Vision-based stacking method

Abstract

The invention relates to the technical field of robot stacking, in particular to a vision-based stacking method which comprises the following steps: information acquisition: acquiring a plate top two-dimensional code image and a plate image; information extraction: obtaining the physical boundary of the two-dimensional code label and the position relation between the physical boundary and the edge of the plate from the top two-dimensional code label image and the plate image; offset calculation: calculating a grabbing compensation angle according to the pose deviation of the edge of the two-dimensional code; performing grabbing adjustment: performing offset posture adjustment on the manipulator according to the grabbing compensation angle, so that the length direction of the grabbing manipulator is parallel to the length direction of the plate; grabbing execution, wherein grabbing action is executed according to the compensated posture; and stacking is conducted, specifically, the grabbed plates are stacked to the stacking position according to program setting. The stacking device has the effect of improving the stacking working efficiency.

Description

Technical Field

[0001] The present application relates to the technical field of robot palletizing, and in particular to a vision-based palletizing method. Background Art

[0002] At present, in the current sheet metal processing industry, in order to reasonably utilize the remaining size of the sheet metal, generally a variety of different specifications of sheets are processed on the same large sheet, and then the cut sheets are grabbed and stacked. There are the following technical pain points for stacking sheets with irregular sizes after cutting: Traditional mechanical positioning methods rely on preset programs and cannot adapt to randomly changing sheet metal sizes, resulting in a grasping failure rate of up to 15%-20%; existing visual positioning systems mostly use contour recognition technology, but the recognition error for sheets with worn edges or uneven surfaces exceeds ±3 degrees; however, for smaller sheets formed after processing, the deviation in the grabbing angle will make the stacks formed by stacking prone to collapse, requiring manual stacking, or manual picking of sheets or repair of collapsed stacks, resulting in reduced work efficiency. Summary of the invention

[0003] In order to improve the working efficiency of palletizing, the present application provides a vision-based palletizing method.

[0004] The present application provides a vision-based palletizing method, which adopts the following technical solutions: A vision-based palletizing method comprises the following steps: Information acquisition: Get the QR code image on the top of the plate and the plate image; Information extraction: From the top QR code label image and the plate image, obtain the physical boundary of the QR code label and its positional relationship with the plate edge; Offset calculation: Calculate the grab compensation angle based on the position deviation of the QR code edge ; Grasping adjustment: adjust the offset posture of the manipulator according to the grasping compensation angle so that the length direction of the grasping manipulator is parallel to the length direction of the plate; Grasp execution: Execute the grasping action according to the compensated posture; Palletizing: According to the program settings, the grabbed boards are stacked at the stacking position.

[0005] By adopting the above technical solution, by obtaining the QR code image and the plate image on the top of the plate, and extracting the physical boundary of the QR code label and its positional relationship with the edge of the plate, the method can accurately determine the orientation and size of the plate; this helps the robot to achieve higher accuracy when grasping the plate and reduce grasping failures or plate damage due to inaccurate positioning.

[0006] Calculate the grip compensation angle based on the position deviation of the QR code edge , and accordingly adjust the offset posture of the manipulator so that the length direction of the grabbing manipulator is parallel to the length direction of the plate; this adaptive adjustment mechanism can cope with plates of different sizes and directions, improving the flexibility and versatility of palletizing operations.

[0007] Through precise grasping and adaptive adjustment, this method can ensure that the robot accurately stacks the plates to the specified position after grasping them; this helps to improve the efficiency of palletizing operations and reduce manual intervention and error rates.

[0008] At the same time, it can reduce the difficulty of grabbing small boards, and can reduce the impact of grabbing offset on stacking, facilitate mixed stacking of small boards and large boards, and reduce the occurrence of small boards being easily overturned during stacking. Compared with manual picking of boards, it is more convenient and can improve the efficiency of stacking. It can also record production data throughout the entire process to make it traceable, and track production status in real time to reduce the occurrence of missing boards.

[0009] Optionally, in the information extraction step, it also includes identifying the QR code information and recording it as specification data; The palletizing step also includes palletizing at the position set by the program according to the specification data.

[0010] By adopting the above technical solution, QR code information recognition is added to the information extraction step and recorded as specification data. This improvement enables the system to obtain more information about the plate; the QR code usually contains key data such as plate size, material, batch, etc., which is crucial for subsequent palletizing operations; by identifying this information, the system can process the plate more intelligently and improve the accuracy and efficiency of the operation.

[0011] In the palletizing step, the program-set position is executed according to the specification data. This improvement realizes the intelligent palletizing operation. The system can automatically adjust the palletizing strategy according to different plate specification data to ensure that the plates are correctly stacked in the specified position. This reduces the need for manual intervention and improves the degree of automation and accuracy of the operation.

[0012] This method can significantly improve production efficiency through precise information extraction and intelligent palletizing operations; the system can quickly identify and process plates, reduce waiting time and error rate, and thus speed up palletizing; in addition, intelligent palletizing strategies can also optimize the stacking method of plates and improve the utilization of warehouse space.

