Task scheduling method, device, equipment and storage medium

Abstract

The present application provides a task scheduling method, apparatus, equipment and storage medium, which relate to the field of robot control technology and solve the problem that the scheduling management of AGV mobile robots cannot meet the picking needs of massive tasks, resulting in low picking efficiency. The present solution calculates task similarity to schedule corresponding tasks for AGV mobile robots, thereby being able to effectively and accurately schedule tasks for AGV mobile robots and effectively improve picking efficiency.

Description

Technical Field

[0001] The present application relates to the field of robot control technology, and in particular to a task scheduling method, device, equipment and storage medium. Background Art

[0002] With the rapid development of the electronic information industry, the e-commerce sector has experienced rapid growth. While the widespread adoption of e-commerce has made shopping more convenient, it has also posed significant challenges to traditional warehouse picking. Amazon's "Kiva" intelligent warehousing system pioneered the use of AGV (Automated Guided Vehicle) mobile robots to replace human pickers, freeing them from the time-consuming task of selecting items and sparking a wave of innovation in the warehousing industry. This picking model using AGVs significantly improves picking efficiency and is being widely tested and applied within the industry.

[0003] The working principle of the goods-to-person picking mode of the AGV mobile robot is: the AGV mobile robot transports the storage shelves from the storage location of the warehouse to the sorting platform for the staff at the sorting platform to pick and then return to the warehouse. The AGV mobile robot will then send the storage shelves back to the original storage location in the warehouse, thus ensuring the orderly storage of the storage shelves.

[0004] However, this model still presents some challenges in warehousing systems. For example, the scheduling and management of AGVs cannot meet the needs of the massive picking tasks, resulting in low picking efficiency. Specifically, during task processing, AGVs need to travel back and forth between sorting platforms and warehouses to transport goods. This often leads to repeated travel paths and unnecessary travel, severely impacting picking efficiency. Summary of the Invention

[0005] The embodiments of the present application provide a task scheduling method, apparatus, equipment and storage medium, which solve the problem that the scheduling management of AGV mobile robots cannot meet the picking needs of massive tasks, resulting in low picking efficiency. This solution can effectively and accurately schedule tasks for AGV mobile robots, effectively improving picking efficiency.

[0006] In a first aspect, an embodiment of the present application provides a task scheduling method, which is applied to a central control device, wherein the central control device is in communication with an AGV mobile robot to schedule the AGV mobile robot. The central control device is provided with a task set in response to the picking requirements corresponding to each storage shelf. The task information corresponding to each task in the task set records the picking status of each storage shelf to identify whether each storage shelf is to be picked. The method includes:

[0007] According to the set task information, determine the task similarity between each task and another task to construct a similarity matrix;

[0008] Select the two seed tasks corresponding to the largest task similarity in the similarity matrix;

[0009] Based on the seed tasks and similarity matrix, multiple tasks are selected as tasks in the same batch until the number of tasks in the same batch equals the storage capacity of the turnover shelf corresponding to the sorting platform;

[0010] Initiate scheduling to multiple AGV mobile robots so that each AGV mobile robot can perform the target task in the same batch of tasks;

[0011] When receiving task completion information from the sorting station, the task with the highest priority is retrieved from the task set to update the tasks in the same batch until the task set is empty.

[0012] In a second aspect, an embodiment of the present application further provides a task scheduling device, which is applied to a central control device, wherein the central control device is connected to an AGV mobile robot for communication to schedule the AGV mobile robot. The central control device is provided with a task set in response to the picking requirements of each storage shelf. The task information corresponding to each task in the task set records the picking status of each storage shelf to identify whether each storage shelf is to be picked. The device includes:

[0013] A similarity determination module is configured to determine the task similarity between each task and another task based on the set task information to construct a similarity matrix;

[0014] A target screening module is configured to select two seed tasks corresponding to the task similarity with the largest value in the similarity matrix;

[0015] A task selection module is configured to select multiple tasks as tasks in the same batch based on the seed task and the similarity matrix until the number of tasks in the same batch is equal to the storage capacity of the turnover shelf corresponding to the sorting platform;

[0016] A task scheduling module is configured to initiate scheduling to multiple AGV mobile robots so that each AGV mobile robot performs a target task in the same batch of tasks;

[0017] The task update module is configured to retrieve the task with the highest priority from the task set upon receiving the task completion information from the sorting station to update the tasks in the same batch until the task set is empty.

