Manipulator grabbing and positioning method and device, electronic equipment and storage medium
By setting intelligent tags on the workpiece and utilizing their association with the workpiece's geometric features, workpiece information can be quickly obtained, solving the problem of low positioning efficiency of robotic arms and achieving efficient gripping and positioning.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-01-27
- Publication Date
- 2026-04-07
AI Technical Summary
In existing technologies, robotic arms have low grasping and positioning efficiency, requiring the acquisition and processing of large amounts of image data, which leads to low positioning efficiency.
Intelligent tags are set on the workpiece, which record workpiece information and are associated with the workpiece's geometric features. By acquiring the image of the intelligent tag, the gripping posture of the robot arm can be determined, achieving fast and accurate positioning.
It eliminates the need to acquire images of each edge of the workpiece, reducing image processing workload, improving the efficiency of the robotic arm's gripping and positioning, and enhancing the overall efficiency of the loading and unloading system.
Smart Images
Figure CN121798620A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of automation technology, and in particular relates to a robotic arm grasping and positioning method, device, electronic device and storage medium. Background Technology
[0002] With the continuous development of industrial automation, more and more industries are beginning to realize automated and intelligent production. For example, in order to meet the needs of batch processing, automated processing equipment is gradually adding automatic loading and unloading systems. These systems replace manual loading and unloading, saving labor costs and improving processing efficiency.
[0003] The automated loading and unloading system automatically loads workpieces by controlling a robotic arm to pick them up from the rack and place them on the worktable of the automated processing equipment. Conversely, it automatically unloads workpieces by controlling a robotic arm to pick them up from the worktable and place them on the unloading platform.
[0004] During the loading and unloading process, it is necessary to control the robotic arm for gripping and positioning to ensure accurate workpiece grasping. Current technologies utilize a vision system to identify the three right-angled sides of the workpiece for positioning. Specifically, the robotic arm, carrying a camera, moves sequentially above the material rack to capture images of the workpiece. Image processing algorithms then identify the workpiece's outline and locate the three right-angled sides, thereby pinpointing the workpiece's location. However, this positioning method requires the acquisition and processing of large amounts of image data, resulting in low positioning efficiency. Summary of the Invention
[0005] This application provides a robotic arm grasping and positioning method, device, electronic device, and storage medium, which can solve the problem of low grasping and positioning efficiency of robotic arms in related technologies.
[0006] In a first aspect, embodiments of this application provide a robotic arm grasping and positioning method, including:
[0007] A smart identification image of a workpiece is acquired. The workpiece is equipped with a smart identification, which records the workpiece information corresponding to the workpiece. The geometric features of the smart identification are related to the geometric features of the workpiece. Based on the geometric features of the smart identifier in the smart identifier image and the workpiece information, the gripping posture corresponding to the robot arm gripping the workpiece is determined; The robotic arm is controlled to grasp the workpiece according to the grasping posture.
[0008] In one possible implementation of the first aspect, determining the gripping pose of the robotic arm for gripping the workpiece based on the geometric features of the smart identifier in the smart identifier image and the workpiece information includes: The first structural feature and positional feature of the smart tag in the smart tag image are obtained. The first structural feature reflects the deflection angle of the smart tag relative to the robot arm, and the positional feature reflects the position of the smart tag. Based on the first structural feature, the deflection angle of the workpiece relative to the robot arm is determined; The gripping posture of the robot arm is determined based on the deflection angle, the position features, and the workpiece information.
[0009] In one possible implementation of the first aspect, determining the gripping pose of the robot arm based on the deflection angle, the first structural feature, and the workpiece information includes: The target turning angle of the robot arm is determined based on the deflection angle; The gripping position of the robotic arm is determined based on the positional features. The opening and closing degree of the robot arm is determined based on the workpiece information; The gripping posture of the robotic arm is determined based on the target turning angle, the gripping position, and the opening degree.
[0010] In one possible implementation of the first aspect, the association between the geometric features of the smart identifier and the geometric features of the workpiece is configured such that the first structural feature and the second structural feature of the workpiece are parallel. And / or, the association between the geometric features of the smart identifier and the geometric features of the workpiece is configured such that the position feature is the geometric center position of the workpiece.
