Task arrangement method and device based on unmanned aerial vehicle flight control platform, and medium

Abstract

The invention discloses a task arrangement method and device based on an unmanned aerial vehicle flight control platform and a medium, and relates to the technical field of unmanned aerial vehicle intelligent control, and the method comprises the steps: obtaining a task demand, and carrying out the task environment observation of the task demand, so as to obtain a task environment state; based on the task environment state, sub-task data are determined through task dynamic splitting analysis; pushing the subtask data to a preset environment, and performing task expert role matching on the subtask data pushed to the preset environment to obtain subtask processing configuration; according to the sub-task processing configuration, determining sub-task real-time decoupling configuration through real-time routing distribution; and performing task environment state analysis on the sub-task real-time decoupling configuration to determine sub-task dynamic adjustment data. According to the method, the technical problem that task disassembly is not intelligent in unmanned aerial vehicle task arrangement in the prior art is solved.

Description

Technical Field

[0001] The present application relates to the field of unmanned aerial vehicle (UAV) intelligent control technology, and in particular to a task scheduling method, device and medium based on an unmanned aerial vehicle (UAV) flight control platform. Background Art

[0002] With the rapid development of drone technology, low-altitude economy has become an important part of the modern economy. Low-altitude economy refers to various economic activities carried out in the low-altitude airspace of 0-3000 meters. Its application scope covers general aviation industry, smart city management, modern agriculture, emergency rescue and logistics distribution and other fields.

[0003] Although drone task scheduling and control technology has been continuously improving, in practical applications, the large number of tasks and high complexity of drone intelligent platforms have limited the scheduling of drones. In addition, due to the limitations of natural language understanding and task decision-making, the efficiency of multi-task coordination and task decomposition is low. The coupling degree of the existing drone task scheduling system architecture is too high, making it difficult to achieve functional expansion and access to new functions. Summary of the invention

[0004] The embodiments of the present application provide a task scheduling method, device and medium based on a UAV flight control platform, which solves the technical problem of unintelligent task decomposition in UAV task scheduling in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a task scheduling method based on a UAV flight control platform, characterized in that the method includes: obtaining task requirements, and performing task environment observation on the task requirements to obtain the task environment status; based on the task environment status, determining subtask data through task dynamic splitting analysis; pushing the subtask data to a preset environment, and performing task expert role matching on the subtask data pushed to the preset environment to obtain a subtask processing configuration; according to the subtask processing configuration, determining the subtask real-time decoupling configuration through real-time routing allocation; performing task environment status analysis on the subtask real-time decoupling configuration to determine the subtask dynamic adjustment data.

[0006] In one implementation of the present application, a task environment is observed for a task requirement to obtain a task environment state, specifically including: determining whether the task requirement conforms to preset task history information; if the task requirement conforms to the preset task history information, processing the task requirement according to the execution flow of the task history information to determine a first task environment state; if the task requirement does not conform to the preset task history information, determining a second task environment state; and determining the task environment state based on the first task environment state and the second task environment state.

[0007] In one implementation of the present application, subtask data is determined through dynamic task splitting analysis based on the task environment state, specifically including: determining the first task disassembly state through a first ReAct decomposition analysis based on the task environment state; when the first task disassembly state is that no disassembly is required, executing the current task, and performing a second ReAct decomposition analysis on the current task to obtain a second task disassembly state; when the first task disassembly state is disassembly, obtaining first subtask data; when the second task disassembly state is that no disassembly is required, executing the current task; when the second task disassembly state is that disassembly is required, obtaining second subtask data; determining subtask data based on the first subtask data and the second subtask data.

[0008] In one implementation of the present application, task expert role matching is performed on subtask data pushed to a preset environment to obtain a subtask processing configuration, specifically including: determining task feature data through multi-agent task analysis based on the subtask data; performing task logic judgment on the task feature data to obtain subtask configuration data; and matching the subtask configuration data with expert group tasks to obtain a subtask processing configuration.

[0009] In one implementation of the present application, the subtask real-time decoupling configuration is determined through real-time routing allocation based on the subtask processing configuration, specifically including: based on the subtask processing configuration, determining the current routing configuration of the task through current routing allocation; performing real-time routing change analysis on the current routing configuration of the task to obtain the task decoupling configuration; according to the task decoupling configuration, determining the subtask real-time decoupling configuration through task routing matching.

