Unmanned aerial vehicle management method and system based on cluster communication

Abstract

The invention provides an unmanned aerial vehicle management method and system based on cluster communication, relates to the technical field of unmanned aerial vehicles, and is used for improving the problem that a task allocation method of an unmanned aerial vehicle may cause poor task achievement quality in related technologies. The method is applied to an unmanned aerial vehicle cluster, unmanned aerial vehicles in the unmanned aerial vehicle cluster are in communication connection, and the method comprises the steps that a task list needing to be executed by the unmanned aerial vehicle cluster is acquired, and the task list comprises a plurality of tasks and corresponding task information; obtaining a task matching degree between each unmanned aerial vehicle and each task according to the operation information of each unmanned aerial vehicle in the unmanned aerial vehicle cluster and the task information of each task; and determining the unmanned aerial vehicle for executing the task in the unmanned aerial vehicle cluster based on the task matching degree.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of drone technology, and in particular to a drone management system and method based on cluster communication. Background Art

[0002] With the continuous development of drone technology, drones are increasingly used in many fields, such as logistics distribution, agricultural monitoring, environmental monitoring, inspection, etc. However, drone control methods have some limitations in practical applications. For example, when allocating tasks, the control method in the relevant technology only arranges the number of drones to complete the task in the cell and the estimated completion time according to the number of drones required and the task time limit, without fully considering factors such as the performance differences of drones and the complexity of the task. For example, different models of drones have different flight speeds, endurance, etc., and their adaptability to complex terrain or special tasks is also different. Simply allocating tasks according to the required quantity and time limit may lead to unreasonable task allocation, affecting the overall collaborative efficiency and the quality of task achievement.

[0003] In summary, the existing UAV task allocation method has deficiencies in considering the performance differences of UAVs and the complexity of tasks, resulting in unreasonable task allocation and affecting the overall coordination efficiency of the UAV cluster. Therefore, a new method is needed to optimize the task allocation of UAVs to improve the efficiency and quality of task completion. Summary of the invention

[0004] The embodiment of the present application provides a method and system for managing drones based on cluster communication, which is used to improve the problem that the task allocation method for drones in related technologies may lead to poor task achievement quality. To achieve the above purpose, the embodiment of the present application adopts the following technical solutions:

[0005] In the first aspect, an embodiment of the present application provides a drone management method based on cluster communication, which is applied to a drone cluster, and the drones in the drone cluster are communicated with each other. The method includes: obtaining a task list that needs to be executed by the drone cluster, and the task list includes multiple tasks and corresponding task information; obtaining the task matching degree of each drone and each task based on the operation information of each drone in the drone cluster and the task information of each task; and determining the drone in the drone cluster for executing the task based on the task matching degree.

[0006] In this way, by comprehensively considering factors such as drone performance, mission complexity, functional requirements, etc., the most suitable drone can be assigned to each task, thereby improving the problem in related technologies that the drone task allocation method may lead to poor task achievement quality.

[0007] In a possible implementation of the first aspect, the mission information includes the action complexity of the mission, the functions required to perform the mission, and the airspace complexity corresponding to the mission, and the operation information includes the operational flexibility of the drone.

[0008] In a possible implementation of the first aspect, obtaining a task matching degree between the drone and the task according to the operation information of the drone and the task information includes:

[0009]

[0010] Among them, r ij is the task matching degree of the i-th UAV to the j-th task, Fu ik is the kth function of the i-th drone, R jk is the kth function required for the jth task, Fl i is the operational flexibility of the i-th human-machine, C j is the action complexity of the jth task, E j is the spatial complexity of the airspace where the jth task is located, α, β and ω k is the weight coefficient.

[0011] In a possible implementation manner of the first aspect, the method further includes: obtaining the airspace complexity according to the number of obstacles, obstacle types, and distances between the obstacles and the task execution location within the airspace range corresponding to the task.

