Control method, apparatus, device, storage medium, and program

Abstract

To provide a control method, an apparatus, a device, a storage medium, and a program.SOLUTION: The method includes: obtaining a first target image collected by a first collection apparatus and a second target image collected by a second collection apparatus in a case where it is determined that characteristic information on a mechanical gripper satisfies a first preset requirement, the first collection apparatus being used to perform image collection for the mechanical gripper, and the second collection apparatus being used to perform image collection for a target yarn-wound package on a trolley to be grabbed by the mechanical gripper; detecting a first center position of the mechanical gripper in the first target image, and detecting a second center position of the target yarn-wound package in the second target image; and generating a calibration command in a case where it is determined that a target positional relationship between the first center position and the second center position does not satisfy a second preset requirement.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to the field of data processing technology, and in particular to a control method, an apparatus, a device, a storage medium, and a program. [Background technology]

[0002] In a yarn package production workshop, when a robot grasps a yarn package from a trolley, problems such as inaccurate positioning may occur due to factors such as mechanical wear, and the mechanical gripper of the robot may damage the yarn package when grasping it, and ultimately fail to grasp the yarn package properly. Therefore, a method for calibrating the gripping position of the robot is required. Summary of the Invention [Problem to be solved by the invention]

[0003] The present disclosure provides a control method, an apparatus, a device, a storage medium, and a program for solving or alleviating one or more technical problems in the prior art. [Means for solving the problem]

[0004] In a first aspect, the present disclosure provides a method of control, the method comprising: When it is determined that the characteristic information of the mechanical gripper satisfies a first preset requirement, acquiring a first target image collected by a first collecting device and a second target image collected by a second collecting device, the first collecting device being used to collect images of the mechanical gripper, and the second collecting device being used to collect images of a target wound yarn package on a trolley to be gripped by the mechanical gripper; Detecting a first center position of the mechanical gripper in the first target image and detecting a second center position of the target wound yarn package in the second target image; generating a calibration command when it is determined that the target positional relationship between the first central position and the second central position does not satisfy a second preset requirement, the calibration command being used to calibrate a central position of the mechanical gripper or being used to calibrate a central position of a target wound yarn package to be gripped by the mechanical gripper.

[0005] In a second aspect, the present disclosure provides a control device, the device comprising: an acquisition unit for acquiring a first target image collected by a first collection device and a second target image collected by a second collection device when it is determined that the characteristic information of the mechanical gripper satisfies a first preset requirement, the first collection device being used to perform image collection for the mechanical gripper, and the second collection device being used to perform image collection for a target wound yarn package on a trolley to be gripped by the mechanical gripper; a detection unit for detecting a first center position of the mechanical gripper in the first target image and detecting a second center position of the target wound yarn package in the second target image; and a processing unit for generating a calibration command when it is determined that the target positional relationship between the first center position and the second center position does not satisfy a second preset requirement, the calibration command being used to calibrate a center position of the mechanical gripper or being used to calibrate a center position of a target wound yarn package to be gripped by the mechanical gripper.

[0006] In a third aspect, the present disclosure provides an electronic device, the device comprising: At least one processor; a memory in communication with the at least one processor; The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, cause the implementation of any one of the methods in the embodiments of the present disclosure. In a fourth aspect, there is provided a non-transitory computer-readable storage medium having stored thereon computer instructions for causing a computer to perform any one of the methods in the embodiments of the present disclosure. In a fifth aspect, the present disclosure provides a program, which, when executed by a processor, implements any one of the methods in the embodiments of the present disclosure.

[0007] In this way, according to the solution disclosed herein, the center position of the mechanical gripper and the center position of the target wound yarn package can be detected based on the acquired first target image and second target image, thereby determining the target positional relationship between the two, and further performing calibration based on the target positional relationship. In this way, the problem of inaccurate positioning and gripping due to mechanical wear can be quickly addressed, the gripping accuracy of the mechanical gripper can be effectively improved, and technical support can be provided for smoothly performing automated calibration of the gripping position of the mechanical gripper.

[0008] It should be understood that the contents described herein are not intended to describe key or important features of the embodiments of the present disclosure, nor are they used to limit the scope of the present disclosure, other features of the present disclosure are facilitated by the following specification. [Brief description of the drawings]

[0009] In the accompanying drawings, the same numbers represent the same or similar parts or elements throughout the several views unless otherwise stated. The accompanying drawings are not necessarily drawn to scale. It should be understood that the drawings depict only some embodiments provided by the present disclosure and should not be considered as limiting the scope of the present disclosure. [Figure 1] 1 is a schematic flowchart of a control method according to an embodiment of the present disclosure. [Figure 2A] 1A-1C are schematic diagrams illustrating a scenario in which a mechanical gripper grips a wound yarn package according to one embodiment of the present disclosure. [Figure 2B]1A-1C are schematic diagrams illustrating a scenario in which a mechanical gripper grips a wound yarn package according to one embodiment of the present disclosure. [Diagram 3] FIG. 2 is a schematic diagram illustrating the configuration of a target detection model according to an embodiment of the present disclosure. [Figure 4] 2 is a second schematic flowchart of a control method according to an embodiment of the present disclosure. [Diagram 5] 3 is a schematic flowchart of a control method according to an embodiment of the present disclosure, part three. [Figure 6] 4 is a schematic flowchart of a control method according to an embodiment of the present disclosure. [Figure 7] FIG. 2 is a schematic diagram illustrating a configuration of a control device according to an embodiment of the present disclosure. [Figure 8] FIG. 2 is a block diagram of an electronic device for implementing a control method according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] The present disclosure will now be described in more detail with reference to the accompanying drawings, in which like reference numbers represent functionally identical or similar elements, and in which various aspects of embodiments are illustrated, and which, unless otherwise noted, are not necessarily drawn to scale.

[0011] Furthermore, in order to better explain the present disclosure, many specific details are described in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can be similarly implemented without specific details. In some embodiments, methods, means, components, circuits, etc. that are well known to those skilled in the art are not described in detail so as not to obscure the gist of the present disclosure. In a yarn package production workshop, when a robot grasps a yarn package from a trolley, problems such as inaccurate positioning can occur due to factors such as mechanical wear. Furthermore, the robot's mechanical gripper may damage the yarn package when grasping it, resulting in the yarn package not being grasped properly.