[0013] QR code information recognition also provides traceability for the board. Once a problem occurs during the subsequent use of the board, its source, batch, production process and other information can be quickly traced by scanning the QR code, which is of great significance for quality control and traceability management.

[0014] Optionally, the affixing of the QR code label satisfies: The four sides of the label should be parallel or collinear with the corresponding sides of the plate; The offset between the center point of the label and the geometric center of the plate is ≤ 2% of the plate length.

[0015] By adopting the above technical solution, the four sides of the QR code label are required to be parallel or colinear with the corresponding sides of the plate. This regulation ensures that the relative position relationship between the QR code label and the plate is stable and easy to identify during the image recognition process; such label pasting method helps the image processing algorithm to more accurately extract the physical boundaries of the QR code and its positional relationship with the edge of the plate, thereby improving the accuracy of information extraction.

[0016] The offset between the center point of the label and the geometric center of the plate is limited to ≤2% of the plate length. This requirement ensures the relative consistency between the position of the QR code label and the overall position of the plate; in the offset calculation step, it helps to calculate the grip compensation angle more accurately. , and then optimize the robot's grasping adjustment strategy; by reducing the grasping error caused by label position deviation, the accuracy and stability of the grasping action can be improved.

[0017] By specifying the pasting requirements of the QR code label, the system can more reliably handle plates of different sizes and orientations; even under different working conditions, as long as the label meets the specified pasting requirements, the system can accurately identify and process the plate, thereby enhancing the robustness and adaptability of the system.

[0018] The vision-based palletizing method with the addition of QR code labeling requirements can significantly improve work efficiency due to more accurate information extraction, more optimized gripping adjustments and stronger system robustness; the system can identify and process sheets more quickly, reducing waiting time and error rates, thereby speeding up palletizing and improving overall production efficiency.

[0019] Optionally, in the grasping execution step, the middle part of the plate is grasped.

[0020] By adopting the above technical solution, the middle part of the plate is grasped. On the one hand, it is convenient for the subsequent stacking work. On the other hand, it is convenient to squeeze the QR code label to reduce the occurrence of loose adhesion such as warping, curling, folding, etc., which is convenient for the subsequent identification of the QR code label.

[0021] Optionally, after the information extraction step, an offset distance calculation step is further provided; The offset distance calculation includes an edge extension step, an offset quantification step, and an intervention step; Edge extension: Get the edge of the QR code label from the top QR code label image, extend the edge of the QR code label, and extend it to the edge of the plate; Offset quantification: Calculate the maximum offset based on the edge inclination, the length of the plate, and the minimum distance between the edge of the QR code label and the edge of the plate; Intervention: Intervene in the palletizing step. When palletizing offset plates, adjust the angle so that the side with the largest offset contacts the already palletized plates first, and then execute the palletizing step.

[0022] By adopting the above technical solution, through the edge extension step, the system can accurately identify the relative position relationship between the edge of the QR code label and the edge of the plate, and calculate the offset on this basis; this helps to more accurately adjust the position of the plate during the stacking process, reduce the inaccurate stacking problem caused by position deviation, and thus improve the stacking accuracy.

[0023] The offset quantification step calculates the maximum offset by comprehensively considering multiple factors such as edge inclination, plate length, and the minimum distance between the edge of the QR code label and the edge of the plate. This quantitative indicator provides an important basis for the subsequent stacking strategy; in the intervention step, the system can adjust the stacking angle of the plate according to the maximum offset, ensuring that the side of the plate with a larger offset contacts the already stacked plate first, thereby optimizing the stacking structure and improving the stacking stability and load-bearing capacity.

[0024] After adding the offset distance calculation step, the system can more flexibly cope with plates of different sizes, shapes and offsets; even if the plates are offset to a certain extent during transportation or placement, the system can ensure the accuracy and stability of palletizing through calculation and adjustment; this enhances the adaptability and flexibility of the system.

[0025] Through accurate offset calculation and palletizing strategy adjustment, the system can complete palletizing operations more quickly, reduce repeated adjustments and error rates caused by inaccurate positioning, and thus improve work efficiency.

[0026] Optionally, after the intervention step, a board specification feedback step is also provided; Plate specification feedback: including size difference calculation step, size judgment step, second judgment step, feedback step, recording step, third judgment step, angle correction step, fourth judgment step and deviation correction step; Calculation of size difference: Calculate the offset difference between the two sides according to the maximum offset between the two sides of the QR code label edge of the same plate in the offset quantification step; Size judgment: According to the offset difference on both sides and the specification width of the plate, it is judged whether there is a cutting deviation. If so, the second acquisition step is executed; Second acquisition: obtaining the actual size specification of the current plate through the plate image, and obtaining the first deviation from the theoretical size specification; Second judgment: Calculate the ratio of cutting deviation to allowable deviation and record it as deviation ratio, and judge whether the deviation ratio is greater than or equal to the first threshold. If so, execute the feedback step, otherwise, execute the third judgment step; Feedback: Feedback the cutting deviation to the cutting side, make cutting corrections, and execute the recording steps; Record: store the cutting deviation data in the QR code label; The third judgment: judging whether there is a plate at one end of the length direction of the plate, if so, executing the angle correction, otherwise, executing the fourth judgment step; Angle correction: Compensation angle for grabbing Perform correction, and after the correction, perform a grasping adjustment step, and perform a fourth judgment step; Fourth judgment: judging whether the cutting deviation is the same as the first deviation, if so, executing the recording step, otherwise, executing the deviation correction step; Deviation correction: Calculate the average of the cutting deviation and the first deviation and record it as the cutting deviation, then perform the recording step.

