Unstacking and stacking method and system suitable for cigarette boxes and electronic equipment

Abstract

The invention relates to an unstacking and stacking method and system and electronic device.The method is applied to the unstacking and stacking system, the unstacking and stacking system comprises a robot and a control module, the method is specifically applied to the control module, and the method comprises the steps that request information which is sent by the robot and comprises a target stack type serial number is received, a target point location is determined from a preset mapping relation based on the target stack type serial number, the preset mapping relation is a mapping relation between a pre-obtained stack type serial number and a point location, and the target point location comprises a grabbing point location and a placing point location; and according to a preset rule, a target path of the target point location is generated through a path planning algorithm, and the target point location and the target path are sent to the robot, so that the robot moves the part box from the grabbing point location to the placing point location based on the target path.

Description

Technical Field

[0001] The present application relates to the field of depalletizing and palletizing, and in particular, to a depalletizing and palletizing method, system and electronic device applicable to cigarette boxes. Background Art

[0002] In the traditional manual handling and palletizing process, every time a new product specification is added, engineers need to go to the factory for debugging, which is time-consuming and laborious. With the rapid development of production technology, various palletizing systems and depalletizing systems have emerged on the market.

[0003] Most of the existing depalletizing systems and palletizing systems are based on the feedback of sensors by PLC, and the motion path is formed by teaching and recording fixed points of the robot. This method requires engineers to debug, and often cannot quickly switch packages of different sizes, dimensions, and materials, and does not support quickly adapting to new cigarette box pallet types.

[0004] The automation degree of the existing depalletizing and palletizing systems is not high, and they can only be targeted at a single product specification and cannot adapt to new pallet types. Summary of the Invention

[0005] Embodiments of the present application provide a depalletizing and palletizing method, system and electronic device applicable to cigarette boxes, so as to at least solve the problem in the related art that the automation degree is not high, and it can only be targeted at a single product specification and cannot adapt to new pallet types.

[0006] In a first aspect, an embodiment of the present application provides a depalletizing and palletizing method applicable to cigarette boxes. The method is applied to a depalletizing and palletizing system, and the depalletizing and palletizing system includes a robot and a control module. The method is specifically applied to the control module, and the method includes:

[0007] Receiving request information including a target pallet type serial number sent by the robot, and determining a target point based on the target pallet type serial number from a preset mapping relationship. The preset mapping relationship is a mapping relationship between the pallet type serial number and the point obtained in advance, and the target point includes a grasping point and a placing point;

[0008] Generating a target path of the target point through a path planning algorithm according to a preset rule, and sending the target point and the target path to the robot, so that the robot moves the case from the grasping point to the placing point based on the target path.

[0009] In an embodiment, the mapping relationship between the pallet type serial number and the point is obtained by the following method:

[0010] Obtaining case parameters and pallet type parameters, and generating an initial point based on the case parameters and the pallet type parameters. The pallet type parameters include a pallet type serial number;

[0011] Filter the initial points based on preset filtering conditions, and perform secondary filtering on the filtered points through collision prediction to obtain the final points.

[0012] In one embodiment, the case parameters include the length, width, and height of the case. Generating the initial points based on the case parameters and the stack shape parameters includes:

[0013] (x,y,z) = (nl,(k - 1)w,(k - 1)h) when k is odd

[0014] when k is even

[0015] where k represents the k-th layer of cases from low to high, (x, y, z) represents the point coordinates of the case, l represents the length of the case, w represents the width of the case, h represents the height of the case, and n represents the n-th case in the x-axis coordinate direction.

[0016] In one embodiment, when the work task is palletizing, generating the target path of the target points according to the preset rules through the path planning algorithm includes:

[0017] Generate the target path of the target points through the path planning algorithm according to the rule from far to near, so that the robot can grasp the cases based on the target path and place them on the tray at the placement point from far to near.

[0018] In one embodiment, when the work task is depalletizing, generating the target path of the target points according to the preset rules through the path planning algorithm includes:

[0019] Generate the target path of the target points through the path planning algorithm according to the rule from near to far, so that the robot can grasp the cases from near to far based on the target path and place them on the de-stacking roller line at the placement point.

[0020] In one embodiment, the palletizing and depalletizing system further includes an image acquisition device. When the work task is depalletizing, the method further includes:

[0021] In response to receiving the stack shape information sent by the robot, control the image acquisition device to acquire a stack shape image, where the stack shape image includes a depth image and an RGB image;

[0022] Segment the stack shape based on the stack shape image and the image segmentation algorithm, and obtain the first grasping pose based on the segmentation result and the suction cup parameters;

[0023] Filter the first grasping pose based on a preset screening rule and a collision prediction method to obtain a second grasping pose;

[0024] Send the second grasping pose to the robot for the robot to grasp the case based on the second grasping pose.