[0011] In one possible implementation of the first aspect, the association between the first structural feature of the smart identifier and the second structural feature of the workpiece is configured to form a preset angle, and determining the deflection angle of the workpiece relative to the robot arm based on the first structural feature includes: Based on the first structural feature and the preset included angle, the deflection angle of the workpiece relative to the robot arm is determined.
[0012] In one possible implementation of the first aspect, the smart identifier includes a QR code, and the first structural feature includes a straight edge of the QR code.
[0013] In one possible implementation of the first aspect, acquiring the intelligent identification image of the workpiece includes: Control the robotic arm to move above the workpiece; The robot arm is leveled according to the plane of the workpiece so that the gripper plane of the robot arm is parallel to the plane of the workpiece. The vision sensor on the robotic arm is controlled to capture an image of the smart label on the workpiece above the smart label.
[0014] Secondly, embodiments of this application provide a robotic gripping and positioning device, comprising: The acquisition module is used to acquire the intelligent identification image of the workpiece, wherein the workpiece is provided with an intelligent identification, the intelligent identification records the workpiece information corresponding to the workpiece, and the geometric features of the intelligent identification are related to the geometric features of the workpiece; The processing module is used to determine the gripping posture corresponding to the robot arm gripping the workpiece based on the geometric features of the smart identifier in the smart identifier image and the workpiece information; The control module is used to control the robot arm to grasp the workpiece according to the grasping posture.
[0015] Thirdly, embodiments of this application provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method described in the first aspect above.
[0016] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect above.
[0017] Fifthly, embodiments of this application provide a computer program product that, when run on a terminal device, causes the terminal device to execute the method described in any one of the first aspects above.
[0018] It is understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant descriptions in the first aspect mentioned above, and will not be repeated here.
[0019] The beneficial effects of this application embodiment compared with the prior art are as follows: In this application embodiment, a smart tag is set on the workpiece to record the corresponding workpiece information, and the association relationship between the geometric features of the smart tag and the geometric features of the workpiece is configured. During the gripping and positioning process of the robot arm, the workpiece information is obtained by acquiring the smart tag image of the workpiece and the workpiece information through the smart tag in the smart tag image. Then, the gripping posture corresponding to the robot arm gripping the workpiece is determined by combining the geometric features in the smart tag image and the workpiece information. Then, the robot arm is controlled to grip the workpiece according to the gripping posture. In the entire gripping and positioning process, the workpiece information is carried by the smart tag. At the same time, based on the association relationship between the geometric features of the smart tag and the geometric features of the workpiece, the gripping posture of the robot arm can be obtained by recognizing the geometric features of the smart tag in the smart tag image. It is not necessary to control the robot arm to move to each edge position of the workpiece to collect images of each right-angled side of the workpiece, nor is it necessary to process multiple image data, thereby improving the efficiency of the robot arm gripping and positioning, and thus improving the loading and unloading efficiency. Attached Figure Description
[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0021] Figure 1 This is a schematic diagram of the circuit board drilling machine feeding section provided in one embodiment of this application; Figure 2 This is a flowchart illustrating a robotic arm grasping and positioning method according to an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a workpiece provided in an embodiment of this application; Figure 4 This is a schematic diagram showing the position of a workpiece intelligent identification image collected by a robotic arm according to an embodiment of this application; Figure 5 This is a flowchart illustrating a robotic gripping and positioning method according to another embodiment of this application; Figure 6 This is a flowchart illustrating a robotic arm grasping and positioning method according to another embodiment of this application; Figure 7 This is a schematic diagram of the structure of a robotic gripping and positioning device provided in an embodiment of this application.
[0022] Figure Labels 100-Robot arm; 101-Gripper; 102-Vision sensor; 200-Workbench; 300-Control cabinet; 400-Automatic guided vehicle; 500-Workpiece; 501-Intelligent label; 502-Pin; 600-Material handling station; Detailed Implementation In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.
[0023] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.
[0024] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.
[0025] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."
[0026] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.
[0027] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.