[0010] In one implementation of the present application, a task environment status analysis is performed on the real-time decoupling configuration of the subtask to determine the dynamic adjustment data of the subtask, specifically including: based on the real-time decoupling configuration of the subtask, determining the current execution status of the subtask through task status judgment; performing a multi-agent expert group environment analysis on the current execution status of the subtask to determine the dynamic adjustment data of the subtask.

[0011] In one implementation of the present application, before obtaining the task requirements, the method further includes: obtaining interface requirements, and based on the interface requirements, determining the task interface type through interface interaction configuration; performing interface interaction analysis on the task interface type to determine the task interface configuration.

[0012] In one implementation of the present application, after performing a task environment status analysis on the real-time decoupling configuration of the subtask to determine the subtask dynamic adjustment data, the method also includes: determining the execution visualization data through task environment feedback based on the subtask dynamic adjustment data; performing a real-time abnormal status analysis on the execution visualization data to obtain scheduling task update data; completing the drone scheduling task according to the scheduling task update data, and resetting the drone's task status.

[0013] In the second aspect, an embodiment of the present application also provides a task scheduling device based on a UAV flight control platform, characterized in that the device includes: at least one processor; and 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, and the instructions are executed by the at least one processor so that the at least one processor can: obtain task requirements, and perform task environment observation on the task requirements to obtain the task environment state; based on the task environment state, determine subtask data through dynamic task splitting analysis; push the subtask data to a preset environment, and perform task expert role matching on the subtask data pushed to the preset environment to obtain a subtask processing configuration; according to the subtask processing configuration, determine the subtask real-time decoupling configuration through real-time routing allocation; perform task environment state analysis on the subtask real-time decoupling configuration to determine the subtask dynamic adjustment data.

[0014] On the third aspect, the embodiment of the present application also provides a non-volatile computer storage medium for task scheduling based on an unmanned aerial vehicle flight control platform, storing computer executable instructions, characterized in that the computer executable instructions are set to: obtain task requirements, and perform task environment observation on the task requirements to obtain the task environment state; based on the task environment state, determine subtask data through task dynamic splitting analysis; push the subtask data to a preset environment, and perform task expert role matching on the subtask data pushed to the preset environment to obtain a subtask processing configuration; according to the subtask processing configuration, determine the subtask real-time decoupling configuration through real-time routing allocation; perform task environment state analysis on the subtask real-time decoupling configuration to determine the subtask dynamic adjustment data.

[0015] The embodiments of the present application provide a task scheduling method, device and medium based on a UAV flight control platform. Through task decomposition analysis, multi-agent expert analysis and task environment management, the technical problem of unintelligent task decomposition in UAV task scheduling in the prior art is solved, and the intelligent decomposition and scheduling of complex UAV tasks is realized, the coupling degree of UAV task execution is reduced, and the efficiency of collaborative execution of multi-scenario tasks is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 A flowchart of a task scheduling method based on a UAV flight control platform provided in an embodiment of the present application; Figure 2 A schematic diagram of the internal structure of a task scheduling device based on a UAV flight control platform provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0018] The embodiments of the present application provide a task scheduling method, device and medium based on a UAV flight control platform. Through task decomposition analysis, multi-agent expert analysis and task environment management, the technical problem of unintelligent task decomposition in UAV task scheduling in the prior art is solved, and the intelligent decomposition and scheduling of complex UAV tasks is realized, the coupling degree of UAV task execution is reduced, and the efficiency of collaborative execution of multi-scenario tasks is improved.

[0019] The technical solution proposed in the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0020] Figure 1 The following is a flow chart of a task scheduling method based on a UAV flight control platform provided in an embodiment of the present application. Figure 1 As shown, the embodiment of the present application provides a task scheduling method based on a UAV flight control platform, which specifically includes the following steps: Step 101: Obtain task requirements, and observe the task environment for the task requirements to obtain the task environment state.

[0021] Specifically, it includes: judging whether the task requirements are consistent with the preset task history information; if the task requirements are consistent with the preset task history information, processing the task requirements according to the execution flow of the task history information to determine a first task environment state; if the task requirements do not meet the preset task history information, determining a second task environment state; determining the task environment state based on the first task environment state and the second task environment state.

[0022] This application obtains mission requirements and observes the mission environment for the mission requirements to obtain the mission environment status, thereby achieving environmental assessment of the UAV mission status and improving the control accuracy of the UAV platform over the execution of the UAV mission.

[0023] In the examples of the present application, detailed explanation is given by the following Example 1.