[0027] By adopting the above technical solution, through the size difference calculation and size judgment steps, the system can accurately identify whether there is a deviation in the plate during the cutting process; once a cutting deviation is found, the system will feed back the deviation information to the cutting side through the feedback step and make timely cutting corrections; this helps to reduce plate waste and quality problems caused by inaccurate cutting and improve cutting quality.

[0028] After identifying the cutting deviation, the system not only makes cutting corrections, but also adjusts the gripping compensation angle according to the deviation. Correction (angle correction step); this ensures that even if the size of the plate changes, the system can accurately adjust the gripping posture of the robot to ensure that the plate is stacked correctly; this dynamic adjustment mechanism optimizes the stacking strategy and improves the stability and accuracy of stacking.

[0029] By recording the steps, the system will store the cutting deviation data records in the QR code label; this not only provides important reference information for subsequent plate processing, but also enhances the traceability of the system; once a plate problem is found during subsequent use, the deviation information in the cutting and stacking process can be quickly traced back by scanning the QR code, which is convenient for problem troubleshooting and quality traceability.

[0030] Although a plate specification feedback step has been added, the implementation of this step does not significantly increase the complexity of the operation; on the contrary, by accurately identifying and processing cutting deviations, the system can reduce the waste of operation time caused by repeated adjustments and error rates, thereby improving operation efficiency.

[0031] Optionally, between the third judging step and the fourth judging step, a fifth judging step and a size difference correction step are further provided; Fifth judgment: judging whether there is a plate on one side of the plate width direction, if yes, executing the size difference correction step, otherwise, executing the fourth judgment step; Size difference correction: intervene in the size difference calculation step, recalculate the size difference, and then execute the fourth judgment step.

[0032] By adopting the above technical solution, when there are plates on the side, the deviation value originally obtained through the size difference calculation step may be inaccurate due to the mutual influence between the plates; at this time, by executing the size difference correction step, the system can recalculate the size difference to ensure the accuracy of cutting deviation identification; this helps the system to adjust the stacking strategy more accurately and reduce stacking errors caused by inaccurate deviation identification.

[0033] Optionally, after the recording step, an associated tag establishment step and a placement feedback step are also included; Establishing associated labels: Record the plates with large cutting deviations, determine the location of the deviations, establish associated labels with adjacent cutting plates, and store them in QR code labels; Placement feedback: Determine the connection between the panels based on the contact tags, and determine the stacking position based on the stacking procedure. Associate the stacking position with the contact tags and store them in the QR code tags.

[0034] By adopting the above technical solution, through the step of establishing associated labels, the system can record the plates with large cutting deviations and establish associated labels with adjacent cut plates; this step helps to quickly track down the problem plates and their adjacent plates in the subsequent production or quality inspection process, thereby improving the efficiency of problem tracking.

[0035] The placement feedback step determines the stacking position of the plates according to the contact tags and the stacking procedure, and associates the stacking position with the contact tags. This step helps the system to arrange the layout of the plates more reasonably during the stacking process, ensuring that the problem plates and their adjacent plates can be stacked in a specific order and position, thereby optimizing the stacking layout.

[0036] By adding the steps of establishing the associated labels and placing feedback, the system can handle the cutting and stacking problems of the plates more intelligently; the system can automatically identify and handle cutting deviations, establish associated labels, and optimize the stacking layout according to the stacking procedure; this intelligent processing method helps to improve the flexibility and adaptability of the system and reduce the cost of manual intervention.

[0037] On the other hand, by adding the steps of establishing the associated tags and placing the feedback, it is convenient for the purchaser to reasonably use the boards with associated relationships, so as to make up for their own defects and reduce the expansion of defects.

[0038] Optionally, in the palletizing step, the stacking sequence is also optimized according to the cutting deviation and the offset position.

[0039] By adopting the above technical solution, in the palletizing step, the stacking order is optimized according to the cutting deviation and offset position, which can ensure that the plates are stacked in the best order during the palletizing process. This optimization helps to reduce palletizing errors caused by inconsistent plate sizes or cutting deviations, thereby improving palletizing efficiency.

[0040] By optimizing the stacking order, the system can arrange the position of the plates in the warehouse more reasonably; after adding the function of optimizing the stacking order, the system can dynamically adjust according to the actual situation of the plates. This flexibility helps the system adapt to different types of plates and different cutting deviations, and improves the versatility and adaptability of the system.