[0025] In one embodiment, a suction cup is provided on the robot in the palletizing and depalletizing system. When the work task is depalletizing, based on the stack type image and the image segmentation algorithm to segment the stack type, and based on the segmentation result and the suction cup parameters to obtain the first grasping pose, including:

[0026] Based on the depth image and the RGB image, obtain the highest plane area on the RGB image, and segment the highest plane area to obtain the case segmentation result;

[0027] Based on the pre-acquired relationship matrix, convert the coordinates of the case segmentation result to the robot coordinate system, and sort the segmented rectangular units based on the preset depalletizing direction and the case segmentation result;

[0028] Traverse the rectangular units in the order, and determine the first grasping pose according to the rectangular units and the parameters of the suction cup.

[0029] In a second aspect, an embodiment of the present application provides a palletizing and depalletizing system applicable to cigarette cases. The system includes a robot and a control module, and the system includes:

[0030] Point position determination module: used to receive the request information including the target stack type serial number sent by the robot, and determine the target point position from the preset mapping relationship. The preset mapping relationship is the mapping relationship between the stack type serial number and the point position pre-acquired, and the target point position includes the grasping point position and the placing point position;

[0031] Grasping module: used to generate the target path of the target point position through the path planning algorithm according to the preset rules, and send the target point position and the target path to the robot for the robot to move the case from the grasping point position to the placing point position based on the target path.

[0032] In a third aspect, an embodiment of the present application provides a palletizing and depalletizing device applicable to cigarette cases. The device is used to implement the palletizing and depalletizing method applicable to cigarette cases described in the first aspect. The device includes a robot, an image acquisition device, a fixture device and a control module,

[0033] The image acquisition device is fixed on the ceiling or bracket directly above the pallet, and is used to photograph the cigarette cases placed on the pallet and send the photographed image to the control module;

[0034] The fixture device is installed on the robot, and the fixture device is used to clamp and place the case;

[0035] The robot is used to control the fixture device to achieve palletizing and depalletizing.

[0036] In a fourth aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, it implements the method for palletizing and depalletizing suitable for cigarette boxes as described in the first aspect above.

[0037] The method for palletizing and depalletizing suitable for cigarette boxes, system, and electronic device provided by the embodiments of the present application have at least the following technical effects.

[0038] In summary, the method for palletizing and depalletizing suitable for cigarette boxes provided by the present application can customize any pallet type, solving the problem that the prior art can only target a single product specification. By customizing and developing various requirements and logical needs through a human-computer interaction method, the scalability of the method is improved. Moreover, by using a robot for palletizing and depalletizing work, the safety of the working environment and the process stability are improved, and human resources are saved.

[0039] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more concise and understandable. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings described herein are used to provide a further understanding of the present application and form a part of the present application. The illustrative embodiments and descriptions thereof of the present application are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0041] Figure 1 is a flowchart of a method for palletizing and depalletizing suitable for cigarette boxes shown according to an embodiment of the present application;

[0042] Figure 2 is a schematic diagram of a pallet type generated according to an exemplary embodiment;

[0043] Figure 3 is a timing diagram of a pallet type shown according to an exemplary embodiment;

[0044] Figure 4 is a timing diagram of a pallet type shown according to another exemplary embodiment;

[0045] Figure 5 is a flowchart of a method for palletizing and depalletizing shown according to an exemplary embodiment;

[0046] Figure 6 is a schematic diagram of a pallet type shown according to an exemplary embodiment;

[0047] Figure 7It is a schematic diagram of camera point cloud shown according to an exemplary embodiment;

[0048] Figure 8 It is a schematic diagram of a segmentation process shown according to an exemplary embodiment;

[0049] Figure 9 It is a schematic diagram of the highest plane area of RGB shown according to an exemplary embodiment;

[0050] Figure 10 It is a schematic diagram of a segmentation result shown according to an exemplary embodiment;

[0051] Figure 11 It is a structural block diagram of a depalletizing and palletizing system applicable to cigarette boxes shown according to an exemplary embodiment;

[0052] Figure 12 It is a schematic structural diagram of a device applicable to a depalletizing and palletizing device for cigarette boxes shown according to an embodiment of the present application;

[0053] Figure 13 It is a schematic structural diagram of a fixture device shown according to an exemplary embodiment;

[0054] Figure 14 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0055] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be described and explained below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. Based on the embodiments provided by the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0056] Obviously, the accompanying drawings in the following description are only some examples or embodiments of the present application. For those of ordinary skill in the art, without creative efforts, the present application can also be applied to other similar scenarios based on these drawings. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for those of ordinary skill in the art related to the content disclosed in the present application, some design, manufacturing or production changes based on the technical content disclosed in the present application are only conventional technical means and should not be understood that the content disclosed in the present application is insufficient.

