Control method and device of stacker and automatic three-dimensional warehouse system

Abstract

The present disclosure provides a control method and device of a stacker and a three-dimensional warehouse automation system, and relates to the technical field of intelligentization of chemical fibers. The specific scheme is: in response to receiving a task allocation request sent by the stacker, an intermediate table is obtained; a plurality of images in a first lane of the three-dimensional warehouse are identified by an image recognition model to obtain storage state information of a plurality of storage locations of the first lane; a temporary work task of the stacker is determined based on the intermediate table; the position of a target storage location corresponding to the temporary work task is determined based on the storage state information of the plurality of storage locations of the first lane; the temporary work task and the position of the target storage location are sent to the stacker, so that the stacker executes the temporary work task based on the position of the target storage location. According to the scheme of the present disclosure, in the case that the communication between the stacker and the warehouse management system is interrupted, the stacker can execute the temporary work task according to the storage state information of the storage location, which helps to improve the efficiency and safety of the stacker in executing the task.

Description

Technical Field

[0001] This disclosure relates to the field of intelligent chemical fiber technology, and in particular to a control method, device and automated storage and retrieval system for a stacker crane. Background Technology

[0002] In the chemical fiber production sector, automated storage and retrieval systems (AS / RS) are widely used in areas such as yarn and spindle packaging plants due to their advantages of high space utilization and high degree of automation. As a key piece of equipment in AS / RS, the stacker crane's operating status significantly impacts the efficiency of inbound and outbound operations. Therefore, improving the efficiency and safety of stacker cranes in performing their tasks has become a pressing technical challenge. Summary of the Invention

[0003] This disclosure provides a control method and device for a stacker crane, as well as an automated storage and retrieval system.

[0004] According to a first aspect of this disclosure, a control method for a stacker crane is provided, applied to an image recognition system, comprising:

[0005] In response to receiving a task assignment request from the stacker crane, an intermediate table is obtained. The intermediate table records at least the work tasks that the warehouse management system has not yet completed. The task assignment request is sent by the stacker crane when communication with the warehouse management system is interrupted.

[0006] Multiple images of the first aisle of the automated warehouse are identified by an image recognition model to obtain the storage status information of multiple storage locations in the first aisle.

[0007] The temporary work tasks of the stacker crane are determined based on the intermediate table;

[0008] Based on the storage status information of multiple storage locations in the first lane, the location of the target storage location corresponding to the temporary work task is determined.

[0009] Send a temporary work task and the location of the target storage location to the stacker crane, so that the stacker crane can execute the temporary work task based on the location of the target storage location.

[0010] According to a second aspect of this disclosure, an automated storage and retrieval system is provided, comprising:

[0011] The warehouse management system is used to send normal work tasks to the stacker crane and intermediate tables to the computing center when communicating with the stacker crane.

[0012] The computing center is used to store intermediate tables, which record at least the unfinished tasks of the warehouse management system.

[0013] The stacker crane is used to execute normal work tasks when it receives normal work tasks from the warehouse management system; it is also used to send task assignment requests to the image recognition system in the event of a communication interruption with the warehouse management system; it receives temporary work tasks and the location of the target storage location returned by the image recognition system, and executes temporary work tasks based on the location of the target storage location.

[0014] The image recognition system is used to respond to a task allocation request sent by a stacker crane, obtain an intermediate table from the computing center, identify multiple images in the first aisle of the automated warehouse using an image recognition model, obtain storage status information of multiple storage locations in the first aisle, determine temporary work tasks for the stacker crane based on the intermediate table, determine the location of the target storage location corresponding to the temporary work task based on the storage status information of multiple storage locations in the first aisle, and send the temporary work task and the location of the target storage location to the stacker crane.

[0015] According to a third aspect of this disclosure, a control device for a stacker crane is provided, applied to an image recognition system, comprising:

[0016] The first acquisition module is used to acquire an intermediate table in response to receiving a task assignment request sent by the stacker crane. The intermediate table records at least the work tasks that the warehouse management system has not yet completed. The task assignment request is sent by the stacker crane when communication with the warehouse management system is interrupted.

[0017] The recognition module is used to identify multiple images in the first aisle of the automated warehouse through an image recognition model, and obtain the storage status information of multiple storage locations in the first aisle.

[0018] The first determination module is used to determine the temporary work tasks of the stacker crane based on the intermediate table;

[0019] The second determination module is used to determine the location of the target storage location corresponding to the temporary work task based on the storage status information of multiple storage locations in the first lane.

[0020] The first sending module is used to send temporary work tasks and the location of the target storage location to the stacker crane, so that the stacker crane can execute the temporary work tasks based on the location of the target storage location.

[0021] According to a fourth aspect of this disclosure, an electronic device is provided, comprising:

[0022] At least one processor; and

[0023] The memory is communicatively connected to the at least one processor; wherein,

[0024] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform any of the methods described in the present disclosure.

[0025] According to a fifth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform any of the methods according to embodiments of this disclosure.

[0026] According to the technology disclosed herein, in the event of a communication interruption between the stacker crane and the warehouse management system, the stacker crane can perform temporary work tasks based on the storage status information of the storage location, which helps to improve the efficiency and safety of the stacker crane in performing tasks.

[0027] It should be understood that the description in the Summary of the Invention is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0028] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. In the drawings, the same or similar reference numerals denote the same or similar elements, wherein:

[0029] Figure 1 This is a flowchart illustrating the control method of a stacker crane according to an embodiment of the present disclosure;

[0030] Figure 2 This is a schematic diagram of the intermediate table content in an embodiment of this disclosure;

[0031] Figure 3 This is a schematic diagram illustrating the training of an image recognition model according to an embodiment of this disclosure;

[0032] Figure 4 This is a schematic block diagram of the control system 400 of the stacker crane according to an embodiment of the present disclosure;

[0033] Figure 5 This is a schematic diagram of the structure of the control device of the stacker crane according to an embodiment of the present disclosure;

[0034] Figure 6 This is a block diagram of an electronic device used to implement the control method of a stacker crane according to embodiments of the present disclosure. Detailed Implementation

[0035] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0036] The terms "first," "second," and "third," etc., used in the embodiments, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, such as including a series of steps or units. A method, system, product, or apparatus is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products, or apparatuses.