[0018] In a third aspect, an embodiment of the present application further provides a central control device, which includes:

[0019] one or more processors;

[0020] a storage device for storing one or more programs,

[0021] When one or more programs are executed by one or more processors, the one or more processors implement the above-mentioned task scheduling method.

[0022] In a fourth aspect, an embodiment of the present application further provides a storage medium for storing computer-executable instructions, which are used to execute the above-mentioned task scheduling method when executed by a processor.

[0023] In the present application, the central control device determines the tasks with similar picking requirements for storage shelves by comparing the similarities between tasks, thereby determining the corresponding seed tasks to obtain tasks in the same batch, so that the AGV mobile robot can give priority to tasks with similar picking requirements, effectively improving the picking efficiency and making the scheduling and management of the AGV mobile robot more reasonable and effective. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A schematic diagram of the steps of a task scheduling method provided in one embodiment of the present application;

[0025] Figure 2 A schematic diagram of the steps for constructing a similarity matrix according to an embodiment of the present application;

[0026] Figure 3 A schematic diagram of the steps for selecting tasks in the same batch provided in one embodiment of the present application;

[0027] Figure 4 A schematic diagram of the steps for updating tasks in the same batch provided in one embodiment of the present application;

[0028] Figure 5 A schematic diagram of the structure of a task scheduling device provided in one embodiment of the present application;

[0029] Figure 6 A schematic diagram of the structure of a central control device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0030] The embodiments of the present application are further described in detail below in conjunction with the accompanying drawings and examples. It will be understood that the specific embodiments described herein are merely used to explain the embodiments of the present application, rather than to limit the embodiments of the present application. It should also be noted that, for ease of description, only portions related to the embodiments of the present application, rather than all structures, are shown in the accompanying drawings. After reading this specification, those skilled in the art should be able to understand that, as long as the technical features do not contradict each other, any combination of the technical features may constitute an optional embodiment.

[0031] The terms "first", "second", etc. in the specification and claims of this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship. In the description of this application, "multiple" means two or more, and "several" means one or more.

[0032] In modern warehousing, sorting stations are handled by staff or sorting robots. Of course, there are turnover shelves with multiple storage locations corresponding to each sorting station to facilitate the temporary storage of goods. With the development of the e-commerce industry, AGV mobile robots are increasingly commonly used in the modern warehousing industry to pick goods. In the goods-to-person picking mode of the AGV mobile robot, the AGV robot selects the shelves that need to be picked from multiple storage shelves in the warehouse and transports them to the sorting station for staff to pick, and finally transports the shelves back to their original locations. However, the scheduling and management of AGV mobile robots in related technologies cannot meet the picking needs of massive tasks, resulting in low picking efficiency.

[0033] To this end, the present application provides a task scheduling method, which is applied to a central control device. It is conceivable that the central control device communicates with the AGV mobile robot to schedule the AGV mobile robot. In addition, a task set is provided corresponding to the picking requirements of each storage shelf. It is conceivable that there are several tasks in the task set, and the task information corresponding to each task records the picking status of each storage shelf to identify whether each storage shelf is to be picked. For example, a corresponding number can be set to identify whether each storage shelf is to be picked. Specifically, 1 is used to identify the storage shelf to be picked, and 0 is used to identify the storage shelf that does not need to be picked.

[0034] The central control device uses the task scheduling method provided in this application to control the AGV mobile robot to schedule the AGV mobile robot to perform tasks in the task set. Figure 1 This is a schematic diagram of the steps of the task scheduling method provided in one embodiment of the present application. The specific steps are as follows:

[0035] Step S110 : Determine the task similarity between each task and any other task based on the set task information to construct a similarity matrix.

[0036] The task information records the picking requirements for each storage shelf. When two tasks require picking the same storage shelf, their task similarity is 1. Similarly, the more identical shelves a task requires picking, the higher the task similarity. The similarity between a task and itself is 0.

