Workpiece processing control method, apparatus, workpiece processing system, and storage medium

Abstract

The workpiece processing control method, device, workpiece processing system and storage medium provided by the application relate to the field of intelligent manufacturing and industrial automation, and aim to solve the problems of insufficient cooperation and poor automation continuity in the processes of workpiece feeding, discharging, stacking and material frame turnover. The method sets two stacking positions as feeding stacking positions and discharging stacking positions, controls the robot to complete the transfer of the workpieces to be processed in the feeding stacking positions to the empty pallets of the conveying line and the recovery of the processed workpieces to the empty positions of the material frames in the discharging stacking positions based on the three-dimensional visual recognition results of the upper material frames in the feeding stacking positions and the ring-shaped conveying line in the working process, and further controls the robot to complete the turnover of the empty material frames by means of the material frame turnover device when it is detected that the upper material frames on the feeding side are empty and the upper material frames on the discharging side are full. Thus, the automation and continuity control of feeding, discharging, finished product recovery and empty material frame turnover are realized, the accuracy of workpiece circulation, the stability of processing rhythm and the continuity of process under complex working conditions are improved, and manual intervention is reduced.

Description

Technical Field

[0001] This application relates to the field of intelligent manufacturing technology, and in particular to a workpiece processing control method, equipment, workpiece processing system and storage medium. Background Technology

[0002] In the fields of intelligent manufacturing and industrial automation, the loading and unloading process of precision parts such as gears and stamped parts is a critical link in machine tool processing units, directly affecting processing efficiency, processing accuracy, and production line continuity. Traditional loading and unloading operations rely heavily on manual operation, resulting in low efficiency, high labor intensity, and unstable processing quality due to human error, failing to meet the high-speed and high-precision requirements of modern production lines. With the popularization of Industry 4.0 and flexible manufacturing technologies, robots replacing manual labor in loading and unloading tasks is becoming a trend.

[0003] Taking gears, a precision component, as an example, their processing involves multiple consecutive steps, including loading, drilling, flipping, positioning, unloading, and stacking, requiring high continuity and precision. Existing robot-based automated processing largely relies on precise structural alignment, with the robot operating along a preset trajectory. However, this approach is insufficiently adaptable to material stacking deviations and workpiece posture changes. Positioning errors can easily lead to gripping failures, affecting the stability of the processing cycle. Furthermore, material turnover often depends on manual labor or external equipment, resulting in complex system coordination and making it difficult to maintain continuous operation of the loading and unloading process.

[0004] Therefore, how to improve the reliability of workpiece loading and unloading positioning and gripping under complex working conditions, while taking into account the continuity of material frame turnover, has become an urgent technical problem to be solved. Summary of the Invention

[0005] The workpiece processing control method, equipment, workpiece processing system, and storage medium provided in this application aim to solve the above-mentioned problems. By utilizing three-dimensional vision recognition technology, an integrated control mechanism for stacking, conveyor lines, and material frame circulation is constructed, enabling workpiece transfer and material frame turnover to be carried out continuously in the same work process, thereby improving the stability of workpiece processing loading and unloading and the continuity of the overall production line operation under complex working conditions.

[0006] In a first aspect, embodiments of this application provide a workpiece processing control method, comprising: after configuring a first stacking position as a loading stacking position and a second stacking position as a unloading stacking position, controlling a robot to perform a loading operation based on the three-dimensional visual recognition results of the collected images of the upper material frame of the first stacking position, so as to transfer the workpiece to be processed stored in the upper material frame of the first stacking position to an empty pallet of the circular conveyor line; controlling a robot to perform an unloading operation based on the three-dimensional visual recognition results of the collected images of the circular conveyor line, so as to transfer the processed workpiece stored in the pallet of the circular conveyor line to an empty space in the upper material frame of the second stacking position; when the upper material frame of the first stacking position is empty and the upper material frame of the second stacking position is full, controlling a robot to grab a material frame turnover device and perform a material frame turnover operation, so as to transfer the upper material frame of the first stacking position to the upper layer of the second stacking position through the material frame turnover device, as a new upper material frame of the second stacking position.

[0007] In some embodiments, after the control robot transfers the workpieces to be processed stored in the upper frame of the first stack to an empty pallet on the circular conveyor line, the method further includes: controlling the image acquisition device mounted on the robot to acquire images of adjacent pallets on the overhead pallet of the circular conveyor line. Correspondingly, based on the three-dimensional visual recognition results of the acquired images of the circular conveyor line, controlling the robot to transfer the processed workpieces stored in the upper frame of the circular conveyor line to an empty space in the upper frame of the second stack includes: based on the three-dimensional visual recognition results of the acquired images of adjacent pallets, controlling the robot to transfer the processed workpieces stored in the adjacent pallets to an empty space in the upper frame of the second stack.

[0008] In some embodiments, when the upper material frame of the first stack is empty and the upper material frame of the second stack is full, the robot is controlled to grab the material frame turnover device and perform the material frame turnover operation, including: after performing one material frame turnover operation, when the number of unloading operations performed by the robot reaches a preset number, the upper material frame of the first stack is empty and the upper material frame of the second stack is full, the robot is controlled to grab the material frame turnover device and perform the material frame turnover operation.

[0009] In some embodiments, the method further includes: when the loading operation performed by the robot after performing one material frame turnover operation reaches a preset number, the upper material frame of the first stack is an empty material frame, and the image acquisition device mounted on the robot is controlled to acquire an image of the circular conveyor line.

[0010] In some embodiments, when the upper material frame of the first stack is empty and the upper material frame of the second stack is full, controlling the robot to grab the material frame turnover device and perform the material frame turnover operation includes: when the number of times the robot performs the unloading operation reaches a preset number based on the three-dimensional visual recognition result of the collected image of the circular conveyor line, the upper material frame of the second stack is full, and the robot is controlled to grab the material frame turnover device and perform the material frame turnover operation.

[0011] In some embodiments, the loading operation includes a first gripping operation and a first transfer operation, and the unloading operation includes a second gripping operation and a second transfer operation. The method further includes: after the robot performs the first gripping operation or the second gripping operation, controlling the image acquisition device to acquire an image of the upper material frame of the first stack or the second stack; and determining whether the upper material frame is empty or full based on the acquired image of the upper material frame.

[0012] In some embodiments, the robot includes a robotic arm and a gripper disposed at the end of the robotic arm; the gripper is used to perform a first gripping operation, a second gripping operation, and to grip a material frame turnover device.

[0013] In some embodiments, the method further includes: when the number of material frames in the first stack position is 0, switching the first stack position to a unloading stack position, and switching the second stack position to a loading stack position.

[0014] In some embodiments, the circular conveyor line is equipped with a processing table, which is equipped with a flipping mechanism. The flipping mechanism is used to flip the workpieces conveyed to the flipping station to achieve double-sided processing of the workpieces. Based on the recognition results of the collected images of the circular conveyor line, the robot is controlled to perform a unloading operation to transfer the processed workpieces stored in the tray of the circular conveyor line to the empty space of the upper material frame of the second stack. This includes: based on the recognition results of the collected images of the circular conveyor line, identifying whether the corresponding workpiece has been flipped and whether the current side of the corresponding workpiece has been processed; if both are true, then the corresponding workpiece is considered a processed workpiece, and the robot is controlled to perform a unloading operation to transfer the processed workpieces stored in the tray of the circular conveyor line to the empty space of the upper material frame of the second stack.

[0015] In some embodiments, the material frame turnover device includes a support structure, a gripper component, and hook-type grippers located on both sides of the support structure. Controlling a robot to grip the material frame turnover device and perform a material frame turnover operation to transfer the upper layer of the first stack to the upper layer of the second stack as a new upper layer material frame for the second stack includes: controlling the robot to grip the gripper component of the material frame turnover device, thereby moving the material frame turnover device to the corresponding position of the upper layer material frame in the first stack; controlling the robot to move along a preset direction to insert the hook-type grippers of the material frame turnover device into the attachment position of the upper layer material frame in the first stack; controlling the robot to move upwards, thereby moving the material frame turnover device and the upper layer material frame in the first stack to the upper layer of the second stack; controlling the robot to move in the opposite direction along the preset direction to disengage the hook-type grippers from the attachment position of the attached material frame; and controlling the robot to return the material frame turnover device to its original position.

[0016] Secondly, embodiments of this application provide a control device, including: a memory and a processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, causing the processor to perform the method provided above.

[0017] Thirdly, embodiments of this application provide a workpiece processing system, including: a robot, an image acquisition device, a material frame turnover device, a first stacking position, a second stacking position, and a circular conveyor line; the image acquisition device is used to acquire images; the robot is used to perform the following steps based on the images acquired by the image acquisition device: after configuring the first stacking position as a loading stacking position and the second stacking position as a unloading stacking position, based on the three-dimensional visual recognition result of the acquired image of the upper material frame of the first stacking position, the robot is controlled to perform a loading operation to load the workpiece stored in the upper material frame of the first stacking position. The workpieces to be processed are transferred to empty pallets on the circular conveyor line. Based on the 3D visual recognition results of the collected images of the circular conveyor line, the robot is controlled to perform a material unloading operation to transfer the processed workpieces stored in the pallets on the circular conveyor line to empty spaces in the upper material frames of the second stack. When the upper material frames of the first stack are empty and the upper material frames of the second stack are full, the robot is controlled to grab the material frame turnover device and perform a material frame turnover operation to transfer the upper material frames of the first stack to the upper layer of the second stack, which then becomes the new upper material frames for the second stack.