[0037] Before introducing the technical solutions of the embodiments of this disclosure, the technical terms that may be used in this disclosure will be further explained:

[0038] Automated storage and retrieval systems (AS / RS), also known as high-bay warehouses, are warehouses that use multi-layered, dozens-layered, or even high-rise racking systems to store goods and employ corresponding material handling equipment for inbound and outbound operations. Their main components consist of racking, aisle-type stacker cranes, inbound / outbound workbenches, and automated transport and control systems.

[0039] Warehouse Management System (WMS): A system specifically designed for warehouse management. It focuses on efficient task execution and process planning strategies, and, in conjunction with location management, barcode / QR code management, and automated warehouse equipment, can greatly improve operational efficiency and resource utilization.

[0040] In related technologies, within a silk spindle packaging chemical production plant, after the silk spindle packaging process is completed, stacker cranes are used to store the packaged silk spindles in an automated warehouse. An automated warehouse comprises multiple aisles, each with at least one stacker crane responsible for product inbound and / or outbound operations. Also known as a high-bay warehouse, an automated warehouse utilizes racks several, dozens, or even hundreds of layers high to store unit goods, employing appropriate material handling equipment for inbound and outbound operations.

[0041] In related technologies, stacker cranes are the main equipment for storing silk spindles in warehouses, with multiple stacker cranes moving within the aisles. To ensure the safe operation of stacker cranes within the aisles of an automated warehouse, regular inspections by shift workers or monitoring through a warehouse management system are the primary methods. However, manual inspections are inefficient; monitoring through a warehouse management system may result in system crashes, affecting the efficiency and safety of the stacker cranes in performing their tasks. Furthermore, workers or animals may accidentally enter the automated warehouse, so real-time monitoring is necessary to ensure operational safety.

[0042] This disclosure proposes a control method, system, and apparatus for a stacker crane to at least partially address one or more of the aforementioned problems and other potential issues. By performing image recognition on the aisles within the automated warehouse to obtain storage status information, the stacker crane can be assisted in performing temporary tasks based on the storage status information of the storage locations, thereby improving the efficiency and safety of the stacker crane in performing its tasks.

[0043] This disclosure provides a control method for a stacker crane, applied to an image recognition system. Figure 1 This is a flowchart illustrating a control method for a stacker crane according to an embodiment of the present disclosure. This control method can be applied to a control device for the stacker crane. The control device is located on an electronic device within an image recognition system. The image recognition system is a component of an automated storage and retrieval system (AS / RS). In some possible implementations, the control method for the stacker crane can also be implemented by a processor calling computer-readable instructions stored in memory. For example... Figure 1 As shown, the control method of the stacker crane includes:

[0044] S101: In response to receiving a task assignment request sent by the stacker crane, obtain an intermediate table. The intermediate table records at least the work tasks that the warehouse management system has not yet completed. The task assignment request is sent by the stacker crane when communication with the warehouse management system is interrupted.

[0045] S102: By using an image recognition model to identify multiple images in the first aisle of the automated warehouse, the storage status information of multiple storage locations in the first aisle is obtained;

[0046] S103: Determine the temporary work tasks of the stacker crane based on the intermediate table;

[0047] S104: Based on the storage status information of multiple storage locations in the first lane, determine the location of the target storage location corresponding to the temporary work task;

[0048] S105: Send a temporary work task and the location of the target storage location to the stacker crane, so that the stacker crane can execute the temporary work task based on the location of the target storage location.

[0049] In this embodiment, the image recognition system can obtain intermediate tables from a computing center. The computing center can be used for the operation of critical software in a chemical production plant and exhibits excellent stability. The image recognition system can communicate with the computing center, and the warehouse management system can also communicate with it. The image recognition system can communicate with a stacker crane. The warehouse management system can also communicate with the stacker crane. The warehouse management system reports task execution status at regular intervals, and the computing center can generate intermediate tables based on this status. Alternatively, the warehouse management system can upload intermediate tables to the computing center at regular intervals.

[0050] In this embodiment, the stacker crane is an important handling equipment in an automated warehouse. The stacker crane can automatically, quickly, and accurately store and retrieve goods within the warehouse, improving warehouse utilization and operational efficiency. The main components of the stacker crane may include: forks for picking up, handling, and stacking goods in the warehouse or workshop; a platform for placing goods; a lifting mechanism for lifting goods; a traveling mechanism for moving the stacker crane within the warehouse; and a control system for controlling various operations and actions of the stacker crane. Here, the forks can be electrically or hydraulically driven and can extend, retract, and rotate as needed; the platform can be made of steel or aluminum alloy, possessing sufficient load-bearing capacity and stability; the lifting mechanism can be electrically or hydraulically driven, featuring high precision, stability, and reliability; the traveling mechanism can be wheeled or tracked, featuring high speed and stable operation; and the control system can use PLC or microcontroller control components, featuring high automation and ease of operation.

[0051] In this embodiment, the task allocation request is a request sent by the stacker crane to the image recognition system when the warehouse management system crashes. This task allocation request can be generated by the stacker crane based on the target scenario; the preset inspection task can also be a task allocation request generated based on manually input instructions. The above is merely illustrative and is not intended to limit all possible methods of obtaining the task allocation request; it is simply not exhaustive.

[0052] Figure 2 A schematic diagram of the intermediate table contents is shown, such as... Figure 2 As shown, this intermediate table can record completed and incomplete work tasks in the warehouse system, but it must at least record work tasks not yet assigned by the warehouse management system. Specifically, the completed work tasks recorded in this intermediate table can include: the quantity of completed work, the completion time of the completed work tasks, and the type of completed work tasks, such as inbound or outbound tasks. The incomplete work tasks recorded in this intermediate table can include: the deadline for the incomplete work tasks, and the type of incomplete work tasks.

[0053] In this embodiment of the disclosure, the warehouse management system can provide functions such as inbound management, outbound management, transfer management, inventory adjustment, and barcode printing. It supports batch management, expiration date management, multiple packaging specifications, and multiple packaging barcodes for products, thereby achieving comprehensive warehouse logistics information management.