[0037] In one embodiment, if Figure 2 As shown, Figure 2 A schematic diagram of the steps for constructing a similarity matrix provided in an embodiment of the present application, wherein the specific steps are as follows:

[0038] Step S210: Construct a task information vector based on the task information corresponding to each task.

[0039] Step S220 : Based on the task information vector of each task, the task similarity between each task and any other task is calculated in sequence to determine a similarity matrix.

[0040] It is understandable that the task information corresponding to each task records the picking requirements for each storage shelf. For this purpose, the picking requirements can be identified by corresponding values, such as 1 to identify the storage shelf to be picked and 0 to identify the storage shelf not to be picked. Therefore, for each task, the constructed task information vector S i =[P1, P2, ..., P j , P s ] j Represents the jth storage shelf, and takes a value of 0 or 1 to indicate whether it is to be picked. It should be noted that P S Indicates the picking demand for the last storage shelf recorded in the task information.

[0041] Therefore, based on the task information vector of each task, the task similarity between each task and another task can be calculated. For example, the task similarity is calculated using the following formula:

[0042]

[0043] Where E represents the identity matrix, S i Indicates the task information corresponding to the current task, S y Indicates the task similarity of another task.

[0044] Furthermore, when the task similarity between each task and another task is determined, the determined task similarity is used as a corresponding element in the similarity matrix to be constructed, thereby providing the similarity matrix for subsequent processing.

[0045] Step S120: Select two seed tasks corresponding to the task similarity with the largest value in the similarity matrix.

[0046] The task similarity between the two seed tasks is the highest in the similarity matrix. It's conceivable that in the similarity matrix, task similarities are arranged in rows and columns, with each task similarity corresponding to two tasks. Therefore, by searching each element in the similarity matrix, we can determine the task with the highest similarity in the matrix, and then determine the corresponding index, that is, the two seed tasks corresponding to that task similarity.

[0047] Step S130: Based on the seed task and the similarity matrix, multiple tasks are selected as tasks in the same batch, until the number of tasks in the same batch is equal to the storage capacity of the turnover shelf corresponding to the sorting platform.

[0048] The number of tasks in the same batch is limited by the storage capacity of the turnover shelf corresponding to the sorting station. The central control device needs to select multiple tasks that meet the storage capacity as tasks in the same batch. When selecting tasks in the same batch, tasks associated with the seed task in the similarity matrix are selected as tasks in the same batch until the tasks meet the corresponding number. In one embodiment, for the selection of tasks in the same batch, Figure 3 As shown, Figure 3 This is a schematic diagram of the steps for selecting tasks in the same batch provided in an embodiment of the present application. The specific steps are as follows:

[0049] Step S310 : Select multiple task similarities in the rows and columns where the task similarity corresponding to the seed task is located in the similarity matrix to construct a candidate set.

[0050] Step S320 : Select the seed task and the task with the highest similarity to the seed task in the candidate set as tasks in the same batch.

[0051] Step S330: If the number of tasks in the current batch is less than the storage capacity of the turnover rack corresponding to the sorting station, tasks in the candidate set are continuously selected as tasks in the same batch in the order of their similarity until the number of tasks in the same batch is equal to the storage capacity of the turnover rack corresponding to the sorting station.

[0052] It is understood that when selecting tasks from the same batch, a candidate set can be constructed accordingly, which also contains multiple task similarities. Specifically, after the seed task is determined, multiple task similarities in the row and column of the similarity matrix corresponding to the seed task are selected as the data in the candidate set to be constructed.

[0053] When selecting tasks from the same batch, the task with the highest similarity to the seed task is selected from the set to be selected as one of the tasks from the same batch. Of course, the seed task is also selected as one of the tasks from the same batch, and the selection of tasks from the same batch is completed in sequence. In addition, the number of tasks from the same batch needs to be detected. If the number is still less than the storage capacity of the turnover shelf corresponding to the sorting station, it is necessary to continue to search for tasks that meet the conditions in the set to be selected. If tasks are selected as tasks from the same batch in the order of task similarity in the set to be selected, it can be imagined that the selection process in the set to be selected is a continuous cycle, and the similarity of the tasks selected in each cycle is smaller than the similarity of the tasks selected in the previous cycle, so that the corresponding tasks are selected in the order of task similarity. Of course, when the number of tasks from the same batch is equal to the storage capacity of the turnover shelf corresponding to the sorting station, the cycle ends, and the final tasks from the same batch are obtained.