[0018] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided above.

[0019] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described above.

[0020] The workpiece processing control method, equipment, system, and storage medium provided in this application configure the first stack as a loading stack and the second stack as a unloading stack. Based on the three-dimensional visual recognition results of the upper material frame of the first stack, the robot is controlled to perform loading operations. Based on the three-dimensional visual recognition results of the circular conveyor line, the robot is controlled to perform unloading operations. When the upper material frame of the first stack is empty and the upper material frame of the second stack is full, the robot is controlled to grasp the material frame turnover device to perform the material frame turnover operation. During loading, unloading, and material frame turnover, three-dimensional vision technology is used to achieve pose alignment, improve the adaptability to material frame stacking deviations and workpiece posture changes, and enhance the reliability of workpiece loading, unloading, positioning, and grasping. This enables continuous and coordinated operation of the loading, unloading, and material frame turnover process, ensures the stability of the processing cycle, and reduces reliance on manual labor or external turnover equipment. Attached Figure Description

[0021] 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.

[0022] Figure 1a This is a three-dimensional structural diagram of a workpiece processing system provided in an embodiment of this application;

[0023] Figure 1b for Figure 1a A top view of the workpiece machining system shown.

[0024] Figure 2 A schematic flowchart illustrating the workpiece machining control method provided in an embodiment of this application;

[0025] Figure 3 A schematic diagram of the layout of the first and second stack positions provided for embodiments of this application;

[0026] Figure 4 A schematic diagram of the structure of a robot provided in an embodiment of this application;

[0027] Figure 5 This application provides a schematic diagram of the structure of a ring conveyor line;

[0028] Figure 6a This is a schematic diagram of the structure of a material frame turnover device provided in this application;

[0029] Figure 6b For robot to grasp Figure 6a Schematic diagram of the combined state of the material frame turnover device;

[0030] Figure 6c For the robot to pass Figure 6a A schematic diagram of the combined state of the material frame turnover device when transferring the material frame.

[0031] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0032] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0033] In view of the above problems, there is an urgent need for a processing control method that can uniformly control the entire process of workpiece loading and unloading, unloading and stacking, and material frame turnover, so as to improve the level of automation and process continuity under complex working conditions. Based on the shortcomings of existing technologies, the inventors of this application have developed a processing approach that uses 3D visual recognition results to drive robot actions, focusing on the collaborative relationship between the first stacking position, the second stacking position, and the circular conveyor line. After the first stacking position is configured as a loading stacking position and the second stacking position as a unloading stacking position, the robot is controlled to perform a loading operation based on the 3D visual recognition results of the upper material frame image of the first stacking position, transferring the workpiece to be processed to an empty pallet on the circular conveyor line. Then, based on the 3D visual recognition results of the circular conveyor line image, the robot is controlled to perform an unloading operation, transferring the processed workpiece to an empty space in the upper material frame of the second stacking position. When the upper material frame of the first stacking position is empty and the upper material frame of the second stacking position is full, the robot is then controlled to grab the material frame turnover device and perform a material frame turnover operation, transferring the upper material frame of the first stacking position to the upper layer of the second stacking position as a new upper material frame for the second stacking position.

[0034] Through this control logic, the system can form a continuous connection between loading and unloading, finished product recycling, and turnover of empty and full material boxes, reducing human intervention and reliance on external logistics equipment. This enables the robot to autonomously complete operation switching based on on-site recognition results, thereby improving the accuracy of workpiece flow, the stability of processing rhythm, and the continuity of the entire processing flow.

[0035] Figure 1a This is a three-dimensional structural diagram of a workpiece processing system provided in an embodiment of this application. Figure 1b for Figure 1a The diagram shows a top view of the workpiece machining system. Figure 1a and Figure 1b As shown, the workpiece processing system includes a first stacking station, a second stacking station, a robot, an image acquisition device, a material frame turnover device, a circular conveyor line, and a processing table.

[0036] The first and second stacks are areas for storing workpiece frames on-site. Each workpiece frame includes multiple storage locations to store multiple workpieces, such as workpieces to be processed or workpieces already processed. Of the two stacks, one is used to store workpieces to be processed, and the other is used to store workpieces already processed.

[0037] The robot is responsible for loading and unloading, including transferring the workpieces to be processed from the upper material frame of the first stack to the circular conveyor line, processing the workpieces at the processing table at the circular conveyor line, and transferring the machined workpieces to the robot via the conveyor line after processing. The robot then transfers the processed workpieces to another stack, such as the upper material frame of the second stack.

[0038] When the upper material frame of the first stack is empty and the upper material frame of the second stack is full, the robot will use the material frame turnover device to transfer the empty material frame to the upper layer of another stack as the new upper material frame of that stack.

[0039] Figure 2 This is a flowchart illustrating the workpiece machining control method provided in an embodiment of this application. The method can be executed by a robot in the system shown in Figure 1, or by the robot's control device, such as... Figure 2 As shown, the workpiece machining control method includes:

[0040] S201: After configuring the first stack position as the loading stack position and the second stack position as the unloading stack position, based on the three-dimensional visual recognition results of the image of the upper material frame of the first stack position, control the robot to perform the loading operation to transfer the workpiece to be processed stored in the upper material frame of the first stack position to the empty pallet of the circular conveyor line.

[0041] The first and second stack positions form a stack position pair, in which one stack position is the loading stack position and the other stack position is the unloading stack position. The workpiece processing system can include multiple stack position pairs. One robot can correspond to one or more stack position pairs and is responsible for performing the loading and unloading operations of the corresponding one or more stack position pairs.

[0042] A stacking station can be understood as a workstation area on-site used for stacking material crates. The loading stacking station is used to store workpieces awaiting processing, while the unloading stacking station is used to receive processed workpieces. The loading and unloading stacking stations are the roles of the stacking station, and these roles can be interchanged.

[0043] The upper layer of the stack (first stack or second stack) refers to the material frame that is currently located at the top of the stack and can be directly approached by the robot to perform grasping or placement operations, that is, the material frame that is not blocked by other material frames in the stack.

[0044] The 3D visual recognition result of an image refers to the set of spatial information obtained by an image acquisition device with depth perception acquiring images of a target area within its field of view, followed by point cloud reconstruction, contour segmentation, pose estimation, and state determination. Alternatively, it can be the 3D visual recognition result obtained from a 2D RGB camera processed by a 3D spatial reconstruction algorithm. The target area can be the area corresponding to the upper material frame of the first stack, the area corresponding to the upper material frame of the second stack, or the area corresponding to the subsequent circular conveyor line, etc. For the 3D visual recognition result of the image of the upper material frame of the first stack, the spatial information includes at least the pose information of the workpieces to be processed stored in the upper material frame, such as 3D position coordinates and pose angles. It can also include the boundary of the upper material frame and the occupancy status of the storage space within the frame to determine whether the upper material frame is empty after grabbing a workpiece to be processed. A workpiece to be processed refers to a workpiece that has not yet completed the predetermined processing steps, while a processed workpiece is a workpiece that has completed the predetermined processing steps.

[0045] A circular conveyor line is a closed-loop conveying mechanism that circulates pallets and workpieces between loading and processing stations. An empty pallet is a pallet unit that has not yet loaded any workpieces and is ready for loading. The loading station is the station on the circular conveyor line where robots load workpieces, and the processing station is the station on the conveyor line where workpieces are processed, such as a processing table.

[0046] In practice, the control system, equipment, modules, units, or controllers first initialize and configure the on-site resources, establishing coordinate mapping relationships between the first stacking position, the second stacking position, the circular conveyor line, and the robot's workspace. This configuration process can be completed by reading pre-calibrated workstation parameter tables or by maintenance personnel inputting data through a teaching method. The relationship between the robot's base coordinate system, vision coordinate system, and reference coordinate systems of each workstation is calibrated after equipment installation and stored in the controller or host computer to ensure that subsequent visual recognition results can be directly converted into robot-executable grasping pose data. After configuration is completed, the automatic loading and unloading process is started. First, the upper material frame of the first stacking position is image-captured using an image acquisition device.

[0047] For example, the image acquisition device can be fixed to the end of the robot arm. After the robot arm is in position, that is, after it moves above the first stack, the image acquisition device acquires an image to obtain an image of the upper layer of the material frame of the first stack.

[0048] For example, the image acquisition device can also be fixed on an independent bracket to continuously acquire images of the upper layer of the first stack of material boxes in a top-down or oblique-view manner.

[0049] For example, the image acquisition device can be a structured light camera, a binocular depth camera, or a laser point cloud sensor, which can output depth information and image information reflecting the spatial distribution of workpieces, material frames, conveyor lines, etc.

[0050] After image acquisition, 3D reconstruction and recognition processing are performed on the acquired image data. Specifically, the original depth map and color image can be preprocessed first, such as through noise reduction, filtering, and background removal. Then, the upper frame region is segmented based on the frame contour model, and workpiece target detection and attitude estimation are performed within this upper frame region. For detected workpieces, the matching results between extracted workpiece features and the features of the workpiece to be processed can be used to determine whether the workpiece is the workpiece to be processed. Taking gear-type workpieces as an example, the current state of the workpiece can be comprehensively identified through features such as the edge features of the ring, the missing features of the central hole, the features of the hole on the back side, and the surface texture features, and based on this, it can be determined whether it is the workpiece to be processed.

