AGV-based pump accessory carrying method and system

Abstract

The invention provides a pump accessory carrying method and system based on an AGV. The method comprises the steps that image information of a pump accessory stacking area is collected in real time, and the number of to-be-carried pump accessories and the loading state of a loading mechanical arm are recognized from the image information; the carrying efficiency of the loading mechanical arm is evaluated based on the number of the carried pump accessories and the loading state of the loading mechanical arm; and when the carrying efficiency of the loading mechanical arm is lower than an efficiency threshold value, the target AGV assembled with the mechanical arm is dispatched to a pump accessory stacking area for auxiliary carrying.

Description

Technical Field

[0001] The present invention relates to the technical field of AGVs, and in particular to an AGV-based pump parts transportation method and system. Background Art

[0002] In the pump parts production workshop, the finished pump parts are usually placed in a specific area and transported to the corresponding storage area by AGV (Automated Guided Vehicle) according to the type of pump parts. In order to improve the handling efficiency, the specific area is usually equipped with a loading robot arm to automatically place the finished pump parts on the AGV.

[0003] However, when there are a large number of pump parts to be transported, due to the limited number of loading robotic arms, the loading robotic arms often fail to place the produced pump parts on the AGV in time, resulting in a significant decrease in transportation efficiency. The traditional solution is usually to increase the number of loading robotic arms to improve the transportation capacity, but this not only increases equipment costs and space occupancy, but also makes it difficult to flexibly adjust transportation resources according to actual needs.

[0004] It can be seen that how to improve the loading and handling efficiency of pump accessories in a lower-cost way without adding loading robotic arms is a technical problem that needs to be solved urgently. Summary of the invention

[0005] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a pump parts handling method, system, electronic equipment, computer storage medium and computer program product based on AGV.

[0006] The present invention provides a pump parts handling method based on AGV, the method comprising the following steps: Collect image information of the pump parts stacking area in real time, and identify the number of pump parts to be transported and the loading status of the loading robot arm from the image information; The handling efficiency of the loading robot arm is evaluated based on the number of pump parts that have been transported and the loading status of the loading robot arm; When the handling efficiency of the loading robot arm is lower than the efficiency threshold, the target AGV equipped with the robot arm is dispatched to the pump parts stacking area for auxiliary handling.

[0007] Optionally, the real-time acquisition of image information of the pump parts stacking area, and identification of the number of pump parts to be transported and the loading status of the loading robot arm from the image information, include: Determine a target high-definition camera according to the layout position of the pump parts stacking area, use the high-definition camera to obtain image information of the pump parts stacking area in real time, and pre-process the obtained image information to improve image quality; Applying the object detection model based on deep learning algorithm, the pre-processed images are subjected to feature extraction and classification to identify the pump parts and loading robot arms in the images. By performing shape analysis and size measurement on the pump accessories, the number of pump accessories to be transported is further determined. In addition, based on the position and posture of the loading robot arm in the image and the preset loading status recognition rules, the current loading status of the loading robot arm is judged.

[0008] Optionally, evaluating the handling efficiency of the loading robot arm based on the number of pump parts that have been handled and the loading status of the loading robot arm includes: Calculate theoretical handling efficiency based on the number of pump parts to be handled and the preset standard handling volume per unit time; Real-time monitoring of the actual handling progress of the loading robot, including the number of pump parts carried and the time consumed in the handling; The actual handling progress is compared with the theoretical handling efficiency, and the delay factors in the handling process are taken into account. The actual handling efficiency evaluation value of the loading robot arm is obtained through dynamic adjustment of the algorithm model. The actual handling efficiency evaluation value is the handling efficiency.