[0054] Step S140: Initiate scheduling to multiple AGV mobile robots so that each AGV mobile robot can execute the target task in the same batch of tasks.

[0055] It's conceivable that tasks within a task set are associated with sorting stations, each of which performs sorting work on shelves to be picked in different tasks. For example, each sorting station is provided with station information that records the picking status of each shelf, identifying whether each shelf is being picked by the sorting station. For example, a task within the same batch is designated as the target task, and the shelves to be picked in that target task are handled by a sorting station. Accordingly, an AGV mobile robot is dispatched to transport the corresponding shelf to that sorting station.

[0056] Step S150: When task completion information is received from the sorting station, the task with the highest priority is retrieved from the task set to update the tasks in the same batch until the task set is empty.

[0057] After a worker completes sorting at a sorting station, they can send a task completion message to the central control device through the sorting station, indicating that they have sorted the goods on the storage shelves. Upon receiving the task completion message, the central control device reallocates tasks to the sorting station, such as retrieving the highest-priority task from the task set and updating tasks in the same batch.

[0058] It's conceivable that during each update, once the number of tasks in the same batch meets the number of storage slots, the update is paused to wait for the sorting station to complete processing. In other words, the central control device responds to task completion information by adding the corresponding task as a task in the same batch, thus repeating the above process to update until all tasks in the task set are processed.

[0059] In one embodiment, the central control device needs to determine the similarity between the station information corresponding to the sorting station and the remaining tasks for updating the same batch of tasks to determine the task priority. Figure 4 As shown, Figure 4 This is a schematic diagram of the steps for updating tasks in the same batch provided in an embodiment of the present application. The specific steps are as follows:

[0060] Step S410: Determine the remaining similarities corresponding to the remaining tasks according to the task information and platform information of the remaining tasks in the task set.

[0061] Step S420: Determine the task response ratio corresponding to the remaining tasks based on the waiting time of the remaining tasks and the task path lengths corresponding to the remaining tasks.

[0062] Step S430: Determine the task priority of each remaining task according to the remaining similarity and task response ratio corresponding to each remaining task.

[0063] Step S440: Select the task with the highest priority and add it to the same batch of tasks.

[0064] It can be understood that the platform information corresponding to the sorting platform is used to represent the statistics of the storage shelves that still need to be picked. That is, similar to the task information, the picking requirements can also be marked with corresponding values, such as 1 to indicate that the storage shelf still needs to be picked, and 0 to indicate that the storage shelf does not need to be picked. Correspondingly, the platform information can also be represented in the form of a vector, such as S res =[P1ˋ,P2ˋ,……,P f ˋ, P s ˋ], where P f ˋ represents the f-th storage shelf, and takes the value 0 or 1 to indicate whether it still needs to be picked. It should be noted that P S ˋIndicates the picking demand for the last storage shelf recorded in the task information.

[0065] Therefore, the central control device can calculate the remaining similarity of the remaining tasks based on the above-mentioned station information and the task information of the remaining tasks, which can be specifically expressed by the following formula:

[0066]

[0067] Among them, K is the number of storage spaces of turnover shelves, S m is the task information corresponding to the remaining task m.

[0068] The central control device also needs to calculate the task response ratio corresponding to the remaining tasks, which is related to the waiting time of the remaining tasks and the task path length corresponding to the remaining tasks. It can be understood that the waiting time of the remaining tasks is the time from the start time of task creation to the current time of calculating the task response ratio. The central control device is equipped with a corresponding coordinate system for the spatial range of the warehouse to facilitate the movement of the AGV mobile robot in the warehouse. Therefore, the task path length corresponding to the remaining tasks can be determined based on the starting coordinates corresponding to the starting position of the task and the end coordinates of the end position of the task.

[0069] After determining the task response ratio, the central control device may further calculate the task priority of the remaining tasks. For example, in some embodiments, the task priority is the sum of the square of the task response ratio and the remaining similarity, which may be specifically expressed by the following formula:

[0070] Q=OS m +W 2

[0071] Where W is the task response ratio, QS m is the remaining similarity corresponding to the remaining tasks m.