[0012] In this way, the airspace complexity at the task execution location can be more reasonably evaluated based on the distribution and type of obstacles in the task execution airspace, providing a basis for the calculation of task matching degree, thereby improving the rationality of task allocation.

[0013] In a possible implementation manner of the first aspect, the method further includes: obtaining the action complexity of the task based on action information of the drone during execution of the task, wherein the action information includes an action type, an action duration, and a number of actions.

[0014] In this way, the complexity of the task's movements can be assessed more accurately, the difficulty of executing the task can be understood, and a reasonable assessment of the match between the drone and the task can be ensured.

[0015] In a possible implementation manner of the first aspect, the method further includes: obtaining the operational flexibility of the drone according to the perception radius, action response speed, and action execution accuracy of the drone.

[0016] In this way, we can fully understand the operational performance of the UAV, provide a basis for the calculation of task matching, make task allocation more in line with the actual capabilities of the UAV, and improve the matching degree of task allocation.

[0017] In a possible implementation of the first aspect, each of the tasks is set with a corresponding priority, and the method further includes: obtaining a list of task matching degrees between each of the tasks and each of the drones; when the task matching degree between the same drone and two tasks is greater than that between other drones in the drone cluster, the drone gives priority to executing the task with a higher priority.

[0018] In a possible implementation manner of the first aspect, the method further includes: setting a distance threshold between the drone and the obstacle according to the type of obstacle within the airspace corresponding to the task and the distance between the obstacle and the task execution location.

[0019] In this way, by setting the distance threshold, it can be ensured that the UAV avoids collision with obstacles when performing tasks, and by reasonably setting the distance threshold in combination with the obstacle type, the UAV can reasonably plan the mission path.

[0020] In a possible implementation of the first aspect, the method also includes: constructing a corresponding task airspace based on the task list and the airspace information of the task, each of the task airspaces including multiple tasks; dividing the drone cluster into subclusters corresponding to the task airspaces, and at least one backup task drone is allocated to any two adjacent subclusters, and the task matching degree between the backup task drone and the tasks in the corresponding two adjacent task airspaces is greater than a matching degree threshold.

[0021] In this way, by dividing sub-clusters and setting up backup mission drones, the fault tolerance and ability to deal with emergencies of the drone cluster can be improved, ensuring the continuity and stability of the mission.

[0022] In a second aspect, an embodiment of the present application provides a drone management system based on cluster communication, which is used to execute the method described in any one of the first aspects, and the system includes: an acquisition module, which is used to acquire the task list, the task information and the operation information of the drone; a data processing module, which is coupled to the acquisition module, and the data processing module is used to obtain the task matching degree according to the task information and the operation information; a task matching module, which is coupled to the acquisition module and the data processing module, and the task matching module determines the drone in the drone cluster used to perform the task based on the task matching degree.

[0023] In this way, by comprehensively considering factors such as drone performance, mission complexity, functional requirements, etc., the most suitable drone can be assigned to each task, thereby improving the problem in related technologies that the drone task allocation method may lead to poor task achievement quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 A flowchart of a management method provided for some embodiments of the present application;

[0025] Figure 2 A flowchart of a management method provided for other embodiments of the present application;

[0026] Figure 3 A schematic diagram of the structure of a management system provided for some embodiments of the present application. DETAILED DESCRIPTION

[0027] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0028] In the following, the terms "first", "second", etc. are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0029] In addition, in the present application, directional terms such as "up", "down", "left" and "right" may be defined including but not limited to the orientation relative to the schematic placement of the components in the drawings. It should be understood that these directional terms may be relative concepts, which are used for relative description and clarification, and may change accordingly according to the change in the orientation of the components in the drawings.

[0030] In this application, unless otherwise specified or limited, the term "connection" should be understood in a broad sense. For example, "connection" can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection or an indirect connection through an intermediate medium. In addition, the term "coupling" can be a way of achieving electrical connection for signal transmission.

