduces the reliance on human labor in the testing and sorting process and ensures the continuous and stable operation of the production line. By introducing state judgment and decision-making logic, the long-term, stable, and safe operation of the system is guaranteed.

[0069] This application also provides a robotic arm testing and classification control system; please refer to... Figure 3 The robotic arm testing and classification control system includes: The visual recognition module 10 is used to perform recognition processing on the acquired workpiece image to obtain the pose information of the target workpiece. The robot control module 20 is used to control the robot to transfer the target workpiece to the testing system according to the pose information; The test control module 30 is used to determine the test result of the target workpiece based on the test system. The classification decision module 40 is used to control the robot to perform a classification operation on the target workpiece based on the test results.

[0070] Optionally, the vision recognition module 10 also includes an industrial camera for acquiring workpiece images and performing vision recognition; a light source module for providing stable illumination and improving image quality; and an image processing unit for recognizing the workpiece position and orientation.

[0071] The robot control module 20 also includes a six-axis robot for performing grasping, placing and sorting actions; and a robot end effector for clamping and releasing workpieces.

[0072] The test control module 30 also includes a test fixture for performing conformity tests after the workpiece is placed; and a test control unit for controlling the test process and collecting data.

[0073] The classification decision module 40 also includes a classification area for storing workpieces with different test results.

[0074] In addition, the robotic arm testing and classification control system may also include a main control computer and a display and operation interface. The main control computer is used to schedule each module and execute control logic; the display and operation interface is used to provide parameter configuration and status monitoring functions.

[0075] Specifically, an industrial camera is installed above the robot's working area, working in conjunction with a light source module to capture workpiece images; an image processing unit connects to the main control computer to process images and output coordinate information; a six-axis robot is mounted on the worktable, with a gripper connected to its end for grasping workpieces; a test rack is fixed in the robot's reachable area and has an electrical interface and positioning structure; a test control unit connects to the test rack to control the testing process and acquire test results; a classification area has multiple material frames to store workpieces with different test results; the main control computer connects to each module via a communication interface for unified scheduling; and a display interface is used by operators to configure parameters, monitor status, and view logs.

[0076] In this embodiment, after the target workpiece enters the visual recognition area, an industrial camera captures an image of the workpiece. Then, the image processing module identifies the position and orientation of the target workpiece and outputs coordinate information. Next, the main control computer schedules the robot control module 20 to control the robot's movement, completing the grasping of the target workpiece. After the robot places the target workpiece at the designated position on the test rack, the test control module 30 initiates the test process and feeds the test results back to the main control computer. The classification decision module 40 generates classification action instructions based on the test results; then, the robot places the target workpiece into the corresponding classification area according to the classification instructions, completing the classification operation. Furthermore, the main control computer records the test data and classification data, generates test records, and updates the test database to achieve anomaly handling and data traceability functions.

[0077] In the technical solution provided in this embodiment, the visual recognition module 10 and the robotic arm control module 20 achieve deep integration of visual recognition and robotic arm control, improving grasping accuracy. Combined with the test control module 30 and the classification decision module 40, test results drive classification actions, forming a closed-loop control. The highly integrated software architecture simplifies deployment and maintenance, supports the identification and classification of multiple workpiece types, and adapts to flexible production needs. Furthermore, by providing anomaly handling and data traceability functions, system reliability is improved.

[0078] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the robotic arm test classification control method of this application. Any simple modifications based on this technical concept are within the protection scope of this application.

[0079] The robotic arm test classification control system provided in this application adopts the robotic arm test classification control method in the above embodiments. Compared with the prior art, the beneficial effects of the robotic arm test classification control system provided in this application are the same as those of the robotic arm test classification control method provided in the above embodiments, and other technical features in the robotic arm test classification control system are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0080] This application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the robotic arm test classification control method in the above embodiments.

[0081] The following is for reference. Figure 4 The diagram illustrates a structural schematic of an electronic device suitable for implementing embodiments of this application. The electronic devices in these embodiments may include, but are not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0082] like Figure 4As shown, the electronic device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the electronic device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. While electronic devices with various systems are shown in the figures, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0083] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0084] The electronic device provided in this application adopts the robotic arm test classification control method in the above embodiments. Compared with the prior art, the beneficial effects of the electronic device provided in this application are the same as those of the robotic arm test classification control method provided in the above embodiments. Furthermore, the other technical features of the electronic device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0085] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0086] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0087] This application provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, which are used to execute the robotic arm test classification control method in the above embodiments.