[0009] Optionally, when the handling efficiency of the loading robot arm is lower than the efficiency threshold, dispatching the target AGV equipped with the robot arm to the pump parts stacking area for auxiliary handling includes: When the handling efficiency of the loading robot arm is lower than the efficiency threshold, the sideline length of the idle area in the pump parts stacking area is obtained according to the image information; wherein the idle area refers to an area in the pump parts stacking area that cannot be covered by the loading robot arm during the loading operation and has no other queued AGVs, and the sideline length of the idle area refers to the length of the contact line between the idle area and the AGV parking area; A first number of target AGVs equipped with robot arms are determined according to the length of the sideline of the idle area, and dispatch instructions are sent to the target AGVs to dispatch them to the pump parts stacking area for auxiliary transportation.

[0010] Optionally, determining a first number of target AGVs equipped with robot arms according to the sideline length of the idle area includes: Determining a second quantity according to the length of the sideline of the idle area; Calculate the difference between the efficiency threshold and the handling efficiency, calculate a first adjustment coefficient according to the difference, obtain the total number of task configurations of the target AGV in an idle state, and calculate a second adjustment coefficient according to the total number of task configurations; The first adjustment coefficient and the second adjustment coefficient are multiplied by the second quantity at the same time to obtain the final first quantity.

[0011] Optionally, the method further comprises: After the target AGV equipped with the robot arm is dispatched to the pump parts storage area, the target AGV communicates with other AGVs in the pump parts storage area to coordinate an entry path.

[0012] The present invention also provides a pump parts handling system based on AGV, the system comprising a processing device and a storage device, the processing device calls and runs a computer program in the storage device to implement the following steps; Collect image information of the pump parts stacking area in real time, and identify the number of pump parts to be transported and the loading status of the loading robot arm from the image information; The handling efficiency of the loading robot arm is evaluated based on the number of pump parts that have been transported and the loading status of the loading robot arm; When the handling efficiency of the loading robot arm is lower than the efficiency threshold, the target AGV equipped with the robot arm is dispatched to the pump parts stacking area for auxiliary handling.

[0013] The present invention also provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute any of the methods described above.

[0014] The present invention also provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, any of the above methods is executed.

[0015] The present invention also provides a computer program product, which includes a computer program stored in a computer storage medium, and when the computer program is executed by a processor of an electronic device, it implements any of the methods described above.

[0016] The beneficial effects of the present invention are at least: Improve handling efficiency: Through real-time data collection and intelligent evaluation, the system can promptly identify bottlenecks in the handling process and dynamically dispatch target AGVs equipped with robotic arms for auxiliary handling, thereby significantly improving the handling efficiency of the pump parts production workshop without increasing the implementation cost.

[0017] Reduce labor costs: Automated and intelligent handling methods reduce dependence on manual labor and reduce labor costs. At the same time, due to the improvement of handling efficiency, it also indirectly reduces the production downtime caused by handling delays. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 It is a schematic diagram of a pump parts handling method based on AGV disclosed in an embodiment of the present invention.

[0020] Figure 2 It is a schematic diagram of a pump parts handling system based on AGV disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0022] When there are a large number of pump parts to be transported, due to the limited number of loading robotic arms, the loading robotic arms often fail to place the produced pump parts on the AGV in time, resulting in a significant decrease in transportation efficiency. The traditional solution is usually to increase the number of loading robotic arms to improve the transportation capacity, but this not only increases equipment costs and space occupancy, but also makes it difficult to flexibly adjust transportation resources according to actual needs.

[0023] It can be seen that how to improve the loading and handling efficiency of pump accessories in a lower-cost way without adding loading robotic arms is a technical problem that needs to be solved urgently.

[0024] For the above technical issues, please refer to Figure 1 The embodiment of the present invention discloses a pump parts handling method based on AGV, and the method comprises the following steps: Collect image information of the pump parts stacking area in real time, and identify the number of pump parts to be transported and the loading status of the loading robot arm from the image information; The handling efficiency of the loading robot arm is evaluated based on the number of pump parts that have been transported and the loading status of the loading robot arm; When the handling efficiency of the loading robot arm is lower than the efficiency threshold, the target AGV equipped with the robot arm is dispatched to the pump parts stacking area for auxiliary handling.