[0031] As used herein, "about," "substantially," or "approximately" includes the stated value and an average value that is within an acceptable range of variation from the particular value as determined by one of ordinary skill in the art taking into account the measurements in question and the errors associated with the measurement of the particular quantity (i.e., the limitations of the measurement system).

[0032] In the embodiments of the present application, the words "exemplarily" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplarily" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplarily" or "for example" is intended to present related concepts in a specific way.

[0033] With the continuous development of drone technology, drones are increasingly used in many fields, such as logistics distribution, agricultural monitoring, environmental monitoring, etc. However, drone control methods have some limitations in practical applications. For example, when the control method in the relevant technology performs drone task allocation, it only arranges the number of drones to complete the task in the cell and the estimated completion time according to the number of drones required and the task time limit, without fully considering the performance differences of drones and the complexity of the task. For example, different models of drones have different flight speeds, endurance, etc., and their adaptability to complex terrain or special tasks is also different. Simply allocating according to the number of requirements and time limits may cause some drone tasks to be too heavy or too light, the quality of task completion is poor, and the overall collaborative efficiency is affected. And the complexity of the task is not reasonably considered. For example, some tasks may require drones to hover and collect data for a long time in a specific area, while other tasks may require drones to move quickly in complex terrain. In addition, the timeliness constraints of the task must also be considered, that is, the drone needs to arrive at the task location before the deadline. These factors all increase the complexity of task allocation.

[0034] In summary, the existing UAV task allocation methods are insufficient in considering the performance differences of UAVs and the complexity of tasks, resulting in unreasonable task allocation, affecting the quality of task achievement and the overall collaborative efficiency of UAV clusters.

[0035] The embodiment of the present application provides a method for managing drones based on cluster communication, which is used to improve the problem in related technologies that a method for allocating tasks to drones may result in poor task achievement quality.

[0036] The method is applied to a drone cluster, such as a management system for a drone cluster. The drones in the drone cluster are connected to each other in communication. Figure 1 to Figure 2 , the method may include:

[0037] S100: Obtain a task list that the drone cluster needs to execute, where the task list includes multiple tasks and corresponding task information.

[0038] For example, the task list may record the task list and the task information of each task. The task information may include the number, name, task description (including the complexity of the action required by the drone when performing the task, the functions required by the drone when performing the task, the airspace range of the task execution and the corresponding airspace complexity), etc.

[0039] When obtaining the task list, the task list to be executed by the drone cluster can be obtained through the management system of the drone cluster or the interface of the task publishing platform. In other embodiments of the present application, other methods can be adopted to obtain the corresponding information according to the needs of those skilled in the art.

[0040] S200: Obtain a task matching degree between each drone and each task according to the operation information of each drone in the drone cluster and the task information of each task.

[0041] For example, the drone management system may store the operation information of each drone in the drone cluster. The operation information may include the model, flight speed, endurance, sensing radius, action response speed, action execution accuracy, and operation flexibility obtained based on the above information.

[0042] The operation information can be obtained based on normal flight data or experimentally measured. In other embodiments, the operation information can be transmitted to the drone management system in real time through the drone's own sensors and communication modules.

[0043] The management system can obtain the matching degree between the drone and the corresponding task based on the operation information of the drone and the task information of each task. Exemplarily, the matching degree is obtained based on the above information and the matching degree formula, and the matching degree formula is:

[0044]

[0045] Among them, r ij is the task matching degree of the i-th UAV to the j-th task, Fu ik is the kth function of the i-th drone, R jk is the kth function required for the jth task, Fl i is the operational flexibility of the i-th human-machine, C j is the action complexity of the jth task, E j is the spatial complexity of the airspace where the jth task is located, α, β and ω k is the weight coefficient, and n is the total number of functions required for the task.

[0046] Weight coefficients α, β, and ω kIt can be adjusted according to the actual application scenario. For example, in a task scenario that requires high operational flexibility, the weight of β can be appropriately increased. In a task scenario that requires high functional matching, the weight of α can be appropriately increased. When a certain function is more important, the corresponding weight coefficient ω k Can be bigger.