[0041] Optionally, in the palletizing step, it also includes: a same-layer deviation statistics step, a quantity judgment step, a sequence maintenance step, a position setting adjustment step and a palletizing execution step; Deviation statistics on the same layer: obtain the number of plates with cutting deviations on the same stacking layer, and record it as the number of deviations; Quantity judgment: judging whether the deviation quantity is greater than or equal to the second threshold value, if so, executing the sequence maintaining step, otherwise, executing the setting position adjustment step; Sequence retention: maintain the sequence set by the stacking program and execute the stacking execution steps; Set position adjustment: determine the stacking position of plates of the same specification according to the set stacking procedure, set the first weight of the plates according to the stacking position, determine the second weight according to the stacking order, and then calculate the stacking importance value according to the size of the deviation ratio and the degree of association between adjacent plates with complementary deviations, adjust the stacking order according to the stacking importance value, and then execute the stacking execution steps.

[0042] By adopting the above technical solution, by counting the number of plates with cutting deviations on the same stacking level, the stacking quality of the current level can be intuitively understood, and this step provides data support for subsequent judgments and adjustments; by judging whether the number of deviations reaches or exceeds the set second threshold, it can be decided whether the stacking order needs to be adjusted; when the number of deviations does not reach the second threshold, maintaining the original stacking order can maintain a high stacking efficiency and avoid production delays caused by frequent adjustments; when the number of deviations reaches or exceeds the second threshold, this step adjusts the stacking order by calculating the stacking importance value; this adjustment takes into account the specifications, stacking positions, stacking order and complementary relationships between adjacent plates of the plates, which helps to optimize the stacking quality and reduce space waste or structural instability caused by cutting deviations; it ensures that the decisions and adjustments of all previous steps are implemented; through precise stacking operations, it can be ensured that the plates remain neat and stable during the stacking process.

[0043] In summary, the present application includes at least one of the following beneficial technical effects: 1. Through precise grasping and adaptive adjustment, this method can ensure that the robot can accurately stack the plates to the specified position after grasping them; this helps to improve the efficiency of palletizing operations and reduce manual intervention and error rates; 2. Through precise stacking operations, it can be ensured that the plates remain neat and stable during the stacking process. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a flow chart of the palletizing method in Example 1 of the present application; Figure 2 is a sub-step flow chart of the offset distance calculation step in Example 2 of the present application; Figure 3 It is a sub-step flow chart of the plate specification feedback step in Example 2 of the present application; Figure 4 It is a flowchart of the associated tag establishment step and the placement feedback step in Example 2 of the present application; Figure 5 It is a sub-step flow chart of the palletizing step in Example 2 of the present application. DETAILED DESCRIPTION

[0045] The following combination Figures 1 to 5 This application is described in further detail.

[0046] This embodiment discloses a vision-based palletizing method.

[0047] Reference Figure 1 , the vision-based palletizing method includes the following steps: Information acquisition: Paste a QR code label on the board, and the QR code label must meet the following requirements: the four sides of the label are parallel or collinear with the corresponding sides of the board, and the offset between the center point of the label and the geometric center of the board is ≤2% of the length of the board. Obtain the QR code image on the top of the board and the board image; Specifically, QR code label pasting: paste the QR code label in the middle of the plate, ensuring that the four sides of the label are parallel or collinear with the corresponding sides of the plate; ensure that the offset between the center point of the label and the geometric center of the plate does not exceed 2% of the length of the plate.

[0048] Use a high-resolution industrial camera to shoot vertically from the top of the plate to obtain the QR code image on the top of the plate and the overall image of the plate. The camera should be fixed to ensure that the viewing angle is consistent each time.

[0049] Information extraction: From the top QR code label image and the plate image, obtain the physical boundary of the QR code label and its positional relationship with the plate edge, identify the information stored in the QR code label, and record it as specification data; Specifically, image processing algorithms (such as edge detection, contour extraction, etc.) are used to identify the physical boundaries of the QR code label and its positional relationship with the edge of the plate; the QR code decoding algorithm is used to read the information stored in the label, which usually includes the specifications and materials of the plate, and is recorded as specification data.

[0050] For example, through the image processing algorithm, the four corner points of the QR code label are identified, and then its boundary is determined. After decoding the QR code, the specifications of the board are obtained as 1000mm*500mm and the material is wood.

[0051] Offset calculation: Calculate the grab compensation angle based on the position deviation of the QR code edge ; Specifically, first, an image processing algorithm (such as a Canny edge detector, etc.) is used to identify the edge of the two-dimensional code label; then, the contour of the two-dimensional code label is obtained through a contour extraction algorithm (such as a Hough transform, etc.).

[0052] Definition of ideal position: The ideal position is usually defined as the relative position of the QR code label and the gripping side of the robot in the length direction, that is, the state that should be presented when the camera is photographed, such as completely horizontal, without tilt and located in the center of the image; in actual applications, the ideal position may vary according to the specific application scenario and requirements, and can be set according to self-needs, such as completely horizontal, biased to one side, and located in the center of the length of the plate.

[0053] Geometric transformation: Perform geometric transformation on the extracted QR code label outline, such as rotation and translation, to align it with the ideal position. The parameters of the geometric transformation (such as the rotation angle) are the compensation angles that need to be calculated. .

