Unmanned aerial vehicle task allocation method, device and equipment and storage medium
By acquiring UAV state models and structuring tasks, and combining them with particle swarm optimization, the problem of low efficiency in UAV task scheduling systems is solved, achieving efficient and safe task allocation and execution.
Patent Information
- Application Number
- CN202411443150.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-16
- Publication Date
- 2025-10-17
- Estimated Expiration
- 2044-10-16
AI Technical Summary
Existing drone mission scheduling systems lack a true scheduling mechanism, resulting in low efficiency when drones perform multiple flight missions, which affects the overall mission completion efficiency.
By acquiring the current state model of the UAV and the structured processing of the tasks to be assigned, combined with the particle swarm optimization algorithm and preset task allocation rules, the UAV is scientifically and rationally selected to perform tasks, ensuring that the task type, observation requirements and energy consumption requirements are met.
It improves the efficiency and success rate of drone task allocation, ensures that high-priority tasks are executed first, and achieves efficient and orderly task allocation and safety assurance.
Smart Images
Figure CN119536370B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of unmanned aerial vehicles, and in particular to an unmanned aerial vehicle task allocation method, device, equipment and storage medium. BACKGROUND
[0002] With the rapid development of unmanned aerial vehicle technology, unmanned aerial vehicles are increasingly widely used in military reconnaissance, environmental monitoring, agricultural plant protection, logistics distribution and other fields. However, in the current unmanned aerial vehicle task scheduling system, there is a relatively primitive task processing method, that is, there is a lack of a true "scheduling" mechanism.
[0003] Traditionally, when unmanned aerial vehicles face multiple flight tasks, these tasks are often treated as a whole and assigned to a specific unmanned aerial vehicle. Once the unmanned aerial vehicle receives these tasks, it will execute them in order according to the internal task queue order. Therefore, the unmanned aerial vehicle is inefficient when executing flight tasks, thereby affecting the overall task completion efficiency. SUMMARY
[0004] The technical problem to be solved by the present application is to provide an unmanned aerial vehicle task allocation method, device, equipment and storage medium, which aims to solve at least one of the above technical problems.
[0005] The technical solution of the present application to solve the above technical problems is as follows:
[0006] In a first aspect, the present application provides an unmanned aerial vehicle task allocation method, which adopts the following technical solution:
[0007] An unmanned aerial vehicle task allocation method comprises:
[0008] Obtaining a to-be-allocated task and current state models of all unmanned aerial vehicles, wherein each current state model of the unmanned aerial vehicles comprises a current position, a remaining power, a sensor type, an observation capability and to-be-executed task information;
[0009] Structurally processing the to-be-allocated task to obtain a task data structure of the to-be-allocated task, wherein the task data structure comprises a task type, a task name, a task priority, target region information and observation requirements, and the task type is point continuous monitoring, line continuous observation, single polygon region imaging, discrete distributed multiple polygon region imaging or ring region imaging;
[0010] Based on the current state models of all unmanned aerial vehicles, a plurality of first unmanned aerial vehicles satisfying the task type and the observation requirements are determined from all unmanned aerial vehicles;
[0011] determine at least one second UAV from each of the first UAVs to execute the to-be-assigned task based on a task data structure of the to-be-assigned task, current state models of all the first UAVs, and preset task assignment rules;
[0012] perform task assignment on all the second UAVs based on the task data structure of the to-be-assigned task.
[0013] The present application has the beneficial effects that: by obtaining the current state models of the UAVs and structurally processing the to-be-assigned task, the method can quickly understand the task requirements and the capabilities of the UAVs, thereby efficiently performing task assignment. Based on the task type and observation requirements, in combination with the current positions, residual power and other factors of the UAVs, a plurality of first UAVs are determined, and then at least one second UAV is selected to execute the task according to the preset task assignment rules, thereby realizing scientific and reasonable UAV task assignment and improving the efficiency and success rate of overall task execution.
[0014] On the basis of the above technical solution, the present application can also be improved as follows.
[0015] Further, the determining of the plurality of first UAVs based on the task type, the observation requirements, and the current state models of all the UAVs comprises:
[0016] determining the sensor type, observation capability and power requirement of the UAVs for executing the to-be-assigned task according to the task type and observation requirements of the to-be-assigned task;
[0017] determining a first UAV set according to the sensor type, observation capability and power requirement of the required UAVs;
[0018] determining a second UAV set satisfying the task priority of the to-be-assigned task according to to-be-executed task information of each UAV in the first UAV set;
[0019] obtaining the historical completion efficiency of each UAV in the second UAV set for executing the task of the task type;
[0020] determining a third UAV set satisfying an efficiency threshold corresponding to the task priority of the to-be-assigned task according to the historical completion efficiency of each UAV in the second UAV set;
[0021] taking all the UAVs in the third UAV set as the first UAVs.