[0012] For this reason, the solution disclosed herein provides a control method to calibrate the gripping position of the robot. 1 is a schematic flow chart of a control method according to an embodiment of the present disclosure, which is optionally applied to electronic devices such as personal computers, servers, server clusters, etc.

[0013] Furthermore, the method includes at least part of the following contents: As shown in FIG. In step S101, if it is determined that the characteristic information of the mechanical gripper meets the first preset requirement, a first target image collected by a first collecting device and a second target image collected by a second collecting device are obtained. Here, the first collecting device is used to collect images of a mechanical gripper, and the second collecting device is used to collect images of a target wound yarn package on a trolley to be gripped by the mechanical gripper.

[0014] In one example, the first collecting device can be installed at any position where it can collect the complete mechanical gripper, for example, the first collecting device is installed on the trolley, and the second collecting device can be installed at any position where it can collect the complete target wound yarn package on the trolley, for example, the second collecting device is installed on the mechanical arm where the mechanical gripper is located, and the solution of the present disclosure is not limited thereto.

[0015] Furthermore, the first collecting device (or the second collecting device) may specifically include a camera, for example, the first target image is obtained after performing image collection on the mechanical gripper using a camera, for example, the camera is used to take a picture of the mechanical gripper to obtain the first target image, or a video collection is performed for a preset time length on the mechanical gripper to obtain a plurality of consecutive video frames, and one image is selected from the consecutive video frames to obtain the first target image. Here, the second collecting device is similar to the first collecting device, and the description thereof is omitted here.

[0016] In addition, the target wound yarn package is the wound yarn package that the mechanical gripper is currently to grasp from the trolley. In one example, as shown in FIG. 2(A), a mechanical gripper is fixed to the end of a mechanical arm, and the mechanical gripper extends to the trolley along a first direction. At this time, when the mechanical gripper moves to a specific position and attempts to grasp the target wound yarn package, a first collection device installed on the mechanical arm can collect the target wound yarn package that the mechanical gripper is to grasp, and a first target image including the complete target wound yarn package is obtained, as shown in FIG. 2(B). It should be understood that by adjusting the position of the first collecting device installed on the mechanical arm, the detailed information of the target body included in the collected first target image can be controlled, for example, by adjusting the position of the first collecting device installed on the mechanical arm, the collected first target image includes one complete wound yarn package, and the complete wound yarn package is the target wound yarn package, thus effectively avoiding other wound yarn packages around the target wound yarn package from interfering with the identification of the center position of the target wound yarn package, and further laying a foundation for effectively improving the calibration accuracy.

[0017] Furthermore, the characteristic information of the mechanical gripper may specifically include, but is not limited to, at least one of the following: the operating time of the mechanical gripper, the number of times the mechanical gripper grips the wound yarn package on the trolley, etc. In one example, the operating time length of the mechanical gripper is determined, and when the operating time length of the mechanical gripper reaches a preset operating time length, a first target image collected by a first collection device and a second target image collected by a second collection device are acquired. In another example, the number of times the mechanical clamp jaw grips a wound yarn package on a trolley is counted, and when the number of grips reaches a preset number, a first target image collected by a first collection device and a second target image collected by a second collection device are obtained.

[0018] In step S102, a first center position of the mechanical gripper in the first target image is detected, and a second center position of the target wound yarn package in the second target image is detected.

[0019] In one specific example, the first center position and the second center position can be obtained by using the following method. Specifically, detecting the first center position of the mechanical gripper in the first target image and detecting the second center position of the target wound yarn package in the second target image (i.e., step S102 described above) specifically includes:

[0020] In step S102-1, the first target image is input into a target detection model to obtain a first center position of the mechanical gripper in the first target image. In step S102-2, the second target image is input to the target detection model to obtain a second center position of the target wound yarn package in the second target image.

[0021] Furthermore, in one specific example, the target detection model in step S102-1 (or step S102-2) described above includes at least a first network layer, a second network layer, and a third network layer.

[0022] Here, the first network layer includes at least a first sub-network layer, a second sub-network layer and a third sub-network layer, the first sub-network layer is used for performing a first convolution process on the input image to obtain a first convolution feature map, the second sub-network layer is used for performing a linear process on the first convolution feature map to obtain a linear feature map, and a connection process between the linear feature map and the first convolution feature map to obtain a connection feature map, and the third sub-network layer is used for performing a second convolution process on the connection feature map to obtain a second convolution feature map, thus effectively improving the richness of the extracted features and further improving the accuracy of the subsequent identification of the mechanical gripper or the target wound yarn package.

[0023] For example, in one example, the first network layer is a ghost network (GhostNet) layer, and the first sub-network layer included in the GhostNet layer is a normal convolution (Conv) network layer, the second sub-network layer is a ghost convolution (GhostConv) network layer, and the third sub-network layer is a hybrid dilated convlution (HDC) network layer. As shown in Figure 3, first, an image (such as a first target image, a second target image) is input into a normal convolution network layer to obtain a normal convolution feature map of the image, and then the normal convolution feature map is input into a ghost convolution network layer, for example, a linear feature map is obtained after linear processing by the ghost convolution network layer, and the linear feature map and the normal convolution feature map are connected to obtain a connected feature map, and finally the connected feature map is input into a hybrid cavity convolution network layer to obtain a hybrid cavity convolution feature map.

[0024] Furthermore, the second network layer is used to respectively perform a first convolution process on the connection feature map and the second convolution feature map, and perform a feature fusion process on the processed result to obtain a fused feature map. For example, the second network layer is a Feature Pyramid Network (FPN) layer, and as shown in FIG. 3, the connection feature map and the mixed cavity convolution feature map obtained by the ghost network layer are input to the FPN layer to perform a feature fusion process to obtain a fused feature map. Further, the third network layer includes a fourth subnetwork layer and a fifth subnetwork layer, the fourth subnetwork layer is used for identifying and obtaining a mechanical gripper or a target wound yarn package in the image based on the fused feature map, and the fifth subnetwork layer is used for obtaining a center position of the mechanical gripper in the image or a center position of the target wound yarn package in the image based on the fused feature map, for example, the fifth subnetwork layer is used for obtaining a center position of the mechanical gripper in the image or a center position of the target wound yarn package in the image based on the fused feature map and the output result of the fourth subnetwork layer.