[0051] If multiple workpieces to be processed are identified in the image of the upper frame of the loading stack, they can be picked up sequentially according to a preset picking order. The preset picking order can be a default order, with the workpieces arranged in a matrix within the frame. This preset picking order can be from left to right, from front to back, or a serpentine order. When there are multiple workpieces to be processed within the upper frame, a picking queue can be generated according to picking priority. This picking priority can be determined based on one or more of the following: workpiece position, orientation, distance from neighboring workpieces, picking accessibility, and assessment results of collision risk.

[0052] After identifying the workpiece to be processed, the robot can be directly controlled to perform the gripping operation and grab the workpiece. Alternatively, the current pallet status of the circular conveyor line can be queried to confirm that at least one empty pallet exists. The empty pallet status of the circular conveyor line can be obtained by identifying images of the conveyor line after being captured by an image acquisition device deployed at the circular conveyor line, or by feedback from position sensors, pallet encoders, or controller status registers deployed on the circular conveyor line.

[0053] Based on the three-dimensional coordinates and posture parameters of the workpiece to be processed obtained from visual recognition, and combined with the robot's gripper structure such as the gripper, a gripping pose and motion path can be generated, thereby controlling the robot to complete the gripping of the workpiece according to the motion path and gripping pose.

[0054] For example, the gripper at the end of the robotic arm can be an external three-finger gripper, which completes the grasping operation through continuous actions such as opening, closing, and lifting.

[0055] In some embodiments, the fixture structure may also employ a two-finger gripper, a vacuum suction fixture, or a special fixture that conforms to the shape of the workpiece.

[0056] To achieve stable transfer, the controller can set approach points, gripping points, lifting points, transition points, and placement points during path planning to avoid interference between the end effector (i.e., the clamping structure) and the side wall of the material frame, adjacent workpieces, and conveyor guardrails.

[0057] After the workpiece is grasped, the robot moves along the planned path, moving the grasped workpiece to an empty pallet on the circular conveyor line, such as above a target empty pallet. Based on the identified pallet positioning reference, the robot places the grasped workpiece in a designated area on the empty pallet. Placement can be combined with force control feedback, position closed-loop, and secondary vision correction to improve the placement accuracy between the workpiece and the empty pallet.

[0058] After releasing the workpiece to be processed, the controller updates the occupancy status of the upper layer of the first stack (indicating the occupancy of each storage location within the upper layer of the stack, i.e., whether a workpiece to be processed is placed there) and the load status of the pallets on the circular conveyor line (indicating the occupancy of each pallet, i.e., whether it is an empty pallet). It then triggers the next round of loading recognition, i.e., re-acquiring the image of the upper layer of the first stack and performing 3D visual recognition. Based on the 3D visual recognition results, the controller controls the robot to perform the next loading operation, or triggers unloading recognition, i.e., step S202. The occupancy status of the upper layer of the first stack can also be updated after grabbing the workpiece to be processed, i.e., updating the occupancy status of the storage location where the grabbed workpiece was originally located to unoccupied, indicating that the storage location is free or empty.

[0059] Based on the above analysis, it can be seen that this step, by performing three-dimensional visual recognition on the upper layer of the first stack and driving the robot to perform loading based on the recognition results, can adapt to the random placement of workpieces in the stack, posture deflection, and stacking position deviation of the stack, thereby reducing the requirements for material consistency and overcoming the defect of poor adaptability of fixed teaching points.

[0060] S202: Based on the three-dimensional visual recognition results of the collected images of the circular conveyor line, control the robot to perform the unloading operation to transfer the processed workpieces stored in the pallet of the circular conveyor line to the empty space of the upper material frame of the second stack position.

[0061] The processed workpiece in this step refers to a workpiece that has completed at least one predetermined processing step, specifically a workpiece that has completed processing steps such as flipping, drilling, milling, and inspection.

[0062] The empty space in the upper frame of the second stack refers to the storage area of ​​the frame that has not yet been occupied by workpieces. This empty space can be a regularly arranged grid or a placeable area dynamically calculated based on the outline of the frame and the position of the already placed workpieces.

[0063] Figure 3A schematic diagram of the layout of the first and second stack positions provided for embodiments of this application, as shown below. Figure 3 As shown, the first and second stacking positions are parallel material frame carrying stations. Each stacking position (including the first and second stacking positions) is equipped with a material frame positioning frame to guide and limit the stacking of multiple material frames, reducing stacking deviation and providing a stable reference for the robot's visual recognition and grasping operations. In this embodiment, the first stacking position is a loading stacking position used to hold material frames containing workpieces to be processed; the second stacking position is a unloading stacking position used to hold material frames containing processed workpieces. When the material frames in the first stacking position are empty, the first stacking position can be switched to an unloading stacking position, and the second stacking position to a loading stacking position, to proceed to the next process. Multiple storage spaces are formed within the material frames, arranged in rows and columns. Each storage space is used to hold a single workpiece, either a workpiece to be processed or a processed workpiece.

[0064] Figure 3 Taking a gear as an example, the storage position of the material frame consists of a central positioning post and an outer peripheral limiting structure. The central positioning post can be inserted into the central hole of the gear to achieve radial limiting; the outer peripheral limiting structure provides auxiliary constraint from the outer edge of the gear, thereby fixing the workpiece in the storage position. This positioning structure not only ensures the consistency of the workpiece's placement posture, but also facilitates the robot fixture to grasp the workpiece from the outside, while reducing the risk of collision with the lower workpiece when the material frames are stacked.

[0065] After the robot places the workpiece to be processed onto an empty pallet on the circular conveyor line, it acquires images of the circular conveyor line and performs 3D visual recognition, or it controls the image acquisition device at the circular conveyor line to acquire images of the circular conveyor line and perform 3D visual recognition, thus obtaining the 3D visual recognition result.

[0066] The three-dimensional visual recognition result of the image of the circular conveyor line refers to the recognition result formed by the image acquisition device after acquiring images of the current pallet and its carried workpiece on the circular conveyor line and performing three-dimensional visual recognition. The recognition result includes at least the position of the pallet within the field of view, as well as the position, posture, and processing status characteristics of the workpiece within the pallet. Unless otherwise specified, the position mentioned in this application refers to the three-dimensional position.

[0067] In practice, after the circular conveyor line transports the pallet carrying the workpiece to the processing station, it triggers the acquisition of images and 3D visual recognition of the circular conveyor line. The image acquisition device takes pictures of the pallet within its field of view and determines whether there is a processed workpiece in the pallet within its field of view through pallet boundary recognition, workpiece contour extraction, point cloud matching, and state analysis.

[0068] For gear-type workpieces, the completion of the corresponding process can be determined by identifying information such as back hole positions, post-processed edge chamfers, surface texture changes, and orientation characteristics after flipping. In some embodiments, a comprehensive determination can also be made by combining temperature characteristics, color differences, laser ranging characteristics, or process completion identification codes collected by auxiliary sensors. After determining that the workpiece has been processed, the gripping posture and safe gripping area of ​​the workpiece are calculated to ensure that the robot can complete the pick-up without colliding with the edge of the pallet. After successful gripping, the status of the corresponding pallet is updated to unoccupied, i.e., an empty pallet.

[0069] After the robot grasps the processed workpiece and moves it to the corresponding position in the second stack, the empty space in the upper layer of the material frame in the second stack is identified or determined. This can be done by using an image acquisition device fixedly installed near the second stack to acquire images of the upper layer of the material frame, or by using an image acquisition device carried by the robot. Based on the acquired images, an empty space in the upper layer of the material frame is determined. In some embodiments, an empty space can be determined based on pre-stored occupancy information of each storage location in the upper layer of the second stack, and the grasped workpiece to be processed can then be placed in that empty space.

[0070] If there are multiple empty spaces in the upper frame of the second stack, the controller can select one empty space as the target empty space according to the stacking order. The stacking order can be set to fill the space from left to right or from front to back, or it can be dynamically selected according to the principle of center of gravity balance, the convenience of subsequent material retrieval, or the local load distribution of the frame.

[0071] At the execution level, the robot first grasps and transfers the processed workpiece, and then performs the placement operation. Specifically, based on the identification result of the processed workpiece, the robot moves to the top of the corresponding pallet on the conveyor line, and the end effector aligns with the identified processed workpiece and completes the grasp. The grasping process can include five sub-processes: approach, posture adjustment, gripping confirmation, lifting, and pallet release. Gripping confirmation can be completed through gripper stroke sensors, negative pressure sensors, torque feedback, and visual secondary confirmation to identify whether the processed workpiece has been successfully grasped. If gripping fails, a retry process can be triggered to replan the approach direction or switch the gripping point. After successful grasping, the robot moves along the planned obstacle avoidance path to the top of the second pallet, and then performs the placement operation according to the center coordinates and orientation of the determined target empty space, thereby placing the grasped processed workpiece in the target empty space.

[0072] For workpieces with directional requirements, the orientation of the gripped, processed workpiece can be rotated and corrected before placement to ensure it is positioned in an orientation consistent with the material frame's structure. After the processed workpiece is placed in the target empty space, the placement result is confirmed. This can be achieved through visual re-photographing, judging changes in gripper load, or updating the material frame's occupancy status. Once confirmed, the occupancy status of the target empty space in the upper layer of the second stack is updated to occupied, thus providing a basis for subsequent cyclical scheduling.