[0022] The beneficial effects of the above further scheme are: by analyzing the task type, observation requirements of the to-be-assigned task, and the sensor type, observation ability, and power demand of the required unmanned aerial vehicle, the method can more accurately screen out the first unmanned aerial vehicle set that meets the task requirements. It ensures a higher matching degree between the task and the unmanned aerial vehicle, improves the success rate and quality of task execution. Further, according to the priority of the to-be-assigned task and the to-be-executed task information of each unmanned aerial vehicle in the first unmanned aerial vehicle set, the second unmanned aerial vehicle set is determined, ensuring that the task with higher priority can be supported by the unmanned aerial vehicle with less to-be-executed task information. In combination with the historical completion efficiency, a more suitable third unmanned aerial vehicle set is screened out, thereby improving the efficiency and quality of the overall task execution.
[0023] Further, the at least one second unmanned aerial vehicle for executing the to-be-assigned task is determined based on the task data structure of the to-be-assigned task, the state model of all first unmanned aerial vehicles, and a preset task assignment rule.
[0024] In step S41, it is determined whether one of the first unmanned aerial vehicles can complete the to-be-assigned task based on the target region information.
[0025] In step S42, if one of the first unmanned aerial vehicles can complete the to-be-assigned task, a second unmanned aerial vehicle that meets a set requirement is determined based on the task data structure of the to-be-assigned task, the current state model of all first unmanned aerial vehicles, and a preset particle swarm algorithm, the set requirement being that the flight path of each first unmanned aerial vehicle meets a set path requirement and the energy consumption meets a set energy consumption requirement.
[0026] In step S43, if one of the unmanned aerial vehicles cannot complete the to-be-assigned task, the target region information of the to-be-assigned task is divided based on a preset region division rule to obtain a plurality of block regions, and a corresponding block task is determined based on each block region, each block task including a block task data structure.
[0027] In step S44, for each block task, a second unmanned aerial vehicle that meets a set requirement is determined based on the block task data structure corresponding to the block task, the current state model of all first unmanned aerial vehicles, and a preset particle swarm algorithm.
[0028] The beneficial effect of the further scheme is that the unmanned aerial vehicle task allocation method can determine whether a single unmanned aerial vehicle can complete a task according to target region information of the task to be allocated. If a single unmanned aerial vehicle can complete the task, a second unmanned aerial vehicle that meets the set requirements of the optimal flight path and energy consumption is further determined through the particle swarm algorithm, thereby ensuring that the task is completed efficiently and energy-savingly. If a single unmanned aerial vehicle cannot complete the task, the target region is divided into multiple block tasks, and a second unmanned aerial vehicle that meets the path and energy consumption requirements is determined for each block task, thereby realizing effective decomposition and efficient allocation of complex tasks.
[0029] Further, the second unmanned aerial vehicle that meets the set requirements is determined based on the task data structure of the task to be allocated, the current state model of all the first unmanned aerial vehicles, and a preset particle swarm algorithm, and includes:
[0030] Based on the task data structure of the task to be allocated and the current state model of all the first unmanned aerial vehicles, a particle swarm is initialized, the particle swarm includes multiple particles, each particle represents a task allocation scheme, and the task allocation scheme represents an unmanned aerial vehicle flight path;
[0031] Based on a preset objective function, the fitness value of each particle is calculated;
[0032] Based on the fitness value, the current position, and the current speed of each particle, the speed and position of each particle are updated;
[0033] The updated speed and position of each particle are taken as the current speed and current position of each particle of the particle swarm in the next iteration, and the cycle is repeated until the fitness value is less than a set threshold, a task allocation scheme corresponding to a particle that meets the set path requirements and energy consumption requirements is selected from the particle swarm in the current iteration period as a target task allocation scheme;
[0034] Based on the target task allocation scheme, a first unmanned aerial vehicle that executes the target task allocation scheme is selected as the second unmanned aerial vehicle.