[0057] References to "embodiments" in this application mean that specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of this application. The phrase appearing in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0058] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the ordinary meanings understood by those of ordinary skill in the technical field to which this application belongs. The words such as "a", "an", "one kind", "the" and the like involved in this application do not represent a limitation in quantity and can represent a singular or plural number. The terms "include", "comprise", "have" and any variations thereof involved in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may further include unlisted steps or units, or may further include other steps or units inherent to these processes, methods, products or devices. The terms "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" involved in this application means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific order for the objects.

[0059] Continue to refer to Figure 1 , step S102 is executed after step S101, specifically as follows.

[0060] In a first aspect, an embodiment of this application provides a method for disassembling and palletizing a cigarette box, which is applied to a disassembling and palletizing system. The disassembling and palletizing system includes a robot and a control module, and the method is specifically applied to the control module.

[0061] Optionally, the depalletizing system includes a robot, an image acquisition device, a fixture device, and a control module. Among them, the robot can be a 6-axis industrial robot. The robot model used in this application is ABB IRB 6700-150 / 3.2, which can be replaced by any robot with the same load and arm span. The image acquisition device is installed on the ceiling or a bracket to take pictures and position the cigarette boxes on the pallet, so as to realize the depalletizing work of multi-size materials. The control module includes an internal PLC and an industrial computer (equipped with a professional graphics card). The PLC receives signals, and the industrial computer processes palletizing algorithms, camera data, vision algorithms, etc. The fixture needs to be equipped with a single-side suction auxiliary device to ensure the stability of auxiliary clamping. The fixture device mainly includes suction cups, solenoid valves, single-side suction side-turning mechanisms, pneumatic components, etc., and can grab 1 to 4 piece boxes at a time.

[0062] Figure 1 is a flowchart of a depalletizing method applicable to cigarette boxes shown according to an embodiment of the present application, as Figure 1 shown, the method includes:

[0063] Step S101, receive the request information including the target pallet type serial number sent by the robot, and determine the target point positions based on the target pallet type serial number from the preset mapping relationship. The preset mapping relationship is the mapping relationship between the pallet type serial number and the point positions obtained in advance. The target point positions include the grasping point position and the placing point position.

[0064] Optionally, when the work station starts to work, a work task to be performed is generated by sending a signal to the feeding equipment. The work includes a palletizing task and a stacking task. When the work task is a palletizing task, the pallet group is transported to the incoming empty pallet group position by manual or an Automated Guided Vehicle (AGV), and the robotic arm grabs an empty pallet and places it at the palletizing position. The piece cigarettes are transported to the palletizing material taking work station by the conveyor line, and the robot requests the point positions from the upper computer through the pallet type serial number sent by the PLC.

[0065] In one example, the mapping relationship between the pallet type serial number and the point positions in step S101 is obtained in the following manner:

[0066] Step S1021, obtain the piece box parameters and the pallet shape parameters, and generate the initial point positions based on the piece box parameters and the pallet shape parameters. The pallet shape parameters include the pallet type serial number.

[0067] Optionally, the piece box parameters include the length, width, height, serial number, and name of the piece box, and the pallet shape parameters include the length, width, height, and pallet type serial number of the pallet shape. The point positions are determined by the piece box parameters and the pallet shape parameters input through the front-end software.

[0068] In one example, the piece box parameters include the length, width, and height of the piece box, and step S1021 includes:

[0069] (x, y, z) = (nl, (k - 1)w, (k - 1)h), where k is odd

[0070] k is even

[0071] Among them, k represents the k-th layer of bins from low to high, (x, y, z) represents the position coordinates of the bin, l represents the length of the bin, w represents the width of the bin, h represents the height of the bin, and n represents the n-th bin in the x-axis coordinate direction. Optionally, among them L represents the length of the pallet, and l represents the length of the bin represents taking the integer part downwards. Figure 2 is a schematic diagram of a stacking pattern shown according to an exemplary embodiment. Figure 3 is a timing diagram of a stacking pattern shown according to an exemplary embodiment. Figure 4 is a timing diagram of a stacking pattern shown according to another exemplary embodiment.

[0072] Step S1022, filter the initial positions based on preset filtering conditions, and perform secondary filtering on the filtered positions through collision prediction to obtain the final positions.