[0024] Example 1: In order to intelligently split the drone mission instructions received by the drone platform in actual applications, it is necessary to analyze the mission requirements in real time and split them according to the corresponding task processing capabilities of the system.

[0025] First, the task requirements input by the user are received, and the current task requirements are judged through environmental observation whether they need to be decomposed. While obtaining the task requirements input by the user, the task historical information of the task requirements will also be judged to determine whether the task has a formed solution logic and historical data. This part is judged based on the memory part, that is, the first task environment state.

[0026] If the environment state required by the task is such that it cannot be directly executed through the task history information, it is necessary to analyze its disassembly situation, that is, whether the second task environment state needs to be split.

[0027] Task decomposition experts use the qwen-long model as the engine and the ReAct mode to think about whether the current task needs to be decomposed. If it needs to be decomposed, the task will be decomposed into subtasks, and the decomposed tasks will be pushed to the execution part for completion.

[0028] Step 102: Based on the task environment status, determine the subtask data through task dynamic splitting analysis.

[0029] Specifically, it includes: based on the task environment state, determining the first task disassembly state through the first ReAct decomposition analysis; when the first task disassembly state is that no disassembly is required, executing the current task, and performing a second ReAct decomposition analysis on the current task to obtain the second task disassembly state; when the first task disassembly state is disassembly, obtaining the first subtask data; when the second task disassembly state is that no disassembly is required, executing the current task; when the second task disassembly state is that disassembly is required, obtaining the second subtask data; determining the subtask data based on the first subtask data and the second subtask data.

[0030] Based on the mission environment status, this application determines the subtask data through dynamic task splitting and analysis, realizes the intelligent decomposition and arrangement of complex UAV tasks, and improves the processing efficiency of UAV tasks.

[0031] In the examples of the present application, detailed explanation is given by the following Example 2.

[0032] Example 2: ReAct decomposition analysis (ReAct mode) refers to the thinking-action cycle, alternating thinking and action in task solving.

[0033] After a task is split into subtasks (including tasks that are determined not to be split), it needs to be executed. During the execution process, since there may be obstacles to the initial processing or execution of the task, both tasks that do not need to be split and tasks that have been split need additional execution process disassembly analysis.

[0034] If the first task decomposition status cannot meet the needs of subsequent task execution, a second ReAct decomposition analysis is required to further decompose the current task or subtask and execute it. This process is repeated until further decomposition is no longer required.

[0035] Step 103: Push the subtask data to the preset environment, and perform task expert role matching on the subtask data pushed to the preset environment to obtain the subtask processing configuration.

[0036] Specifically, it includes: based on subtask data, determining task feature data through multi-agent task analysis; performing task logic judgment on the task feature data to obtain subtask configuration data; and matching the subtask configuration data with expert group tasks to obtain subtask processing configuration.

[0037] This application pushes subtask data to a preset environment and matches the task expert roles of the subtask data pushed to the preset environment to obtain the subtask processing configuration, thereby realizing real-time configuration mapping of subtasks and corresponding multi-agent expert groups, and reducing the degree of coupling of complex task processing.

[0038] In the examples of the present application, this is explained in detail through the following Example 3.

[0039] Example 3: A multi-agent expert group includes multiple expert roles, such as navigation expert (NavigationExpert), object detection expert (ObjectDetectExpert), longitude and latitude query expert (QueryCoordinationExpert), etc. Each expert is responsible for handling a specific type of task, such as navigation, object detection, location query, etc. Experts communicate and coordinate with each other through the environment module to jointly complete the task objectives.

[0040] For subtasks that have been decomposed and do not need to be decomposed again, the corresponding expert role is queried and configured according to the nature of the subtask.

[0041] Step 104: Determine the subtask real-time decoupling configuration through real-time routing allocation according to the subtask processing configuration.

[0042] Specifically, it includes: based on the subtask processing configuration, determining the current routing configuration of the task through the current routing allocation; performing real-time routing change analysis on the current routing configuration of the task to obtain the task decoupling configuration; according to the task decoupling configuration, determining the subtask real-time decoupling configuration through task routing matching.

[0043] This application determines the real-time decoupling configuration of subtasks based on subtask processing configuration and real-time routing allocation, thereby reducing the coupling degree of drone task execution.

[0044] In the examples of the present application, a detailed explanation is given by the following Example 4.