[0028] With the continuous development of industrial automation, more and more industries are beginning to achieve automated and intelligent production of workpieces. Taking PCB (Printed Circuit Board) as an example, the PCB manufacturing industry is currently developing towards high density, multi-layering, and flexibility, which places increasingly higher demands on the efficiency and precision of drilling. Traditional manual loading and unloading methods suffer from low efficiency, high labor intensity, and susceptibility to human error, making them unsuitable for the needs of modern intelligent manufacturing. Therefore, automated loading and unloading systems are gradually becoming widespread, and composite robotic arms have become the core equipment for realizing the automatic handling of PCB boards between warehouses and workstations.
[0029] In PCB manufacturing, the efficiency of automated loading and unloading systems is one of the core performance indicators. A robotic arm needs to pick up PCBs from the rack and accurately place them onto the worktable. This process typically involves two stages: coarse positioning and fine positioning. The purpose of coarse positioning is to ensure that the robotic arm's grippers can accurately approach and grasp the PCB, which requires identifying the PCB's dimensions, center position, and planar orientation.
[0030] In related technologies, the gripping and positioning methods of robotic arms typically rely on a vision system to identify the three right-angled sides of a workpiece. Specifically, this requires the robotic arm, carrying a camera, to move sequentially above the material rack, capturing multiple images of the workpiece. Image processing algorithms then identify the workpiece's outline and locate the three right-angled sides, thereby pinpointing the workpiece's location. However, this positioning method requires acquiring and processing a large amount of image data, resulting in low positioning efficiency.
[0031] Taking the loading and unloading system of a circuit board drilling rig as an example, Figure 1 This is a partial structural diagram of the loading and unloading system of the circuit board drilling machine provided in an embodiment of this application, as shown below. Figure 1 As shown, the loading and unloading system of the circuit board drilling rig includes a robotic arm 100, a control cabinet 300, and an automated guided vehicle (AGV) 400. The control cabinet 300 is mounted on the AGV 400, and the robotic arm 100 is communicatively connected to the controller inside the control cabinet 300. The robotic arm 100 includes a robotic arm (… Figure 1(not marked in the text) and gripper 101, optionally, the robotic arm is mounted on the control cabinet 300, and the gripper 101 is located at the end of the robotic arm.
[0032] As an example, the robot arm 100 is equipped with a vision sensor to acquire images of the circuit board for positioning, or to acquire images of the worktable for positioning.
[0033] As an example, a circuit board drilling machine includes a worktable 200, with a loading and unloading system located on one side of the worktable 200. The worktable 200 is used to drill holes in circuit boards.
[0034] As an example, the loading and unloading system also includes a material handling platform ( Figure 1 (Not marked in the text) The picking platform is located on the automated guided vehicle 400, next to the robot arm 100. The picking platform is used to place circuit boards, and the robot arm 100 is used to pick up the circuit boards from the picking platform and transfer them to the worktable 200 for drilling.
[0035] like Figure 1 As shown, in some scenarios, circuit boards have positioning pins. To avoid stacking these pins, the circuit boards are stacked irregularly, such as in a star or cross shape. In these scenarios, the specific position and orientation of each circuit board are not fixed. Each time the robotic arm picks up a circuit board, it needs to identify the board's size, center position, and planar orientation. The vision system needs to process a large amount of image data, resulting in high computational complexity and low processing efficiency. Furthermore, for larger circuit boards, the robotic arm 100 needs to move to various positions to acquire images over a wide area, increasing wasted movement time. Therefore, in the circuit board processing steps, there is a higher demand for the robotic arm 100 to achieve rapid grasping and positioning.
[0036] Therefore, this application provides a robotic gripper positioning method. By setting an intelligent tag on the workpiece, and associating the intelligent tag with information such as the workpiece's direction, position, and size, the robotic gripper can quickly determine the relevant parameters of the workpiece based on the direction and position of the intelligent tag during gripping and positioning, thereby determining the gripping position of the robotic gripper and achieving rapid gripping and positioning.
[0037] The following examples illustrate this in detail.
[0038] Figure 2 A schematic flowchart of the robotic gripping and positioning method provided in this application is shown. This is an example and not a limitation; the method can be applied to the aforementioned loading and unloading system. Figure 2 As shown, it includes: S201, Obtain the intelligent identification image of the workpiece. The workpiece is equipped with an intelligent identification, which records the workpiece information corresponding to the workpiece. The geometric features of the intelligent identification are related to the geometric features of the workpiece.