[0054] In this embodiment of the disclosure, the warehouse management system can communicate with the computing center and the stacker crane. Communication interruptions between the stacker crane and the warehouse management system can occur in the following situations: a crash of the warehouse management system or a malfunction of the stacker crane. Specifically, a crash of the warehouse management system can be caused by: software problems leading to a system crash, such as software defects or virus attacks; hardware problems leading to a system crash, such as malfunctions in servers, network equipment, storage devices, or power modules; or power fluctuations leading to a system crash, such as unstable power supply or voltage fluctuations.

[0055] In this embodiment, the image recognition model is used to identify multiple images within the aisles of an automated warehouse to obtain storage status information. The training method for the image recognition model includes: acquiring historical storage status information and historical images of multiple sample storage locations in the automated warehouse; inputting the historical storage status information and historical images of the multiple sample storage locations into a preset model to obtain predicted storage status values ​​for the multiple sample storage locations; constructing a loss function based on the true storage status values ​​and predicted storage status values ​​of the multiple sample storage locations; and training the preset model based on the loss function to obtain the image recognition model. Here, the image recognition model is a pre-trained model.

[0056] In some embodiments, the first aisle serves as a passageway connecting the warehouse racks and the stacker crane. The first aisle is typically located between the racks, parallel to the stacker crane tracks. The width and height of the aisle can be determined based on the size and design of the warehouse. In automated warehouses, aisles are primarily used for the movement of the stacker crane and the storage and retrieval of goods.

[0057] In some embodiments, the multiple images are pictures of the first aisle of the automated warehouse. These multiple images can be captured by cameras deployed on control frames within the aisle; they can also be captured by cameras deployed around the stacker crane; or they can be images captured by a drone. The cameras can be mounted on the support frame of the stacker crane or on an elevated structure above the aisle. The multiple images can be images directly captured by the cameras, or they can be frames extracted from video footage captured by the cameras. The multiple images within the first aisle can be images captured by different cameras within the same time period, or multiple images captured by the same camera during the stacker crane's several rotations within the first aisle.

[0058] In some embodiments, the storage status information may include: stored yarn spindles, unstored yarn spindles, batch number of stored yarn spindles, quantity of stored yarn spindles, and type of stored yarn spindles. The main types of yarn involved in the schemes of this disclosure may include one or more of partially oriented yarns (POY), fully drawn yarns (FDY), and drawn textured yarns (DTY) (or low-elasticity yarns). For example, the specific types of yarn may include polyester partially oriented yarns, polyester fully drawn yarns, polyester drawn yarns, polyester low-elasticity yarns, and polyester staple fiber.

[0059] In some embodiments, the temporary work task is a task that the stacker crane should perform when communication between the stacker crane and the warehouse management system is interrupted. Here, the temporary work task can be a temporary inbound task, a temporary outbound task, a temporary relocation task, or other similar tasks.

[0060] In some embodiments, the location of the target storage location is the location of a temporary work task. For example, a storage task is performed on DTY spindles with batch number A001, storing the DTY spindles with batch number A001 into the third storage location on the 10th floor on the left side of aisle 20.

[0061] In some embodiments, when the temporary work task is a product warehousing task, the stacker crane performs the temporary work task based on the location of the target storage location, including: storing the product to be warehoused to the target storage location.

[0062] When the temporary work task is a product outbound task, the stacker crane performs the temporary work task based on the location of the target storage location, including: retrieving the product to be outbound from the target storage location. Communication interruption between the stacker crane and the warehouse management system includes: the stacker crane not receiving a preset signal from the warehouse management system within a preset time.

[0063] Here, the preset signal can be a heartbeat signal. The warehouse management system can periodically send heartbeat signals to the stacker crane to notify it whether the warehouse management system is in a normal state. The stacker crane can also determine whether the warehouse management system is in a normal state based on whether it receives a heartbeat signal within a preset time. If no heartbeat signal is received from the warehouse management system within the preset time, it is determined whether an anomaly has occurred in the warehouse management system. In order not to affect the efficiency of inbound and outbound operations, a task allocation request is sent to the image recognition system. The images in this first aisle can be captured by a camera or a drone.

[0064] The technical solution of this disclosure, in response to receiving a task allocation request sent by a stacker crane, obtains an intermediate table; identifies multiple images in the first aisle of the automated warehouse using an image recognition model to obtain storage status information of multiple storage locations in the first aisle; determines temporary work tasks for the stacker crane based on the intermediate table; determines the location of the target storage location corresponding to the temporary work task based on the storage status information of the multiple storage locations in the first aisle; and sends the temporary work task and the location of the target storage location to the stacker crane so that the stacker crane can execute the temporary work task based on the location of the target storage location. Thus, even if communication between the stacker crane and the warehouse management system is interrupted, the stacker crane can still execute temporary work tasks based on the storage status information of the storage locations, which helps improve the efficiency and safety of the stacker crane in executing tasks.

[0065] In some embodiments, the control method of the stacker crane further includes: receiving the execution status of temporary work tasks sent by the stacker crane; and updating an intermediate table based on the execution status of the temporary work tasks.

[0066] In some embodiments, the execution status of the temporary task may include the progress of the temporary task, the start time of the temporary task, the end time of the temporary task, the number of temporary tasks completed, etc. Here, the progress of the temporary task may include: temporary task not completed, temporary task completed, temporary task in progress, etc.

[0067] In some embodiments, updating the intermediate table based on the execution status of temporary tasks may include: when a temporary task is detected to be incomplete, determining the temporary task as incomplete in the intermediate table; when a temporary task is detected to be completed, determining the temporary task as completed in the intermediate table; and when a temporary task is detected to be in progress, determining the temporary task as in progress in the intermediate table.

[0068] In this way, the image recognition system can perform timely statistics and updates on the intermediate table, which makes it easy for the warehouse management system to quickly understand the operation of the stacker crane during the crash after it resumes operation. This helps the warehouse management system to quickly assign new work tasks to the stacker crane, improve the working efficiency of the stacker crane, and thus improve the efficiency of outbound and inbound operations.

[0069] In some embodiments, the control method of the stacker crane further includes: in response to receiving a task termination request sent by the stacker crane, the image recognition system sends an updated intermediate table to the warehouse management system, so that the warehouse management system can perform summary processing based on the updated intermediate table and the intermediate table stored by the warehouse management system itself, and determine the normal working task based on the summarized intermediate table; wherein, the task termination request is sent after the communication between the stacker crane and the warehouse management system is restored.