[0073] Based on the above analysis, this step uses 3D vision recognition to simultaneously determine the processing completion status of the workpieces in the conveyor tray and the empty space status of the upper material frame in the second stack. This eliminates the reliance on fixed cycle times and manual judgment for the unloading action, allowing for dynamic decision-making based on the actual scene conditions. This effectively prevents unfinished workpieces from being mistakenly placed into the material frame and avoids collisions, misalignment, or workpiece damage caused by inaccurate judgment of empty space in the material frame. Once vision recognition and robot path control form a closed loop, it exhibits greater adaptability to conveyor line position deviations, workpiece posture changes, and material frame stacking progress, thereby improving unloading accuracy and the continuous operation capability of the entire line.

[0074] S203: When the upper material frame of the first stack is empty and the upper material frame of the second stack is full, control the robot to grab the material frame turnover device and perform the material frame turnover operation so as to transfer the upper material frame of the first stack to the upper layer of the second stack as a new upper material frame of the second stack.

[0075] In this step, an empty material frame means that there are no more workpieces to be processed in the topmost material frame of a stack, and a full load means that the topmost material frame of the second stack no longer has space to receive new workpieces, for example, the grid is already filled with processed workpieces.

[0076] A material frame turnover device is a special device used by robots to grasp and reliably connect with the material frame to realize the material frame transportation. It can be a hook-type gripper, a snap-on gripper, a telescopic hanger, or a turnover mechanism with adaptive clamping capability.

[0077] After an empty material frame is placed on top of the second stack, it becomes the new upper material frame for the second stack. Specifically, this means transferring the empty material frame originally located on top of the first stack and stacking it on top of the existing material frame stack in the second stack, making it a new material frame for receiving the unloading of processed workpieces.

[0078] In practice, the control system continuously maintains the status tables of the material frames at the first and second stacks. These tables can be generated from the occupancy updates after each loading and unloading operation, or periodically corrected using visual verification. A turnover task is generated when all cells in the upper stack of the first stack are empty of workpieces and all target cells in the upper stack of the second stack are filled with processed workpieces. This detection can be performed using a dual-condition interlocking method, meaning that the turnover process is only allowed when both the empty and full conditions are met simultaneously. This prevents the upper stack from covering the material frame before it is fully loaded, resulting in low space utilization, and also prevents the material frame from being moved to the unloading stack while still containing workpieces, causing missed processing steps.

[0079] The status of the material frame can be determined through visual recognition, or by fusing historical grabbing records with visual recognition results to improve robustness. The number of storage locations within different material frames is fixed and identical. After completing a corresponding number of loading and unloading operations, two stacks in a set of stacks simultaneously satisfy the following conditions: the upper material frame of the loading stack is empty, and the upper material frame of the unloading stack is full. At this point, a turnover task can be generated to control the robot to perform the material frame turnover operation. To improve the accuracy of material frame status determination, an image of the upper material frame can be captured after each workpiece grabbing and placement. Based on this image, the status of the upper material frame can be identified to determine whether it is empty or full.

[0080] After generating the turnover task, you can first confirm that the material frame turnover device is in a grabbable position or in place, and that there are no personnel or obstacles intruding on the transfer path between the first stack and the second stack. Then, control the robot to execute the turnover task, that is, grab the material frame turnover device and perform the material frame turnover operation.

[0081] When performing a turnover task, the robot moves to the storage position of the material frame turnover device and uses a gripper to grasp the workpiece or switches to a gripper specifically for the material frame turnover device to grasp the material frame turnover device. In the hook-type implementation, the material frame turnover device includes a hook structure that can extend into the material frame hooking position and a gripper component for the robot to grasp. After the robot grasps the gripper component, it moves to the hooking position of the upper layer of the first stack and aligns itself according to the coordinates of the material frame edge, hole position, or hooking point obtained by 3D vision recognition. After alignment, the hook is inserted into the preset connection part of the material frame, and the robot performs a slight lifting action to confirm whether the hooking is secure. The confirmation method can be torque feedback, displacement feedback, or visual confirmation. After successful hooking, the robot lifts the empty material frame of the upper layer of the first stack off the stack surface along a preset lifting path, and then moves along the turnover path to the top of the second stack. After reaching the second stack, the system calculates the placement posture of the new material frame according to the spatial position and posture of the current top of the stack in the second stack, and slowly lowers the empty material frame to stack it on the top layer of the second stack. After placement, the robot unattaches the material frame and returns the material frame turnover device to its original storage location or holds it in place for use in the next turnover task.

[0082] In other embodiments, the material frame turnover device may employ an adjustable gripping position structure to accommodate material frames of different sizes; it may also be equipped with a pressure feedback element to output a contact confirmation signal when the material frame contacts the top layer of the second stack position, thereby improving stacking stability.

[0083] For scenarios with significant variations in stacking height, the top-level height information of the first and second stacks can be re-collected before the material frame turnover operation. This corrects the height parameters in the robot's grasping and placement path, preventing collisions or improper placement due to stacking height deviations. After turnover is complete, the status information of the first and second stacks is updated synchronously. The next layer of material frames exposed at the first stack is set as the new loading material frame, and the empty material frames newly moved to the top of the second stack are set as the new unloading receiving object, i.e., the new upper layer material frame, thus re-entering the loading and unloading cycle.

[0084] Based on the above analysis, this step automatically performs material frame turnover when empty material frames appear simultaneously in the first stack and full material frames in the second stack. This allows empty material frames to be directly transferred to the second stack as new receiving carriers, establishing an automatic connection between the end of loading, the continuation of unloading, and the switching of material frames. This achieves a closed-loop flow of material frame resources between the two stacks without relying on manual handling or additional logistics equipment, avoiding production interruptions caused by full unloading frames or depleted loading frames. Simultaneously, the robot's grasping of the turnover device and execution of turnover operations based on visual recognition results helps adapt to material frame position deviations and changes in stacking height, improving the safety and accuracy of material frame transfer.

[0085] The workpiece processing control method provided in this application configures the first stack as a loading stack and the second stack as a unloading stack. Based on the three-dimensional visual recognition results of the upper material frame of the first stack, the robot is controlled to perform loading operations. Based on the three-dimensional visual recognition results of the circular conveyor line, the robot is controlled to perform unloading operations. When the upper material frame of the first stack is empty and the upper material frame of the second stack is full, the robot is controlled to grasp the material frame turnover device to perform the material frame turnover operation. During loading, unloading, and material frame turnover, three-dimensional vision technology is used to achieve pose alignment, improve the adaptability to material frame stacking deviations and workpiece posture changes, and enhance the reliability of workpiece loading, unloading, positioning, and grasping. This enables continuous and coordinated operation of the loading, unloading, and material frame turnover process, ensures the stability of the processing cycle, and reduces the reliance on manual labor or external turnover equipment.

[0086] It should be understood that the above examples are merely illustrative and not limiting. In some embodiments, the 3D vision device, robot model, fixture form, state determination criteria, and material frame turnover device structure can all be equivalently replaced according to specific production line requirements. As long as the collaborative control of the robot to complete loading, unloading, and material frame turnover based on the visual recognition results can be achieved, it should fall within the scope of the technical ideas disclosed in the embodiments of this application.

[0087] In one possible implementation, after the robot transfers the workpieces to be processed from the upper pallet of the first stack to an empty pallet on the circular conveyor line, the method further includes: controlling the image acquisition device mounted on the robot to acquire images of adjacent pallets on the overhead pallet of the circular conveyor line. Correspondingly, based on the three-dimensional visual recognition results of the acquired images of the circular conveyor line, controlling the robot to transfer the processed workpieces stored in the upper pallet of the circular conveyor line to an empty space in the upper pallet of the second stack includes: based on the three-dimensional visual recognition results of the acquired images of adjacent pallets, controlling the robot to transfer the processed workpieces stored in the adjacent pallets to an empty space in the upper pallet of the second stack.

[0088] The image acquisition device can be a 3D camera, structured light camera, or depth camera mounted on the end effector of the robot arm. It acquires point clouds of the pallet surface, workpiece contours, and height information to identify whether there are processed workpieces and their spatial orientation in adjacent pallets. The circular conveyor line may include multiple pallets arranged sequentially along a closed-loop trajectory. Each pallet has positioning edges and limiting surfaces to ensure the stability of the workpiece's orientation during transport. The upper frame of the second stack is used to hold processed workpieces. Empty spaces refer to unoccupied areas within the frame that can be used for workpiece placement. The robot can determine the center coordinates of these empty spaces based on 3D vision recognition results and complete the placement.

[0089] After transferring the workpiece to the empty pallet, the robot maintains visual tracking of the circular conveyor line, collects data on adjacent pallets on both sides of the empty pallet or on the opposite side of the conveying direction of the circular conveyor line, and combines depth information and image features to match the pallet number, workpiece shape and gripping posture, thereby determining the adjacent pallets that can be unloaded.

[0090] Based on the 3D vision recognition results, the robot's end effector gripper is generated to grasp the processed workpiece in the adjacent pallet, transport it to the empty space in the upper layer of the second stack, and then release it. The end effector gripper can adopt a claw-type structure or an adsorption-type structure. The claw material can be aluminum alloy or high-strength steel to balance rigidity and response speed. In practical applications, other models of this component can also be selected, and this application embodiment does not limit this.