[0035] The beneficial effect of the further scheme is that the particle swarm algorithm has global search capability and parallel computing characteristics, and can find a relatively optimal task allocation and flight path scheme in a relatively short time. By adjusting the weight coefficient in the objective function, multiple performance indicators such as path length and energy consumption can be balanced to adapt to different application scenarios.
[0036] Further, the task allocation is performed on all the second unmanned aerial vehicles based on the task data structure of the task to be allocated, and includes:
[0037] For any one of the second unmanned aerial vehicles, a task execution order of the second unmanned aerial vehicle is determined based on a task priority of the task to be allocated and a priority of task information to be executed by the second unmanned aerial vehicle.
[0038] For any one of the second unmanned aerial vehicles, the second unmanned aerial vehicle is allocated with the task based on the task execution order.
[0039] The beneficial effect of the further scheme is that the task execution order of the second unmanned aerial vehicle can be reasonably determined based on the priority of the task to be allocated and the priority of the task information to be executed by the second unmanned aerial vehicle, so as to realize efficient and orderly task allocation, ensure that high-priority tasks are executed first, and improve the overall efficiency of task execution and resource utilization.
[0040] Further, after the task allocation is performed on all the second unmanned aerial vehicles based on the task data structure of the task to be allocated, the method further comprises:
[0041] obtaining flight state information and current task execution information of each of the second unmanned aerial vehicles;
[0042] For any one of the second unmanned aerial vehicles, a safety flight threshold of the second unmanned aerial vehicle is determined based on the current task execution information.
[0043] For any one of the second unmanned aerial vehicles, the flight state information of the second unmanned aerial vehicle is compared with the corresponding safety flight threshold.
[0044] For any one of the second unmanned aerial vehicles, if the flight state information of the second unmanned aerial vehicle exceeds the corresponding safety flight threshold, an alarm information is sent to the command center.
[0045] The beneficial effect of the further scheme is that after the task allocation is completed, the flight state information and the current task execution information of the second unmanned aerial vehicle can be obtained in real time, the safety flight threshold is determined based on the current task execution information, the abnormality is found in time by comparing the flight state information with the safety flight threshold, so as to effectively ensure the safe operation of the unmanned aerial vehicle, and the alarm information is sent to the command center in time in the abnormal condition, so as to ensure the reliability of task execution.
[0046] Further, the flight state information of each of the second unmanned aerial vehicles is obtained by:
[0047] For any one of the second unmanned aerial vehicles, the position signal information, the pose information, the flight speed information, the device running information and the device configuration information of the unmanned aerial vehicle are obtained by a sensor on the second unmanned aerial vehicle.
[0048] For any second unmanned aerial vehicle, flight state evaluation is performed based on the position signal information, the pose information, the flight speed information, the device operation information and the device configuration information, and flight state information of the unmanned aerial vehicle is determined.
[0049] The beneficial effect of the further scheme is that for any second unmanned aerial vehicle, the position signal information, the pose information, the flight speed information, the device operation information and the device configuration information of the unmanned aerial vehicle can be obtained in real time by sensors thereon. Comprehensive flight state evaluation is performed based on these information, so that the flight state information of the unmanned aerial vehicle is accurately determined, and the safety and reliability of the unmanned aerial vehicle in the task execution process are ensured.
[0050] In a second aspect, the present application provides an unmanned aerial vehicle task allocation device, which adopts the following technical scheme:
[0051] An unmanned aerial vehicle task allocation device comprises:
[0052] An acquisition module is configured to acquire a to-be-allocated task and current state models of all unmanned aerial vehicles, wherein each current state model of the unmanned aerial vehicles comprises a current position, a remaining power, a sensor type, an observation capability and to-be-executed task information;
[0053] A structured processing module is configured to perform structured processing on the to-be-allocated task to obtain a task data structure of the to-be-allocated task, wherein the task data structure comprises a task type, a task name, a task priority, target region information and observation requirements, and the task type is point continuous monitoring, line continuous observation, single polygon region imaging, discrete distributed multiple polygon region imaging or ring region imaging;
[0054] A first determination module is configured to determine, based on the current state models of all unmanned aerial vehicles, a plurality of first unmanned aerial vehicles that meet the task type and the observation requirements from among all the unmanned aerial vehicles;
[0055] A second determination module is configured to determine, based on the task data structure of the to-be-allocated task, the current state models of all first unmanned aerial vehicles and a preset task allocation rule, at least one second unmanned aerial vehicle that executes the to-be-allocated task from among the first unmanned aerial vehicles;
[0056] A task allocation module is configured to perform task allocation on all second unmanned aerial vehicles based on the task data structure of the to-be-allocated task.