[0039] This application embodiment is applied to a loading and unloading system, which is based on a robot arm to perform loading and unloading operations. This application embodiment uses the loading process as an example to illustrate the process of the robot arm grasping and positioning.
[0040] It should be noted that in the application scenario of this application embodiment, a smart identifier is set on the surface of each workpiece. The smart identifier records the workpiece information corresponding to the workpiece, and the geometric features of the smart identifier are associated with the geometric features of the workpiece. For example, and not as a limitation, the smart identifier records the dimensions of the workpiece (such as length and width), or the smart identifier records the dimensions of the workpiece and the association between the geometric features of the smart identifier and the geometric features of the workpiece.
[0041] It is understandable that information recorded by smart signs can be obtained through images of smart signs captured by visual sensors. For example... Figure 3 As shown, by way of example and not limitation, workpiece 500 is provided with a smart label 501, which includes a QR code.
[0042] As an example, such as Figure 4 As shown, the robotic arm 100 is equipped with a vision sensor 102, which is used to acquire images of the smart label. For example, when a loading command is received, the robotic arm 100 is controlled to move above the workpiece 500, and the vision sensor 102 acquires an image of the smart label on the workpiece, that is, an image of the location of the smart label.
[0043] In this embodiment, only the smart label image needs to be collected, without the need to collect a large number of images of each side of the workpiece. Moreover, the smart label image can be collected at once without moving the position of the robot arm, which can reduce the number of images collected and the image collection time.
[0044] S202, Based on the geometric features of the smart label in the smart label image and the workpiece information, determine the gripping posture corresponding to the robot arm gripping the workpiece.
[0045] As an example, after acquiring the smart tag image, the image is decoded to obtain the workpiece information carried by the smart tag. As an example, and not a limitation, if the smart tag is a QR code, then the workpiece information is obtained by scanning the QR code in the smart tag image and recognizing and parsing it.
[0046] As an example, after acquiring the smart sign image, the features of the smart sign image are analyzed to obtain the geometric features of the smart sign in the image. Optionally, algorithms such as image enhancement and edge detection can be used to accurately extract the geometric features of the smart sign.
[0047] Since the geometric features of the smart identifier are related to the geometric features of the workpiece, after obtaining the geometric features of the smart identifier, the geometric features of the workpiece can be determined based on the preset relationship. Then, combined with the workpiece information, the workpiece can be positioned, and the gripping posture corresponding to the robot arm gripping the workpiece can be determined.
[0048] In one possible implementation, the geometric features identified and extracted from the smart tag image include a first structural feature and a positional feature. The first structural feature reflects the deflection angle of the smart tag relative to the robot arm, while the positional feature reflects the position of the smart tag. Based on the first structural feature, the positional feature, and workpiece information, the gripping pose corresponding to the robot arm grasping the workpiece is determined.
[0049] As an example, step S202 includes: A1: Obtain the first structural features and positional features of the smart label in the smart label image.
[0050] A2: Based on the first structural feature, determine the deflection angle of the workpiece relative to the robot arm.
[0051] As an example, the vision sensor includes a camera, which acquires intelligent image labels. Determining the deflection angle of the workpiece relative to the robot arm based on a first structural feature includes: determining the angle between the first structural feature and the camera coordinate system, and determining the deflection angle of the workpiece relative to the robot arm based on this angle.
[0052] It should be noted that, based on the first structural feature reflecting the deflection angle of the intelligent identifier relative to the robot arm, and the correlation between the first structural feature of the intelligent identifier and the corresponding second structural feature of the workpiece, the deflection angle of the workpiece relative to the robot arm can be determined based on the first structural feature and this correlation. For example, if the first and second structural features are parallel, then the angle between the first structural feature and the robot arm in the camera coordinate system is the angle between the workpiece and the robot arm in the camera coordinate system. If the camera coordinates and the robot arm coordinates are the same, then this angle is the deflection angle of the workpiece relative to the robot arm. If the camera coordinates and the robot arm coordinates are different, then the angle is transformed using a transformation matrix between the camera coordinates and the robot arm coordinates to obtain the deflection angle of the workpiece relative to the robot arm.