[0073] Optionally, the preset filtering conditions include the length and width of the suction cup, the spacing between stacking patterns, the unpacking or stacking order, the incoming material area, etc. Among them, (1) Suction cup length and width filtering: Determine the effective grasping points according to the preset length and width of the suction cup. When the size of the suction cup does not match the bin or the stacking pattern, filter this position. (2) Stacking pattern spacing filtering: There are certain spacing requirements between stacking patterns. The back-end algorithm will filter out the grasping points that violate the spacing limit based on the input stacking pattern size and the set spacing parameters. (3) Unpacking / stacking order: Screen according to the unpacking / stacking order to optimize the efficiency and accuracy of unpacking the stack. (4) Incoming material area: Consider the area where the robot receives the incoming material. For example, the robot cannot grasp items from places outside this area.

[0074] Perform collision prediction on the filtered positions to ensure that the robot will not collide with the surrounding environment (such as walls, equipment, other objects, etc.) during the grasping process. If a certain grasping posture will cause the robot to collide with other objects, filter this posture. Further, select the optimal posture from the postures filtered by collision prediction as the grasping posture. At the same time, calculate the number of bins to be grasped corresponding to the optimal grasping posture as the quantitative result of the completion degree of the unpacking and stacking tasks. Among them, the quality of the grasping posture is determined according to evaluation criteria such as grasping stability and unpacking efficiency. The grasping posture includes position information, and save the stacking pattern and the corresponding position file in the specified directory. In this way, any stacking pattern can be customized, solving the problem that the prior art can only target a single product specification, and at the same time avoiding collisions and operation errors through the collision prediction algorithm.

[0075] Continue to refer to Figure 1, step S102 is executed after step S101.

[0076] Step S102: Generate a target path for the target point by means of a path planning algorithm according to a preset rule, and send the target point and the target path to the robot, so that the robot moves the part box from the grasping point to the placing point based on the target path.

[0077] Optionally, generate a target path through path planning algorithms such as the A* algorithm, Dijkstra algorithm, greedy algorithm, and artificial potential field method. Send the target point and the target path to the robot side through the SOCKET communication protocol to guide the robot to perform the palletizing and depalletizing tasks. Figure 5 It is a flowchart of a palletizing and depalletizing method shown according to an exemplary embodiment.

[0078] In one example, when the work task is palletizing, step S102 includes: generating a target path for the target point by means of a path planning algorithm according to the rule from far to near, so that the robot grasps the part box and places it on the pallet at the placing point from far to near based on the target path.

[0079] In one example, when the work task is depalletizing, step S102 includes: generating a target path for the target point by means of a path planning algorithm according to the rule from near to far, so that the robot grasps the part box from near to far and places it on the discharging roller line at the placing point based on the target path.

[0080] In this way, various requirements and logical requirements can be customized and developed through the human-machine interaction method, improving the scalability of the method. And by using the robot for palletizing and depalletizing work, the safety of the working environment and the process stability are improved, and human resources are saved.

[0081] In one example, the palletizing and depalletizing system further includes an image acquisition device. When the work task is depalletizing, the method further includes:

[0082] Step S301: In response to receiving the stack type information sent by the robot, control the image acquisition device to acquire a stack type image, and the stack type image includes a depth image and an RGB image.

[0083] Optionally, the robot sends the stack type sent by the PLC to the upper computer. After the upper computer responds, it retrieves the prior size of the product specification, and then triggers the image acquisition device to acquire a stack type image. Among them, the image acquisition device is a 3D camera. Figure 6 It is a stack type schematic diagram shown according to an exemplary embodiment. Figure 7 It is a camera point cloud schematic diagram shown according to an exemplary embodiment.

[0084] Step S302: Segment the stack type based on the stack type image and the image segmentation algorithm, and obtain the first grasping pose based on the segmentation result and the suction cup parameters.

[0085] In one example, a suction cup is provided on the robot in the palletizing and depalletizing system. Step S302 includes:

[0086] Step S3021: Obtain the highest plane area on the RGB image based on the depth image and the RGB image, and segment the highest plane area to obtain the part box segmentation result.

[0087] Optionally, filter the depth image through the ROI candidate box, and eliminate the noise in the image through the denoising algorithm to ensure that the extracted plane data is more accurate. Extract the highest plane area of the stack through plane fitting. Figure 8 FIG. is a schematic diagram of a segmentation process shown according to an exemplary embodiment. Through the binocular relationship between the depth image and the RGB image, the highest plane area on the RGB image is obtained. Figure 9 FIG. is a schematic diagram of the RGB highest plane area shown according to an exemplary embodiment. Through algorithms such as edge extraction, deep learning instance segmentation, corner detection, and rectangle detection on the highest plane area of the RGB image, the rectangular segmentation result of the part box is obtained. Figure 10 FIG. is a schematic diagram of a segmentation result shown according to an exemplary embodiment.