[0091] Through the aforementioned design, a one-to-one collaborative operation is achieved, where one workpiece to be processed is loaded and one processed workpiece is unloaded. This effectively reduces the robot's idle round-trip time, improving operational efficiency and equipment utilization. Simultaneously, utilizing 3D recognition results, the robot can stably identify transferable workpieces during continuous operation of the circular conveyor line, and directly use the recognition results for trajectory planning and placement control, thereby reducing recognition interruptions caused by pallet position changes. By unloading adjacent pallets, the robot can maintain a workpiece retrieval rhythm in a continuous conveying environment, coordinating with the filling process of the second pallet position, improving the continuity and accuracy of the unloading action and the overall line operation efficiency.

[0092] Based on the aforementioned embodiments, further, when the upper material frame of the first stack is empty and the upper material frame of the second stack is full, the robot is controlled to grab the material frame turnover device and perform the material frame turnover operation, including: after performing one material frame turnover operation, when the robot performs a preset number of unloading operations, the upper material frame of the first stack is empty and the upper material frame of the second stack is full, the robot is controlled to grab the material frame turnover device and perform the material frame turnover operation.

[0093] The material frame turnover device is used to transfer upper material frames between two stacks, the first stack and the second stack. The robot can be a six-axis industrial robot with a gripping mechanism at its end, suitable for attaching to the material frame turnover device. The gripping mechanism can adopt a hook-type, clamp-type, or plug-in structure, such as a gripper, so as to stably complete the gripping and transfer when the material frame is in a full-load or empty-load state.

[0094] In actual control, the controller or system continuously counts the number of unloading operations performed by the robot since the last material box turnover operation and compares this number with a preset number. The preset number can be determined based on the capacity of a single material box; that is, the preset number equals the number of storage spaces or the number of workpieces that can be accommodated in a single material box in the current stacking position. When the number of unloading operations reaches the preset number, it indicates that the upper material box of the first stacking position is empty and the upper material box of the second stacking position is fully loaded. Furthermore, visual recognition results can be used to confirm whether the upper material box of the first stacking position is currently empty and whether the upper material box of the second stacking position is fully loaded. This generates a material box turnover command, driving the robot to move to the gripping position of the material box turnover device to complete the gripping, and transferring the upper material box of the first stacking position to the upper layer of the second stacking position, forming a new upper material box.

[0095] This control method ensures that the turnover of material frames no longer relies solely on the result of a single visual recognition. Instead, it uses the cumulative number of material feedings as one of the trigger criteria for turnover, keeping the material frame usage progress consistent with the production line's operating rhythm. By confirming the empty / full status and executing turnover only after a preset number of feedings has been completed, it reduces rhythm fluctuations caused by premature or delayed turnover, ensuring that the second stacking station continuously has space to receive processed workpieces, while allowing the first stacking station to replenish new available material frames in a timely manner.

[0096] After adopting the above implementation method, the robot can automatically determine the turnover time of the material frame after completing a certain number of unloading operations, and perform grabbing and transfer when the empty and full conditions are met. This avoids the waiting time and operation error caused by manual intervention, improves the accuracy and stability of material frame turnover, enhances the continuity between unloading, unloading and stacking, and material frame switching, thereby improving the automation level and production line continuity of the entire processing control process.

[0097] exist Figure 2 Based on the illustrated embodiment, the method further includes: when the loading operation performed by the robot after one material frame turnover operation reaches a preset number, the upper material frame of the first stack is an empty material frame, and the image acquisition device mounted on the robot is controlled to acquire an image of the circular conveyor line.

[0098] The material frame turnover operation refers to the robot using a material frame turnover device to transfer the upper material frames between the first and second stack positions, thereby switching the positional relationship of the upper material frames to maintain the continuity of material supply between stack positions. The image acquisition device can be installed near the robot's end effector, wrist, or gripping mechanism, with its acquisition direction aligned with the circular conveyor line, enabling it to acquire image information such as pallet distribution, workpiece occupancy status, and empty pallet positions.

[0099] After the robot has performed a preset number of loading operations following the last material frame turnover, it can first determine whether the upper material frame of the first stack is empty based on the stack position status. If this condition is met, the robot continues to perform the current loading operation. After completion, the workpiece to be processed is placed in the empty pallet of the circular conveyor line, and the system switches to vision acquisition mode. The onboard image acquisition device acquires the latest image data of the circular conveyor line, and then performs 3D vision recognition on the acquisition results to update the determination results of the empty pallet and workpiece positions. With this method, the system can perceive the status of the conveyor line in real time during the continuous loading stage after the material frame turnover, so as to execute subsequent continuous unloading operations.

[0100] By linking the number of loading operations with the image acquisition of the circular conveyor line, the system can trigger conveyor line status acquisition when the upper material frame of the first stack is empty. This provides a basis for subsequent continuous loading decisions, improving the accuracy and cycle stability of workpiece transfer, and reducing the probability of misjudgments caused by changes in conveyor line status. Because the acquisition timing matches the actual operating rhythm of the production line, the robot can automatically enter image acquisition and recognition mode after completing several loading operations, thereby achieving continuous connection of the processing control process and improving the automation level and on-site adaptability of the entire system.

[0101] Based on the aforementioned embodiments, further, when the upper material frame of the first stack is empty and the upper material frame of the second stack is full, controlling the robot to grab the material frame turnover device and perform the material frame turnover operation includes: when the number of times the robot performs the unloading operation reaches a preset number based on the three-dimensional visual recognition result of the collected image of the circular conveyor line, the upper material frame of the second stack is full, and controlling the robot to grab the material frame turnover device and perform the material frame turnover operation.

[0102] In this embodiment, the image of the circular conveyor line is acquired by an image acquisition device installed at the end of the robot or at a fixed station of the circular conveyor line.

[0103] For example, the image acquisition device includes an industrial camera and a depth sensing unit. The industrial camera is used to acquire images of the pallet surface, and the depth sensing unit is used to obtain the height information and spatial pose information of the workpiece inside the pallet.

[0104] After performing 3D visual recognition on the acquired images of the circular conveyor line, the position, orientation, and graspable area of ​​the processed workpieces on the conveyor line can be identified, and the robot can be driven to complete the unloading and transfer accordingly. The preset number of operations is used to characterize the cumulative amount of unloading operations completed based on the visual recognition results, and can be determined based on the capacity of the second stacking position's material frame.

[0105] In practical implementation, the controller counts each unloading action triggered by the 3D vision recognition result, and the counting information can be stored in the controller's internal cache unit or database. When the count value reaches a preset number, the controller further verifies the full-load status of the upper material frame of the second stack; the full-load status can be determined by the vision recognition result that there is no space left in the material frame, or by the number of workpieces in the material frame reaching the capacity threshold. If the upper material frame of the second stack is in a full-load state, the robot is controlled to grasp the material frame turnover device and transfer the empty material frame of the first stack to the upper layer of the second stack, thereby completing the material frame switching. The material frame turnover device can adopt a hook-type gripper, a clamping turnover fixture, or a telescopic linkage mechanism. It can be connected to the robot's end effector through a flange connection or a quick-change mechanism to improve gripping stability and replacement efficiency. In practical applications, other models of this component can also be selected, and this application embodiment does not limit this.

[0106] By linking the number of material feeding operations with the full load status of the material frame, the controller can promptly trigger a turnover action after the cumulative material feeding driven by vision recognition reaches a set threshold. This prevents continuous material feeding after the second stack is full, which could cause stacking interference or process interruption. After receiving the turnover instruction, the robot first performs positioning and grasping on the material frame turnover device, and then completes the transportation and placement according to the predetermined trajectory. This allows the empty material frame in the first stack to be transferred to the second stack as a new upper-level material frame, thereby providing new space for subsequent material feeding.

[0107] The aforementioned design enables continuous loading operations followed by N consecutive unloading operations (N being a preset number), resulting in concentrated and orderly robot movements and improved operational safety and stability. While maintaining visual recognition accuracy, it achieves cumulative control of the unloading cycle time and automatically completes the material frame turnover when the second stack is fully loaded, reducing manual intervention, improving the continuity of loading / unloading and material frame switching, lowering the risk of full-load blockage, and enhancing the stability and automation level of the entire processing flow.

[0108] Based on the aforementioned embodiments, the loading operation further includes a first gripping operation and a first transfer operation, and the unloading operation includes a first gripping operation and a second transfer operation. The method further includes: after the robot performs the second gripping operation, controlling the image acquisition device to acquire an image of the upper material frame of the first stack or the second stack; and determining whether the upper material frame is empty or full based on the acquired image of the upper material frame.

[0109] The gripping operation (including the first gripping operation and the second gripping operation) refers to the robot using end effectors, vacuum grippers, or electromagnetic adsorption mechanisms to grip workpieces to be processed or already processed. The material, surface morphology, and weight of the gripped object are matched with the gripping mechanism. The first transfer operation is used to transfer the gripped workpiece to be processed to an empty pallet on the circular conveyor line, and the second transfer operation is used to transfer the gripped already processed workpiece to an empty space in the upper material frame of the second stack. The image acquisition device can be configured as a 3D camera, a fixed industrial camera, or a structured light vision sensor mounted on the robot's end effector, with its imaging field of view covering the upper material frame area of ​​both the first and second stacks, so as to acquire the material frame status image in a timely manner after the gripping action is completed.