[0045] Example 4: In the prior art, the execution allocation of drone tasks is achieved through continuous analysis of the execution process. However, in actual applications, this method will result in a high degree of coupling in the analysis of drone task execution, and it is impossible to specifically analyze the task completion status of the drone at each stage or step.

[0046] This application maps the expert modules of the drone subtask requirements through routing allocation, and the decomposed tasks are analyzed by different expert modules, which are the various expert roles in the multi-agent expert group.

[0047] Through the technical solution of the present application, the relationship between the subtasks and expert modules decomposed from a task is one-to-one corresponding. When it is necessary to analyze and process them, the individual subtasks and their expert modules can be directly analyzed, thereby reducing the coupling degree of the entire technical solution and facilitating the expansion of the expert modules at any time.

[0048] In order to meet the needs of real-time analysis, this application dynamically configures the routes of tasks that require changes in analysis methods during task execution through real-time route change analysis, so as to realize automatic replacement of analysis expert modules and improve data stability and accuracy.

[0049] Step 105: Perform task environment status analysis on the subtask real-time decoupling configuration to determine subtask dynamic adjustment data.

[0050] Specifically, it includes: based on the real-time decoupling configuration of subtasks, determining the current execution status of the subtasks through task status judgment; performing multi-agent expert group environment analysis on the current execution status of the subtasks to determine the dynamic adjustment data of the subtasks.

[0051] Before obtaining the task requirements, the method further includes: obtaining interface requirements, and based on the interface requirements, determining the task interface type through interface interaction configuration; and performing interface interaction analysis on the task interface type to determine the task interface configuration.

[0052] After performing task environment status analysis on the real-time decoupling configuration of the subtask to determine the dynamic adjustment data of the subtask, the method also includes: determining execution visualization data based on the dynamic adjustment data of the subtask through task environment feedback; performing real-time abnormal status analysis on the execution visualization data to obtain scheduling task update data; completing the drone scheduling task according to the scheduling task update data, and resetting the drone's task status.

[0053] This application analyzes the task environment status by decoupling the subtasks in real time to determine the subtask dynamic adjustment data, thereby improving the efficiency of collaborative execution of multi-scenario tasks.

[0054] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, the embodiment of this application also provides a task scheduling device based on a UAV flight control platform, whose structure is as follows: Figure 2 shown.

[0055] Figure 2 This is a schematic diagram of the internal structure of a task scheduling device based on a UAV flight control platform provided in an embodiment of the present application. Figure 2 As shown, the device includes: at least one processor 201; and, a memory 202 communicatively connected to the at least one processor; The memory 202 stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor 201 to enable at least one processor 201 to: Obtain task requirements and observe the task environment for the task requirements to obtain the task environment status; based on the task environment status, determine the subtask data through dynamic task splitting analysis; push the subtask data to the preset environment, and match the subtask data pushed to the preset environment with the task expert role to obtain the subtask processing configuration; according to the subtask processing configuration, determine the subtask real-time decoupling configuration through real-time routing allocation; perform task environment status analysis on the subtask real-time decoupling configuration to determine the subtask dynamic adjustment data.

[0056] Some embodiments of the present application provide corresponding Figure 1 A non-volatile computer storage medium for task scheduling based on a UAV flight control platform stores computer executable instructions, and the computer executable instructions are set as follows: Obtain task requirements and observe the task environment for the task requirements to obtain the task environment status; based on the task environment status, determine the subtask data through dynamic task splitting analysis; push the subtask data to the preset environment, and match the subtask data pushed to the preset environment with the task expert role to obtain the subtask processing configuration; according to the subtask processing configuration, determine the subtask real-time decoupling configuration through real-time routing allocation; perform task environment status analysis on the subtask real-time decoupling configuration to determine the subtask dynamic adjustment data.

[0057] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0058] The system and medium provided in the embodiments of the present application correspond one-to-one to the method. Therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0059] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0060] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0061] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0062] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0063] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0064] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0065] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. 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 disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0066] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0067] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A task scheduling method based on a UAV flight control platform, characterized in that: The method comprises: Obtaining task requirements, and performing task environment observation on the task requirements to obtain a task environment state; Based on the task environment state, determining subtask data through task dynamic splitting analysis; Pushing the subtask data to a preset environment, and performing task expert role matching on the subtask data pushed to the preset environment to obtain a subtask processing configuration; According to the subtask processing configuration, determining the subtask real-time decoupling configuration through real-time routing allocation; Perform task environment status analysis on the subtask real-time decoupling configuration to determine subtask dynamic adjustment data.