[0070] In some embodiments, the task termination request is sent by the stacker crane to the image recognition system when the warehouse management system returns to normal. When the image recognition system receives the task termination request from the stacker crane, it stops generating temporary work tasks.

[0071] In some embodiments, after the storage system resumes communication with the stacker crane, the image recognition system can send an updated intermediate table to the storage system. The storage system compares the updated intermediate table with the intermediate table stored in the storage management system itself, and then summarizes them to obtain a summarized intermediate table. Based on the summarized intermediate table, the normal working task of the stacker crane is determined.

[0072] Here, the image recognition system can also send updated intermediate tables to the warehouse management system through the computing center.

[0073] In some embodiments, if the image recognition system can establish communication with the warehouse management system, it can also directly send the updated intermediate table to the warehouse management system.

[0074] In some embodiments, the normal operation task is issued by the storage system. At this time, the storage system and the stacker crane are in normal communication.

[0075] In some embodiments, when the stacker crane A detects that communication with the storage system has returned to normal, it sends a task termination request to the image recognition system; the image recognition system sends an updated intermediate table to the storage system; the storage management system performs summary processing based on the updated intermediate table and the intermediate table stored in the storage management system itself, and determines the normal working task based on the summarized intermediate table; the content of its updated intermediate table is: DTY spindles with batch number A001 are performing an inbound task - completed, FDY spindles with batch number B005 are performing an inbound task - incomplete, and POY spindles with batch number F011 are performing an outbound task - completed; the content of its own intermediate table is: DTY spindles with batch number A001 are performing an inbound task - incomplete, FDY spindles with batch number B005 are performing an inbound task - incomplete, and POY spindles with batch number F011 are performing an outbound task - incomplete; based on the summarized intermediate table, the normal working task is determined to be: FDY spindles with batch number B005 are performing an inbound task.

[0076] In this way, after the warehousing system returns to normal, the normal work tasks can be redefined based on the intermediate table sent by the image recognition system. This helps the warehousing system quickly return to normal operation, improves the efficiency and accuracy of the stacker crane, and thus improves the efficiency of inbound / outbound of silk spindles.

[0077] In some embodiments, after receiving a task assignment request, the control method of the stacker crane further includes: an image recognition system sending an image shooting instruction to the stacker crane, the shooting instruction indicating the storage location to be photographed and the shooting angle, so that the stacker crane can photograph an image of the storage location to be photographed at the shooting angle based on the image shooting instruction, the storage location to be photographed being a portion of all storage locations included in the first aisle; receiving images of the storage locations to be photographed in the first aisle sent by the stacker crane, wherein multiple images include images of the storage locations to be photographed.

[0078] Here, the image capture command can be a capture command specified by the image recognition system for certain storage locations.

[0079] In some embodiments, the image capture instruction can be used to: indicate the number of stacker cranes to be activated, the shooting angle of the stacker crane camera, and the location where the stacker crane camera is shooting. Here, the image capture instruction can also be implemented based on the stacker crane's lifting and traveling mechanisms. For example, the image capture instruction could be to activate the right-side camera of the stacker crane and capture three images at a 60-degree elevation angle, or to activate all the equipment heads of the stacker crane and capture one image each at elevation angles of 30 degrees, 60 degrees, and 90 degrees.

[0080] In some embodiments, the location to be photographed may be a single location; multiple locations may be photographed consecutively; or a specific location may be designated for photographing. The shooting angle may be a single angle; multiple angles may be photographed consecutively; or a specific location may be designated for photographing.

[0081] In some embodiments, the image recognition system can continuously receive images captured by cameras located on an elevated platform in the first aisle. Based on these images, the system can analyze the storage status information of at least some storage locations. Upon receiving a task allocation request from a stacker crane, the system can determine the storage location to be photographed from all storage locations within the first aisle by combining the storage status information of at least some storage locations, and then instruct the stacker crane to photograph the image of that storage location.

[0082] For example, the image recognition system sends image capture instructions to stacker cranes A, B, and C. The image capture instruction for stacker crane A is: simultaneously activate the left and right cameras to take one image of the 14th storage location on the 10th floor from a 30-degree downward angle. The image capture instruction for stacker crane B is: activate all deployed cameras to take three images of the 11th storage location on the 20th floor from a 75-degree upward angle and a 30-degree downward angle. The image capture instruction for stacker crane C is: activate the left and right cameras to take one image of the 7th, 8th, 9th, and 10th storage locations on the 27th floor from an 80-degree downward angle. Stacker cranes A, B, and C then send the captured images to the image recognition system.

[0083] In this way, the stacker crane takes images according to the image capture instructions sent by the image recognition system and sends the captured images to the image recognition system. This helps the image recognition system confirm the storage status information of multiple storage locations in the first aisle, which helps to accurately generate temporary work tasks, thereby improving the accuracy of the stacker crane in executing work tasks.

[0084] In this embodiment of the disclosure, the control method of the stacker crane further includes: an image recognition system determining the storage status information of at least some storage locations in the first aisle within a preset time period based on an intermediate table, wherein the preset time period is a period of time starting from the generation time of the intermediate table and lasting for a preset threshold; comparing the storage status information obtained through the image recognition model with the storage status information determined based on the intermediate table; and recording a first type of storage location where the storage status information obtained through the image recognition model is inconsistent with the storage status information determined based on the intermediate table, wherein the first type of storage location is a storage location whose storage status needs to be verified.

[0085] Here, the preset time period can be set or adjusted according to user or task requirements. The preset time period starts from the generation time of the intermediate table, and the end point can be adjusted according to user and task requirements.