[0110] In practical implementation, after the robot completes the first or second grasping operation, the controller immediately sends a capture command to the image acquisition device, instructing it to photograph or acquire point cloud data of the upper material frame at the corresponding stack location, and transmit the acquisition results to the vision processing unit. The vision processing unit identifies the frame outline, workpiece-occupied area, empty space distribution, and depth information in the image. Based on the identification results, it determines whether the upper material frame is fully occupied by workpieces or whether there are no workpieces remaining, thus outputting an empty or full material frame status. This status result can be used to update the current availability of the stack location and fed back to the robot controller. Alternatively, the robot controller can handle the empty or full material frame status.

[0111] By performing image verification on the upper material frame after grasping, the recognition results before grasping can be compared with the actual state after grasping, improving the accuracy of determining the state of the upper material frame and the grasping results. Since the empty or full state judgment is directly based on the currently acquired image, the robot can more accurately decide whether to continue performing loading or unloading actions, thereby ensuring the continuity of material frame turnover and workpiece transfer.

[0112] By adopting this implementation method, the status of the first and second stack of material frames can be confirmed in real time without increasing complex manual intervention, improving the accuracy of identifying empty and full material frames, enhancing the linkage reliability between loading, unloading and material frame turnover, and improving the stability and automation of the entire processing control process.

[0113] Figure 4 This application provides a schematic diagram of the structure of a robot, as shown in the embodiment of the present application. Figure 4As shown, the robot includes a robotic arm and a gripper at the end of the robotic arm; the gripper is used to perform a first gripping operation, a second gripping operation, and to grip a material frame turnover device. The robotic arm can be a six-degree-of-freedom or seven-degree-of-freedom industrial robotic arm, with each joint driven by a servo motor to provide precise adjustment capability for spatial pose. The end gripper is fixed to the robotic arm flange and electrically connected to the control system, used to complete the picking and placing of workpieces and material frame turnover devices between different workstations.

[0114] The gripper can be a two-finger parallel gripper, a three-finger adaptive gripper, or an external gripper structure. Its gripping surface can be provided with an anti-slip pad to improve the coefficient of friction. The gripper body can be made of aluminum alloy or high-strength steel to balance lightweight and load-bearing capacity. In practical applications, other models of this component can also be selected, but this application embodiment does not limit this.

[0115] See also Figure 4 The robot's robotic arm is also equipped with an image acquisition device at its end, which is used to acquire images, including images that support 3D visual recognition and other visual recognition images.

[0116] In the operation mode of this application, the robotic arm moves the gripper to the gripping position based on the visual recognition result. After the gripper closes, it performs the first gripping operation and the second gripping operation on the workpiece to be processed or the already processed workpiece, and transfers the gripped object to the corresponding tray or empty space in the material frame. When the material frame needs to be turned over, the gripper can also switch to the gripping state of the material frame turning device, gripping its preset gripping part and cooperating with the robotic arm to complete the transfer and positioning, so that the upper material frame can switch between the first stack position and the second stack position. The gripper can integrate an opening and closing sensor, a force feedback sensor or a position feedback sensor to judge the gripping status in real time during the gripping process, so as to avoid the workpiece slipping or the material frame turning device not gripping properly.

[0117] By adopting a combined structure of robotic arm and end effector, the same actuator can handle workpiece loading, unloading, and gripping of the material frame turnover device, reducing the number of times the robot end effector switches, improving the system's continuous operation capability, and enabling the control system to quickly adjust the motion trajectory and gripping state according to different gripping objects, thereby improving gripping stability, reducing the need for manual intervention, and enhancing the continuity of the entire production line cycle.

[0118] Based on any of the foregoing embodiments, the method further includes: when the number of material frames in the first stack position is 0, switching the first stack position to a material unloading stack position, and switching the second stack position to a material loading stack position.

[0119] In this scheme, the first stacking position and the second stacking position are used to cooperate with the circular conveyor line to complete the loading and unloading of workpieces. The number of material frames is 0, which means that there are no material frames available for continued loading at the first stacking position. The control system, robot or robot controller can switch the functional attributes, i.e., roles of the stacking position accordingly to maintain the continuity of subsequent workpiece flow.

[0120] The number of material frames can be determined by visual recognition results, material frame occupancy detection results, or stack layer statistics results. Among them, visual recognition results can identify the outline of the material frames, stacking positions, and empty space status based on stack images captured by the camera, thereby determining whether the first stack has no material frames.

[0121] When the number of material frames in the first stack is detected to be 0, the controller outputs a stack switching command, switching the first stack to a unloading stack and the second stack to a loading stack. This reverses the roles of the stacks that were originally responsible for loading and unloading. This switching process can be synchronized with the material frame turnover, robot handling, and conveyor line cycle time, so that the workpieces stored in the second stack become the workpieces to be processed, and loading and unloading can continue to complete the next processing step of the workpiece.

[0122] The controller can be integrated into the robot, and can be an industrial controller, motion controller, or a host computer independent of the robot. It generates switching logic based on the stacking position status signal to drive the robot, conveyor line and related clamping mechanism to work together. In practical applications, other models of the controller can also be selected, and this application embodiment does not limit this.

[0123] By instantly switching the stack position's functional attributes when there is no material frame in the first stack position, the system can avoid operation interruptions caused by the depletion of material frames on the loading side. This maintains a dynamic balance between unloading and loading replenishment in terms of spatial arrangement, thereby improving the continuity, adaptability, and compatibility of the entire production line with different working conditions. This method also reduces the frequency of manual intervention, lowers waiting time caused by fixed stack position configurations, and better matches the material frame turnover process with the workpiece processing cycle, thus improving the stability and automation level of processing control.

[0124] Figure 5 A schematic diagram of a circular conveyor line provided in this application is shown below. Figure 5 As shown, based on any of the aforementioned embodiments, the circular conveyor line is further provided with a processing table, which is equipped with a flipping mechanism. The flipping mechanism is used to flip the workpieces conveyed to the flipping station to achieve double-sided processing of the workpieces.

[0125] Accordingly, based on the recognition results of the collected images of the circular conveyor line, the robot is controlled to perform a unloading operation to transfer the processed workpieces stored in the tray of the circular conveyor line to the empty space in the upper material frame of the second stack position. This includes: based on the recognition results of the collected images of the circular conveyor line, identifying whether the corresponding workpiece has been flipped and whether the current face of the corresponding workpiece has been processed; if both are yes, then the corresponding workpiece is considered a processed workpiece, and the robot is controlled to perform a unloading operation to transfer the processed workpieces stored in the tray of the circular conveyor line to the empty space in the upper material frame of the second stack position.

[0126] The processing table is used to support the workpiece on the circular conveyor line. The flipping mechanism is installed in the flipping area of ​​the processing table and is set accordingly with the conveyor path so that the workpiece can be stably flipped after being transported to the flipping station with the pallet. The flipping mechanism can adopt a rotary clamping structure, a swing arm flipping structure, or a pallet lifting flipping structure. Its driving components can be composed of servo motors, cylinders, or electric push rods to ensure that the flipping angle and positioning accuracy meet the requirements of double-sided processing.

[0127] The image recognition results of the circular conveyor line can include the posture, edge contour and surface processing features of the workpiece stored in the corresponding tray, so as to determine whether the workpiece has been flipped and whether the side currently facing the image acquisition device (hereinafter referred to as the current side) has been processed based on the image recognition results.

[0128] Once the preceding processing is complete, it can be characterized by hole forming, surface deburring, consistent texture, and color characteristics, meeting the processing completion conditions of the corresponding process. After confirming that the workpiece in the pallet has been flipped and processed, the robot performs a material unloading operation including gripping, lifting, shifting, and placing, transferring the processed workpiece from the circular conveyor pallet to an empty space in the upper layer of the second stack.

[0129] In this structure, the flipping mechanism enables workpieces to undergo double-sided processing on the same circular conveyor line. Visual recognition results are used to distinguish whether a workpiece is ready for unloading, thus preventing workpieces with only single-sided processing from being prematurely moved. When the robot unloads the workpiece based on the recognition results, it accurately places workpieces that meet the double-sided processing conditions into empty spaces in the upper layer of the second stack, achieving coordinated control of processing, recognition, and unloading actions. This ensures that the unloading timing matches the actual processing state of the workpiece, reducing the risk of incorrect unloading and rework, and improving the continuity, accuracy, and automation level of the double-sided processing flow.

[0130] Figure 6a This is a structural schematic diagram of a material frame turnover device provided in this application. Figure 6b For robot to grasp Figure 6a A schematic diagram of the combined state of the material frame turnover device. Figure 6c For the robot to pass Figure 6aA schematic diagram of the combined state of the material frame turnover device when transferring the material frame.

[0131] like Figure 6a As shown, based on the aforementioned embodiments, the material frame turnover device further includes a support structure, a gripper component, and hook-type grippers located on both sides of the support structure.

[0132] Accordingly, controlling the robot to grasp the material frame turnover device and perform the material frame turnover operation to transfer the upper material frame of the first stack to the upper layer of the second stack as a new upper material frame for the second stack includes: controlling the robot to grasp the gripper component of the material frame turnover device, and using the gripper component to drive the material frame turnover device to move to the corresponding position of the upper material frame of the first stack; controlling the robot to move along a preset direction to insert the hook-type gripper of the material frame turnover device into the hooking position of the upper material frame of the first stack; controlling the robot to move upward and drive the material frame turnover device and the upper material frame of the first stack to the upper layer of the second stack; controlling the robot to move in the opposite direction along the preset direction to disengage the hook-type gripper from the hooking position of the hooked material frame; and controlling the robot to return the material frame turnover device to its original position.