[0088] Step S3022: Convert the coordinates of the part box segmentation result to the robot coordinate system based on the pre-acquired relationship matrix, and sort the segmented rectangular units based on the preset depalletizing direction and the part box segmentation result.

[0089] Optionally, based on the pre-acquired calibration matrix between the camera and the robot, convert the coordinates in the image to the actual coordinates in the robot base coordinate system, so as to directly guide the robot to perform the grasping task according to the coordinates. According to the depalletizing direction and task requirements, sort the recognized rectangular results to determine the grasping order.

[0090] Step S3023: Traverse the rectangular units in order, and determine the first grasping pose according to the parameters of the rectangular unit and the suction cup.

[0091] Optionally, generate a series of possible grasping poses based on the rectangular features (such as size, direction, etc.) of the part box. Judge the feasibility of each grasping position according to the rectangular features (such as suction cup size, shape, etc.) of the suction cup.

[0092] Step S303: Screen the first grasping pose based on the preset screening rules and the collision prediction method to obtain the second grasping pose.

[0093] Optionally, the preset filtering conditions include the length and width of the suction cup, the spacing between stack types, the order of unpacking or stacking, the incoming material area, etc. Among them, (1) Suction cup length and width filtering: Determine the effective grasping points according to the preset length and width of the suction cup. When the size of the suction cup does not match the case or stack type, filter this point position. (2) Stack type spacing filtering: There are certain spacing requirements between stack types. The backend algorithm will filter out the grasping points that violate the spacing limit based on the input stack type size and the set spacing parameters. (3) Unpacking and stacking order: Screen according to the unpacking and stacking order to optimize the efficiency and accuracy of unstacking. (4) Incoming material area: Consider the area where the robot receives the incoming materials. For example, the robot cannot grasp items from places outside this area.

[0094] Perform collision prediction on the filtered point positions to ensure that the robot will not collide with the surrounding environment (such as walls, equipment, other objects, etc.) during the grasping process. If a certain grasping posture will cause the robot to collide with other objects, filter this posture. Further, select the optimal posture from the postures filtered by the collision prediction as the grasping posture. At the same time, calculate the number of cases to be grasped corresponding to the optimal grasping posture as the quantitative result of the completion degree of the unstacking and stacking tasks. Among them, determine the quality of the grasping posture according to evaluation criteria such as grasping stability and unstacking efficiency. The grasping posture includes point position information.

[0095] Step S304: Send the second grasping posture to the robot for the robot to grasp the case based on the second grasping posture.

[0096] Optionally, generate the target path through path planning algorithms such as the A* algorithm, Dijkstra algorithm, greedy algorithm, and artificial potential field method. Send the target point position and the target path to the robot side through the SOCKET communication protocol to guide the robot to perform unstacking.

[0097] In this way, through the cooperation of the camera and the robot, the efficiency of unstacking and stacking is improved and the operation difficulty is reduced. Moreover, there is no limit on the size and specification of the materials, making up for the shortcomings of the traditional method that can only handle a single product specification, as well as the problems such as inability to unstack inverted cases and inclined cases. Accurately identify any stack type through the vision algorithm, which is beneficial to the segmentation processing of the image, thereby improving the unstacking efficiency and accuracy. And integrate devices such as the control module, high-precision camera, robot, and suction cup together, and cooperate with each other for collaborative operation, with simple operation.

[0098] In summary, the unpacking and palletizing method for cigarette boxes provided by this application integrates devices such as a control module, a high-precision camera, a robot, and a suction cup, which cooperate with each other to perform operations. The operation is simple. Any pallet type can be customized, solving the problem in the prior art that it can only be applied to a single product specification. At the same time, collision prediction algorithms are used to avoid collisions and operation errors. Various requirements and logical needs are customized and developed through a human-computer interaction method, improving the scalability of the method. And the unpacking and palletizing work is carried out by a robot, improving the safety of the working environment and the process stability, and saving human resources. By the cooperation of the camera and the robot, the efficiency of unpacking and palletizing is improved and the operation difficulty is reduced, making up for the shortcomings of the traditional method that can only handle a single product specification, as well as the problems that unpacking cannot be carried out for inverted boxes, inclined boxes, etc. The visual algorithm can accurately identify any pallet type, which is beneficial to image segmentation processing, thereby improving the unpacking efficiency and accuracy.