[0086] In some embodiments, the first type of storage location is a storage location whose storage status needs to be verified. For example, the storage status information obtained according to the image recognition model is: the 3rd storage location on the 10th floor to the left of aisle 20 - received - FDY spindles with batch number B005; the 17th storage location on the 21st floor to the right of aisle 70 - received - DTY spindles with batch number A011; the 21st storage location on the 16th floor to the right of aisle 60 - received; the 2nd storage location on the 32nd floor to the left of aisle 90 - not received; the storage status information obtained according to the intermediate table is: the 3rd storage location on the 10th floor to the left of aisle 20 - received - batch number B005. FDY spindles, the 17th storage location on the 21st floor to the right of aisle 70 - already stored - batch number A011 DTY spindles, the 21st storage location on the 16th floor to the right of aisle 60 - not stored, the 2nd storage location on the 32nd floor to the left of aisle 90 - not stored; compare the storage status information obtained through the image recognition model with the storage status information determined based on the intermediate table; record the first type of storage location where the storage status information obtained through the image recognition model is inconsistent with the storage status information determined based on the intermediate table, namely the 21st storage location on the 16th floor to the right of aisle 60. This 21st storage location on the 16th floor to the right of aisle 60 is a first type of storage location, and its storage status needs to be verified.

[0087] Thus, by comparing the storage status information obtained from the image recognition model with the storage status information determined based on the intermediate table, the first type of storage location with inconsistent storage status information can be identified. This allows for timely verification of the storage status information of the first type of storage location, avoiding duplicate operations and helping to improve the efficiency and safety of the stacker crane in performing its tasks.

[0088] In this embodiment of the disclosure, determining the location of the target storage location corresponding to the temporary work task based on the storage status information of multiple storage locations in the first lane includes: when the temporary work task is a temporary warehousing task, selecting a target storage location for the temporary warehousing task from at least one second-type storage location whose storage status information obtained through the image recognition model is consistent with the storage status information determined based on the intermediate table, and determining the location of the target storage location; wherein, the second-type storage location is a storage location that has not yet stored goods.

[0089] In some embodiments, the second type of storage location is a storage location that has not yet stored goods. For example, when the temporary work task is a temporary warehousing task, the storage status information obtained according to the image recognition model is: the 7th storage location on the 2nd floor to the left of aisle 14 - already stored - FDY spindles with batch number B011; the 14th storage location on the 36th floor to the right of aisle 21 - not stored; the 19th storage location on the 22nd floor to the right of aisle 44 - not stored; the 12th storage location on the 25th floor to the left of aisle 16 - not stored; the storage status information obtained according to the intermediate table is: the 7th storage location on the 2nd floor to the left of aisle 14 - already stored - FDY spindles with batch number B011. DY silk spindles, the 14th storage location on the 36th floor to the right of aisle 21 - already stored, the 19th storage location on the 22nd floor to the right of aisle 44 - not stored, the 12th storage location on the 25th floor to the left of aisle 16 - not stored; from at least one second-class storage location whose storage status information obtained through image recognition model is consistent with the storage status information determined based on the intermediate table, a target storage location is selected for the temporary storage task, namely the 19th storage location on the 22nd floor to the right of aisle 44 and the 12th storage location on the 25th floor to the left of aisle 16; this second-class storage location is a storage location that has not yet stored goods.

[0090] In this way, selecting a target storage location for a temporary storage task from at least one second-class storage location whose storage status information obtained through the image recognition model is consistent with the storage status information determined based on the intermediate table helps to improve the efficiency and accuracy of the temporary storage task.

[0091] In this embodiment of the disclosure, determining the location of the target storage location corresponding to the temporary work task based on the storage status information of multiple storage locations in the first lane includes: when the temporary work task is a temporary outbound task, selecting a target storage location for the temporary outbound task from at least one third-type storage location whose storage status information obtained through the image recognition model is consistent with the storage status information determined based on the intermediate table, and combining the batch number of the goods targeted by the temporary outbound task; wherein, the third-type storage location is a storage location that already stores goods.

[0092] In some embodiments, the third type of storage location is a storage location that already stores goods. For example, when the temporary work task is a temporary outbound task, the storage status information obtained according to the image recognition model is: the 20th storage location on the 14th floor to the left of aisle 4 - already received - FDY spindles with batch number B011; the 6th storage location on the 20th floor to the right of aisle 41 - FDY spindles with batch number B011; the 9th storage location on the 12th floor to the right of aisle 31 - DTY spindles with batch number A011; the 12th storage location on the 25th floor to the left of aisle 16 - not received; the storage status information obtained according to the intermediate table is: the 20th storage location on the 14th floor to the left of aisle 4 - not received; the 6th storage location on the 20th floor to the right of aisle 41 - batch number B011. The following are examples of warehouse locations: FDY spindles, DTY spindles (A011) located at the 9th location on the 12th floor to the right of aisle 31, and DTY spindles (A011) located at the 12th location on the 25th floor to the left of aisle 16; at least one third-class warehouse location whose storage status information obtained through image recognition model matches the storage status information determined based on the intermediate table, namely, the 6th location on the 20th floor to the right of aisle 41 (FDY spindle with batch number B011) and the 9th location on the 12th floor to the right of aisle 31 (DTY spindle with batch number A011). If the temporary outbound task targets DTY spindles with batch number A011, then the temporary outbound task selects the 9th location on the 12th floor to the right of aisle 31 as the target warehouse location. This location already contains goods.

[0093] In this way, by selecting a target storage location for a temporary outbound task from at least one third-class storage location whose storage status information obtained through the image recognition model matches the storage status information determined based on the intermediate table, and combining the batch number of the goods targeted by the temporary outbound task, the efficiency and accuracy of the temporary outbound task can be improved.

[0094] In this embodiment of the disclosure, the method of recognizing multiple images in the first aisle of the automated warehouse using an image recognition model to obtain storage status information of multiple storage locations in the first aisle includes: the image recognition system inputting multiple images and historical storage status information of the automated warehouse into the image recognition model to obtain storage status information of multiple storage locations output by the image recognition model; wherein, the image recognition model is used to identify whether goods are stored in the storage location and the identification of the goods stored in the storage location.

[0095] In some embodiments, the historical storage status information may refer to the historical records of each inbound and outbound shipment of goods stored in the storage management system. Historical storage status information may include the location of goods in the automated warehouse, inventory quantity, inbound date, outbound date, and batch number of the silk spindles, etc.

[0096] In some embodiments, the identification of the goods may be a goods number, label, QR code, etc.

[0097] Thus, the warehouse status information identified by the image recognition model can improve the accuracy of the image recognition model by referencing the historical warehouse status information.