[0053] A3: Determine the gripping posture of the robot arm based on the deflection angle, position characteristics, and workpiece information.
[0054] The position of the intelligent tag reflects its location, and since the position of the intelligent tag is correlated with the position of the workpiece, the position of the workpiece can be determined based on the positional features of the intelligent tag. Specifically, the position information of the workpiece is determined based on the deflection angle and positional features. Based on the position information and workpiece information, the gripping pose of the robot arm can be determined. It is understood that workpiece information includes workpiece dimensions, such as length, width, and thickness.
[0055] It should be noted that the correlation between the geometric features of the smart tag and the geometric features of the workpiece refers to a correlation between features of the same type. For example, the first structural feature of the smart tag and the second structural feature of the workpiece are related; the first structural feature reflects the deflection angle (or orientation) of the smart tag relative to the robot arm, and the second structural feature reflects the deflection angle (or orientation) of the workpiece relative to the robot arm. Alternatively, the positional features of the smart tag and the positional features of the workpiece are related.
[0056] As an example, and not a limitation, the association between the geometric features of the smart tag and the geometric features of the workpiece is configured such that the first structural feature and the second structural feature of the workpiece are parallel; and / or, the association between the geometric features of the smart tag and the geometric features of the workpiece is configured such that the position feature is the geometric center position of the workpiece. That is, the loading / unloading system determines the orientation of the workpiece using the first structural feature of the smart tag, determines the geometric center position of the workpiece using the position feature of the smart tag, and then obtains the orientation and geometric center position of the smart tag based on the first structural feature and the position feature. By default, the orientation and geometric center position of the smart tag are taken as the orientation and geometric center position of the workpiece, and the gripping pose of the robot arm can be calculated based on the first structural feature and the position feature.
[0057] It is understood that the first structural feature can be an edge of the smart identifier, or any pre-defined feature on the smart identifier reflecting its orientation. As an example and not a limitation, the smart identifier includes a QR code, where the first structural feature is the right-angled edge of the QR code.
[0058] It is understood that the positional feature can be any position of the smart identifier, and the positional feature of the smart identifier and the positional feature of the workpiece can have any association relationship. As an example and not a limitation, the smart identifier includes a QR code, and the positional feature is the center position of the QR code, which is aligned with the center position of the workpiece, or the center position of the QR code and the geometric center position of the workpiece have a set vector.
[0059] In an alternative embodiment, such as Figure 3 As shown, the smart label is located on the line connecting the two PIN pins 502 on both sides of the workpiece, which facilitates the positioning of the PIN pins 502 and improves the positioning efficiency of the PIN pins 502.
[0060] In one possible implementation, the gripping pose of the robot arm is determined based on the deflection angle, the first structural feature, and the workpiece information, including: B1: Determine the target turning angle of the robot arm based on the deflection angle.
[0061] Based on the deflection angle of the workpiece relative to the robot arm, the target turning angle that the robot arm needs to rotate can be determined.
[0062] As an example, the deflection angle is opposite to the target steering angle of the robot.
[0063] B2: Determine the gripping position of the robotic arm based on its positional characteristics.
[0064] As an example, the geometric center position of the workpiece is determined based on the correlation between the positional features and the positional features of the workpiece, and the geometric center position of the workpiece is used as the gripping position of the robot arm.
[0065] B3: Determine the opening and closing degree of the robot arm based on the workpiece information.
[0066] As an example, workpiece information includes workpiece dimensions, such as workpiece length and width, and the opening and closing degree of the robot arm is determined based on the workpiece length and width.
[0067] For example, please continue to refer to Figure 4 The robot arm 100 also includes grippers 101, which are used to grasp the edge of the workpiece 500 to lift the workpiece 500 from the loading table 600 and transfer it to the worktable. The opening degree of the robot arm 100 refers to the opening degree of the grippers 101.
[0068] B4: Determine the gripping posture of the robotic arm based on the target turning angle, gripping position, and opening degree.