[0054] Angle calculation: Before or after geometric transformation, the compensation angle can be obtained by calculating the angle between a specific point of the contour (such as the center point, corner point, etc.) and the ideal position. , angle calculation usually involves vector operations and trigonometric functions. For example, assuming that we have obtained the outline of the QR code label through edge detection and contour extraction, and have determined the ideal position, the following is a simplified calculation formula for calculating the compensation angle : Calculate the contour center point: Assume that the contour consists of a series of points (x1, y1), (x2, y2), ..., (xn, yn).

[0055] The center point of the contour (Cx, Cy) can be obtained by calculating the average coordinates of all points: Cx=(x1+x2+...+xn) / n; Cy=(y1+y2+...+yn) / n; Calculate the ideal center point: The ideal center point (Ix, Iy) is defined according to the application scenario and requirements.

[0056] In many cases, the ideal center point may be the center point of the image or some predetermined position; Calculate the vector: The vector V from the contour center point (Cx, Cy) to the ideal center point (Ix, Iy) can be expressed as: V = (Ix-Cx, Iy-Cy); Calculate the angle: Assume there is a horizontal vector H = (1, 0), which represents the ideal non-tilt state.

[0057] The angle between vector V and vector H is the compensation angle It can be calculated by the following formula: θ=arctan2(Vy,Vx)-π / 2(If necessary, Adjust to the range of 0 to π); Where arctan2 is a variation of the inverse tangent function that accepts two arguments and returns the angle between them (in radians). Vx and Vy are the x and y components of vector V, respectively.

[0058] Adjust angle: Depending on the requirements of the application scenario, the calculated angle may need to be adjusted.

[0059] For example, if you need to rotate the QR code label to a completely horizontal position, you may need to Negate or perform other transformations.

[0060] Grasping adjustment: adjust the offset posture of the manipulator according to the grasping compensation angle so that the length direction of the grasping manipulator is parallel to the length direction of the plate; Specifically, according to the calculated compensation angle , adjust the posture of the robot. This is usually achieved through the robot's control system to ensure that the length of the robot is parallel to the length of the plate.

[0061] Grasping execution: The grasping action is executed according to the compensated posture, and the middle part of the plate is grasped during grasping; Specifically, the grasping position is determined according to the plate image and specification data, and the middle of the plate is usually selected as the grasping point to ensure stable grasping.

[0062] Execute grabbing action: control the robot to move to the grabbing position and execute the grabbing action.

[0063] Palletizing: According to the program settings, according to the specification data, execute the program settings and stack the grabbed boards to the stacking position.

[0064] Specifically, the stacking position is determined according to the program settings and specification data. This usually involves position calculation in three-dimensional space; the stacking action is performed: the robot arm is controlled to move the grasped sheet to the stacking position and then release the sheet.

[0065] This embodiment determines the position of the plate and the deflection angle of the plate and the robot arm through the angle between the QR code label and the plate, performs angle compensation, and achieves accurate grasping, which can reduce missed plates and insufficient plates, and facilitate the grasping of small plates. At the same time, it can meet the mixed stacking of large and small plates, reduce the occurrence of stacking, and improve work efficiency.

[0066] Example 2: Reference Figure 2 , which is different from Embodiment 1 in that, after the information extraction step, an offset distance calculation step is also provided; The offset distance calculation includes an edge extension step, an offset quantification step, and an intervention step; Edge extension: Get the edge of the QR code label from the top QR code label image, extend the edge of the QR code label, and extend it to the edge of the plate; Offset quantification: Calculate the maximum offset based on the edge inclination, the length of the plate, and the minimum distance between the edge of the QR code label and the edge of the plate; Intervention: Intervene in the palletizing step. When palletizing offset plates, adjust the angle so that the side with the largest offset contacts the already palletized plates first, and then execute the palletizing step.

[0067] Specifically, use image processing algorithms (such as edge detection, straight line fitting, etc.) to accurately obtain the edges of the QR code label from the top QR code label image, and then extend these edges until they intersect with the edge of the plate or reach a predetermined extension distance; the purpose of this step is to determine the relative position relationship between the QR code label and the edge of the plate; calculate the edge inclination (i.e., the angle between the edge extension line and the edge of the plate) based on the edge extension line obtained in the edge extension step; then, combine the length distance of the plate (i.e., the distance from the location of the QR code label to one end of the plate) and the minimum distance from the edge of the QR code label to the edge of the plate, and use geometric transformation and trigonometric functions to calculate the maximum offset. This maximum offset represents the degree of offset of the QR code label relative to the ideal position, which is equivalent to the maximum offset of the end of the plate compared with the correct grab after the QR code label is grabbed.

[0068] Before the palletizing step, the palletizing process is intervened according to the maximum offset calculated in the offset quantification step. For the offset plates, the gripping angle of the robot or the placement angle of the plates is adjusted during palletizing so that the side with the maximum offset first contacts the already stacked plates, and then the plates are gradually moved and adjusted for placement. This can reduce the problem of unstable palletizing or space waste caused by offset, and can reduce the pushing of other plates caused by stacking according to the standard gripping position, thereby reducing the possibility of stacking over.