[0025] For example, the fourth subnetwork layer is a classification subnetwork layer, and the fifth subnetwork layer is a regression subnetwork layer. As shown in FIG. 3, the output result of the FPN layer, for example, a fused feature map, is input to the classification subnetwork layer to identify a mechanical gripper in an image, for example, a mechanical gripper in an image is selected by a frame, and the fused feature map and the mechanical gripper in the image selected by the frame (for example, a partial image including a mechanical gripper) are further input to the regression subnetwork layer to obtain the center position of the mechanical gripper in the image; alternatively, the fused feature map is input to the classification subnetwork layer to identify a target winding package in an image, for example, a target winding package in an image is selected by a frame, and the fused feature map and the target winding package in the image selected by the frame (for example, a partial image including the target winding package) are further input to the regression subnetwork layer to obtain the center position of the target winding package in the image.

[0026] In this manner, the solution of the present disclosure can utilize a target detection model to obtain the center position of the mechanical gripper and the center position of the target wound yarn package, and facilitate determining the target positional relationship between the two, thus laying the foundation for calibrating the subsequent gripping position of the mechanical gripper.

[0027] In step S103, if it is determined that the target positional relationship between the first center position and the second center position does not satisfy the second preset requirement, a calibration command is generated, and the calibration command is used to calibrate the center position of the mechanical gripper, or is used to calibrate the center position of the target wound yarn package to be gripped by the mechanical gripper.

[0028] In this way, according to the solution disclosed herein, the center position of the mechanical gripper and the center position of the target wound yarn package can be detected based on the acquired first target image and second target image, thereby determining the target positional relationship between the two, and further performing calibration based on the target positional relationship. In this way, the problem of inaccurate positioning and gripping due to mechanical wear can be quickly addressed, the gripping accuracy of the mechanical gripper can be effectively improved, and technical support can be provided for smoothly performing automated calibration of the gripping position of the mechanical gripper.

[0029] Furthermore, in a wound yarn package production workshop, especially in the automatic wrapping process of wound yarn packages, the solution disclosed herein enables the mechanical gripper to accurately position and grip the wound yarn package, which lays the foundation for avoiding damage caused when gripping the subsequent wound yarn package, and also ensures the normal operation of the subsequent wound yarn package wrapping process, and lays the foundation for greatly improving the wrapping efficiency.

[0030] In a specific example, after the execution of the calibration command is completed, the calibration result can be further verified, thus ensuring that the gripping position of the mechanical gripper has been reliably calibrated, laying the foundation for the subsequent mechanical gripper to accurately grip the wound yarn package. Specifically, FIG. 4 is a schematic flowchart of a control method according to an embodiment of the present disclosure. The method can be optionally applied to electronic devices such as personal computers, servers, server clusters, etc. It should be understood that the relevant content of the method shown in FIG. 1 above can also be applied to this example, and the detailed description of the relevant content will be omitted in this example.

[0031] In addition, the method includes at least one of the following: Specifically, as shown in FIG.

[0032] In step S401, determine whether the characteristic information of the mechanical gripper meets the first preset requirement, and if so, proceed to step S402; if not, proceed to step S406.

[0033] In step S402, a first target image collected by a first collecting device and a second target image collected by a second collecting device are obtained, and then the method proceeds to step S403. In step S403, a first center position of the mechanical gripper in the first target image is detected, and a second center position of the target wound yarn package in the second target image is detected, and then the process proceeds to step S404.

[0034] In step S404, determine whether the target position relationship between the first center position and the second center position satisfies a second preset requirement, and if so, proceed to step S406; if not, proceed to step S405.

[0035] In step S405, if it is determined that the target positional relationship between the first center position and the second center position does not satisfy the second preset requirement, generate a calibration command, which is used to calibrate the center position of the mechanical gripper or is used to calibrate the center position of the target wound yarn package to be gripped by the mechanical gripper, and then proceed to step S407.

[0036] In step S406, the grasping task is continued. In step S407, after the execution of the calibration command is completed, a first control command is generated, and the process returns to step S402 to newly acquire a new first target image and a new second target image.

[0037] Here, the first control command is used to instruct the first acquisition device to acquire a new first target image and to instruct the second acquisition device to acquire a new second target image.

[0038] That is, in the current calibration process, after the execution of the generated calibration command is completed, a new first target image and a new second target image can be obtained again, and based on the new first target image and the new second target image, a first center position of the mechanical gripper in the new first target image and a second center position of the target wound yarn package in the new second target image are detected, and a new target positional relationship is obtained. At this time, it is determined whether the obtained new target positional relationship satisfies a second preset requirement. If yes, that is, if the second preset requirement is satisfied, the calibration is successful and the current calibration process is terminated; otherwise, that is, if the second preset requirement is not satisfied, a new calibration command is generated until the new target positional relationship satisfies the second preset requirement.

[0039] In one specific example, Figure 5 is a schematic flow chart of a third embodiment of a control method according to an embodiment of the present disclosure. The method can be optionally applied to electronic devices such as personal computers, servers, server clusters, etc. It should be understood that the relevant content of the method shown in Figure 1 above can also be applied to this example, and detailed description of the relevant content will be omitted in this example. In addition, the method includes at least one of the following: Specifically, as shown in FIG.

[0040] In step S501, if it is determined that the characteristic information of the mechanical gripper meets the first preset requirement, a first target image collected by a first collecting device and a second target image collected by a second collecting device are obtained.

[0041] Here, the first collecting device is used to collect images of a mechanical gripper, and the second collecting device is used to collect images of a target wound yarn package on a trolley to be gripped by the mechanical gripper. In step S502, a first center position of the mechanical gripper in the first target image is detected, and a second center position of the target wound yarn package in the second target image is detected. Here, the detection of the first center position and the second center position can be referred to the above example, and the description will be omitted here. In step S503, a target distance is estimated based on the first center position and the second center position, and the target distance represents a relative distance between the center positions of the mechanical gripper and the target wound yarn package in the same target coordinate system.

[0042] Here, the first center position is position information in a first coordinate system corresponding to the first target image, the second center position is position information in a second coordinate system corresponding to the second target image, and the target coordinate system is one of a first coordinate system, a second coordinate system, and a global coordinate system.