[0072] Then, the task with the highest priority corresponding to each of the remaining tasks is selected and used as the task in the same batch. It is conceivable that if the number of tasks in the same batch has not yet reached the storage limit, the next task with the highest priority can be selected as the task in the same batch. It should be noted that the tasks selected in each selection process will not be selected in the next selection process.

[0073] From the above scheme, it can be seen that the central control equipment determines the tasks with similar picking requirements for storage shelves by comparing the task similarities between the tasks, and thus determines the corresponding seed tasks to obtain tasks in the same batch, so that the AGV mobile robot can give priority to tasks with similar picking requirements, effectively improving the picking efficiency and making the scheduling and management of the AGV mobile robot more reasonable and effective.

[0074] In some embodiments, for calculating the task response ratio, the central control device can use the absolute value of the quotient of the waiting time and the task path length multiplied by the task coefficient as the task response ratio. The waiting time is the difference between the current time when the task response ratio is calculated and the start time of the task; and the task path length is represented by the distance between the starting coordinate and the end coordinate. Specifically, it can be expressed using the following formula:

[0075]

[0076] Where t is the current time, is the starting time of task w, is the starting coordinate of task w, is the end point coordinate of task w, and φ is the task coefficient.

[0077] It should be noted that in some embodiments, the value of the task coefficient is associated with the number of tasks in the task set, and the greater the number of tasks, the smaller the value of the task coefficient. That is, the specific value of the task coefficient is negatively correlated with the number of tasks. The specific value can be set based on system operation conditions, such as within a set range (10-40), and the specific value also satisfies the principle that the greater the number of tasks, the smaller the value of the task coefficient.

[0078] Figure 5 This is a schematic diagram of the structure of a task scheduling device provided in one embodiment of the present application. The device is used to execute the task scheduling method described above and has the functional modules and beneficial effects of the execution method. The device is applied to a central control device, which communicates with an AGV mobile robot to schedule the AGV mobile robot. The central control device is provided with a task set in response to the picking requirements corresponding to each storage shelf. The task information corresponding to each task in the task set records the picking status of each storage shelf to indicate whether each storage shelf is ready for picking. As shown in the figure, the device includes a similarity determination module 501, a target screening module 502, a task selection module 503, a task scheduling module 504, and a task update module 505.

[0079] The similarity determination module 501 is configured to determine the task similarity between each task and another task according to the set task information to construct a similarity matrix;

[0080] The target screening module 502 is configured to select two seed tasks corresponding to the task similarity with the largest value in the similarity matrix;

[0081] The task selection module 503 is configured to select multiple tasks as tasks in the same batch based on the seed task and the similarity matrix, until the number of tasks in the same batch is equal to the storage capacity of the turnover shelf corresponding to the sorting platform;

[0082] The task scheduling module 504 is configured to initiate scheduling to multiple AGV mobile robots so that each AGV mobile robot performs a target task in the same batch of tasks;

[0083] The task update module 505 is configured to retrieve the task with the highest priority from the task set upon receiving task completion information from the sorting station to update the tasks in the same batch until the task set is empty.

[0084] Based on the above embodiment, the similarity determination module 501 is further configured to:

[0085] According to the task information corresponding to each task, a task information vector is constructed;

[0086] Based on the task information vector of each task, the task similarity between each task and another task is calculated in turn to determine a similarity matrix.

[0087] Based on the above embodiment, the task selection module 503 is further configured to:

[0088] Select multiple task similarities in the rows and columns where the task similarity corresponding to the seed task is located in the similarity matrix to construct a candidate set;

[0089] Select the seed task and the task with the highest similarity to the seed task in the candidate set as tasks in the same batch;

[0090] If the current number of tasks in the same batch is less than the storage capacity of the turnover shelf corresponding to the sorting platform, tasks will continue to be selected as tasks in the same batch in the order of task similarity until the number of tasks in the same batch is equal to the storage capacity of the turnover shelf corresponding to the sorting platform.