[0098] Figure 3 The diagram illustrates the training of an image recognition model, as shown below. Figure 3 As shown, the image recognition model is obtained through the following training method: acquiring historical storage status information and historical images of multiple sample storage locations in an automated warehouse; inputting the historical storage status information and historical images of multiple sample storage locations into a preset model to obtain predicted storage status values ​​of multiple sample storage locations; constructing a loss function based on the true storage status values ​​and predicted storage status values ​​of multiple sample storage locations; and training the preset model based on the loss function to obtain the image recognition model.

[0099] In some embodiments, the sample storage location can be set and adjusted as needed.

[0100] In some embodiments, the historical image is an image corresponding to the historical storage status information of the sample storage location. This historical image may be obtained through a camera deployed on a stacker crane; it may also be obtained through an elevated camera deployed in an aisle; or it may be obtained through a drone. The above are merely illustrative examples and are not intended to limit the scope of all possible methods of acquiring historical images; they are simply not exhaustive.

[0101] In this way, the storage status information of the warehouse can be predicted by the pre-trained image recognition model, and the location of the target warehouse corresponding to the temporary work task can be determined based on the storage status information of the warehouse. This helps to improve the working efficiency of the stacker crane, and thus helps to realize the intelligent management of the silk spindle inbound / outbound.

[0102] This disclosure also proposes an automated storage and retrieval system capable of executing the control method for the stacker crane described above. Figure 4 This is a schematic block diagram of an automated warehouse system 400 according to an embodiment of this disclosure. Figure 4As shown, the automated storage and retrieval system 400 includes: a warehouse management system 410, used to send normal work tasks to the stacker crane when communicating with it; and also used to send intermediate tables to a computing center; a computing center 420, used to store the intermediate tables, which at least record the work tasks that the warehouse management system has not yet completed; a stacker crane 430, used to execute normal work tasks when receiving them from the warehouse management system; and also used to send task allocation requests to an image recognition system when communication with the warehouse management system is interrupted; and to receive temporary data returned by the image recognition system. The system identifies the work task and the location of the target storage location, and executes temporary work tasks based on the location of the target storage location. An image recognition system 440, in response to a task allocation request sent by the stacker crane, obtains an intermediate table from the computing center. It identifies multiple images within the first aisle of the automated warehouse using an image recognition model to obtain storage status information for multiple storage locations in the first aisle. Based on the intermediate table, it determines the temporary work task of the stacker crane. Based on the storage status information of multiple storage locations in the first aisle, it determines the location of the target storage location corresponding to the temporary work task. Finally, it sends the temporary work task and the location of the target storage location to the stacker crane.

[0103] It should be noted that this disclosure does not limit the number of stacker cranes in the automated storage and retrieval system.

[0104] In this way, through the cooperation of the warehouse management system, computing center, stacker crane and image recognition system of the automated warehouse, the stacker crane can perform temporary work tasks based on the storage status information of the storage location when communication with the warehouse management system is interrupted, which helps to improve the efficiency and safety of the stacker crane in performing tasks.

[0105] It should be understood that Figure 2 and Figure 3 The diagrams shown are merely illustrative and not restrictive. The content in the diagrams can be adapted or modified according to operational requirements, and will not be elaborated further here. Those skilled in the art can use them as a basis for... Figure 2 and Figure 3 Even with various obvious changes and / or substitutions to the examples, the resulting technical solutions still fall within the scope of this disclosure.

[0106] This disclosure provides a control device for a stacker crane, such as... Figure 5 As shown, the control device for the stacker crane may include:

[0107] The first acquisition module 510 is used to acquire an intermediate table in response to receiving a task allocation request sent by the stacker crane. The intermediate table records at least the work tasks that the warehouse management system has not yet completed. The task allocation request is sent by the stacker crane when communication with the warehouse management system is interrupted.

[0108] The recognition module 520 is used to recognize multiple images in the first aisle of the automated warehouse through an image recognition model, and obtain the storage status information of multiple storage locations in the first aisle.

[0109] The first determining module 530 is used to determine the temporary work tasks of the stacker crane based on the intermediate table;

[0110] The second determining module 540 is used to determine the location of the target storage location corresponding to the temporary work task based on the storage status information of multiple storage locations in the first alleyway.

[0111] The first sending module 550 is used to send a temporary work task and the location of the target storage location to the stacker crane, so that the stacker crane can execute the temporary work task based on the location of the target storage location.

[0112] In some embodiments, the control device of the stacker crane further includes: a first receiving module ( Figure 5 (Not shown in the image), used to receive the execution status of temporary work tasks sent by the stacker crane; update module ( Figure 5 (Not shown in the table), used to update the intermediate table based on the execution status of temporary work tasks.

[0113] In some embodiments, the control device of the stacker crane further includes: a second sending module ( Figure 5 (Not shown in the image) is used to send an updated intermediate table to the warehouse management system in response to receiving a task termination request from the stacker crane. The warehouse management system then performs summary processing based on the updated intermediate table and the intermediate tables stored in the warehouse management system itself, and determines the normal working tasks based on the summarized intermediate table. The task termination request is sent after communication between the stacker crane and the warehouse management system is restored.

[0114] In some embodiments, the control device of the stacker crane further includes: a third sending module ( Figure 5 (Not shown in the image) is used to send an image capturing instruction to the stacker crane after receiving a task allocation request. The capturing instruction indicates the storage location to be captured and the capturing angle, so that the stacker crane can capture an image of the storage location to be captured at the capturing angle based on the image capturing instruction. The storage location to be captured is a portion of all storage locations included in the first aisle; the second receiving module ( Figure 5 (Not shown in the image), used to receive images of the storage location to be photographed in the first aisle sent by the stacker crane, including multiple images of the storage location to be photographed.

[0115] In some embodiments, the control device of the stacker crane further includes: a third determining module ( Figure 5 (Not shown in the image), used to determine the storage status information of at least some storage locations in the first aisle within a preset time period based on an intermediate table. The preset time period is a period of time starting from the generation time of the intermediate table and lasting for a preset threshold; comparison module ( Figure 5 (Not shown in the image), used to compare the warehouse status information obtained through the image recognition model with the warehouse status information determined based on the intermediate table; Recording module ( Figure 5 (Not shown in the image), used to record the first type of storage location where the storage status information obtained through the image recognition model is inconsistent with the storage status information determined based on the intermediate table. The first type of storage location is the storage location whose storage status needs to be verified.