[0088] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having 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 fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0089] The aforementioned computer-readable storage medium may be included in an electronic device or may exist independently without being assembled into an electronic device.

[0090] The aforementioned computer-readable storage medium carries one or more programs, which, when executed by an electronic device, cause the electronic device to perform the functions defined in the methods of the embodiments disclosed in this application.

[0091] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a Local Area Network (LAN) or a Wide Area Network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0092] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0093] The modules described in the embodiments of this application can be implemented in software or hardware. The names of the modules do not necessarily limit the functionality of the unit itself.

[0094] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-described robotic arm test classification control method. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the robotic arm test classification control method provided in the above embodiments, and will not be repeated here.

[0095] The above description is only a part of the embodiments of this application and does not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the contents of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included in the patent protection scope of this application.

Claims

1. A robotic arm testing and classification control method, characterized in that, The robotic arm test classification control method includes: The acquired workpiece image is processed to obtain the pose information of the target workpiece; Based on the pose information, the robot arm is controlled to transfer the target workpiece to the testing system; Based on the testing system, the test results of the target workpiece are determined; Based on the test results, the robot arm is controlled to perform a sorting operation on the target workpiece.

2. The robotic arm testing and classification control method as described in claim 1, characterized in that, The step of performing recognition processing on the acquired workpiece image to obtain the pose information of the target workpiece includes: Based on edge detection algorithms, fuzzy matching algorithms, and deep learning recognition algorithms, the workpiece image is processed to obtain the pose data and position data of the target workpiece.

3. The robotic arm testing and classification control method as described in claim 1, characterized in that, The step of controlling the robot to transfer the target workpiece to the testing system based on the pose information includes: Based on the position data of the pose information, the movement trajectory of the robotic arm is determined; and, Based on the posture data of the pose information, the grasping angle of the robotic arm is determined; Based on the movement trajectory and the grasping angle, a grasping action command is generated; The gripping action command is executed to control the robotic arm to grip the target workpiece, move and place the target workpiece into the testing system.

4. The robotic arm testing and classification control method as described in claim 1, characterized in that, The step of determining the test result of the target workpiece based on the test system includes: Identify the test pose of the target workpiece and determine whether the test pose is correct; If so, execute the test program to obtain the test results of the target workpiece, the test results including qualified, unqualified, and pending re-inspection.

5. The robotic arm testing and classification control method as described in claim 1, characterized in that, The step of controlling the robotic arm to perform a sorting operation on the target workpiece based on the test results includes: Based on the test results, generate classification action instructions; Execute the classification action instruction, grab the target workpiece, move and place the target workpiece to the target classification area.

6. The robotic arm testing and classification control method as described in claim 5, characterized in that, After the step of generating categorized action instructions based on the test results, the method further includes: Determine the surplus or shortage status of the target classification region; When the surplus / shortage state is full, the execution of the classification action instruction is stopped, and the full signal of the target classification area is output. When the surplus / shortage state is empty, the execution of the classification action instruction continues.

7. The robotic arm test classification control method as described in claim 1, characterized in that, The step of determining the test result of the target workpiece based on the test system includes: The test procedure is executed to perform a conformity test on the target workpiece, and test data and test results are obtained. The conformity test includes electrical performance testing and functional testing. Based on the test data, generate test records; Update the test database based on the test records.

8. A robotic arm testing and classification control system, characterized in that, The robotic arm test classification control system includes: The visual recognition module is used to recognize and process the acquired workpiece images to obtain the pose information of the target workpiece. The robot control module is used to control the robot to transfer the target workpiece to the testing system based on the pose information. A test control module is used to determine the test results of the target workpiece based on the test system. The classification decision module is used to control the robot to perform a classification operation on the target workpiece based on the test results.

9. An electronic device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the robotic arm test classification control method as described in any one of claims 1 to 7.

10. A readable storage medium, characterized in that, The readable storage medium is a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the steps of the robotic arm test classification control method as described in any one of claims 1 to 7.

Images