[0043] In other words, after step S502, a target distance for representing the target positional relationship can be estimated and obtained based on the obtained first center position and second center position, which is convenient for determining whether or not calibration needs to be performed based on the target distance. If, in step S504, it is determined that the target distance is greater than a preset threshold, a calibration command is generated. Furthermore, in one specific example, the target distance can be obtained by the following method, specifically, estimating and obtaining the target distance based on the first center position and the second center position described above (i.e., step S503 described above) specifically includes the following: In step S503-1, a first center coordinate of the mechanical gripper in the target coordinate system is estimated based on the first center position. For example, in one example, when the target coordinate system is a first coordinate system, a first center coordinate can be obtained directly based on the first center position; for example, when the first center position is a coordinate point, the coordinate point indicating the first center position can be directly set as the first center coordinate in the first coordinate system; alternatively, when the first center position is a central region (for example, a central region including multiple coordinate points), a center coordinate can be obtained based on multiple coordinate points within the central region, and the obtained center coordinate can be directly set as the first center coordinate in the first coordinate system.

[0044] Alternatively, in another example, when the target coordinate system is the second coordinate system, a first center coordinate of the target wound yarn package in the second coordinate system can be estimated and obtained based on the first center position and the coordinate transformation relationship between the first coordinate system and the second coordinate system. For example, when the first center position is a coordinate point, the coordinate point indicating the first center position can be transformed into the second coordinate system based on the coordinate transformation relationship between the first coordinate system and the second coordinate system to obtain the first center coordinate. Alternatively, when the first center position is a central region (e.g., a central region including a plurality of coordinate points), a center coordinate corresponding to the first center position can be obtained based on a plurality of coordinate points within the central region, and the center coordinate corresponding to the obtained first center position can be transformed into the second coordinate system to obtain the first center coordinate. Alternatively, when the first center position is a central region (e.g., a central region including a plurality of coordinate points), a plurality of coordinate points within the central region can be transformed into the second coordinate system based on the coordinate transformation relationship between the first coordinate system and the second coordinate system to obtain a plurality of coordinate points in the second coordinate system, and the first center coordinate can be further obtained based on the plurality of coordinate points in the second coordinate system.

[0045] Alternatively, in another example, when the target coordinate system is a global coordinate system, a first center coordinate in the global coordinate system of the target wound yarn package can be estimated and obtained based on the first center position and the coordinate transformation relationship between the first coordinate system and the global coordinate system. For example, when the first center position is a coordinate point, the coordinate point indicating the first center position can be transformed into the global coordinate system based on the coordinate transformation relationship between the first coordinate system and the global coordinate system to obtain the first center coordinate. Alternatively, when the first center position is a central region (e.g., a central region including a plurality of coordinate points), center coordinates corresponding to the first center position can be obtained based on a plurality of coordinate points within the central region, and the center coordinates corresponding to the obtained first center position can be transformed into the global coordinate system to obtain the first center coordinate. Alternatively, when the first center position is a central region (e.g., a central region including a plurality of coordinate points), a plurality of coordinate points within the central region can be transformed into the global coordinate system based on the coordinate transformation relationship between the first coordinate system and the global coordinate system to obtain a plurality of coordinate points in the global coordinate system, and the first center coordinate can be further obtained based on the plurality of coordinate points in the global coordinate system.

[0046] In step S503-2, second center coordinates of the target wound yarn package in the target coordinate system are estimated based on the second center position. For example, in one example, when the target coordinate system is a first coordinate system, a second center coordinate in the first coordinate system of the target wound yarn package can be estimated and obtained based on the second center position and the coordinate transformation relationship between the first coordinate system and the second coordinate system. For example, when the second center position is a coordinate point, the coordinate point indicating the second center position can be converted into the first coordinate system based on the coordinate transformation relationship between the first coordinate system and the second coordinate system to obtain the second center coordinate. Alternatively, when the second center position is a central region (e.g., a central region including a plurality of coordinate points), a center coordinate corresponding to the second center position can be obtained based on a plurality of coordinate points in the central region, and the center coordinate corresponding to the obtained second center position can be converted into the first coordinate system to obtain the second center coordinate. Alternatively, when the second center position is a central region (e.g., a central region including a plurality of coordinate points), a plurality of coordinate points in the central region can be converted into the first coordinate system based on the coordinate transformation relationship between the first coordinate system and the second coordinate system to obtain a plurality of coordinate points in the first coordinate system, and the second center coordinate can be obtained based on the plurality of coordinate points in the first coordinate system.

[0047] Alternatively, in another example, when the target coordinate system is a second coordinate system, a second center coordinate can be obtained directly based on the second center position; for example, when the second center position is a coordinate point, the coordinate point indicating the second center position can be directly set as the second center coordinate in the second coordinate system; or, when the second center position is a central region (for example, a central region including multiple coordinate points), a center coordinate can be obtained based on multiple coordinate points within the central region, and the obtained center coordinate can be directly set as the second center coordinate in the second coordinate system.

[0048] Alternatively, in another example, when the target coordinate system is a global coordinate system, a second center coordinate in the global coordinate system of the target wound yarn package can be estimated and obtained based on the second center position and the coordinate transformation relationship between the second coordinate system and the global coordinate system. For example, when the second center position is a coordinate point, the coordinate point indicating the second center position can be transformed into the global coordinate system based on the coordinate transformation relationship between the second coordinate system and the global coordinate system to obtain the second center coordinate. Alternatively, when the second center position is a central region (e.g., a central region including a plurality of coordinate points), center coordinates corresponding to the second center position can be obtained based on a plurality of coordinate points within the central region, and the center coordinates corresponding to the obtained second center position can be transformed into the global coordinate system to obtain the second center coordinate. Alternatively, when the second center position is a central region (e.g., a central region including a plurality of coordinate points), a plurality of coordinate points within the central region can be transformed into the global coordinate system based on the coordinate transformation relationship between the second coordinate system and the global coordinate system to obtain a plurality of coordinate points in the global coordinate system, and the second center coordinate can be obtained based on the plurality of coordinate points in the global coordinate system.