[0047] For example, α, β, and ω k The value range of can be 0-1. For example, in some embodiments, α and β are 0.6 and 0.4 respectively, and ω corresponding to n functions k The sum of is 1, that is

[0048] Exemplarily, the drone functions required for the mission may include one or more of load function, hovering, image transmission, flaw detection, ultrasonic detection, temperature and humidity detection, etc. It is understandable that the functions may also be added or reduced by those skilled in the art according to the mission requirements.

[0049] In other examples, each indicator in the task information may also be used as an indicator of each drone. Based on the indicator value of the corresponding indicator of each drone and the indicator value of each indicator in the task information, the matching degree of each indicator of the drone and each indicator in the task information is determined, and the task matching degree of the total drone and the task is obtained based on the matching degree of each indicator.

[0050] For example, the mission information may include the following indicators: the complexity of the mission's movements, the drone functions required to perform the mission, the airspace complexity corresponding to the mission, and the drone's operational flexibility. Each of the above indicators is normalized and a corresponding indicator value is set. The indicator value of the drone's corresponding indicator is obtained and compared with the indicator value corresponding to each of the above indicators to obtain the matching degree of the corresponding indicator. The sum of the matching degrees of each indicator is the mission matching degree between the drone and the mission.

[0051] It is understandable that the establishment and evaluation of the indicator values ​​of the corresponding indicators can be determined by those skilled in the art according to needs, and this application will not elaborate on this.

[0052] Exemplarily, the calculated task matching degree can be stored in a database to form a task matching degree matrix between the drone and the task, thereby facilitating subsequent task allocation query and decision-making.

[0053] S300: Determine the drone in the drone cluster for executing the task based on the task matching degree. Exemplarily, based on the task matching degree matrix established above, for each task, the drone with the highest task matching degree can be found.

[0054] In this way, by comprehensively considering factors such as the performance of the drone, the complexity of the mission, and functional requirements, the most suitable drone can be assigned to each task, thereby improving the problem in related technologies that the drone task allocation method may lead to poor task achievement quality.

[0055] In some embodiments, if there are multiple drones with the same and highest task matching degree, the current state of the drone (such as battery power, whether it is performing other tasks, etc.) can be further considered for selection. The information of the drone that is determined to perform the task is fed back to the management system of the drone cluster, and the task instruction is sent to the corresponding drone. The task instruction may include the specific requirements of the task, the execution path, the time node, and other detailed information in the above embodiments. In this way, it can be ensured that when the task matching degree is the same, the drone with the best current state is selected to perform the task, further improving the rationality of task allocation and the quality of task completion.

[0056] like Figure 2 As shown, in some embodiments, the method further includes:

[0057] S210. Obtain the airspace complexity according to the number of obstacles, obstacle types, and distances between the obstacles and the task execution location within the airspace range corresponding to the task.

[0058] For example, the obstacle information in the airspace can be collected by sensors carried by drones or monitoring equipment pre-installed in the mission area. For example, when the airspace information at the mission location is missing or insufficient, a drone in the drone cluster that is specifically used for detection (image acquisition) can be dispatched for detection.

[0059] Based on the information obtained, the number, type and distance of obstacles in the airspace are analyzed and quantified, and the airspace complexity is calculated according to preset rules.

[0060] For example, a corresponding obstacle value is set for each obstacle based on the type of each obstacle, and the airspace complexity is the sum of the obstacle values ​​of all obstacles. For example, the obstacles in the airspace can be divided into fixed obstacles and movable obstacles, and the risk value of movable obstacles is greater than that of fixed obstacles.

[0061] For example, the risk value of a fixed obstacle is m, and the risk value of a movable obstacle is k. 1 *m, where k is the obstacle type coefficient. The faster the obstacle moves and the greater its randomness, the higher the k 1 The larger the value of k 1 The value of is 1<k<10. The values ​​of m and k can be set by those skilled in the art, and this application does not impose any limitation on this.