[0057] In a third aspect, the present application provides an electronic device, which adopts the following technical scheme:
[0058] An electronic device comprises a memory and a processor, and the memory stores a computer program capable of being loaded and executed by the processor to perform the unmanned aerial vehicle task allocation method of any one of the first aspect.
[0059] In a fourth aspect, the present application provides a computer readable storage medium, adopting the technical scheme as follows:
[0060] A computer readable storage medium, storing a computer program capable of being loaded and executed by a processor to perform the unmanned aerial vehicle task allocation method according to any one of the first aspect.
[0061] Additional aspects and advantages of the present application will be given in part in the following description, which will become apparent from the following description, or will be learned by practice of the present application. BRIEF DESCRIPTION OF DRAWINGS
[0062] Figure 1 A flowchart of an unmanned aerial vehicle task allocation method provided for an embodiment of the present application is shown in the figure;
[0063] Figure 2 A structural block diagram of an unmanned aerial vehicle task allocation device provided for an embodiment of the present application is shown in the figure;
[0064] Figure 3 A structural block diagram of an electronic device provided for an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION
[0065] In order to make the purpose, technical scheme and advantages of the embodiments of the present application more clear, the technical scheme of the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.
[0066] In addition, the term "and / or" in this paper is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper, unless otherwise specified, generally represents an "or" relationship between the associated objects before and after it.
[0067] The embodiments of the present application provide an unmanned aerial vehicle task allocation method, which can be executed by an electronic device. The electronic device can be a server or a mobile terminal device. The server can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The mobile terminal device can be a notebook computer, a desktop computer, etc., but is not limited thereto.
[0068] As Figure 1As shown, a UAV task allocation method includes steps S11-S15:
[0069] In step S11, a task to be allocated and current state models of all UAVs are obtained, each of the current state models of the UAVs including a current position, a remaining power, a sensor type, an observation ability, and to-be-executed task information.
[0070] In an embodiment, the task to be allocated includes, but is not limited to, a power inspection task, a terrain mapping task, and an environmental monitoring task.
[0071] The current position of the UAV is obtained in real time by a GPS module or other positioning technology; different types of UAVs can be equipped with different sensors, such as a camera, an infrared sensor, a laser radar, etc.; the observation ability represents the type and range of information that the UAV can obtain through its own sensors, for example, the resolution of the camera, the detection distance of the infrared sensor, etc. The to-be-executed task information of the UAV represents the number of tasks to be executed or needed to be executed by the UAV and the task priority of each of the to-be-executed tasks.
[0072] In step S12, the task to be allocated is structurally processed to obtain a task data structure of the task to be allocated, the task data structure including a task type, a task name, a task priority, target region information, and observation requirements, the task type being point continuous monitoring, line continuous observation, single polygon region imaging, discrete distributed multiple polygon region imaging, or ring region imaging.
[0073] In an embodiment, a task instance is created based on the task to be allocated, specifically, the task type is extracted from the task to be allocated, and it is verified whether the task type is valid, if the task type is valid, the task name is extracted from the task to be allocated, the task name having a unique identifier. Then, the task priority is extracted from the task to be allocated, and the task priority is converted into structured data. Then, the target region description is extracted from the task to be allocated, for the point continuous monitoring task, the target region description is parsed into a point object, for the line continuous observation task, the target region description is parsed into a line object, for the single polygon region imaging task, the target region description is parsed into a single polygon object, for the discrete distributed multiple polygon region imaging task, the target region description is parsed into a polygon object collection, and for the ring region imaging task, the target region description is parsed into a ring region object. Finally, the observation requirements are extracted from the input information and converted into a dictionary type.
[0074] The above task type, task name, task priority, target region information, and observation requirements are integrated into a structured task data structure to obtain the task data structure of the task to be allocated.
[0075] Then, it is checked whether the task priority is within the set range, whether the target area information meets the geometric object requirement, and whether the observation requirement meets the set observation requirement. If all the conditions are met, the task data structure is added to the task list for task allocation.
[0076] In step S13, based on the current state model of all the UAVs, a plurality of first UAVs meeting the task type and the observation requirement are determined from all the UAVs.
[0077] In an embodiment, step S13 specifically includes the following sub-steps (steps S131-S136):
[0078] In step S131, according to the task type and the observation requirement of the task to be allocated, the sensor type, the observation capability, and the power requirement of the UAV for executing the task to be allocated are determined.