[0025] In this solution, the present invention acquires image information of the area in real time by deploying high-definition cameras or other image acquisition devices in the pump accessories stacking area. These image information include the stacking situation, quantity and current operation status of the loading robot arm of the pump accessories. Using advanced image recognition technology, such as deep learning algorithm, the collected image information is processed and analyzed to accurately identify the number of pump accessories to be transported and the loading status of the loading robot arm (such as idle, loading, loading completed, etc.). Then, according to the identified number of pump accessories to be transported and the loading status of the loading robot arm, combined with the preset handling efficiency evaluation model, the handling efficiency of the current loading robot arm can be dynamically calculated and evaluated. Finally, when the evaluation result shows that the handling efficiency of the loading robot arm is lower than the preset efficiency threshold, the scheduling mechanism will be automatically triggered to dispatch the target AGV equipped with the robot arm to the pump accessories stacking area. Compared with conventional AGVs, these target AGVs do not need the loading robot arm to load the pump accessories onto their bearing parts, but can use the robot arm equipped with itself to load the pump accessories onto their bearing parts by itself to improve the overall handling efficiency.

[0026] It should be noted that although the pump parts production workshop is equipped with target AGVs equipped with mechanical arms, due to the lack of an intelligent scheduling system, these target AGVs often cannot fully exert their potential and still face the problem of insufficient handling efficiency. The above solution of the present invention can achieve reasonable scheduling of the target AGVs.

[0027] Optionally, the real-time acquisition of image information of the pump parts stacking area, and identification of the number of pump parts to be transported and the loading status of the loading robot arm from the image information, include: Determine a target high-definition camera according to the layout position of the pump parts stacking area, use the high-definition camera to obtain image information of the pump parts stacking area in real time, and pre-process the obtained image information to improve image quality; Applying the object detection model based on deep learning algorithm, the pre-processed images are subjected to feature extraction and classification to identify the pump parts and loading robot arms in the images. By performing shape analysis and size measurement on the pump accessories, the number of pump accessories to be transported is further determined. In addition, based on the position and posture of the loading robot arm in the image and the preset loading status recognition rules, the current loading status of the loading robot arm is judged.

[0028] In this embodiment, first, a suitable high-definition camera is selected according to the layout of the pump parts stacking area, that is, a high-definition camera deployed in the pump parts stacking area. The camera is scheduled to capture the image data of the pump parts stacking area in real time. These cameras should have high resolution and fast response capabilities to ensure that the collected image information is clear, accurate and highly real-time.

[0029] Due to factors such as lighting changes and noise interference that may exist in the actual environment, direct recognition of the original image may cause errors. Therefore, before recognition, the image needs to be preprocessed, including denoising (reducing noise interference in the image) and contrast enhancement (increasing the contrast between different objects in the image to make recognition more accurate), etc., to improve image quality and lay a good foundation for subsequent recognition steps.

[0030] The pre-processed images will be sent to the target detection model based on the deep learning algorithm for processing. After a lot of training, the model can automatically extract features in the image and classify them, so as to accurately identify the pump parts and loading robot arms in the image. Among them, the deep learning algorithm is usually various algorithms based on neural networks, and the present invention does not specifically limit it.

[0031] After identifying the pump parts, the system will further determine the number of pump parts to be transported through shape analysis (including contour extraction), size measurement (including area calculation), etc. For the loading robot arm, the system will determine its current state by analyzing its position and posture in the image and combining it with the preset loading state recognition rules. Among them, the loading state recognition rules may include feature information such as the extension degree of the robot arm and the position of the end effector, and obtain accurate loading state judgment results by matching with the preset state.