[0062] Exemplarily, a mapping table of obstacles and obstacle values ​​can be established and stored in a management system. When the obstacle situation is obtained based on image information or other methods, the type of obstacle can be obtained based on image recognition or corresponding recognition methods, and a corresponding obstacle value can be assigned to each obstacle, thereby calculating the sum of the obstacle values ​​of all obstacles in the airspace.

[0063] like Among them, E j is the spatial complexity of the airspace corresponding to the jth task, z p is the obstacle value of the pth obstacle, M j is the set of obstacles in the corresponding airspace of the jth task.

[0064] For example, the obstacle value of the obstacle can be corrected according to the distance between the obstacle and the task execution location, such as setting an obstacle value correction coefficient K 2 , the correction coefficient of obstacles within the threshold range (such as 3m) of the task execution area is greater than the obstacle value of obstacles outside the threshold range of the task execution area. p Multiply to correct the obstacle value of the obstacle based on its distance from the task execution.

[0065] In this way, the airspace complexity at the task execution location can be more reasonably evaluated based on the distribution and type of obstacles in the task execution airspace, providing a basis for the calculation of task matching degree, thereby improving the rationality of task allocation.

[0066] In some embodiments, the method further comprises:

[0067] According to the obstacle type within the airspace corresponding to the task and the distance between the obstacle and the task execution location, set the distance threshold between the drone and the obstacle. The distance threshold is the minimum distance that the drone should maintain from the obstacle during flight. For example, the distance threshold L1 of a movable obstacle is greater than the distance threshold L2 of a fixed obstacle.

[0068] In this way, by setting the distance threshold, it can be ensured that the UAV avoids collision with obstacles when performing tasks, and by reasonably setting the distance threshold in combination with the obstacle type, the UAV can reasonably plan the mission path.

[0069] In some examples, for obstacles of the same type, a distance threshold for obstacles located within a certain distance (eg, 3 m) from the task execution location is smaller than a distance threshold for obstacles located outside the task execution location.

[0070] In this way, by reasonably setting the distance threshold in combination with the location of the obstacle, the UAV can avoid collision with the obstacle as much as possible when not performing the mission, thus reducing the risk of the UAV as much as possible.

[0071] In some embodiments, the method further comprises:

[0072] S220. Obtain the action complexity of the task according to the action information of the drone during the execution of the task, where the action information includes action type, action duration, and action number.

[0073] Exemplarily, the actions involved in the task execution are obtained, and the complexity is defined by type, such as the corresponding complexity can be set for straight flight, hovering, turning, circling, etc. It can be understood that the complexity evaluation of the action can be performed based on the needs of those skilled in the art, and this application does not limit this.

[0074] Exemplarily, a mapping table of action types and complexities may be established and stored in a management system. When a corresponding task is received, the action complexity of the actions involved in the task is determined based on the actions involved in the task execution and the mapping table.

[0075] For the same action, the more times it is performed and the longer it takes, the higher the requirements for the drone, that is, the greater the impact of the action complexity. The number of executions and time are used to correct the action complexity. In this way, the action complexity of the task can be more accurately evaluated, the difficulty of executing the task can be understood, and the matching degree between the drone and the task can be reasonably evaluated.

[0076] Exemplarily, the action complexity of the task is obtained according to the following formula.

[0077]

[0078] Among them, C j is the action complexity of the jth task, A j is the set of all actions of the jth task, w a is the complexity of the a-th action, t a is the action duration of the a-th action, s a is the number of the a-th action.

[0079] Another exemplary method is to only consider the influence of action type and action duration on action complexity, that is, only use the above two parameters to calculate action complexity. It is understandable that based on the inspiration of the concept of this application, those skilled in the art may also adopt other calculation methods, but they should still be within the scope of protection of this application.

[0080] In some embodiments, the method further comprises:

[0081] S230: Obtain the operational flexibility of the drone according to the perception radius, action response speed, and action execution accuracy of the drone.