[0049] In step S503-3, a target distance is obtained based on a first center coordinate of the mechanical gripper in the target coordinate system and a second center coordinate of the target wound yarn package in the target coordinate system. In this way, according to the solution disclosed herein, a target distance representing the target positional relationship between the detected center position of the mechanical gripper and the center position of the target wound yarn package can be estimated and obtained, and the gripping position of the mechanical gripper can be calibrated based on the target distance. In this way, the problem of inaccurate positioning and gripping due to mechanical wear can be quickly addressed, effectively improving the gripping accuracy of the mechanical gripper and laying a foundation for improving the gripping efficiency of subsequent mechanical grippers gripping wound packages, as well as avoiding damage when gripping subsequent wound yarn packages and avoiding inability to grip the wound yarn package.

[0050] Furthermore, in one specific example, a calibration command can be further generated using the following manner, specifically, when it is determined that the target distance described above is greater than a predetermined threshold, generating a calibration command (i.e., step S504 described above) specifically includes:

[0051] In method 1, when it is determined that the target distance is greater than the first-level critical value and the target distance is less than or equal to the second-level critical value, a calibration command is generated, and the calibration command is used to instruct adjusting a control parameter of the mechanical gripper based on the target distance. or, In method 2, when it is determined that the target distance is greater than the first level critical value and the target distance is greater than the second level critical value, a calibration command is generated, and the calibration command is used to instruct the position of the trolley where the target wound yarn package is located to be adjusted based on the target distance. Here, the first level critical value is smaller than the second level critical value, and the first level critical value and the second level critical value are both empirical values ​​and can be set according to actual needs, and the solution of the present disclosure is not limited thereto.

[0052] Specifically, Fig. 6 is a schematic flow chart of a fourth embodiment of a control method according to the present disclosure. The method can be optionally applied to electronic devices such as personal computers, servers, server clusters, etc. It should be understood that the relevant contents of the methods shown in Figs. 1 and 5 above can also be applied to this example, and detailed descriptions of the relevant contents will be omitted in this example.

[0053] In addition, the method includes at least one of the following: Specifically, as shown in FIG. In step S601, if it is determined that the characteristic information of the mechanical gripper meets the first preset requirement, a first target image collected by a first collecting device and a second target image collected by a second collecting device are obtained. Here, the first collecting device is used to collect images of a mechanical gripper, and the second collecting device is used to collect images of a target wound yarn package on a trolley to be gripped by the mechanical gripper. In step S602, a first center position of the mechanical gripper in the first target image is detected, and a second center position of the target wound yarn package in the second target image is detected. In step S603, a target distance is estimated based on the first center position and the second center position, and the target distance represents a relative distance between the center positions of the mechanical gripper and the target wound yarn package in the same target coordinate system.

[0054] Here, the first center position is position information in a first coordinate system corresponding to the first target image, the second center position is position information in a second coordinate system corresponding to the second target image, and the target coordinate system is one of a first coordinate system, a second coordinate system, and a global coordinate system.

[0055] In step S604, determine whether the target distance is greater than a first level threshold, if so, proceed to step S606, if not, proceed to step S605. In step S605, the characteristic information of the mechanical gripper is determined again, and the process returns to step S601.

[0056] For example, when it is determined that the operating time length of the mechanical gripper reaches a preset time (e.g., 1 hour) and the target distance is smaller than a first level critical value, the operating time length of the mechanical gripper is initialized, the operating time length of the mechanical gripper is re-statisticized, and it is determined whether the operating time obtained by the re-statistic has reached 1 hour; or, when it is determined that the number of gripping times of the mechanical gripper reaches a preset number (e.g., 80 times) and the target distance is smaller than a first level critical value, the number of gripping times of the mechanical gripper is initialized, the number of gripping times of the mechanical gripper is re-statisticized, and it is determined whether the number of gripping times obtained by the re-statistic has reached 80 times.

[0057] In step S606, determine whether the target distance is less than or equal to a second level threshold, if so, proceed to step S607, if not, proceed to step S608. In step S607, if it is determined that the target distance is greater than a first-level critical value and the target distance is less than or equal to a second-level critical value, a calibration command is generated, and the calibration command is used to instruct adjusting a control parameter of the mechanical gripper based on the target distance. In step S608, if it is determined that the target distance is greater than the first level critical value and the target distance is greater than the second level critical value, a calibration command is generated, and the calibration command is used to instruct adjusting the position of the trolley where the target wound yarn package is located based on the target distance.

[0058] It should be understood that when the first center position and the second center position are obtained, a target distance in the same target coordinate system is estimated and obtained, and whether the obtained target distance is greater than a first level critical value is determined, and if so, whether the obtained target distance is equal to or less than a second level critical value is determined, and if so, a calibration command is generated to instruct adjusting the control parameters of the mechanical gripper according to the target distance, so as to realize the adjustment to the center position of the mechanical gripper. It should also be understood that in this example, when the obtained target distance is greater than the first level critical value and equal to or less than the second level critical value, it is considered that the deviation between the center position of the mechanical gripper and the center position of the target wound yarn package is small, and at this time, the center position of the mechanical gripper can be adjusted by adjusting the control parameters of the mechanical gripper through a fine adjustment method, so as to reduce the distance between the center position of the mechanical gripper and the center position of the target wound yarn package.

[0059] Furthermore, if the obtained target distance is greater than the first level critical value, or if the obtained target distance is greater than the second level critical value, a calibration command is generated to instruct the position of the trolley where the target wound yarn package is located to be adjusted based on the target distance, thereby achieving an adjustment to the center position of the target wound yarn package. It should also be understood that in this example, if the obtained target distance is greater than the second level critical value, it is considered that the deviation between the mechanical gripper and the center position of the target wound yarn package is large, and at this time, the gripping position of the mechanical gripper can be calibrated by adjusting the position of the trolley, thereby reducing the distance between the mechanical gripper and the center position of the target wound yarn package. In this way, the calibration can be performed quickly, improving the processing efficiency of the calibration and improving the gripping accuracy of the mechanical gripper.

[0060] In addition, in an actual scenario, the control parameters of the mechanical gripper can be adjusted or the position of the trolley can be adjusted by referring to the target distance, for example, to obtain an actual relative distance in the global coordinate system of the target distance, and then the control parameters of the mechanical gripper can be adjusted or the position of the trolley can be adjusted based on the actual relative distance. As described above, the control method provided by the solution of the present disclosure has several advantages over the prior art, specifically including:

[0061] First, it is more automated. Compared with the prior art, the solution disclosed herein can quickly address the problem of inaccurate positioning and gripping caused by mechanical wear, and provides technical support for realizing automatic calibration of the gripping position of the mechanical gripper in the automatic wrapping process of a wound yarn package, without the need for human intervention in the process, thus making the automatic wrapping process more automated and saving a large amount of labor and time costs.