[0099] In a second aspect, an embodiment of this application provides an unpacking and palletizing system for cigarette boxes, and the system includes a robot and a control module. Figure 11 It is a structural block diagram of an unpacking and palletizing system for cigarette boxes shown according to an exemplary embodiment, as Figure 11 shown, the system includes:

[0100] Point position determination module 100: configured to receive request information including a target pallet type serial number sent by the robot, and determine a target point position from a preset mapping relationship based on the target pallet type serial number. The preset mapping relationship is a mapping relationship between the pallet type serial number and the point position obtained in advance, and the target point position includes a grasping point position and a placing point position.

[0101] Grasping module 200: configured to generate a target path of the target point position through a path planning algorithm according to a preset rule, and send the target point position and the target path to the robot, so that the robot moves the piece box from the grasping point position to the placing point position based on the target path.

[0102] In one example, the mapping relationship between the pallet type serial number and the point position in the point position determination module 100 is obtained through the following method:

[0103] Obtain the piece box parameters and the pallet shape parameters, and generate an initial point position based on the piece box parameters and the pallet shape parameters. The pallet shape parameters include the pallet type serial number.

[0104] Filter the initial point position based on a preset filtering condition, and perform secondary filtering on the filtered point position through collision prediction to obtain the final point position.

[0105] In one example, the piece box parameters include the length, width, and height of the piece box, and the point position determination module 100 includes:

[0106] (x,y,z)=(nl,(k - 1)w,(k - 1)h) k is odd

[0107] k is an even number

[0108] Wherein, k represents the k-th layer of bins from low to high, (x, y, z) represents the position coordinates of the bin, l represents the length of the bin, w represents the width of the bin, h represents the height of the bin, and n represents the n-th bin in the x-axis coordinate direction.

[0109] In one example, when the work task is palletizing, the grasping module 200 includes: generating a target path of the target position through a path planning algorithm according to the rule from far to near, so that the robot can grasp the bins from far to near and place them on the tray at the placement position based on the target path.

[0110] In one example, when the work task is depalletizing, the grasping module 200 includes: generating a target path of the target position through a path planning algorithm according to the rule from near to far, so that the robot can grasp the bins from near to far and place them on the de-stacking roller conveyor line at the placement position based on the target path.

[0111] In one example, the de-palletizing and palletizing system further includes an image acquisition device. When the work task is depalletizing, the system further includes:

[0112] Image unit: for controlling the image acquisition device to acquire a stack type image in response to receiving the stack type information sent by the robot. The stack type image includes a depth image and an RGB image.

[0113] First pose unit: for segmenting the stack type based on the stack type image and an image segmentation algorithm, and obtaining a first grasping pose based on the segmentation result and the sucker parameters.

[0114] Second pose unit: for screening the first grasping pose based on a preset screening rule and a collision prediction method to obtain a second grasping pose.

[0115] Grasping unit: for sending the second grasping pose to the robot, so that the robot can grasp the bins based on the second grasping pose.

[0116] In one example, a sucker is provided on the robot in the de-palletizing and palletizing system. When the work task is depalletizing, the first pose unit includes:

[0117] For obtaining the highest plane area on the RGB image based on the depth image and the RGB image, and segmenting the highest plane area to obtain a bin segmentation result.

[0118] Converting the coordinates of the bin segmentation result to the robot coordinate system based on a pre-acquired relationship matrix, and sorting the segmented rectangular units based on a preset depalletizing direction and the bin segmentation result.

[0119] Traverse the rectangular units in sequence, and determine the first grasping pose according to the parameters of the rectangular units and the suction cups.

[0120] In summary, the present application integrates devices such as a control module, a high-precision camera, a robot, and suction cups, and they cooperate with each other to perform collaborative operations, with simple operations. Any stack type can be customized, solving the problem that the prior art can only target a single product specification. At the same time, collision prediction algorithms are used to avoid collisions and operation errors. Various requirements and logical needs are customized and developed through a human-computer interaction method, improving the scalability of the method. And the robot is used for palletizing and depalletizing operations, improving the safety of the working environment and the process stability, and saving human resources. By the cooperation of the camera and the robot, the efficiency of palletizing and depalletizing is improved and the operation difficulty is reduced, making up for the shortcomings of the traditional method that can only handle a single product specification, as well as the problems that pallets cannot be depalletized in the cases of inverted boxes and inclined boxes. Through visual algorithms, any stack type can be accurately identified, which is beneficial to image segmentation processing, thereby improving the efficiency and accuracy of depalletizing.

[0121] In a third aspect, an embodiment of the present application provides a depalletizing and palletizing device applicable to cigarette boxes, and the device is used to implement the depalletizing and palletizing method applicable to cigarette boxes in the first aspect. Figure 12 It is a schematic structural diagram of a depalletizing and palletizing device applicable to cigarette boxes shown according to an embodiment of the present application. As Figure 12 shown, the device includes a robot 10, an image acquisition device 20, a fixture device 30, and a control module (not shown in the figure).