[0079] In step S132, according to the sensor type, the observation capability, and the power requirement of the required UAV, a first UAV set is determined.
[0080] In step S133, according to the task information to be executed by each UAV in the first UAV set, a second UAV set meeting the task priority of the task to be allocated is determined.
[0081] In step S134, the historical completion efficiency of each UAV in the second UAV set for executing the task of the task type is obtained.
[0082] In step S135, according to the historical completion efficiency of each UAV in the second UAV set, a third UAV set meeting the efficiency threshold corresponding to the task priority of the task to be allocated is determined.
[0083] In step S136, all the UAVs in the third UAV set are determined as the first UAV.
[0084] In the above embodiments, firstly, the sensor type, observation capability and power requirement required by the task to be allocated are analyzed according to the task type and observation requirement of the task to be allocated, for example, an infrared sensor is required to be used, the resolution is a preset first resolution, and the flight time is a preset first flight time. Then, the unmanned aerial vehicles that meet the sensor type, observation capability and power requirement are screened out from the currently available unmanned aerial vehicles to form a first unmanned aerial vehicle set. Then, the unmanned aerial vehicles that can execute the new task within a reasonable time are further screened out according to the priority of the task to be allocated and the task information to be executed by each unmanned aerial vehicle in the first unmanned aerial vehicle set, such as the task urgency and the remaining task amount, to form a second unmanned aerial vehicle set. Then, the unmanned aerial vehicle that is most likely to complete the task efficiently is screened out using a ranking selection method according to the historical completion efficiency of the unmanned aerial vehicles in the second unmanned aerial vehicle set in executing the task of the task type and the task priority of the task to be allocated, to form a third unmanned aerial vehicle set, so as to finally determine the plurality of first unmanned aerial vehicles.
[0085] In step S14, at least one second unmanned aerial vehicle that executes the task to be allocated is determined from each of the first unmanned aerial vehicles based on the task data structure of the task to be allocated, the current state model of all the first unmanned aerial vehicles and the preset task allocation rule.
[0086] In one embodiment, step S14 includes:
[0087] In step S41, it is judged whether one of the first unmanned aerial vehicles can complete the task to be allocated based on the target region information.
[0088] In step S42, if one of the first unmanned aerial vehicles can complete the task to be allocated, a second unmanned aerial vehicle that meets the set requirement is determined based on the task data structure of the task to be allocated, the current state model of all the first unmanned aerial vehicles and the preset particle swarm algorithm, the set requirement being that the flight path of each first unmanned aerial vehicle meets the set path requirement and the energy consumption meets the set energy consumption requirement.
[0089] In step S43, if one of the unmanned aerial vehicles cannot complete the task to be allocated, the target region information of the task to be allocated is divided based on the preset region division rule to obtain a plurality of block regions, and a corresponding block task is determined based on each of the block regions, each of the block tasks including a block task data structure.
[0090] In step S44, for each of the block tasks, a second unmanned aerial vehicle that meets the set requirement is determined based on the block task data structure corresponding to the block task, the current state model of all the first unmanned aerial vehicles and the preset particle swarm algorithm.
[0091] The target region information of the task to be allocated is used to determine whether a single UAV can complete the task. If a single UAV can complete the task, a second UAV that meets the set requirements in terms of optimal flight path and energy consumption is determined by using a particle swarm algorithm, so that the task is completed efficiently and with energy saving. If a single UAV cannot complete the task, the target region is divided into multiple block tasks, and a second UAV that meets the path and energy consumption requirements is determined for each block task, so that the complex task is effectively decomposed and efficiently allocated.
[0092] Optionally, the second UAV that meets the set requirements is determined based on the task data structure of the task to be allocated, the current state model of all first UAVs and a preset particle swarm algorithm, and includes:
[0093] Based on the task data structure of the task to be allocated and the current state model of all first UAVs, a particle swarm is initialized, the particle swarm includes multiple particles, each particle represents a task allocation scheme, and the task allocation scheme represents a UAV flight path;
[0094] Based on a preset objective function, the fitness value of each particle is calculated;
[0095] Based on the fitness value, the current position and the current speed of each particle, the speed and the position of each particle are updated;
[0096] The updated speed and position of each particle are used as the current speed and the current position of each particle of the particle swarm in the next iteration, and the iteration is repeated until the fitness value is less than a set threshold, a task allocation scheme corresponding to a particle that meets the set path requirements and the energy consumption requirements is selected from the particle swarm in the current iteration period as a target task allocation scheme;
[0097] Based on the target task allocation scheme, a first UAV that executes the target task allocation scheme is selected as the second UAV.