[0062] Second, the gripping is more accurate. According to the solution of the present disclosure, different calibration methods can be provided based on the obtained target distance, for example, the control parameters of the mechanical gripper are adjusted when the deviation between the center position of the mechanical gripper and the center position of the target wound yarn package is considered to be small, or the position of the trolley is adjusted when the deviation between the center position of the mechanical gripper and the center position of the target wound yarn package is considered to be large, thus effectively improving the gripping accuracy of the mechanical gripper.

[0063] Third, the efficiency of automatic packaging is higher. The solution disclosed herein effectively solves the problem of inaccurate positioning and gripping of the mechanical gripper, laying the foundation for avoiding the mechanical gripper damaging or being unable to grip the wound yarn package due to inaccurate subsequent gripping, ensuring the normal operation of the packaging process of the subsequent wound yarn package, and laying the foundation for greatly improving packaging efficiency.

[0064] The solution of the present disclosure further provides a control device, as shown in FIG. an acquisition unit 701 for acquiring a first target image collected by a first collecting device and a second target image collected by a second collecting device when it is determined that the characteristic information of the mechanical gripper satisfies a first preset requirement, the first collecting device being used to perform image collection for the mechanical gripper, and the second collecting device being used to perform image collection for a target wound yarn package on a trolley to be gripped by the mechanical gripper; a detection unit 702 for detecting a first center position of the mechanical gripper in the first target image and detecting a second center position of the target wound yarn package in the second target image; and a processing unit 703 for generating a calibration command when it is determined that the target positional relationship between the first center position and the second center position does not satisfy a second preset requirement, the calibration command being used to calibrate a center position of the mechanical gripper or being used to calibrate a center position of a target wound yarn package to be gripped by the mechanical gripper.

[0065] In one specific example of the solution of the present disclosure, the detection unit specifically comprises: inputting the first target image into a target detection model to obtain a first center position of the mechanical gripper in the first target image; inputting the second target image into the target detection model to obtain a second center position of the target wound yarn package in the second target image. In one specific example of the solution of the present disclosure, the target detection model includes at least a first network layer, a second network layer and a third network layer; Wherein, the first network layer includes at least a first sub-network layer, a second sub-network layer and a third sub-network layer, the first sub-network layer is used for performing a first convolution process on an input image to obtain a first convolution feature map, the second sub-network layer is used for performing a linear process on the first convolution feature map to obtain a linear feature map, and for performing a connection process between the linear feature map and the first convolution feature map to obtain a connection feature map, and the third sub-network layer is used for performing a second convolution process on the connection feature map to obtain a second convolution feature map; the second network layer is used for performing a first convolution process on the connection feature map and the second convolution feature map respectively, and performing a feature fusion process on the processed result to obtain a fusion feature map; The third network layer includes a fourth sub-network layer and a fifth sub-network layer, the fourth sub-network layer is used to identify and obtain a mechanical gripper or a target wound yarn package in the image based on the fused feature map, and the fifth sub-network layer is used to obtain a center position of the mechanical gripper in the image or a center position of the target wound yarn package in the image based on the fused feature map.

[0066] In one specific example of the solution of the present disclosure, the processing unit comprises: a target distance is estimated based on the first center position and the second center position, the target distance represents a relative distance between center positions of the mechanical gripper and the target wound yarn package in a same target coordinate system, the first center position is position information in a first coordinate system corresponding to the first target image, the second center position is position information in a second coordinate system corresponding to the second target image, and the target coordinate system is one of a first coordinate system, a second coordinate system, and a global coordinate system; and generating a calibration command if the target distance is determined to be greater than a preset threshold. In one specific example of the solution of the present disclosure, the processing unit specifically comprises: Estimating a first center coordinate of the mechanical gripper in the target coordinate system based on the first center position; estimating and obtaining second center coordinates of the target wound yarn package in the target coordinate system based on the second center position; and obtaining a target distance based on a first center coordinate of the mechanical gripper in the target coordinate system and a second center coordinate of the target wound yarn package in the target coordinate system.

[0067] In one specific example of the solution of the present disclosure, the processing unit specifically comprises: generating a calibration command when the target distance is greater than a first-level critical value and when the target distance is determined to be less than or equal to a second-level critical value, the calibration command being used to instruct adjusting a control parameter of the mechanical gripper based on the target distance; or When it is determined that the target distance is greater than the first level critical value and that the target distance is greater than the second level critical value, a calibration command is generated, and the calibration command is used to instruct adjusting the position of a trolley on which the target wound yarn package is located based on the target distance. In one specific example of the solution of the present disclosure, The processing unit is further used to generate a first control command after execution of the calibration command is completed, the first control command is further used to instruct the first acquisition device to acquire a new first target image and to instruct the second acquisition device to acquire a new second target image; The acquisition unit is further used for acquiring a new first target image acquired by the first acquisition device, and acquiring a new second target image acquired by a second acquisition device; the detection unit is further used for detecting a first center position of the mechanical gripper in the new first target image and a second center position of the target wound yarn package in the new second target image; The processing unit is further used for determining whether a target position relationship between a first center position in the new first target image and a second center position in the new second target image satisfies a second preset requirement. The specific functions and exemplary descriptions of each module and sub-module of the apparatus in the embodiments of the present disclosure may refer to the relevant descriptions of the corresponding steps in the embodiments of the above method, and will not be repeated here. In the technical solution disclosed herein, the acquisition, storage, and application of users' personal information complies with the provisions of relevant laws and regulations and does not violate public order and morals.