[0032] Optionally, evaluating the handling efficiency of the loading robot arm based on the number of pump parts that have been handled and the loading status of the loading robot arm includes: Monitor the actual handling progress of the loading robot arm in real time, including the number of pump parts that have been handled and the time consumed for handling, and calculate the actual handling volume per unit time, i.e., the actual handling efficiency, based on the number and time; Taking into account the delay factors in the handling process, the actual handling efficiency of the loading robot arm is dynamically adjusted through the algorithm model to obtain the handling efficiency; And, the efficiency threshold is specifically: the standard handling volume per unit time configured according to the identified number of pump parts to be handled, that is, the efficiency threshold.

[0033] In this embodiment, the actual handling progress of the loading robot arm is monitored in real time, which includes the number of pump parts that have been successfully transported and the time consumed to complete these handling tasks. Next, the actual handling progress is compared with the theoretical handling efficiency. However, simply comparing the two is not enough, because there are often various delay factors in the actual handling process. For example, the operating speed of the robot arm may be affected by factors such as load size and complexity of the handling path. Therefore, the system needs to use a complex algorithm model to comprehensively consider these factors, dynamically adjust the actual handling efficiency, and obtain a more accurate evaluation value. This evaluation value reflects the actual handling efficiency that the robot arm can achieve under the current working conditions. The algorithm model is preferably built based on Transformer, or based on a general large model (GPT series, BERT series, etc.).

[0034] In addition, a standard handling volume per unit time is configured according to the number of pump parts to be transported obtained through image recognition technology (i.e., the number of pump parts that the robot can transport per hour or per minute under ideal conditions), and a theoretical handling efficiency is calculated, which is used as the aforementioned efficiency threshold. This theoretical value represents the handling speed that the robot should achieve in the absence of any delays or interference. Among them, the more pump parts to be transported, the greater the standard handling volume per unit time, and vice versa. That is, the loading robot arm of the present invention can dynamically adjust the loading speed according to the amount of loading tasks.

[0035] Optionally, when the handling efficiency of the loading robot arm is lower than the efficiency threshold, dispatching the target AGV equipped with the robot arm to the pump parts stacking area for auxiliary handling includes: When the handling efficiency of the loading robot arm is lower than the efficiency threshold, the sideline length of the idle area in the pump parts stacking area is obtained according to the image information; wherein the idle area refers to an area in the pump parts stacking area that cannot be covered by the loading robot arm during the loading operation and has no other queued AGVs, and the sideline length of the idle area refers to the length of the contact line between the idle area and the AGV parking area; A first number of target AGVs equipped with robot arms are determined according to the length of the sideline of the idle area, and dispatch instructions are sent to the target AGVs to dispatch them to the pump parts stacking area for auxiliary transportation.

[0036] In this embodiment, when the handling efficiency is lower than the preset efficiency threshold, the scheduling mechanism is triggered, that is, the target AGV equipped with a robotic arm is controlled to come forward for auxiliary handling. After the scheduling mechanism is triggered, the idle area in the pump parts stacking area is identified based on the image information captured by the high-definition camera. The "idle area" here refers to those areas that cannot be covered by the loading robotic arm during the loading operation and are not currently occupied by other queued AGVs. Next, the length of the contact line between the idle area and the AGV parking area (that is, the area where the AGV stops and waits for the loading robotic arm to load the pump parts) is measured, that is, the "edge length of the idle area". This length information is crucial to determining the number of AGVs that need to be scheduled, because it is directly related to the number of target AGVs that can be accommodated in the idle area and the operating space of these target AGVs in the area.

[0037] According to the length of the edge of the free area, the first number of target AGVs equipped with robotic arms that need to be dispatched is calculated and determined. The determination of this number needs to take into account factors such as the size of the AGV, the operating requirements, and the layout of the free area. Once the number of target AGVs is determined, dispatch instructions will be sent to these AGVs to guide them to the pump parts stacking area for auxiliary handling.

[0038] Optionally, determining a first number of target AGVs equipped with robot arms according to the sideline length of the idle area includes: Determining a second quantity according to the length of the sideline of the idle area; Calculate the difference between the efficiency threshold and the handling efficiency, calculate a first adjustment coefficient according to the difference, obtain the total number of task configurations of the target AGV in an idle state, and calculate a second adjustment coefficient according to the total number of task configurations; The first adjustment coefficient and the second adjustment coefficient are multiplied by the second quantity at the same time to obtain the final first quantity.