[0069] It is understandable that the gripping posture of a robotic arm includes the turning angle, gripping position, and opening / closing degree.
[0070] The turning angle of a robot refers to the orientation of the gripper. For example, controlling the end joint of the robot to rotate by a target turning angle θ degrees aligns the gripper's clamping direction with the edge of the workpiece.
[0071] The opening and closing degree of a robotic gripper refers to the opening width of the gripper jaws, which is the optimal position for holding the workpiece.
[0072] The gripping position refers to the target position of the robot arm, such as the center geometric position of the workpiece, where the opening of the gripper can just hold the workpiece.
[0073] S203 controls the robotic arm to grasp the workpiece based on the grasping posture.
[0074] After determining the gripping posture of the robot arm, control the robot arm to grip the workpiece and complete the positioning and gripping operation of the robot arm.
[0075] In this embodiment, a smart tag is set on the workpiece to record the corresponding workpiece information, and the geometric features of the smart tag are configured to correlate with the geometric features of the workpiece. During the robotic arm's gripping and positioning process, the workpiece information is obtained by acquiring the smart tag image of the workpiece and then by combining the geometric features in the smart tag image with the workpiece information. The gripping posture corresponding to the robotic arm gripping the workpiece is then determined based on the gripping posture. Throughout the gripping and positioning process, the smart tag carries the workpiece information, and based on the correlation between the geometric features of the smart tag and the geometric features of the workpiece, the gripping posture of the robotic arm can be obtained by recognizing the geometric features of the smart tag in the smart tag image. This eliminates the need to control the robotic arm to move to each edge of the workpiece to collect images of each right-angled side, and also eliminates the need to process multiple image data. This achieves fast and accurate workpiece positioning, precise workpiece gripping, and improves the efficiency of robotic arm gripping and positioning, thereby improving loading and unloading efficiency.
[0076] Figure 5 This is a flowchart illustrating a robotic arm grasping and positioning method according to another embodiment of this application. Based on the foregoing embodiments, it is intended as an example and not a limitation. Figure 5 As shown, it includes: S501, acquire the intelligent identification image of the workpiece. The workpiece is equipped with an intelligent identification, which records the workpiece information corresponding to the workpiece. The geometric features of the intelligent identification are related to the geometric features of the workpiece.
[0077] S502, Obtain the first structural features and positional features of the smart sign in the smart sign image.
[0078] S503, determine the deflection angle of the workpiece relative to the robot arm based on the first structural feature and the preset angle between the first structural feature and the second structural feature of the workpiece.
[0079] In this embodiment, the specific implementation process and principle of steps S501 to S502 are the same as those in the aforementioned embodiments. For details, please refer to the aforementioned embodiments, which will not be repeated here.
[0080] The difference between this embodiment and the previous embodiments is that the association between the first structural feature of the smart tag and the second structural feature of the workpiece is configured to form a preset angle (rather than parallel). As an example, a smart tag is set on the workpiece, with the smart tag and the workpiece forming a preset angle. The preset angle and the workpiece size are encapsulated into workpiece information and recorded in the smart tag. During gripping and positioning, the workpiece size and the preset angle are obtained by decoding the smart tag, and then the deflection angle of the tool relative to the robot arm is determined based on the first structural feature and the preset angle.
[0081] As another example, the relationship between the first structural feature and the second structural feature of the workpiece (with a preset angle) is stored in advance. During gripping and positioning, the preset angle is directly retrieved from the memory, and then the deflection angle of the workpiece relative to the robot arm is determined based on the first structural feature and the preset angle.
[0082] For example, based on the angle between the first structural feature and the camera coordinates and a preset angle, the angle between the workpiece and the camera coordinates is determined, and then based on the transformation matrix between the camera coordinates and the robot, the deflection angle of the workpiece relative to the robot is determined.
[0083] S504 determines the gripping posture of the robot arm based on the deflection angle, position characteristics, and workpiece information; S505 controls the robot arm to grasp the workpiece based on the grasping posture.
[0084] In this embodiment, the specific implementation process and principle of steps S504 to S505 are the same as those in the aforementioned embodiments. For details, please refer to the aforementioned embodiments, which will not be repeated here.