[0069] Reference Figure 3 , in other embodiments, after the intervention step, a plate specification feedback step is also provided; Plate specification feedback: including size difference calculation step, size judgment step, second judgment step, feedback step, recording step, third judgment step, angle correction step, fourth judgment step, deviation correction step, fifth judgment step and size difference correction step; Calculation of size difference: Calculate the offset difference between the two sides according to the maximum offset between the two sides of the QR code label edge of the same plate in the offset quantification step; Size judgment: According to the offset difference on both sides and the specification width of the plate, it is judged whether there is a cutting deviation. If so, the second acquisition step is executed; Specifically, in the offset quantification step, the maximum offset between the two sides of the same plate and the edge of the QR code label has been calculated; in this step, we subtract these two offsets to obtain the offset difference on both sides; this difference reflects the deviation of the plate in the width direction due to inaccurate cutting or placement; based on the known plate specification width (such as the standard width is 1200mm) and the offset difference calculated in the previous step, we can determine whether there is a cutting deviation in the plate; if the offset difference exceeds the allowable range (set according to the process requirements), it is considered that there is a cutting deviation.

[0070] Second acquisition: obtaining the actual size specification of the current plate through the plate image, and obtaining the first deviation from the theoretical size specification; Second judgment: Calculate the ratio of cutting deviation to allowable deviation and record it as deviation ratio, and judge whether the deviation ratio is greater than or equal to the first threshold. If so, execute the feedback step, otherwise, execute the third judgment step; Specifically, when it is determined that there is a cutting deviation, the image of the plate is photographed again and image processing technology is used to obtain the actual size specification of the current plate; then, this actual size is compared with the theoretical size (i.e., the standard size) to obtain the first deviation; the ratio of the cutting deviation (i.e., the deviation determined in the size judgment step) to the allowable deviation (the maximum acceptable deviation set according to process requirements) is calculated and recorded as the deviation ratio; if the deviation ratio is greater than or equal to a set first threshold (e.g., 5%), and the first threshold is determined according to customer requirements, it is considered that the deviation is large and a feedback step needs to be executed.

[0071] Feedback: Feedback the cutting deviation to the cutting side, make cutting corrections, and execute the recording steps; Record: store the cutting deviation data in the QR code label; Specifically, the information of cutting deviation is fed back to the person in charge of the cutting equipment or the cutting process so that cutting correction can be made; at the same time, the recording step is executed to record and store the cutting deviation data in a QR code label for subsequent tracking and analysis; the cutting deviation data, plate number, time and other information are recorded using a database or file system, and the data is stored in a QR code label affixed to the plate to facilitate subsequent operations and tracking.

[0072] The third judgment: judging whether there is a plate at one end of the length direction of the plate, if so, executing the angle correction, otherwise, executing the fifth judgment step; Specifically, the edge extension line of the QR code label is extended based on the length direction of the plate to determine whether there is a plate below the length direction of the plate. If there is, it means that the plates are stacked during the process of conveying the plates after cutting, making the plate higher at one end than at the other end in the length direction of the placement plane, which will change the deflection angle between the QR code label and the plate. Therefore, the gripping compensation angle needs to be adjusted. Make corrections to ensure palletizing stability.

[0073] Angle correction: Compensation angle for grabbing Perform correction, and after the correction, perform a grasping adjustment step, and perform a fourth judgment step; Specifically, according to the result of the third judgment, the grasping compensation angle Make necessary corrections. During the correction, since the plate has thickness, after one end is padded, the side close to the placement plane will be exposed. By obtaining the exposed width, and then through geometric calculation, the deviation of the actual pasting angle between the QR code label and the plate is obtained. The corrected angle should be able to reduce the deviation and tilt of the plate during the stacking process and improve the stability of the stacking. After the correction, perform the grasping adjustment step and perform the grasping and placement operations according to the new angle.

[0074] Fifth judgment: judging whether there is a plate in the width direction of the plate, if so, executing the size difference correction step, otherwise, executing the fourth judgment step; Fourth judgment: judging whether the cutting deviation is the same as the first deviation, if so, executing the recording step, otherwise, executing the deviation correction step; Deviation correction: Calculate the average of the cutting deviation and the first deviation and record it as the cutting deviation, then perform the recording step.

[0075] Specifically, after the angle correction, it is determined again whether the cutting deviation is the same as the first deviation. If they are the same, it means that the correction is effective and the recording step can be performed; if they are different, it means that there may be other factors affecting the size of the plate, and the deviation correction step needs to be performed. By calculating the average of the first deviation and the cutting deviation, the error is reduced and the data accuracy is improved.

[0076] Size difference correction: intervene in the size difference calculation step, recalculate the size difference, and then execute the fourth judgment step.

[0077] Specifically, determine whether there is a plate on one side in the width direction of the plate. If so, it means that there are other plates under the plate during the plate conveying process, which makes the width direction of the photographed plate higher on one side and lower on the other side compared to the placement plane, which affects the acquisition of the size difference. Therefore, it is necessary to intervene in the size difference calculation step and recalculate the size difference.