[0098] The preset objective function can be F(x)=w1×L(x)+w2×E(x).
[0099] F(x) is an objective function, x represents a task allocation and a flight path scheme, w1 and w2 are weight coefficients, L(x) and E(x) are sub-functions corresponding to path length and energy consumption respectively.
[0100] The global search capability and parallel computing characteristics of the particle swarm algorithm can find a relatively optimal task allocation and flight path scheme in a relatively short time, so as to determine the second UAV that meets the set requirements. By adjusting the weight coefficients in the objective function, multiple performance indicators such as path length and energy consumption can be balanced to adapt to different application scenarios.
[0101] Step S15, task allocation is performed for all the second unmanned aerial vehicles based on the task data structure of the task to be allocated.
[0102] In an embodiment, the task allocation is performed for all the second unmanned aerial vehicles based on the task data structure of the task to be allocated, including:
[0103] For any of the second unmanned aerial vehicles, a task execution order of the second unmanned aerial vehicle is determined based on the priority of the task to be allocated and the priority of the to-be-executed task information of the second unmanned aerial vehicle.
[0104] For any of the second unmanned aerial vehicles, the second unmanned aerial vehicle is allocated a task based on the task execution order.
[0105] In the above embodiment, the priority of the to-be-executed task information includes tasks that the unmanned aerial vehicle has received but not completed and the priorities of these tasks.
[0106] The task execution order of the second unmanned aerial vehicle is determined by comparing the priority of the task to be allocated and the priority of the to-be-executed task information of the second unmanned aerial vehicle. Generally, a task with a higher priority will be executed by the second unmanned aerial vehicle in priority.
[0107] By comparing the priority of the task to be allocated and the priority of the to-be-executed task information of the second unmanned aerial vehicle, the task execution order of the second unmanned aerial vehicle can be reasonably determined, thereby realizing efficient and orderly task allocation, ensuring that high-priority tasks are executed in priority, and improving the overall efficiency of task execution and resource utilization.
[0108] As an optional embodiment of the present application, after the task allocation is performed for all the second unmanned aerial vehicles based on the task data structure of the task to be allocated, the method further includes:
[0109] Step S16, flight state information and current task execution information of each of the second unmanned aerial vehicles are obtained.
[0110] In an embodiment, for any of the second unmanned aerial vehicles, position signal information, pose information, flight speed information, device running information, and device configuration information of the unmanned aerial vehicle are obtained through sensors on the second unmanned aerial vehicle.
[0111] For any of the second unmanned aerial vehicles, flight state assessment is performed based on the position signal information, pose information, flight speed information, device running information, and device configuration information to determine the flight state information of the unmanned aerial vehicle.
[0112] Step S17, for any of the second unmanned aerial vehicles, a safe flight threshold of the second unmanned aerial vehicle is determined based on the current task execution information.
[0113] Step S18, for any of the second unmanned aerial vehicle, the flight state information of the second unmanned aerial vehicle is compared with the corresponding safe flight threshold;
[0114] Step S19, for any of the second unmanned aerial vehicle, if the flight state information of the second unmanned aerial vehicle exceeds the corresponding safe flight threshold, the alarm information is sent to the command center.
[0115] By acquiring the flight state information of the second unmanned aerial vehicle and its current task information, and determining the safe flight threshold based on the current task information, comparing the flight state information with the safe flight threshold to find abnormalities in time, the safety of the unmanned aerial vehicle is effectively ensured, and the alarm information is sent to the command center in time in the abnormal situation, and the reliability of the task execution is ensured.
[0116] The method can quickly understand the task demand and the ability of the unmanned aerial vehicle by acquiring the current state model of the unmanned aerial vehicle and structurally processing the to-be-assigned task, so that the task assignment is efficiently performed. Based on the task type and the observation requirement, in combination with the current position, the remaining power and other factors of the unmanned aerial vehicle, a plurality of first unmanned aerial vehicles are determined, and then at least one second unmanned aerial vehicle is selected according to a preset task assignment rule to execute the task, so that scientific and reasonable unmanned aerial vehicle task assignment is realized, and the efficiency and success rate of the overall task execution are improved.
[0117] Figure 2 A structural block diagram of an unmanned aerial vehicle task assignment device 200 provided for an embodiment of the application.