[0085] In this embodiment of the application, when the first structural feature of the smart tag and the second structural feature of the workpiece form a preset angle, the gripping posture of the robot arm can be determined based on the geometric features of the smart tag and the workpiece information. It is not required that the first structural feature of the smart tag and the second structural feature of the workpiece be parallel, and the structural settings or type settings of the smart tag can be diversified.
[0086] Figure 6 This is a flowchart illustrating a robotic arm grasping and positioning method according to another embodiment of this application. Based on the foregoing embodiments, it is intended as an example and not a limitation. Figure 6 As shown, it includes: S601 controls the robot arm to move above the workpiece.
[0087] S602, the robot arm is leveled according to the plane of the workpiece so that the gripper plane of the robot arm is parallel to the plane of the workpiece.
[0088] If the visual sensor's shooting angle is deviated, the acquired smart label image will also be deviated, resulting in an error between the geometric features extracted from the smart label image and the true value. Therefore, the accuracy of the robotic arm's grasping pose determined based on the smart label's geometric features is low. To improve the accuracy of the robotic arm's grasping and positioning, the robotic arm grasping and positioning method proposed in this application pre-levels the robotic arm before positioning the workpiece, making the plane of the robotic arm's gripper parallel to the plane of the workpiece. When the plane of the robotic arm's gripper and the plane of the workpiece are parallel, the error of the smart label image acquired by the visual sensor is small, and thus the workpiece can be accurately positioned based on the smart label image.
[0089] As an example, and not a limitation, the following methods can be used to level a robotic arm: For example, the robotic arm is equipped with at least three detection devices located at different positions on the gripper plane and not on the same straight line. Based on the principle that three points can form a plane, the parallelism between the gripper plane and the workpiece plane can be determined by the detection signals detected by the at least three detection devices.
[0090] It is understood that the detection device includes, but is not limited to, distance sensors; for example, the detection device may also include contact sensors. Examples are given below: As an example, the detection device includes distance sensors that detect the distance between the sensor's location and the workpiece plane. Based on the differences in the distances from the three distance sensors to the workpiece plane, the parallelism between the gripper plane and the workpiece plane can be determined. This allows for adjustment of the robot's gripping posture until the difference is less than or equal to a preset threshold, at which point the gripper plane and workpiece plane are determined to be parallel, thus completing the leveling process for the robot.
[0091] As an example and not a limitation, the distance sensor is a laser displacement sensor.
[0092] As an example, the detection device includes a contact sensor, controls the gripper plane of the robot to contact the workpiece plane, obtains the contact signal from the contact sensor, determines the parallelism between the gripper plane and the workpiece plane, and then adjusts the gripping posture of the robot until the difference is less than or equal to a preset threshold, determines that the gripper plane and the workpiece plane are parallel, and completes the leveling process of the robot.
[0093] S603 controls the vision sensor on the robotic arm to capture images of the smart markings on the workpiece above the smart markings. S604, based on the geometric features of the smart tag in the smart tag image and the workpiece information, determines the gripping posture corresponding to the robot arm gripping the workpiece.
[0094] S605 controls the robot arm to grasp the workpiece based on the grasping posture.
[0095] In this embodiment, the specific implementation process and principle of steps S603 to S605 are the same as those in the aforementioned embodiments. For details, please refer to the aforementioned embodiments, which will not be repeated here.
[0096] In this embodiment, a detection device is used in advance to automatically level the robot arm with reference to the workpiece plane, providing a flat reference surface for the vision sensor to collect the intelligent label image when the workpiece is positioned, thereby reducing the error of the intelligent label image.
[0097] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.
[0098] Corresponding to the robotic arm grasping and positioning method in the above embodiments, Figure 7 The diagram shows a structural block diagram of the robotic gripping and positioning device provided in the embodiments of this application. For ease of explanation, only the parts related to the embodiments of this application are shown.
[0099] Reference Figure 7 The robotic gripper positioning device 70 includes: The acquisition module 701 is used to acquire the intelligent identification image of the workpiece. The workpiece is equipped with an intelligent identification, which records the workpiece information corresponding to the workpiece. The geometric features of the intelligent identification are related to the geometric features of the workpiece. The processing module 702 is used to determine the gripping posture of the robot arm to grip the workpiece based on the geometric features of the smart tag in the smart tag image and the workpiece information. The control module 703 is used to control the robot arm to grasp the workpiece according to the grasping posture.