[0082] For example, by testing the performance of the drone's sensing equipment and determining its sensing radius, the drone's response speed and execution accuracy to action commands are measured in a simulated environment or in actual flight tests. These parameters are comprehensively evaluated to obtain the drone's operational flexibility.

[0083] It can be understood that an evaluation value can be set for each parameter. Technical personnel in this field determine the evaluation value of the corresponding parameter of the UAV based on the actual performance of the UAV, and combine the evaluation value of each parameter to obtain the operational flexibility of the UAV. For example, the operational flexibility of the UAV is obtained by weighting each indicator and summing them up.

[0084] In this way, we can fully understand the operational performance of the UAV, provide a basis for the calculation of task matching, make task allocation more in line with the actual capabilities of the UAV, and improve the matching degree of task allocation.

[0085] In some embodiments, a corresponding priority may be set for each of the tasks. A list of task matching degrees between each of the tasks and each of the drones is obtained. When the task matching degree between the same drone and two tasks is greater than that between other drones in the drone cluster, the drone will preferentially execute the task with a higher priority. In this way, by setting task priorities, the completion of important tasks can be prioritized when the task matching degrees are similar.

[0086] In some embodiments, a corresponding task airspace is constructed based on the task list and the airspace information of the task, and each task airspace includes a plurality of the tasks.

[0087] For example, based on the airspace information of the mission, multiple mission areas can be divided using technologies such as geographic information system (GIS), and each mission airspace can be marked.

[0088] The drone cluster is divided into subclusters corresponding to the mission airspace, and at least one backup mission drone is allocated to any two adjacent subclusters, and the task matching degree between the backup mission drone and the tasks in the corresponding two adjacent mission airspaces is greater than a matching degree threshold.

[0089] For example, those skilled in the art may assign a corresponding drone to each mission airspace based on the mission matching degree, such as giving priority to assigning drones with high mission matching degrees to missions with higher priorities within each mission airspace.

[0090] Exemplarily, during allocation, at least one backup mission drone is allocated to any two adjacent subclusters, and the backup drone is used to perform the task when the drone in the corresponding airspace fails or is otherwise unable to perform the task. Therefore, the backup mission drone should at least meet the minimum requirements of the task, that is, the task matching degree should be greater than the minimum matching degree requirement (matching degree threshold) of the task. The matching degree threshold can be set according to the importance and difficulty of the task. For example, for difficult tasks, the matching degree threshold can be set higher to ensure that the backup mission drone is competent for the task.

[0091] In this way, by dividing sub-clusters and setting up backup mission drones, the fault tolerance and ability to deal with emergencies of the drone cluster can be improved, ensuring the continuity and stability of the mission.

[0092] When dividing subclusters, the current location and flight range of the drone can also be considered to ensure that the drones in each subcluster can cover the corresponding mission airspace.

[0093] like Figure 3 As shown, the embodiment of the present application also provides a UAV management system 100 based on cluster communication, which is used to execute any management method in the above embodiments. The system includes an acquisition module 110, a data processing module 120 and a task matching module 130.

[0094] The acquisition module 110 is used to acquire the task list, the task information and the operation information of the drone. The data processing module 120 is coupled to the acquisition module 110, and the data processing module 120 is used to obtain the task matching degree according to the task information and the operation information. The task matching module 130 is coupled to the acquisition module 110 and the data processing module 120, and the task matching module 130 determines the drone in the drone cluster for performing the task based on the task matching degree. Through such a system architecture, it is possible to realize automated and intelligent management of drone task allocation, improve the efficiency and accuracy of task allocation, and enhance the overall performance and collaborative operation capability of the drone cluster.

[0095] In this way, by comprehensively considering factors such as the performance of the drone, the complexity of the mission, and functional requirements, the most suitable drone can be assigned to each task, thereby improving the problem in related technologies that the drone task allocation method may lead to poor task achievement quality.