[0118] As shown in Figure 2 An unmanned aerial vehicle task assignment device 200 includes:
[0119] An acquisition module 201 is configured to acquire a to-be-assigned task and current state models of all unmanned aerial vehicles, and each current state model of the unmanned aerial vehicle includes a current position, a remaining power, a sensor type, an observation ability and to-be-executed task information;
[0120] A structurally processing module 202 is configured to structurally process the to-be-assigned task to obtain a task data structure of the to-be-assigned task, the task data structure including a task type, a task name, a task priority, target area information and observation requirements, and the task type being point continuous monitoring, line continuous observation, single polygon area imaging, discrete distributed multiple polygon area imaging or ring area imaging;
[0121] A first determination module 203 is configured to determine a plurality of first unmanned aerial vehicles meeting the task type and the observation requirements from all unmanned aerial vehicles based on the current state models of all unmanned aerial vehicles;
[0122] The second determining module 204 is configured to determine at least one second UAV for executing the to-be-assigned task from the first UAVs based on the task data structure of the to-be-assigned task, the current state model of all the first UAVs, and a preset task assignment rule.
[0123] The task assignment module 205 is configured to perform task assignment on all the second UAVs based on the task data structure of the to-be-assigned task.
[0124] Optionally, the first determining module 203 is specifically configured to:
[0125] determine a sensor type, an observation capability, and a power requirement of the UAV for executing the to-be-assigned task according to a task type and an observation requirement of the to-be-assigned task;
[0126] determine the first UAV set according to the sensor type, the observation capability, and the power requirement of the required UAV;
[0127] determine the second UAV set satisfying the task priority of the to-be-assigned task according to to-be-executed task information of each UAV in the first UAV set;
[0128] obtain a historical completion efficiency of each UAV in the second UAV set in executing a task of the task type;
[0129] determine the third UAV set satisfying an efficiency threshold corresponding to the task priority of the to-be-assigned task according to the historical completion efficiency of each UAV in the second UAV set;
[0130] all the UAVs in the third UAV set are taken as the first UAVs.
[0131] Optionally, the second determining module is specifically configured to perform the following steps:
[0132] Step S41: determining whether one of the first UAVs can complete the to-be-assigned task based on the target region information;
[0133] Step S42: if one of the first UAVs can complete the to-be-assigned task, determining a second UAV satisfying a set requirement based on the task data structure of the to-be-assigned task, the state model of all the first UAVs, and a preset particle swarm algorithm, the set requirement being that a flight path of each first UAV satisfies a set path requirement and an energy consumption satisfies a set energy consumption requirement;
[0134] Step S43, if one unmanned aerial vehicle cannot complete the to-be-assigned task, dividing target region information of the to-be-assigned task based on preset region division rules to obtain a plurality of block regions, and determining a corresponding block task based on each block region, each block task including a block task data structure;
[0135] Step S44, for each block task, determining a second unmanned aerial vehicle satisfying a set requirement based on the block task data structure corresponding to the block task, a state model of all first unmanned aerial vehicles, and a preset particle swarm algorithm.
[0136] Optionally, the second determining module performs step S42, which includes:
[0137] Initializing a particle swarm based on the task data structure of the to-be-assigned task and the state model of all first unmanned aerial vehicles, the particle swarm including a plurality of particles, each particle representing a task assignment scheme;
[0138] Calculating an adaptability value of each particle based on a preset target function;
[0139] Updating a speed and a position of each particle based on the adaptability value, the current position, and the current speed of each particle;
[0140] Taking the updated speed and position of each particle as the current speed and the current position of each particle of the particle swarm in the next iteration, and repeating the process until the adaptability value is less than a set threshold, selecting a task assignment scheme corresponding to a particle satisfying a set path requirement and an energy consumption requirement from the particle swarm in the current iteration period as the second unmanned aerial vehicle performing the to-be-assigned task, the task assignment scheme including a flight path of the unmanned aerial vehicle.
[0141] Optionally, the task assignment module is specifically configured to:
[0142] For any one of the second unmanned aerial vehicles, determining a task execution order of the second unmanned aerial vehicle based on a task priority of the to-be-assigned task and a priority of to-be-executed task information of the second unmanned aerial vehicle;
[0143] For any one of the second unmanned aerial vehicles, performing task assignment on the second unmanned aerial vehicle based on the task execution order.