[0039] In this embodiment, based on the length of the sideline of the idle area, the size of the AGV, the operation requirements, the layout of the idle area and other factors are comprehensively considered to determine the preliminary second number of target AGVs that need to be scheduled.

[0040] At the same time, the present invention also calculates the first adjustment coefficient based on the difference between the efficiency threshold and the handling efficiency. The first adjustment coefficient is positively correlated with the difference, that is, the higher the degree to which the handling efficiency of the loading robot arm is lower than the efficiency threshold, the larger the first adjustment coefficient is set, so as to use a higher first adjustment coefficient to appropriately increase the second quantity, and vice versa. The smaller the first adjustment coefficient is set. However, the present invention does not limit the calculation formula between the first adjustment coefficient and the difference.

[0041] Furthermore, the present invention is also configured to obtain the total number of task configurations of target AGVs in an idle state, that is, to count the task configuration types of each target AGV in an idle state, and to obtain the number of each type of configuration tasks as the total number of task configurations, and then to calculate the second adjustment coefficient based on the total number of task configurations. Among them, the greater the total number of task configurations, the higher the probability that the target AGV will be scheduled to other tasks. At this time, the smaller the second adjustment coefficient is set, that is, the number of target AGVs used for auxiliary transportation is reduced, and vice versa. The larger the second adjustment coefficient is set. Similar to the above, the present invention does not limit the calculation formula between the second adjustment coefficient and the total number of task configurations.

[0042] Optionally, the method further comprises: After the target AGV equipped with the robot arm is dispatched to the pump parts storage area, the target AGV communicates with other AGVs in the pump parts storage area to coordinate an entry path.

[0043] In this embodiment, after the target AGV reaches the pump accessories stacking area, since there are already many conventional AGVs waiting to be loaded in the pump accessories stacking area, the target AGV is controlled to communicate with these conventional AGVs to coordinate and obtain an entry path. The target AGV can then smoothly enter the above-mentioned idle area through the entry path to realize self-loading and transportation of pump accessories.

[0044] See also Figure 2 As shown, an embodiment of the present invention further provides a pump parts handling system based on AGV, the system comprising a processing device and a storage device, characterized in that: the processing device calls and runs a computer program in the storage device to implement the following steps; Collect image information of the pump parts stacking area in real time, and identify the number of pump parts to be transported and the loading status of the loading robot arm from the image information; The handling efficiency of the loading robot arm is evaluated based on the number of pump parts that have been transported and the loading status of the loading robot arm; When the handling efficiency of the loading robot arm is lower than the efficiency threshold, the target AGV equipped with the robot arm is dispatched to the pump parts stacking area for auxiliary handling.

[0045] An embodiment of the present invention further provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the method described in any of the above embodiments.

[0046] An embodiment of the present invention further provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in any of the above embodiments is executed.

[0047] An embodiment of the present invention further provides a computer program product, which includes a computer program stored in a computer storage medium, and when the computer program is executed by a processor of an electronic device, the method described in any of the above embodiments is implemented.

[0048] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (apparatus), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0049] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0050] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0051] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A pump parts handling method based on AGV, characterized in that: The method comprises the following steps: Collect image information of the pump parts stacking area in real time, and identify the number of pump parts to be transported and the loading status of the loading robot arm from the image information; The handling efficiency of the loading robot arm is evaluated based on the number of pump parts that have been transported and the loading status of the loading robot arm; When the handling efficiency of the loading robot arm is lower than the efficiency threshold, the target AGV equipped with the robot arm is dispatched to the pump parts stacking area for auxiliary handling.