[0133] The support structure supports the gripper components and hook-type grippers, providing overall rigid support for the turnover device. The gripper components can be configured as receiving bosses, holding beams, etc., for the robotic arm's end effector to grasp. Hook-type grippers are positioned on both sides of the support structure to create symmetrical force distribution at the hook-up points on both sides of the material frame. The hook-up points are functional mating areas on the material frame designed to facilitate hook-up and lifting actions. These areas consist of gaps / slots formed by the frame's edge structure, allowing the hook-type grippers to extend into and engage. Figure 6c The region corresponding to the dashed ellipse.

[0134] The support structure can be made of aluminum alloy profiles or steel welded frames to balance strength and weight. The gripper component and the support structure can be fixedly connected by bolts. The hook-type gripper can be made of wear-resistant steel plate bent into shape, which is convenient to insert into the hook position and can be reused. In practical applications, other models of this component can also be selected. This application embodiment does not limit this.

[0135] In actual operation, the robot gripper first grasps the hand gripper component, then moves upward to pick up the material frame turnover device, such as... Figure 6b As shown; this then moves the material frame turnover device to the corresponding position of the upper layer of the first stack of material frames, aligning the hook-type grippers on both sides with the hook-up positions on the sides of the material frame. Subsequently, the robot moves horizontally in a preset direction, pushing the hook-type grippers into the hook-up positions of the empty material frame and forming a locking relationship, as shown. Figure 6cAs shown, the robot then lifts the upper material frame attached to the hook-type gripper. Because the material frame turnover device and the material frame share the force, the empty material frame can maintain a stable posture as it is transferred from the first stack to above the second stack, and then settles into its position upon reaching the upper layer of the second stack. Afterwards, the robot moves in the opposite direction along a preset path, causing the hook-type gripper to detach from its attachment point, thus releasing the support for the material frame. Finally, the material frame turnover device is returned to its initial position for the next turnover operation.

[0136] By adopting the above structure, the material frame turnover device can reliably grasp, hook, lift, and return empty material frames under robot control, avoiding the risks of posture deviation and collision caused by manual handling, and ensuring high repeatability in the switching of material frames between the first and second stack positions. Because the hook-type gripper and the material frame hooking position form a mechanical cooperation, the force on the material frame during turnover is clearly defined, reducing the probability of disengagement or tilting, thereby improving turnover stability, shortening switching time, and providing a continuous and reliable equipment foundation for workpiece loading / unloading and material frame circulation management.

[0137] This application embodiment also provides a workpiece processing control device, including: a loading control module, used to control a robot to perform a loading operation based on the three-dimensional visual recognition result of the image of the upper material frame of the first stack after configuring the first stack as a loading stack and the second stack as a unloading stack, so as to transfer the workpiece to be processed stored in the upper material frame of the first stack to an empty pallet of the circular conveyor line; an unloading control module, used to control a robot to perform an unloading operation based on the three-dimensional visual recognition result of the image of the circular conveyor line, so as to transfer the processed workpiece stored in the pallet of the circular conveyor line to an empty space in the upper material frame of the second stack; and a material frame turnover control module, used to control a robot to grab a material frame turnover device and perform a material frame turnover operation when the upper material frame of the first stack is empty and the upper material frame of the second stack is full, so as to transfer the upper material frame of the first stack to the upper layer of the second stack as a new upper material frame of the second stack.

[0138] In one possible implementation, the device further includes a first image acquisition module, used to: after the control robot transfers the workpiece to be processed stored in the upper frame of the first stack to the empty pallet of the circular conveyor line, control the image acquisition device mounted on the robot to acquire images of the adjacent pallets of the empty pallet on the circular conveyor line.

[0139] Correspondingly, the unloading control module is specifically used to: control the robot to transfer the processed workpieces stored in the adjacent pallets to the empty space of the upper material frame of the second stack position based on the three-dimensional visual recognition results of the collected images of the adjacent pallets.

[0140] In one possible implementation, the material frame turnover control module is specifically used to: after performing a material frame turnover operation, when the number of unloading operations performed by the robot reaches a preset number, the upper material frame of the first stack is empty and the upper material frame of the second stack is full, control the robot to grab the material frame turnover device and perform the material frame turnover operation.

[0141] In one possible implementation, the device further includes a second image acquisition module, used to: when the loading operation performed by the robot after one material frame turnover operation reaches a preset number, and the upper material frame of the first stack is empty, control the image acquisition device mounted on the robot to acquire images of the circular conveyor line.

[0142] In one possible implementation, the material frame turnover control module is specifically used to: when the number of times the robot performs the unloading operation reaches a preset number based on the three-dimensional visual recognition results of the collected images of the circular conveyor line, the upper material frame of the second stack is fully loaded, and the robot is controlled to grab the material frame turnover device and perform the material frame turnover operation.

[0143] In one possible implementation, the loading operation includes a first gripping operation and a first transfer operation, and the unloading operation includes a second gripping operation and a second transfer operation. The device also includes a material frame status detection module, used to: after the robot performs the first gripping operation or the second gripping operation, control the image acquisition device to acquire images of the upper material frames of the first stack or the second stack; and determine whether the upper material frame is empty or full based on the acquired images of the upper material frame.

[0144] In one possible implementation, the device further includes a stack position role switching module, used to: switch the first stack position to a unloading stack position when the number of material frames in the first stack position is 0, and switch the second stack position to a loading stack position.

[0145] In one possible implementation, the circular conveyor line is equipped with a processing table, which is fitted with a flipping mechanism. This flipping mechanism flips the workpieces conveyed to the flipping station to achieve double-sided processing of the workpieces. The unloading control module is specifically used for:

[0146] Based on the recognition results of the collected images of the circular conveyor line, it is determined whether the corresponding workpiece has been flipped and whether the current face of the corresponding workpiece has been processed. If both are true, the corresponding workpiece is taken as the processed workpiece, and the robot is controlled to perform the unloading operation to transfer the processed workpiece stored in the tray of the circular conveyor line to the empty space of the upper material frame of the second stack.

[0147] In one possible implementation, the material frame turnover device includes a support structure, a gripper component, and hook-type grippers located on both sides of the support structure. The material frame turnover control module is specifically used for: controlling a robot to grip the gripper component of the material frame turnover device, thereby moving the material frame turnover device to the corresponding position of the upper layer material frame in the first stack; controlling the robot to move along a preset direction to insert the hook-type grippers of the material frame turnover device into the hooking position of the upper layer material frame in the first stack; controlling the robot to move upwards, thereby moving the material frame turnover device and the upper layer material frame of the first stack to the upper layer of the second stack; controlling the robot to move in the opposite direction along the preset direction to disengage the hook-type grippers from the hooking position of the hooked material frame; and controlling the robot to return the material frame turnover device to its original position.

[0148] The workpiece processing control device provided in this embodiment can execute the workpiece processing control method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0149] This application also provides a control device, including: a memory and a processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, causing the processor to perform the method provided above.

[0150] In this embodiment, the control device, through the cooperation of memory and processor, programmatically carries and executes the above-mentioned processing control method, enabling centralized realization of coordinated control between the first stacking position, the second stacking position, and the circular conveyor line. When the processor executes computer instructions, it can drive the robot to complete loading, unloading, and material frame turnover operations based on the 3D vision recognition results, thereby enabling the equipment to automatically switch the work process according to the on-site working conditions. Since the method logic is solidified into executable instructions and uniformly scheduled by the control device, it can reduce manual intervention and the burden of external equipment coordination, making the processes of workpiece transfer, finished product stacking, and empty / full material frame switching continuous and connected, thereby improving the level of automation, processing cycle stability, and overall line operation continuity under complex working conditions.

[0151] In the specific implementation process, the processor executes computer execution instructions stored in the memory, causing the processor to perform the method provided in the above embodiments.

[0152] The specific implementation process of the processor can be found in the above method embodiments, and its implementation principle and technical effect are similar, so it will not be repeated here.

[0153] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0154] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0155] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0156] This application provides a workpiece processing system, including: a robot, an image acquisition device, a material frame turnover device, a first stacking position, a second stacking position, and a circular conveyor line; the image acquisition device is used to acquire images; the robot is used to perform the following steps based on the images acquired by the image acquisition device: after configuring the first stacking position as a loading stacking position and the second stacking position as a unloading stacking position, based on the three-dimensional visual recognition result of the acquired image of the upper material frame of the first stacking position, the robot is controlled to perform a loading operation to load the workpiece to be processed stored in the upper material frame of the first stacking position. The workpieces are transferred to empty pallets on the circular conveyor line. Based on the 3D visual recognition results of the collected images of the circular conveyor line, the robot is controlled to perform a feeding operation to transfer the processed workpieces stored in the pallets of the circular conveyor line to empty spaces in the upper material frames of the second stack. When the upper material frames of the first stack are empty and the upper material frames of the second stack are full, the robot is controlled to grab the material frame turnover device and perform a material frame turnover operation to transfer the upper material frames of the first stack to the upper layer of the second stack, which then becomes the new upper material frames for the second stack.

[0157] In one possible implementation, the robot includes a robotic arm and a gripper disposed at the end of the robotic arm; the gripper is used to perform a first gripping operation, a second gripping operation, and to grip a material frame turnover device.