[0116] In some embodiments, the second determining module 540 includes: a first determining submodule, configured to select a target storage location for the temporary storage task from at least one second-type storage location whose storage status information obtained through an image recognition model is consistent with the storage status information determined based on an intermediate table, and determine the location of the target storage location when the temporary work task is a temporary storage task; wherein the second-type storage location is a storage location that has not yet stored goods.

[0117] In some embodiments, the second determining module 540 includes: a second determining submodule, configured to, when the temporary work task is a temporary outbound task, select a target storage location for the temporary outbound task from at least one third-type storage location whose storage status information obtained through the image recognition model is consistent with the storage status information determined based on the intermediate table, in combination with the goods batch number targeted by the temporary outbound task, and determine the location of the target storage location; wherein, the third-type storage location is a storage location that already stores goods.

[0118] In some embodiments, the recognition module 520 includes: an input submodule, used to input multiple images and historical storage status information of the automated warehouse into an image recognition model to obtain storage status information of multiple storage locations output by the image recognition model; wherein, the image recognition model is used to identify whether goods are stored in the storage location and the identifier of the goods stored in the storage location.

[0119] In some embodiments, the image recognition model is obtained through the following training method: acquiring historical storage status information and historical images of multiple sample storage locations in an automated warehouse; inputting the historical storage status information and historical images of multiple sample storage locations into a preset model to obtain predicted storage status values ​​of multiple sample storage locations; constructing a loss function based on the true storage status values ​​and predicted storage status values ​​of multiple sample storage locations; and training the preset model based on the loss function to obtain the image recognition model.

[0120] Those skilled in the art should understand that the functions of each processing module in the control device of the stacker crane of the present disclosure embodiment can be understood with reference to the relevant description of the control method of the stacker crane described above. Each processing module in the control device of the stacker crane of the present disclosure embodiment can be implemented by an analog circuit that implements the function of the present disclosure embodiment, or it can be implemented by the software that executes the function of the present disclosure embodiment running on an electronic device.

[0121] The control device for the stacker crane in this embodiment enables the stacker crane to perform temporary work tasks based on the storage status information of the storage location when communication between the stacker crane and the warehouse management system is interrupted, which helps to improve the efficiency and safety of the stacker crane in performing tasks.

[0122] According to embodiments of this disclosure, this disclosure also provides an electronic device and a readable storage medium.

[0123] Figure 6 This is a structural block diagram of an electronic device according to an embodiment of the present disclosure. Figure 6 As shown, the electronic device includes a memory 610 and a processor 620. The memory 610 stores a computer program that can run on the processor 620. There can be one or more memories 610 and processors 620. The memory 610 can store one or more computer programs, which, when executed by the electronic device, cause the electronic device to perform the methods provided in the above-described method embodiments. The electronic device may also include a communication interface 630 for communicating with external devices and performing data exchange and transmission.

[0124] If the memory 610, processor 620, and communication interface 630 are implemented independently, they can be interconnected via a bus to communicate with each other. This bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0125] Optionally, in a specific implementation, if the memory 610, processor 620, and communication interface 630 are integrated on a single chip, then the memory 610, processor 620, and communication interface 630 can communicate with each other through an internal interface.

[0126] It should be understood that the aforementioned processor can be a Central Processing Unit (CPU), or other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. General-purpose processors can be microprocessors or any conventional processor. It is worth noting that the processor can be a processor supporting Advanced Reduced Instruction Set Machines (ARM) architecture.

[0127] Further, optionally, the aforementioned memory may include read-only memory and random access memory, and may also include non-volatile random access memory. The memory may be volatile or non-volatile, or may include both. Non-volatile memory may include read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory may include random access memory (RAM), which serves as an external cache. Many forms of RAM are available by way of example, but not limitation. Examples include Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate Synchronous DRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct RAMBUS RAM (DR RAM).

[0128] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this disclosure are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line, DSL) or wireless (e.g., infrared, Bluetooth, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer, or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., Digital Versatile Discs (DVDs)), or semiconductor media (e.g., Solid State Disks (SSDs)). It is worth noting that the computer-readable storage media mentioned in this disclosure can be non-volatile storage media; in other words, it can be non-transient storage media.

[0129] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0130] In the description of the embodiments of this disclosure, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this disclosure. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0131] In the description of the embodiments disclosed herein, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone.

[0132] In the description of embodiments of this disclosure, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of embodiments of this disclosure, unless otherwise stated, "a plurality of" means two or more.

[0133] The above description is merely an exemplary embodiment of this disclosure and is not intended to limit this disclosure. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the protection scope of this disclosure.

[0134] In the description of this specification, it should be understood that the terms "center," "longitudinal," "transverse," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this disclosure and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this disclosure.

Claims

1. A control method for a stacker crane, applied to an image recognition system, characterized in that, include: In response to receiving a task allocation request sent by the stacker crane, an intermediate table is obtained, which records at least the work tasks that the warehouse management system has not yet completed. The task allocation request is sent by the stacker crane when communication with the warehouse management system is interrupted. Based on the intermediate table, the storage status information of at least some storage locations in the first aisle of the automated warehouse within a preset time period is determined. The preset time period is a period of time starting from the generation time of the intermediate table and lasting for a preset threshold. Multiple images in the first aisle of the automated warehouse are identified by an image recognition model to obtain the storage status information of multiple storage locations in the first aisle. Compare the warehouse status information obtained through the image recognition model with the warehouse status information determined based on the intermediate table; The temporary work tasks of the stacker crane are determined based on the intermediate table; Based on the storage status information of the multiple storage locations in the first aisle, the location of the target storage location corresponding to the temporary work task is determined; wherein, determining the location of the target storage location corresponding to the temporary work task based on the storage status information of the multiple storage locations in the first aisle includes: when the temporary work task is a temporary inbound task, selecting the target storage location for the temporary inbound task from at least one second-type storage location whose storage status information obtained through the image recognition model is consistent with the storage status information determined based on the intermediate table, and determining the location of the target storage location; wherein, the second-type storage location is a storage location that has not yet stored goods; The temporary work task and the location of the target storage location are sent to the stacker crane so that the stacker crane can execute the temporary work task based on the location of the target storage location.