[0078] Reference Figure 4 In other embodiments, after the recording step, it also includes an associated tag establishment step and a placement feedback step; Establishing associated labels: Record the plates with large cutting deviations, determine the location of the deviations, establish associated labels with adjacent cutting plates, and store them in QR code labels; Specifically, for the plates with large cutting deviations, the deviation position is recorded and determined. Then, a connection label is established with the adjacent cut plates. This label contains the relative position relationship and deviation information between the plates, where the relative position relationship includes the deviation of the plate and the corresponding deviation of the adjacent plates. This information is stored in the QR code label for subsequent tracking and analysis. At the same time, it is convenient for the plate purchaser to arrange the arrangement and use of the plates according to needs.

[0079] Placement feedback: Determine the connection between the panels based on the contact tags, and determine the stacking position based on the stacking procedure. Associate the stacking position with the contact tags and store them in the QR code tags.

[0080] Specifically, the connection and relative position between the plates are determined based on the information in the contact tag; then, the stacking position of the plates is determined according to the requirements of the stacking program. The stacking position is associated with the contact tag and stored in the QR code tag; in the subsequent stacking process, the stacking strategy can be optimized and the stacking efficiency can be improved based on the tag information.

[0081] In other embodiments, the stacking step further includes optimizing the stacking sequence according to the cutting deviation and the offset position.

[0082] Reference Figure 5 In other embodiments, in the palletizing step, it also includes: a same-layer deviation statistics step, a quantity judgment step, a sequence maintenance step, a position setting adjustment step and a stacking execution step; Deviation statistics on the same layer: obtain the number of plates with cutting deviations on the same stacking layer, and record it as the number of deviations; Quantity judgment: judging whether the deviation quantity is greater than or equal to the second threshold value, if so, executing the sequence maintaining step, otherwise, executing the setting position adjustment step; Sequence retention: maintain the sequence set by the stacking program and execute the stacking execution steps; Set position adjustment: determine the stacking position of plates of the same specification according to the set stacking procedure, set the first weight of the plates according to the stacking position, determine the second weight according to the stacking order, and then calculate the stacking importance value according to the size of the deviation ratio and the degree of association between adjacent plates with complementary deviations, adjust the stacking order according to the stacking importance value, and then execute the stacking execution steps.

[0083] Specifically, by obtaining information of all plates stacked on the same stacking level, the number of plates with cutting deviations is counted, wherein the cutting deviation may include size deviation, shape deviation or position deviation, etc., and the present embodiment is preferably size deviation, the number of plates with size deviations on the same level is counted, and according to a preset second threshold, it is determined whether the number of deviations has reached a critical value that requires adjustment of the stacking order, wherein the second threshold is determined according to the area of ​​the stacking level and the total number of stackings; if the number of deviations is greater than or equal to the second threshold, it means that the deviation is more serious, and the original stacking order needs to be maintained to reduce the overall impact; if the number of deviations is less than the second threshold, it means that the deviation is less serious, and the stacking effect can be optimized by adjusting the stacking position; when the number of deviations is greater than or equal to the second threshold, the system will maintain the order set by the original stacking program unchanged, and directly execute the stacking execution step. This is done to avoid greater deviations or confusion that may be caused by adjusting the order; when the number of deviations is less than the second threshold, the system will determine the stacking position of plates of the same specification according to the set stacking program, and set the first weight and the second weight for each plate according to the stacking position and stacking order. Then, the system will calculate the stacking importance value of each plate according to the size of the deviation ratio and the degree of correlation between adjacent plates with complementary deviations. Finally, the stacking order will be adjusted according to the stacking importance value to optimize the stacking effect.

[0084] After determining the final stacking order and position, the system will control actuators such as palletizing robots or conveyor belts to stack the plates at the designated location according to the adjusted order and position.

[0085] in, The calculation model for expressing the importance of stacking is as follows: ; Among them, the important values ​​are placed. Indicates the number of the current plate. Indicates the plate number adjacent to the current plate. It is the weight coefficient set according to the stacking position. It is the weight coefficient set according to the stacking order. is the correlation coefficient between adjacent plates (can be set according to actual conditions, such as when they are adjacent and have the same specifications, the correlation is higher). Is numbered Deviation ratio of the plate, Number The deviation ratio of the plate, deviation ratio = cutting deviation / allowable deviation.

[0086] The calculation of the compensation angle can be based on the specific type and degree of deviation. For example, for dimensional deviation, the compensation angle can be calculated based on the size and direction of the deviation; for shape deviation, the compensation angle can be calculated based on the shape characteristics of the deviation. At the same time, the degree of correlation between adjacent plates needs to be considered to ensure that the adjusted stacking effect is more stable.

[0087] The above are all preferred embodiments of the present application, and the protection scope of the present application is not limited thereto. Therefore, any equivalent changes made according to the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A vision-based palletizing method, characterized in that: The following steps are involved: Information acquisition: Get the QR code image on the top of the plate and the plate image; Information extraction: From the top QR code label image and the plate image, obtain the physical boundary of the QR code label and its positional relationship with the plate edge; Offset calculation: Calculate the grabbing compensation angle based on the posture deviation of the QR code edge; Grasping adjustment: adjust the offset posture of the manipulator according to the grasping compensation angle so that the length direction of the grasping manipulator is parallel to the length direction of the plate; Grasp execution: Execute the grasping action according to the compensated posture; Palletizing: According to the program settings, the grabbed boards are stacked at the stacking position.