[0091] Based on the above embodiment, the sorting station is provided with station information corresponding to the sorting station, and the station information records the picking status of the storage shelves to identify whether each storage shelf is picked by the sorting station; the task update module 505 is further configured to:

[0092] Determine the remaining similarities corresponding to the remaining tasks based on the task information and platform information of the remaining tasks in the task set;

[0093] Determine the task response ratio corresponding to the remaining tasks based on the waiting time of the remaining tasks and the task path length corresponding to the remaining tasks;

[0094] Determine the task priority of each remaining task based on the remaining similarity and task response ratio corresponding to each remaining task;

[0095] Select the task with the highest priority and add it to the same batch of tasks.

[0096] Based on the above embodiment, the task updating module 505 is further configured to:

[0097] The absolute value of the quotient of the waiting time and the task path length multiplied by the task coefficient is taken as the task response ratio.

[0098] Based on the above embodiment, the value of the task priority is the sum of the square of the task response ratio and the residual similarity.

[0099] Based on the above embodiment, the value of the task coefficient is associated with the number of tasks in the task set, and the greater the number of tasks, the smaller the value of the task coefficient.

[0100] It is worth noting that in the embodiment of the above-mentioned task scheduling device, each module is divided only according to functional logic, but is not limited to the above-mentioned division, as long as the corresponding functions can be realized; in addition, the specific names of each module are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application.

[0101] Figure 6 This is a structural diagram of a central control device provided in an embodiment of the present application, which is used to execute the task scheduling method provided in the above embodiment, and has functional modules and beneficial effects corresponding to the execution method. As shown in the figure, the server includes a processor 601, a memory 602, an input device 603 and an output device 604. The number of processors 601 can be one or more, and the figure takes one processor 601 as an example; the processor 601, the memory 602, the input device 603 and the output device 604 can be connected via a bus or other means, and the figure takes the connection via a bus as an example. The memory 602, as a computer-readable storage medium, can be used to store software programs, computer executable programs and modules, such as program instructions / modules corresponding to the task scheduling method in the embodiment of the present application. The processor 601 executes various corresponding functional applications and data processing by running the software programs, instructions and modules stored in the memory 602, that is, realizes the above-mentioned task scheduling method.

[0102] The memory 602 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system and at least one application required for a function; the data storage area may store data recorded or created during use, etc. In addition, the memory 602 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 602 may further include a memory remotely located relative to the processor 601, and these remotely located memories may be connected to the terminal device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0103] The input device 603 can be used to input corresponding digital or character information to the processor 601, and generate key signal input related to the user settings and function control of the device; the output device 604 can be used to send or display key signal output related to the user settings and function control of the device.

[0104] An embodiment of the present application further provides a storage medium storing computer-executable instructions, which, when executed by a processor, are used to perform relevant operations in the task scheduling method provided in any embodiment of the present application.

[0105] Computer-readable storage media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0106] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0107] Note that the above are only preferred embodiments of the present application and the technical principles employed. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments, and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments and may include many other equivalent embodiments without departing from the scope of the present application. The scope of the present application is determined by the scope of the appended claims.

Claims

1. A task scheduling method, characterized in that: Applied to a central control device, the central control device is in communication with an AGV mobile robot to schedule the AGV mobile robot, the central control device is provided with a task set in response to the picking requirements corresponding to each storage shelf, and the task information corresponding to each task in the task set records the picking status of each storage shelf to identify whether each storage shelf is to be picked. The method includes: According to the set task information, determine the task similarity between each task and another task to construct a similarity matrix; Selecting two seed tasks corresponding to the largest task similarity in the similarity matrix; Based on the seed task and the similarity matrix, multiple tasks are selected as tasks in the same batch, until the number of tasks in the same batch is equal to the storage capacity of the turnover shelf corresponding to the sorting platform; Initiate scheduling to multiple AGV mobile robots so that each of the AGV mobile robots performs the target task in the same batch of tasks; When receiving task completion information from the sorting station, calling the task with the highest priority from the task set to update the tasks in the same batch until the task set is empty; The sorting station is provided with station information corresponding to the sorting station, and the station information records the picking status of the storage shelves to identify whether each storage shelf is picked by the sorting station; When receiving task completion information from the sorting station, the task with the highest priority is retrieved from the task set to update the tasks in the same batch until the task set is empty, including: Determining the remaining similarities corresponding to the remaining tasks according to the task information of the remaining tasks in the task set and the platform information; Determining a task response ratio corresponding to the remaining tasks based on the waiting time of the remaining tasks and the task path length corresponding to the remaining tasks; Determining the task priority of each of the remaining tasks according to the remaining similarities corresponding to each of the remaining tasks and the task response ratio; The task with the highest priority is selected and added to the same batch of tasks.