2. The pump parts handling method based on AGV according to claim 1 is characterized in that: The real-time acquisition of image information of the pump parts stacking area, and identification of the number of pump parts to be transported and the loading status of the loading robot arm from the image information, include: Determine a target high-definition camera according to the layout position of the pump parts stacking area, use the high-definition camera to obtain image information of the pump parts stacking area in real time, and pre-process the obtained image information to improve image quality; Applying the target detection model based on deep learning algorithm, the pre-processed images are subjected to feature extraction and classification to identify the pump parts and loading robot arms in the images. By performing shape analysis and size measurement on the pump accessories, the number of pump accessories to be transported is further determined. In addition, based on the position and posture of the loading robot arm in the image and the preset loading status recognition rules, the current loading status of the loading robot arm is judged.

3. The pump parts handling method based on AGV according to claim 2 is characterized in that: The handling efficiency of the loading robot arm is evaluated based on the number of pump parts that have been handled and the loading status of the loading robot arm, including: Calculate theoretical handling efficiency based on the number of pump parts to be handled and the preset standard handling volume per unit time; Real-time monitoring of the actual handling progress of the loading robot, including the number of pump parts carried and the time consumed in the handling; The actual handling progress is compared with the theoretical handling efficiency, and the delay factors in the handling process are taken into account. The actual handling efficiency evaluation value of the loading robot arm is obtained through dynamic adjustment of the algorithm model. The actual handling efficiency evaluation value is the handling efficiency.

4. The pump parts handling method based on AGV according to claim 3 is characterized in that: When the handling efficiency of the loading robot arm is lower than the efficiency threshold, dispatching the target AGV equipped with the robot arm to the pump parts stacking area for auxiliary handling, including: When the handling efficiency of the loading robot arm is lower than the efficiency threshold, the sideline length of the idle area in the pump parts stacking area is obtained according to the image information; wherein the idle area refers to an area in the pump parts stacking area that cannot be covered by the loading robot arm during the loading operation and has no other queued AGVs, and the sideline length of the idle area refers to the length of the contact line between the idle area and the AGV parking area; A first number of target AGVs equipped with robot arms are determined according to the length of the sideline of the idle area, and dispatch instructions are sent to the target AGVs to dispatch them to the pump parts stacking area for auxiliary transportation.

5. The pump parts handling method based on AGV according to claim 4 is characterized in that: The step of determining a first number of target AGVs equipped with robotic arms according to the length of the sideline of the idle area comprises: Determining a second quantity according to the length of the sideline of the idle area; Calculate the difference between the efficiency threshold and the handling efficiency, calculate a first adjustment coefficient according to the difference, obtain the total number of task configurations of the target AGV in an idle state, and calculate a second adjustment coefficient according to the total number of task configurations; The first adjustment coefficient and the second adjustment coefficient are multiplied by the second quantity at the same time to obtain the final first quantity.

6. The pump parts handling method based on AGV according to claim 1 is characterized in that: The method further comprises: After the target AGV equipped with the robot arm is dispatched to the pump parts storage area, the target AGV communicates with other AGVs in the pump parts storage area to coordinate an entry path.

7. A pump parts handling system based on AGV, the system comprising a processing device and a storage device, characterized in that: The processing device calls and runs the computer program in the storage device to implement the following steps: Collect image information of the pump parts stacking area in real time, and identify the number of pump parts to be transported and the loading status of the loading robot arm from the image information; The handling efficiency of the loading robot arm is evaluated based on the number of pump parts that have been transported and the loading status of the loading robot arm; When the handling efficiency of the loading robot arm is lower than the efficiency threshold, the target AGV equipped with the robot arm is dispatched to the pump parts stacking area for auxiliary handling.

8. An electronic device comprising: A memory storing executable program code; A processor coupled to the memory; characterized in that: the processor calls the executable program code stored in the memory to execute the method according to any one of claims 1-6.

9. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is executed.

10. A computer program product, comprising a computer program stored in a computer storage medium, characterized in that: When the computer program is executed by a processor of an electronic device, the method according to any one of claims 1 to 6 is implemented.

Images