2. The vision-based palletizing method according to claim 1, characterized in that: In the information extraction step, it also includes identifying the QR code information and recording it as specification data; The palletizing step also includes palletizing at the position set by the program according to the specification data.

3. The vision-based palletizing method according to claim 1, characterized in that: The affixing of the QR code label satisfies: The four sides of the label should be parallel or collinear with the corresponding sides of the plate; The offset between the center point of the label and the geometric center of the plate is ≤ 2% of the plate length.

4. The vision-based palletizing method according to claim 1, characterized in that: In the grasping execution step, the middle of the plate is grasped.

5. The vision-based palletizing method according to any one of claims 1 to 4, characterized in that: After the information extraction step, an offset distance calculation step is also provided; The offset distance calculation includes an edge extension step, an offset quantification step, and an intervention step; Edge extension: Get the edge of the QR code label from the top QR code label image, extend the edge of the QR code label, and extend it to the edge of the plate; Offset quantification: Calculate the maximum offset based on the edge inclination, the length of the plate, and the minimum distance between the edge of the QR code label and the edge of the plate; Intervention: Intervene in the palletizing step. When palletizing offset plates, adjust the angle so that the side with the largest offset contacts the already palletized plates first, and then execute the palletizing step.

6. The vision-based palletizing method according to claim 5, characterized in that: After the intervention step, there is also a board specification feedback step; Plate specification feedback: including size difference calculation step, size judgment step, second judgment step, feedback step, recording step, third judgment step, angle correction step, fourth judgment step and deviation correction step; Calculation of size difference: Calculate the offset difference between the two sides according to the maximum offset between the two sides of the QR code label edge of the same plate in the offset quantification step; Size judgment: According to the offset difference on both sides and the specification width of the plate, it is judged whether there is a cutting deviation. If so, the second acquisition step is executed; Second acquisition: obtaining the actual size specification of the current plate through the plate image, and obtaining the first deviation from the theoretical size specification; Second judgment: Calculate the ratio of cutting deviation to allowable deviation and record it as deviation ratio, and judge whether the deviation ratio is greater than or equal to the first threshold. If so, execute the feedback step, otherwise, execute the third judgment step; Feedback: Feedback the cutting deviation to the cutting side, make cutting corrections, and execute the recording steps; Record: store the cutting deviation data in the QR code label; The third judgment: judging whether there is a plate at one end of the length direction of the plate, if so, executing the angle correction, otherwise, executing the fourth judgment step; Angle correction: correct the grabbing compensation angle, execute the grabbing adjustment step after correction, and execute the fourth judgment step; Fourth judgment: judging whether the cutting deviation is the same as the first deviation, if so, executing the recording step, otherwise, executing the deviation correction step; Deviation correction: Calculate the average of the cutting deviation and the first deviation and record it as the cutting deviation, then perform the recording step.

7. The vision-based palletizing method according to claim 6, characterized in that: Between the third judging step and the fourth judging step, a fifth judging step and a size difference correction step are also provided; Fifth judgment: judging whether there is a plate on one side of the plate width direction, if yes, executing the size difference correction step, otherwise, executing the fourth judgment step; Size difference correction: intervene in the size difference calculation step, recalculate the size difference, and then execute the fourth judgment step.

8. The vision-based palletizing method according to claim 6, characterized in that: After the recording step, there are also steps of establishing associated tags and placing feedback; Establishing associated labels: Record the plates with large cutting deviations, determine the location of the deviations, establish associated labels with adjacent cutting plates, and store them in QR code labels; Placement feedback: Determine the connection between the panels based on the contact tags, and determine the stacking position based on the stacking procedure. Associate the stacking position with the contact tags and store them in the QR code tags.

9. The vision-based palletizing method according to claim 6, characterized in that: The palletizing step also includes optimizing the stacking sequence based on cutting deviation and offset position.

10. The vision-based palletizing method according to claim 9, characterized in that: The palletizing step also includes: a same-layer deviation counting step, a quantity judging step, a sequence keeping step, a position setting adjustment step and a palletizing execution step; Deviation statistics on the same layer: obtain the number of plates with cutting deviations on the same stacking layer, and record it as the number of deviations; Quantity judgment: judging whether the deviation quantity is greater than or equal to the second threshold value, if so, executing the sequence maintaining step, otherwise, executing the setting position adjustment step; Sequence retention: maintain the sequence set by the stacking program and execute the stacking execution steps; Set position adjustment: determine the stacking position of plates of the same specification according to the set stacking procedure, set the first weight of the plates according to the stacking position, determine the second weight according to the stacking order, and then calculate the stacking importance value according to the size of the deviation ratio and the degree of association between adjacent plates with complementary deviations, adjust the stacking order according to the stacking importance value, and then execute the stacking execution steps.

Images