2. The task scheduling method according to claim 1, characterized in that: The step of determining the task similarity between each task and another task based on the set task information to construct a similarity matrix includes: According to the task information corresponding to each task, a task information vector is constructed; Based on the task information vector of each task, the task similarity between each task and another task is calculated in sequence to determine the similarity matrix.

3. The task scheduling method according to claim 1, wherein: The selecting, based on the seed task and the similarity matrix, multiple tasks as tasks in the same batch until the number of tasks in the same batch is equal to the storage capacity of the turnover shelf corresponding to the sorting platform includes: Selecting multiple task similarities in the rows and columns where the task similarities corresponding to the seed task are located in the similarity matrix to construct a candidate set; Selecting the seed task and the task with the highest similarity to the seed task in the candidate set as tasks in the same batch; If the current number of tasks in the same batch is less than the storage capacity of the turnover shelf corresponding to the sorting platform, tasks will continue to be selected as tasks in the same batch in the order of task similarity until the number of tasks in the same batch is equal to the storage capacity of the turnover shelf corresponding to the sorting platform.

4. The task scheduling method according to claim 1, wherein: The determining, based on the waiting time of the remaining tasks and the task path lengths corresponding to the remaining tasks, the task response ratios corresponding to the remaining tasks includes: The task response ratio is obtained by multiplying the absolute value of the quotient of the waiting time and the task path length by the task coefficient.

5. The task scheduling method according to claim 1 or 4, characterized in that: The value of the task priority is the sum of the square of the task response ratio and the residual similarity.

6. The task scheduling method according to claim 4, characterized in that: The value of the task coefficient is associated with the number of tasks in the task set, and the greater the number of tasks, the smaller the value of the task coefficient.

7. A task scheduling device, characterized in that: Applied to a central control device, the central control device is in communication with an AGV mobile robot to schedule the AGV mobile robot, the central control device is provided with a task set in response to the picking requirements of each storage shelf, and the task information corresponding to each task in the task set records the picking status of each storage shelf to identify whether each storage shelf is to be picked. The device includes: A similarity determination module is configured to determine the task similarity between each task and another task based on the set task information to construct a similarity matrix; A target screening module is configured to select two seed tasks corresponding to the task similarities with the largest values ​​in the similarity matrix; a task selection module configured to select multiple tasks as tasks in the same batch based on the seed task and the similarity matrix, until the number of tasks in the same batch is equal to the storage capacity of the turnover shelf corresponding to the sorting platform; A task scheduling module is configured to initiate scheduling to multiple AGV mobile robots so that each of the AGV mobile robots performs the target task in the same batch of tasks; a task updating module configured to, upon receiving task completion information from a sorting station, retrieve a task with the highest priority from the task set to update the tasks in the same batch until the task set is empty; The sorting station is provided with station information corresponding to the sorting station, and the station information records the picking status of the storage shelves to identify whether each storage shelf is picked by the sorting station; The task update module is further configured to: Determining the remaining similarities corresponding to the remaining tasks according to the task information of the remaining tasks in the task set and the platform information; Determining a task response ratio corresponding to the remaining tasks based on the waiting time of the remaining tasks and the task path length corresponding to the remaining tasks; Determining the task priority of each of the remaining tasks according to the remaining similarities corresponding to each of the remaining tasks and the task response ratio; The task with the highest priority is selected and added to the same batch of tasks.

8. A central control device, characterized in that: include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, enables the one or more processors to implement the task scheduling method according to any one of claims 1 to 6.

9. A storage medium storing computer executable instructions, characterized in that: When the computer executable instructions are executed by a processor, they are used to perform the task scheduling method according to any one of claims 1 to 6.

Images