2. The task scheduling method based on the UAV flight control platform according to claim 1 is characterized in that: Performing task environment observation on the task requirements to obtain the task environment status, specifically including: Determine whether the task requirement meets the preset task history information, and if the task requirement meets the preset task history information, process the task requirement according to the execution process of the task history information to determine the first task environment state; In the case where the task requirement does not meet the preset task history information, determining a second task environment state; The task environment state is determined according to the first task environment state and the second task environment state.

3. The task scheduling method based on the UAV flight control platform according to claim 1 is characterized in that: Based on the task environment status, subtask data is determined through task dynamic splitting analysis, specifically including: Based on the task environment state, determining a first task disassembly state through a first ReAct decomposition analysis; When the first task disassembly state is that disassembly is not required, executing the current task, and performing a second ReAct decomposition analysis on the current task to obtain a second task disassembly state; When the disassembly state of the first task is disassembly, obtaining first subtask data; When the disassembly status of the second task is that disassembly is not required, executing the current task; When the disassembly state of the second task is disassembly, obtaining second subtask data; The subtask data is determined according to the first subtask data and the second subtask data.

4. The task scheduling method based on the UAV flight control platform according to claim 1 is characterized in that: The subtask data pushed to the preset environment is matched with the task expert role to obtain the subtask processing configuration, including: Based on the subtask data, determining task feature data through multi-agent task analysis; Performing task logic determination on the task feature data to obtain subtask configuration data; The subtask configuration data is subjected to expert group task matching to obtain the subtask processing configuration.

5. The task scheduling method based on the UAV flight control platform according to claim 1 is characterized in that: According to the subtask processing configuration, the subtask real-time decoupling configuration is determined through real-time routing allocation, specifically including: Based on the subtask processing configuration, determine the current routing configuration of the task through the current routing allocation; Performing real-time route change analysis on the current route configuration of the task to obtain a task decoupling configuration; According to the task decoupling configuration, the subtask real-time decoupling configuration is determined through task routing matching.

6. The task scheduling method based on the UAV flight control platform according to claim 1 is characterized in that: Performing task environment status analysis on the subtask real-time decoupling configuration to determine subtask dynamic adjustment data, specifically including: Based on the real-time decoupling configuration of the subtask, the current execution status of the subtask is determined by task status judgment; A multi-agent expert group environment analysis is performed on the current execution status of the subtask to determine the subtask dynamic adjustment data.

7. The task scheduling method based on the UAV flight control platform according to claim 1 is characterized in that: Before obtaining the task requirements, the method further includes: Obtaining interface requirements, and determining the task interface type through interface interaction configuration based on the interface requirements; An interface interaction analysis is performed on the task interface type to determine the task interface configuration.

8. The task scheduling method based on the UAV flight control platform according to claim 1 is characterized in that: After performing task environment status analysis on the subtask real-time decoupling configuration to determine subtask dynamic adjustment data, the method further includes: Dynamically adjust data based on the subtasks, and determine execution visualization data through task environment feedback; Performing real-time abnormal state analysis on the execution visualization data to obtain scheduling task update data; Update data according to the scheduling task, complete the drone scheduling task, and reset the drone's task status.

9. A task scheduling device based on a UAV flight control platform, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Obtaining task requirements, and performing task environment observation on the task requirements to obtain a task environment state; Based on the task environment state, determining subtask data through task dynamic splitting analysis; Pushing the subtask data to a preset environment, and performing task expert role matching on the subtask data pushed to the preset environment to obtain a subtask processing configuration; According to the subtask processing configuration, determining the subtask real-time decoupling configuration through real-time routing allocation; Perform task environment status analysis on the subtask real-time decoupling configuration to determine subtask dynamic adjustment data.

10. A non-volatile computer storage medium for task scheduling based on an unmanned aerial vehicle flight control platform, storing computer executable instructions, characterized in that: The computer executable instructions are configured to: Obtaining task requirements, and performing task environment observation on the task requirements to obtain a task environment state; Based on the task environment state, determining subtask data through task dynamic splitting analysis; Pushing the subtask data to a preset environment, and performing task expert role matching on the subtask data pushed to the preset environment to obtain a subtask processing configuration; According to the subtask processing configuration, determining the subtask real-time decoupling configuration through real-time routing allocation; Perform task environment status analysis on the subtask real-time decoupling configuration to determine subtask dynamic adjustment data.

Images