[0096] It can be understood that in the calculation of the above-mentioned embodiments of the present application, each parameter can be selected whether to be normalized based on the needs of those skilled in the art. This is a conventional technical means of those skilled in the art and will not be elaborated in this application.

[0097] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0098] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0099] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0100] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated units may be implemented in the form of hardware.

[0101] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application shall be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for managing unmanned aerial vehicles based on cluster communication, characterized in that: The method is applied to a drone cluster, where drones in the drone cluster are connected to each other in communication, and the method comprises: Obtain a task list that the drone cluster needs to perform, the task list including multiple tasks and corresponding task information; Obtaining a task matching degree between each drone and each task according to the operation information of each drone in the drone cluster and the task information of each task; A drone in the drone cluster for performing the task is determined based on the task matching degree.

2. The method for managing unmanned aerial vehicles based on cluster communication according to claim 1, characterized in that: The mission information includes the action complexity of the mission, the functions required to execute the mission, and the airspace complexity corresponding to the mission, and the operation information includes the operational flexibility of the UAV.

3. The method for managing unmanned aerial vehicles based on cluster communication according to claim 2, characterized in that: The obtaining, according to the operation information of each drone in the drone cluster and the task information of each task, a task matching degree between each drone and each task includes: Among them, r ij is the task matching degree of the i-th UAV to the j-th task, Fu ik is the kth function of the i-th drone, R jk is the kth function required for the jth task, Fl i is the operational flexibility of the i-th human-machine, C j is the action complexity of the jth task, E j is the spatial complexity of the airspace where the jth task is located, α, β and ω k is the weight coefficient.

4. The method for managing unmanned aerial vehicles based on cluster communication according to claim 3, characterized in that: The method further includes: obtaining the airspace complexity according to the number of obstacles, the types of obstacles, and the distance between the obstacles and the task execution location within the airspace range corresponding to the task.

5. The method for managing unmanned aerial vehicles based on cluster communication according to claim 3, characterized in that: The method further includes: obtaining the action complexity of the task according to the action information of the drone during the execution of the task, wherein the action information includes the action type, action duration, and action number.

6. The method for managing unmanned aerial vehicles based on cluster communication according to claim 3, characterized in that: The method further includes: obtaining the operational flexibility of the drone according to the perception radius, action response speed, and action execution accuracy of the drone.

7. The method for managing unmanned aerial vehicles based on cluster communication according to claim 1, characterized in that: Each of the tasks is provided with a corresponding priority, and the method further comprises: Obtain a list of the task matching degrees of each of the tasks and each of the drones; When the task matching degree between the same drone and the two tasks is greater than that of other drones in the drone cluster, the drone will preferentially execute the task with a higher priority.

8. The method for managing unmanned aerial vehicles based on cluster communication according to claim 1, characterized in that: The method further includes: setting a distance threshold between the UAV and the obstacle according to the type of obstacle within the airspace corresponding to the task and the distance between the obstacle and the task execution location.

9. The method for managing unmanned aerial vehicles based on cluster communication according to claim 1, characterized in that: The method further comprises: Constructing a corresponding task airspace based on the task list and the airspace information of the task, each task airspace including a plurality of the tasks; The drone cluster is divided into subclusters corresponding to the mission airspace, and at least one backup mission drone is allocated to any two adjacent subclusters, and the task matching degree between the backup mission drone and the tasks in the corresponding two adjacent mission airspaces is greater than a matching degree threshold.

10. A UAV management system based on cluster communication, used to execute the method according to any one of claims 1 to 9, characterized in that: The system comprises: An acquisition module, the acquisition module is used to acquire the task list, the task information and the operation information of the drone; A data processing module, coupled to the acquisition module, and configured to obtain the task matching degree according to the task information and the operation information; A task matching module is coupled to the acquisition module and the data processing module, and the task matching module determines a drone in the drone cluster for executing the task based on the task matching degree.

Images