[0100] It should be noted that the information interaction and execution process between the above-mentioned devices / units are based on the same concept as the method embodiments of this application. For details on their specific functions and technical effects, please refer to the method embodiments section, and they will not be repeated here.
[0101] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.
[0102] This application also provides an electronic device, which includes: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the steps in any of the above method embodiments.
[0103] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.
[0104] This application provides a computer program product that, when run on a mobile terminal, enables the mobile terminal to implement the steps described in the above-described method embodiments.
[0105] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0106] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0107] In the embodiments provided in this application, it should be understood that the disclosed apparatus / network devices and methods can be implemented in other ways. For example, the apparatus / network device embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.
[0108] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.
Claims
1. A method for gripping and positioning by a robotic arm, characterized in that, The method includes: A smart identification image of a workpiece is acquired. The workpiece is equipped with a smart identification, which records the workpiece information corresponding to the workpiece. The geometric features of the smart identification are related to the geometric features of the workpiece. Based on the geometric features of the smart identifier in the smart identifier image and the workpiece information, the gripping posture corresponding to the robot arm gripping the workpiece is determined; The robotic arm is controlled to grasp the workpiece according to the grasping posture.
2. The method according to claim 1, characterized in that, The step of determining the gripping pose of the robotic arm for gripping the workpiece based on the geometric features of the smart identifier in the smart identifier image and the workpiece information includes: The first structural feature and positional feature of the smart tag in the smart tag image are obtained. The first structural feature reflects the deflection angle of the smart tag relative to the robot arm, and the positional feature reflects the position of the smart tag. Based on the first structural feature, the deflection angle of the workpiece relative to the robot arm is determined; The gripping posture of the robot arm is determined based on the deflection angle, the position features, and the workpiece information.
3. The method according to claim 2, characterized in that, Determining the gripping pose of the robot arm based on the deflection angle, the first structural feature, and the workpiece information includes: The target turning angle of the robot arm is determined based on the deflection angle; The gripping position of the robotic arm is determined based on the positional features. The opening and closing degree of the robot arm is determined based on the workpiece information; The gripping posture of the robotic arm is determined based on the target turning angle, the gripping position, and the opening degree.
4. The method according to claim 2, characterized in that, The association between the geometric features of the smart identifier and the geometric features of the workpiece is configured such that the first structural feature and the second structural feature of the workpiece are parallel. And / or, the association between the geometric features of the smart identifier and the geometric features of the workpiece is configured such that the position feature is the geometric center position of the workpiece.
5. The method according to claim 2, characterized in that, The association between the first structural feature of the smart identifier and the second structural feature of the workpiece is configured to form a preset angle. Determining the deflection angle of the workpiece relative to the robot arm based on the first structural feature includes: Based on the first structural feature and the preset included angle, the deflection angle of the workpiece relative to the robot arm is determined.
6. The method according to any one of claims 2 to 5, characterized in that, The smart identifier includes a QR code, and the first structural feature includes the straight edge of the QR code.
7. The method according to any one of claims 1 to 5, characterized in that, The acquisition of the intelligent identification image of the workpiece includes: Control the robotic arm to move above the workpiece; The robot arm is leveled according to the plane of the workpiece so that the gripper plane of the robot arm is parallel to the plane of the workpiece. The vision sensor on the robotic arm is controlled to capture an image of the smart label on the workpiece above the smart label.
8. A robotic gripping and positioning device, characterized in that, include: The acquisition module is used to acquire the intelligent identification image of the workpiece, wherein the workpiece is provided with an intelligent identification, the intelligent identification records the workpiece information corresponding to the workpiece, and the geometric features of the intelligent identification are related to the geometric features of the workpiece; The processing module is used to determine the gripping posture corresponding to the robot arm gripping the workpiece based on the geometric features of the smart identifier in the smart identifier image and the workpiece information; The control module is used to control the robot arm to grasp the workpiece according to the grasping posture.
9. An electronic device, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the method as claimed in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 7.