[0068] FIG. 8 is a structural block diagram of an electronic device according to an embodiment of the present disclosure. As shown in FIG. 8, the electronic device includes a memory 810 and a processor 820, and the memory 810 stores a computer program executable by the processor 820. The number of the memory 810 and the processor 820 may be one or more. The memory 810 may store one or more computer programs, which, when executed by the electronic device, cause the electronic device to perform the method provided by the above method embodiment. The electronic device may further include: The communication interface 830 is used for communicating with an external device and performing data interaction and transmission. When the memory 810, the processor 820, and the communication interface 830 are implemented independently, the memory 810, the processor 820, and the communication interface 830 are connected to each other via a bus and can communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus can be classified into an address bus, a data bus, a control bus, and the like. For ease of explanation, only one thick line is shown in FIG. 8, but it does not represent only one bus or only one type of bus.

[0069] Optionally, in a specific implementation, when the memory 810, the processor 820, and the communication interface 830 are integrated on one chip, the memory 810, the processor 820, and the communication interface 830 can communicate with each other via an internal interface.

[0070] It should be understood that the processor may be a Central Processing Unit (CPU) or may be other general purpose processors, Digital Signal Processing (DSP), Application Specific Integrated Circuits (ASIC), Field Programmable Gate Arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general purpose processor may be a microprocessor or any conventional processor, etc. Additionally, the processor may be a processor supporting the Advanced RISC Machines (ARM) architecture. In addition, optionally, the memory may include read-only memory and random access memory, and may further include non-volatile random access memory. The memory may be either volatile or non-volatile memory, or may include both volatile and non-volatile memory. Here, non-volatile memory may include Read-Only Memory (ROM), Programmable ROM (PROM), Erasable PROM (EPROM), Electrically EPROM (EEPROM), or flash memory. Volatile memory may include Random Access Memory (RAM) that acts as an external cache. By way of example and not limitation, many forms of RAM are available. For example, static random access memory (Static RAM, SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (Enhanced SDRAM, ESDRAM), synchlink DRAM (SLDRAM), and direct RAMBUS RAM (DR RAM).

[0071] The above-mentioned embodiments may be implemented in whole or in part in software, hardware, firmware, or any combination thereof. When implemented in software, the whole or in part may be implemented in the form of a computer program product. A computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, a process or function according to the embodiments of the present disclosure is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center via wire (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, Bluetooth, microwave, etc.). The computer-readable storage medium may be any available medium that can be accessed by a computer, or a data storage device including a server, data center, etc. integrated with one or more available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a digital versatile disk (DVD)), or a semiconductor medium (e.g., a solid state disk (SSD)). Note that the computer-readable storage medium referred to in this disclosure may be a non-volatile storage medium, in other words, a non-transitory storage medium.

[0072] Those skilled in the art can understand that all or part of the steps for realizing the above embodiments may be implemented by hardware, or may be implemented by instructing relevant hardware by a program, and the program may be stored in a computer-readable storage medium, and the storage medium may be a read-only memory, a magnetic disk, an optical disk, etc. In describing the embodiments of the present disclosure, the reference words "one embodiment", "some embodiments", "examples", "particular examples", or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present disclosure. And, the specific features, structures, materials, or characteristics described can be combined in any suitable manner in any one or more embodiments or examples. Furthermore, a person skilled in the art may combine different embodiments or examples described herein and features of different embodiments or examples to the extent that they are not mutually inconsistent.

[0073] In the description of the embodiments of the present disclosure, unless otherwise specified, " / " means "or", for example, A / B can mean either A or B. In this specification, "and / or" is merely for describing the related relationship of related objects, and indicates that three kinds of relationships may exist, for example, A and / or B can indicate the following three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0074] In the description of the embodiments of the present disclosure, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance, nor should they be construed as implying the number of technical features depicted. Thus, features defined as "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the embodiments of the present disclosure, "plurality" means two or more, unless otherwise specified.

[0075] The above are merely illustrative examples of the present disclosure, and are not intended to limit the present disclosure. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present disclosure should be included within the scope of protection of the present disclosure.

Claims

1. When it is determined that the characteristic information of the mechanical gripper satisfies a first preset requirement, acquiring a first target image collected by a first collecting device and a second target image collected by a second collecting device, the first collecting device being used to collect images of the mechanical gripper, and the second collecting device being used to collect images of a target wound yarn package on a trolley to be gripped by the mechanical gripper; Detecting a first center position of the mechanical gripper in the first target image and detecting a second center position of the target wound yarn package in the second target image; generating a calibration command when it is determined that the target positional relationship between the first center position and the second center position does not satisfy a second preset requirement, the calibration command being used to calibrate a center position of the mechanical gripper or to calibrate a center position of a target wound yarn package to be gripped by the mechanical gripper. Control methods.

2. Detecting a first center position of the mechanical gripper in the first target image and detecting a second center position of the target wound yarn package in the second target image includes: inputting the first target image into a target detection model to obtain a first center position of the mechanical gripper in the first target image; inputting the second target image into the target detection model to obtain a second center location of the target wound yarn package in the second target image. The control method according to claim 1 .

3. the target detection model includes at least a first network layer, a second network layer and a third network layer; Here, the first network layer includes at least a first sub-network layer, a second sub-network layer and a third sub-network layer, the first sub-network layer is used to perform a first convolution process on an input image to obtain a first convolution feature map, the second sub-network layer is used to perform a linear process on the first convolution feature map to obtain a linear feature map, and perform a connection process between the linear feature map and the first convolution feature map to obtain a connection feature map, and the third sub-network layer is used to perform a second convolution process on the connection feature map to obtain a second convolution feature map; the second network layer is used for performing a first convolution process on the connection feature map and the second convolution feature map respectively, and performing a feature fusion process on the processed result to obtain a fusion feature map; the third network layer includes a fourth sub-network layer and a fifth sub-network layer, the fourth sub-network layer is used for identifying and obtaining a mechanical gripper or a target wound yarn package in the image based on the fused feature map, and the fifth sub-network layer is used for obtaining a center position of the mechanical gripper in the image or a center position of the target wound yarn package in the image based on the fused feature map; The control method according to claim 2 .

4. The control method includes: before determining that the target positional relationship between the first central position and the second central position does not satisfy a second preset requirement; and estimating a target distance based on the first center position and the second center position, the target distance representing a relative distance between center positions of the mechanical gripper and the target wound yarn package in a same target coordinate system, the first center position being position information in a first coordinate system corresponding to the first target image, the second center position being position information in a second coordinate system corresponding to the second target image, and the target coordinate system being one of a first coordinate system, a second coordinate system, and a global coordinate system. generating a calibration command when determining that a target position relationship between the first central position and the second central position does not satisfy a second preset requirement; generating a calibration command when the target distance is determined to be greater than a preset threshold. The control method according to claim 1 .