2. The method according to claim 1, characterized in that, The method further includes: Receive the execution status of the temporary work task sent by the stacker crane; The intermediate table is updated based on the execution status of the temporary work task.

3. The method according to claim 2, characterized in that, The method further includes: In response to receiving a task termination request from the stacker crane, an updated intermediate table is sent to the warehouse management system. The warehouse management system then performs summary processing based on the updated intermediate table and its own stored intermediate tables, and determines normal working tasks based on the summarized intermediate tables. The task termination request is sent after communication between the stacker crane and the warehouse management system is restored.

4. The method according to claim 1, characterized in that, After receiving the task allocation request, the method further includes: Send an image capture command to the stacker crane. The image capture command is used to indicate the storage location to be captured and the shooting angle, so that the stacker crane can capture an image of the storage location to be captured at the shooting angle based on the image capture command. The storage location to be captured is a portion of all storage locations included in the first aisle. The system receives images of the storage location to be photographed within the first aisle, sent by the stacker crane. The multiple images include images of the storage location to be photographed.

5. The method according to claim 1, characterized in that, Also includes: Record the first type of storage location whose storage status information obtained through the image recognition model is inconsistent with the storage status information determined based on the intermediate table. The first type of storage location is the storage location whose storage status needs to be verified.

6. The method according to claim 1, characterized in that, Determining the location of the target storage location corresponding to the temporary work task based on the storage status information of the multiple storage locations in the first alleyway includes: When the temporary work task is a temporary outbound task, from at least one third-type storage location whose storage status information obtained through the image recognition model is consistent with the storage status information determined based on the intermediate table, the target storage location is selected for the temporary outbound task in combination with the batch number of the goods targeted by the temporary outbound task, and the location of the target storage location is determined; wherein, the third-type storage location is a storage location that already stores goods.

7. The method according to claim 1, characterized in that, The process of identifying multiple images within the first aisle of the automated warehouse using an image recognition model to obtain storage status information for multiple storage locations within the first aisle includes: The multiple images and the historical storage status information of the automated warehouse are input into the image recognition model to obtain the storage status information of the multiple storage locations output by the image recognition model; wherein, the image recognition model is used to identify whether goods are stored in the storage location and the identification of the goods stored in the storage location.

8. The method according to claim 1, characterized in that, The image recognition model is obtained through the following training methods, including: Obtain historical storage status information and historical images of multiple sample storage locations in the automated warehouse; The historical storage status information and historical images of the multiple sample storage locations are input into a preset model to obtain the predicted storage status values ​​of the multiple sample storage locations. A loss function is constructed based on the true values ​​of the storage status of the multiple sample storage locations and the predicted values ​​of the storage status; The image recognition model is obtained by training the preset model based on the loss function.

9. An automated storage and retrieval system, characterized in that, include: The warehouse management system is used to send normal work tasks to the stacker crane and intermediate tables to the computing center when communicating with the stacker crane. A computing center is used to store the intermediate table, which records at least the unfinished work tasks of the warehouse management system. The stacker crane is used to execute the normal work task when it receives the normal work task sent by the warehouse management system; it is also used to send a task allocation request to the image recognition system in the event of a communication interruption with the warehouse management system; it receives a temporary work task and the location of the target storage location returned by the image recognition system, and executes the temporary work task based on the location of the target storage location; An image recognition system is used to obtain an intermediate table from the computing center in response to receiving a task allocation request sent by a stacker crane. Based on the intermediate table, the storage status information of at least some storage locations in the first aisle of the automated warehouse within a preset time period is determined. The preset time period is a period of time starting from the generation time of the intermediate table and lasting for a preset threshold. Multiple images of the first aisle of the automated warehouse are identified by an image recognition model to obtain the storage status information of multiple storage locations in the first aisle; the storage status information obtained by the image recognition model is compared with the storage status information determined based on the intermediate table. The temporary work tasks of the stacker crane are determined based on the intermediate table; Based on the storage status information of the multiple storage locations in the first aisle, the location of the target storage location corresponding to the temporary work task is determined; the temporary work task and the location of the target storage location are sent to the stacker crane, wherein determining the location of the target storage location corresponding to the temporary work task based on the storage status information of the multiple storage locations in the first aisle includes: if the temporary work task is a temporary inbound task, selecting the target storage location for the temporary inbound task from at least one second-type storage location whose storage status information obtained through the image recognition model is consistent with the storage status information determined based on the intermediate table, and determining the location of the target storage location; wherein the second-type storage location is a storage location that has not yet stored goods; and sending the temporary work task and the location of the target storage location to the stacker crane.

10. A control device for a stacker crane, applied to an image recognition system, characterized in that, include: The first acquisition module is used to acquire an intermediate table in response to receiving a task allocation request sent by the stacker crane. The intermediate table records at least the work tasks that the warehouse management system has not yet completed. The task allocation request is sent by the stacker crane when communication with the warehouse management system is interrupted. The third determining module is used to determine the storage status information of at least some storage locations in the first aisle of the automated warehouse within a preset time period based on the intermediate table. The preset time period is a period of time starting from the generation time of the intermediate table and lasting for a preset threshold. The recognition module is used to recognize multiple images in the first aisle of the automated warehouse through an image recognition model, and obtain the storage status information of multiple storage locations in the first aisle. The comparison module is used to compare the warehouse status information obtained by the image recognition model with the warehouse status information determined based on the intermediate table; The first determining module is used to determine the temporary work task of the stacker crane based on the intermediate table; The second determining module is used to determine the location of a target storage location corresponding to the temporary work task based on the storage status information of the multiple storage locations in the first aisle; wherein, determining the location of the target storage location corresponding to the temporary work task based on the storage status information of the multiple storage locations in the first aisle includes: when the temporary work task is a temporary inbound task, selecting the target storage location for the temporary inbound task from at least one second-type storage location whose storage status information obtained through the image recognition model is consistent with the storage status information determined based on the intermediate table, and determining the location of the target storage location; wherein, the second-type storage location is a storage location that has not yet stored goods; and sending the temporary work task and the location of the target storage location to the stacker crane. The first sending module is used to send the temporary work task and the location of the target storage location to the stacker crane, so that the stacker crane can execute the temporary work task based on the location of the target storage location.

11. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 8.

12. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 8.

Images