[0158] The robot can perform the methods provided in any of the foregoing embodiments. It can control the robot's robotic arm to perform corresponding actions and control the onboard image acquisition device to acquire images through the controller or control unit integrated inside the robot.

[0159] In one possible implementation, the material frame turnover device includes a support structure, a gripper component, and hook-type grippers located on both sides of the support structure.

[0160] In one possible implementation, the circular conveyor line is equipped with a processing table, which is equipped with a flipping mechanism. The flipping mechanism is used to flip the workpieces conveyed to the flipping station to achieve double-sided processing of the workpieces.

[0161] Images of the first stack and the circular conveyor line are acquired by an image acquisition device, and the robot's movements are driven by the 3D vision recognition results. This enables the robot to accurately identify the workpieces to be processed, the processed workpieces, and the empty status of the material frames, thus completing the continuous connection between loading and unloading. Furthermore, when the upper material frame of the first stack is detected to be empty and the upper material frame of the second stack is full, the robot grabs the material frame turnover device to perform the material frame turnover operation. This eliminates the need for additional manual handling when switching between empty and full material frames, ensuring that loading and unloading, finished product recycling, and material frame turnover are completed uniformly within the same system. Therefore, it can improve the accuracy of workpiece flow, the stability of processing cycle, and the continuity of the entire processing flow.

[0162] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the methods provided above.

[0163] In this embodiment, by pre-storing the computer execution instructions used to implement the above method in a computer-readable storage medium, the processor can complete the various steps of coordinated control for the first stacking position, the second stacking position, and the circular conveyor line after calling the corresponding instructions. This enables the programmed integration of loading, unloading, and frame turnover operations based on 3D vision recognition, allowing the system to automatically switch workflows under different conditions such as an empty frame at the first stacking position and a full frame at the second stacking position, thereby ensuring continuous connection between workpiece transfer, finished product stacking, and frame replacement. Therefore, this storage medium facilitates the deployment, portability, and repeated execution of the method, reduces manual intervention and reliance on external logistics equipment, and thus improves the level of automation, processing cycle stability, and the coherence of the entire processing flow under complex working conditions.

[0164] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the method provided above.

[0165] In this embodiment, the computer program product carries all the control logic of the above-mentioned processing control method in the form of program instructions. After the processor executes the computer program, it can complete the loading, unloading, and material frame turnover control based on the three-dimensional vision recognition results, around the coordinated relationship of the first stacking position, the second stacking position, and the circular conveyor line. This allows the robot to automatically switch the work process according to the on-site recognition status. Since the computer program can be directly deployed in the controller or industrial computing platform, it can integrate workpiece transfer, finished product stacking, and empty / full material frame switching into the same control system, making the whole process control continuous and stable. This reduces the risk of interruption caused by manual intervention and equipment switching, thus improving the level of automation, processing cycle stability, and overall flow accuracy under complex working conditions.

[0166] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage 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 storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0167] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0168] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0169] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0170] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0171] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0172] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0173] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A workpiece machining control method, characterized in that, include: After configuring the first stacking position as a loading stacking position and the second stacking position as a unloading stacking position, the robot is controlled to perform a loading operation based on the three-dimensional visual recognition results of the image of the upper material frame of the first stacking position, so as to transfer the workpiece to be processed stored in the upper material frame of the first stacking position to the empty pallet of the circular conveyor line. Based on the three-dimensional visual recognition results of the collected images of the circular conveyor line, the robot is controlled to perform a material unloading operation to transfer the processed workpieces stored in the tray of the circular conveyor line to the empty space of the upper material frame of the second stack position. When the upper material frame of the first stack is empty and the upper material frame of the second stack is full, the robot is controlled to grab the material frame turnover device and perform the material frame turnover operation, so as to transfer the upper material frame of the first stack to the upper layer of the second stack through the material frame turnover device, as the new upper material frame of the second stack.

2. The method according to claim 1, characterized in that, After the controlled robot transfers the workpieces to be processed stored in the upper frame of the first stack to an empty pallet on the circular conveyor line, the method further includes: Control the image acquisition device mounted on the robot to acquire images of adjacent pallets of the empty pallet on the circular conveyor line; The step of controlling the robot to transfer the processed workpieces stored in the tray of the circular conveyor line to the empty space in the upper frame of the second stack position based on the three-dimensional visual recognition results of the collected images of the circular conveyor line includes: Based on the three-dimensional visual recognition results of the images of the adjacent pallets, the robot is controlled to transfer the processed workpieces stored in the adjacent pallets to the empty space of the upper material frame of the second stacking position.

3. The method according to claim 2, characterized in that, When the upper material frame of the first stack is empty and the upper material frame of the second stack is full, controlling the robot to grasp the material frame turnover device and perform the material frame turnover operation includes: After performing one material frame turnover operation, when the robot performs the unloading operation a preset number of times, the upper material frame of the first stack is empty and the upper material frame of the second stack is full. The robot is then controlled to grab the material frame turnover device and perform the material frame turnover operation.

4. The method according to claim 1, characterized in that, The method further includes: When the loading operation performed by the robot after one material frame turnover operation reaches a preset number, the upper material frame of the first stack is empty, and the image acquisition device mounted on the robot is controlled to acquire an image of the circular conveyor line.

5. The method according to claim 4, characterized in that, When the upper material frame of the first stack is empty and the upper material frame of the second stack is full, controlling the robot to grasp the material frame turnover device and perform the material frame turnover operation includes: Based on the three-dimensional visual recognition results of the collected images of the circular conveyor line, when the number of times the robot performs the unloading operation reaches the preset number, the upper material frame of the second stack is fully loaded, and the robot is controlled to grab the material frame turnover device and perform the material frame turnover operation.

6. The method according to claim 1, 2 or 4, characterized in that, The loading operation includes a first gripping operation and a first transfer operation, the unloading operation includes a second gripping operation and a second transfer operation, and the method further includes: After the robot performs the first grasping operation or the second grasping operation, the image acquisition device is controlled to acquire an image of the upper material frame of the first stack or the second stack. Based on the acquired image of the upper material frame, determine whether the upper material frame is empty or full.

7. The method according to claim 6, characterized in that, The robot includes a robotic arm and a gripper disposed at the end of the robotic arm; the gripper is used to perform the first gripping operation, the second gripping operation, and to grip the material frame turnover device.

8. The method according to any one of claims 1-5, characterized in that, The method further includes: When the number of material frames in the first stack position is 0, the first stack position is switched to the unloading stack position, and the second stack position is switched to the loading stack position.

9. The method according to any one of claims 1-5, characterized in that, The circular conveyor line is equipped with a processing table, which is fitted with a flipping mechanism. The flipping mechanism flips the workpieces conveyed to the flipping station to achieve double-sided processing of the workpieces. The step of controlling the robot to perform a material unloading operation based on the recognition results of the collected images of the circular conveyor line, to transfer the processed workpieces stored in the tray of the circular conveyor line to an empty space in the upper material frame of the second stacking position, includes: Based on the recognition results of the collected images of the circular conveyor line, it is determined whether the corresponding workpiece has been flipped and whether the current surface of the corresponding workpiece has been processed. If both are true, then the corresponding workpiece is taken as the processed workpiece, and the robot is controlled to perform a feeding operation to transfer the processed workpiece stored in the tray of the circular conveyor line to the empty space of the upper material frame of the second stack position.

10. The method according to any one of claims 1-5, characterized in that, The material frame turnover device includes a support structure, a gripper component, and hook-type grippers located on both sides of the support structure. Controlling the robot to grip the material frame turnover device and perform a material frame turnover operation, so as to transfer the upper material frame of the first stack to the upper layer of the second stack as a new upper material frame for the second stack, includes: The robot is controlled to grasp the gripper component of the material frame turnover device, and the gripper component drives the material frame turnover device to move to the corresponding position of the upper material frame of the first stack. Control the robot to move along a preset direction so that the hook-type gripper of the material frame turnover device can be inserted into the hooking position of the upper material frame of the first stack. Control the robot to move upwards, and drive the material frame turnover device and the upper material frame of the first stack to the upper layer of the second stack; Control the robot to move in the opposite direction along the preset direction so that the hook-type gripper is disengaged from the attachment position of the attached material frame; The robot is controlled to return the material frame turnover device to its original position.

11. A control device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-10.

12. A workpiece processing system, characterized in that, include: The system includes a robot, an image acquisition device, a material frame turnover device, a first stacking position, a second stacking position, and a circular conveyor line; the image acquisition device is used to acquire images. The robot is used to perform the following steps based on the images acquired by the image acquisition device: After configuring the first stack position as a loading stack position and the second stack position as a unloading stack position, the robot is controlled to perform a loading operation based on the three-dimensional visual recognition results of the image of the upper material frame of the first stack position, so as to transfer the workpiece to be processed stored in the upper material frame of the first stack position to the empty pallet of the circular conveyor line. Based on the three-dimensional visual recognition results of the collected images of the circular conveyor line, the robot is controlled to perform a material unloading operation to transfer the processed workpieces stored in the tray of the circular conveyor line to the empty space of the upper material frame of the second stack position. When the upper material frame of the first stack is empty and the upper material frame of the second stack is full, the robot is controlled to grab the material frame turnover device and perform the material frame turnover operation, so as to transfer the upper material frame of the first stack to the upper layer of the second stack through the material frame turnover device, as the new upper material frame of the second stack.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-10.

14. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-10.

Images