5. The method of estimating a target distance based on the first center position and the second center position includes: Estimating a first center coordinate of the mechanical gripper in the target coordinate system based on the first center position; estimating and obtaining second center coordinates of the target wound yarn package in the target coordinate system based on the second center position; obtaining a target distance based on a first center coordinate of the mechanical gripper in the target coordinate system and a second center coordinate of the target wound yarn package in the target coordinate system. The control method according to claim 4.

6. generating a calibration command when determining that the target distance is greater than a preset threshold; generating a calibration command when the target distance is greater than a first-level critical value and when the target distance is determined to be less than or equal to a second-level critical value, the calibration command being used to instruct adjusting a control parameter of the mechanical gripper based on the target distance; or generating a calibration command when it is determined that the target distance is greater than the first level critical value and that the target distance is greater than the second level critical value, the calibration command being used to instruct a position of a trolley on which the target wound yarn package is located to be adjusted based on the target distance. The control method according to claim 4.

7. The control method includes: After generating the calibration commands, generating a first control command after execution of the calibration command is completed, the first control command being used to instruct the first acquisition device to acquire a new first target image and to instruct the second acquisition device to acquire a new second target image; acquiring a new first target image acquired by the first acquisition device and acquiring a new second target image acquired by a second acquisition device; Detecting a first center position of the mechanical gripper in the acquired new first target image and a second center position of the target wound yarn package in the acquired new second target image; determining whether a target position relationship between the first center position in the new first target image and the second center position in the new second target image satisfies a second preset requirement; The control method according to claim 1 .

8. an acquisition unit for acquiring a first target image collected by a first collection device and a second target image collected by a second collection device when it is determined that the characteristic information of the mechanical gripper satisfies a first preset requirement, the first collection device being used to perform image collection for the mechanical gripper, and the second collection device being used to perform image collection for a target wound yarn package on a trolley to be gripped by the mechanical gripper; a detection unit for detecting a first center position of the mechanical gripper in the first target image and detecting a second center position of the target wound yarn package in the second target image; a processing unit for generating a calibration command when it is determined that a target positional relationship between the first center position and the second center position does not satisfy a second preset requirement, the calibration command being used to calibrate a center position of the mechanical gripper or to calibrate a center position of a target wound yarn package to be gripped by the mechanical gripper. Control device.

9. The detection unit specifically includes: inputting the first target image into a target detection model to obtain a first center position of the mechanical gripper in the first target image; inputting the second target image into the target detection model to obtain a second center position of the target wound yarn package in the second target image; The control device according to claim 8.

10. the target detection model includes at least a first network layer, a second network layer and a third network layer; Here, the first network layer includes at least a first sub-network layer, a second sub-network layer and a third sub-network layer, the first sub-network layer is used to perform a first convolution process on an input image to obtain a first convolution feature map, the second sub-network layer is used to perform a linear process on the first convolution feature map to obtain a linear feature map, and perform a connection process between the linear feature map and the first convolution feature map to obtain a connection feature map, and the third sub-network layer is used to perform a second convolution process on the connection feature map to obtain a second convolution feature map; the second network layer is used for performing a first convolution process on the connection feature map and the second convolution feature map respectively, and performing a feature fusion process on the processed result to obtain a fusion feature map; the third network layer includes a fourth sub-network layer and a fifth sub-network layer, the fourth sub-network layer is used for identifying and obtaining a mechanical gripper or a target wound yarn package in the image based on the fused feature map, and the fifth sub-network layer is used for obtaining a center position of the mechanical gripper in the image or a center position of the target wound yarn package in the image based on the fused feature map; The control device according to claim 9.

11. The processing unit includes: a target distance is estimated based on the first center position and the second center position, the target distance representing a relative distance between center positions of the mechanical gripper and the target wound yarn package in a same target coordinate system, the first center position being position information in a first coordinate system corresponding to the first target image, the second center position being position information in a second coordinate system corresponding to the second target image, and the target coordinate system being one of a first coordinate system, a second coordinate system, and a global coordinate system; and generating a calibration command when the target distance is determined to be greater than a preset threshold. The control device according to claim 8.

12. The processing unit specifically includes: Estimating a first center coordinate of the mechanical gripper in the target coordinate system based on the first center position; estimating and obtaining second center coordinates of the target wound yarn package in the target coordinate system based on the second center position; and obtaining a target distance based on a first center coordinate of the mechanical gripper in the target coordinate system and a second center coordinate of the target wound yarn package in the target coordinate system. The control device according to claim 11.

13. The processing unit specifically includes: generating a calibration command when the target distance is greater than a first-level critical value and when the target distance is determined to be less than or equal to a second-level critical value, the calibration command being used to instruct adjusting a control parameter of the mechanical gripper based on the target distance; or generating a calibration command when it is determined that the target distance is greater than the first level critical value and that the target distance is greater than the second level critical value, the calibration command being used to instruct to adjust a position of a trolley on which the target wound yarn package is located based on the target distance. The control device according to claim 11.

14. The processing unit is further used to generate a first control command after execution of the calibration command is completed, the first control command being further used to instruct the first acquisition device to acquire a new first target image and to instruct the second acquisition device to acquire a new second target image; The acquisition unit is further used for acquiring a new first target image acquired by the first acquisition device and acquiring a new second target image acquired by a second acquisition device; the detection unit is further used for detecting a first center position of the mechanical gripper in the new first target image and a second center position of the target wound yarn package in the new second target image; the processing unit is further used for determining whether a target position relationship between a first center position in the new first target image and a second center position in the new second target image satisfies a second preset requirement; A control device according to any one of claims 8 to 13.

15. At least one processor; a memory in communication with the at least one processor; An electronic device, wherein the memory stores instructions executable by the at least one processor, the instructions, when executed by the at least one processor, causing the at least one processor to perform a control method according to any one of claims 1 to 7.

16. A non-transitory computer-readable storage medium having stored thereon computer instructions for causing a computer to carry out the control method according to any one of claims 1 to 7.

17. A program for implementing the control method according to any one of claims 1 to 7 when executed by a processor.

Images