[0122] The image acquisition device 20 is fixed to the ceiling or bracket directly above the pallet, and is used to photograph the cigarette boxes placed on the pallet and send the photographed image to the control module.

[0123] The fixture device 30 is installed on the robot 10, and the fixture device is used to clamp and place the piece boxes.

[0124] Optionally, Figure 13It is a schematic structural diagram of a fixture device shown according to an exemplary embodiment. The fixture device is equipped with a unilateral suction assist device to ensure the stability of auxiliary clamping. The fixture device mainly consists of a suction cup body, a solenoid valve, a unilateral suction side-turning mechanism, a pneumatic component, etc., and can meet the function of grasping 1 to 4 pieces at a time. The fixture device uses a combined large-area suction cup. The large-area vacuum suction cup can quickly establish a vacuum and lift the cigarette case. The grasping and releasing of the suction cup are controlled by the solenoid valve respectively. In order to assist the stability of suction clamping, a fixture with a unilateral suction side-turning mechanism is adopted. During operation, the solenoid valve controlling the vacuum pipeline is opened, and a vacuum is generated in the inner cavity of the suction cup by the vacuum generating device to suck the piece of cigarettes. After the robot lifts the piece of cigarettes to a certain height from the grasping position, the side-turning mechanism flips, and the side suction cup starts to suck the side of the piece case. The robot clamps the cigarette case to carry the piece of cigarettes. After reaching a certain distance above the designated position, the side suction cup is closed, the side-turning mechanism resets, the robot descends, the vacuum pipeline is closed, and the piece of cigarettes is released to the designated position. A drop-box sensor is installed on the fixture to detect in real time whether the suction cup has a drop-box problem.

[0125] The robot 10 is used to control the fixture device 30 to achieve palletizing and depalletizing.

[0126] The control module is used to implement the palletizing and depalletizing method for cigarette cases in the first aspect.

[0127] In summary, this application integrates devices such as a control module, a high-precision camera, a robot, and a suction cup, and they cooperate with each other for collaborative operation, with simple operation. By using the robot for palletizing and depalletizing work, the safety of the working environment and the process stability are improved, and human resources are saved. By the cooperation of the camera and the robot, the efficiency of palletizing and depalletizing is improved and the operation difficulty is reduced, making up for the shortcomings of the traditional method that can only handle a single product specification, as well as the problems such as the inability to depalletize inverted boxes and inclined boxes.

[0128] In the fourth aspect, the embodiments of this application provide an electronic device. Figure 14 It is a schematic structural diagram of an electronic device provided by the embodiment of this application. The electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the palletizing and depalletizing method for cigarette cases provided in the first aspect. Figure 14 The shown electronic device 60 is only an example and should not bring any restrictions to the functions and usage scope of the embodiments of this application.

[0129] The electronic device 60 can be presented in the form of a general computing device. For example, it can be a server device. The components of the electronic device 60 may include but are not limited to: at least one of the above-mentioned processors 61, at least one of the above-mentioned memories 62, and a bus 63 connecting different system components (including the memory 62 and the processor 61).

[0130] The bus 63 includes a data bus, an address bus, and a control bus.

[0131] The memory 62 may include volatile memory, such as random access memory (RAM) 621 and / or cache memory 622, and may further include read-only memory (ROM) 623.

[0132] The memory 62 may also include a program / utilities 625 having a set (at least one) of program modules 624. Such program modules 624 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment.

[0133] The processor 61 executes various functional applications and data processing by running computer programs stored in the memory 62, such as the unpacking and palletizing method for cigarette boxes provided in the first aspect of the present application.

[0134] The electronic device 60 may also communicate with one or more external devices 64 (such as a keyboard, a pointing device, etc.). Such communication may be carried out through an input / output (I / O) interface 65. Moreover, the model generation device 60 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 66. As shown in the figure, the network adapter 66 communicates with other modules of the model generation device 60 through the bus 63. It should be understood that although not shown in the figure, other hardware and / or software modules may be used in combination with the model generation device 60, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (redundant array of independent disks) systems, tape drives, and data backup storage systems, etc.

[0135] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present invention, the features and functions of two or more of the above-described units / modules may be embodied in one unit / module. Conversely, the features and functions of one unit / module described above may be further divided and embodied by multiple units / modules.

[0136] The technical features of the above-described embodiments may be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0137] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.

Claims

1. A method for depalletizing cigarette boxes, characterized in that: The method is applied to a palletizing system, the palletizing system comprising a robot and a control module, and the method is specifically applied to the control module, the method comprising: Receive request information including a target stack type serial number sent by the robot, and determine a target point from a preset mapping relationship based on the target stack type serial number, wherein the preset mapping relationship is a mapping relationship between a pre-acquired stack type serial number and a point, and the target point includes a grabbing point and a placing point; A target path for the target point is generated by a path planning algorithm according to preset rules, and the target point and the target path are sent to the robot so that the robot can move the box from the grabbing point to the placing point based on the target path.

2. The method for depalletizing cigarette boxes according to claim 1, characterized in that: The mapping relationship between the stack type serial number and the point position is obtained in the following way: Obtaining box parameters and stack shape parameters, and generating an initial point based on the box parameters and stack shape parameters, wherein the stack shape parameters include a stack shape sequence number; The initial points are filtered based on preset filtering conditions, and the filtered points are filtered for a second time through collision prediction to obtain final points.

3. The method for depalletizing cigarette boxes according to claim 2, characterized in that: The box parameters include the length, width and height of the box, and the generating of the initial point based on the box parameters and the stack shape parameters includes: (x,y,z)=(nl,(k-1)w,(k-1)h) k is an odd number Among them, k represents the kth layer of the parcel box from low to high, (x, y, z) represents the point coordinates of the parcel box, l represents the length of the parcel box, w represents the width of the parcel box, h represents the height of the parcel box, and n represents the nth parcel box in the x-axis coordinate direction.

4. The method for depalletizing cigarette boxes according to claim 1, characterized in that: When the work task is palletizing, the target path of the target point is generated by the path planning algorithm according to the preset rules, including: A target path of the target point is generated by a path planning algorithm according to the rule of from far to near, so that the robot can grab the box from far to near based on the target path and place it on the pallet of the placement point.

5. The method for depalletizing cigarette boxes according to claim 1, characterized in that: When the work task is to depalletize, the target path of the target point is generated by a path planning algorithm according to preset rules, including: The target path of the target point is generated by a path planning algorithm according to the rule from near to far, so that the robot can grab the box from near to far based on the target path and place it on the removal roller line of the placement point.

6. The method for depalletizing cigarette boxes according to claim 1, characterized in that: The depalletizing system further includes an image acquisition device. When the work task is depalletizing, the method further includes: In response to receiving the stacking type information sent by the robot, controlling the image acquisition device to acquire a stacking type image, wherein the stacking type image includes a depth image and an RGB image; Segmenting the stack based on the stack image and an image segmentation algorithm, and obtaining a first grasping posture based on the segmentation result and suction cup parameters; The first grasping posture is screened based on a preset screening rule and a collision prediction method to obtain a second grasping posture; The second grasping posture is sent to the robot, so that the robot grasps the box based on the second grasping posture.

7. The method for depalletizing cigarette boxes according to claim 6, characterized in that: A suction cup is provided on the robot in the depalletizing and stacking system. When the work task is depalletizing, the stack type is segmented based on the stack type image and the image segmentation algorithm, and a first grasping posture is obtained based on the segmentation result and the suction cup parameter, including: Based on the depth image and the RGB image, a highest plane area on the RGB image is obtained, and the highest plane area is segmented to obtain a box segmentation result; The coordinates of the box segmentation result are converted into the robot coordinate system based on the pre-acquired relationship matrix, and the segmented rectangular units are sorted based on the preset depalletizing direction and the box segmentation result; The rectangular unit is traversed in the order, and a first grasping posture is determined according to the parameters of the rectangular unit and the suction cup.

8. A palletizing system suitable for cigarette boxes, characterized in that: The system comprises a robot and a control module, and the system comprises: Point determination module: used for receiving the request information including the target stack type serial number sent by the robot, and determining the target point from a preset mapping relationship based on the target stack type serial number, wherein the preset mapping relationship is a mapping relationship between the stack type serial number and the point obtained in advance, and the target point includes a grabbing point and a placing point; Grabbing module: used to generate the target path of the target point through the path planning algorithm according to preset rules, and send the target point and the target path to the robot so that the robot can move the box from the grasping point to the placement point based on the target path.

9. A depalletizing device suitable for cigarette boxes, characterized in that: The device is used to implement the method for stacking and unstacking cigarette boxes according to any one of claims 1 to 7, and comprises a robot, an image acquisition device, a clamp device and a control module. The image acquisition device is fixed to the ceiling or bracket directly above the pallet, and is used to photograph the cigarette box placed on the pallet, and send the photographed image to the control module; The clamp device is installed on the robot, and the clamp device is used to clamp and place the parts box; The robot is used to control the clamp device to achieve depalletizing and palletizing.

10. An electronic device, characterized in that: include Memory, processor, and A computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for depalletizing and stacking cigarette boxes according to any one of claims 1 to 7 is implemented.

Images