[0144] Optionally, the unmanned aerial vehicle task assignment apparatus 200 further includes a monitoring module, which includes:
[0145] An acquisition sub-module, configured to, after performing task assignment on the second unmanned aerial vehicles based on the task data structure of the to-be-assigned task, acquire flight state information and current execution task information of each second unmanned aerial vehicle.
[0146] determining a safety flight threshold of the second UAV based on the current execution task information for any of the second UAVs;
[0147] comparing the flight state information of the second UAV with the corresponding safety flight threshold for any of the second UAVs;
[0148] sending an alarm information to the command center if the flight state information of the second UAV exceeds the corresponding safety flight threshold for any of the second UAVs.
[0149] Optionally, the obtaining sub-module is specifically configured to:
[0150] for any of the second UAVs, obtaining the position signal information, the pose information, the flight speed information, the device running information and the device configuration information of the UAV through sensors on the second UAV;
[0151] for any of the second UAVs, performing flight state evaluation based on the position signal information, the pose information, the flight speed information, the device running information and the device configuration information to determine the flight state information of the UAV.
[0152] In one example, the modules in any of the above apparatuses can be one or more integrated circuits configured to implement one or more of the above methods, for example: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.
[0153] In another example, when the modules in the apparatuses can be implemented in the form of a processing element scheduler, the processing element can be a general purpose processor, such as a central processing unit (CPU) or other processor that can invoke programs. In another example, these modules can be integrated together to implement in the form of a system-on-a-chip (SOC).
[0154] In another example, when the modules in the apparatuses can be implemented in the form of a processing element scheduler, the processing element can be a general purpose processor, such as a central processing unit (CPU) or other processor that can invoke programs. In another example, these modules can be integrated together to implement in the form of a system-on-a-chip (SOC).
[0155] Various objects in the present application are named as various messages / information / equipment / network elements / systems / devices / actions / operations / processes / concepts, etc. It can be understood that these specific names do not constitute a limitation on the related objects, and the names can be changed according to the scene, context or usage habits, etc. The technical meaning of the technical terms in the present application should be mainly determined according to the function and technical effect embodied / executed in the technical scheme.
[0156] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the system, device and module described above can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.
[0157] Those skilled in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized by hardware or software depends on the specific application and design constraints of the technical scheme. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.
[0158] Figure 3 A structural block diagram of an electronic device 300 according to an embodiment of the present application is shown.
[0159] As shown in Figure 3 The electronic device 300 includes a processor 301 and a memory 302, and can further include one or more of an information input / output (I / O) interface 303, a communication component 304 and a communication bus 305.
[0160] The processor 301 is configured to control overall operations of the electronic device 300 to complete all or part of the steps of the above-described method for assigning tasks to UAVs. The memory 302 is configured to store various types of data to support operations of the electronic device 300. The data can include, for example, instructions for operating any application or method on the electronic device 300, and application-related data. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as one or more of a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic storage, a flash memory, a magnetic disk, or an optical disk.
[0161] The I / O interface 303 provides an interface between the processor 301 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 304 is configured to test wired or wireless communication between the electronic device 300 and other devices. The wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so the corresponding communication component 304 can include a Wi-Fi component, a Bluetooth component, and an NFC component.
[0162] The communication bus 305 can include a path for transmitting information between the above-mentioned components. The communication bus 305 can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, or the like. The communication bus 305 can be divided into an address bus, a data bus, a control bus, and the like.
[0163] The electronic device 300 can be implemented by one or more Application Specific Integrated Circuits (ASIC), Digital Signal Processors (DSP), Digital Signal Processing Devices (DSPD), Programmable Logic Devices (PLD), Field Programmable Gate Arrays (FPGA), controllers, micro-controllers, microprocessors, or other electronic elements for performing the method of task allocation for unmanned aerial vehicles given by the above embodiments.
[0164] The computer readable storage medium provided by the embodiments of the present application is described below, and the computer readable storage medium described below can be referred to in conjunction with the method of task allocation for unmanned aerial vehicles described above.
[0165] The present application also provides a computer readable storage medium, and the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the steps of the method of task allocation for unmanned aerial vehicles.
[0166] The computer readable storage medium can include a U disk, a mobile hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.
[0167] The term "comprising" or "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device.
[0168] The above description is merely preferred embodiments of the present application and a description of the principles of the applied technology. It should be understood by those skilled in the art that the scope of the application involved in the present application is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or equivalent features without departing from the above application concept. For example, the above features can be replaced with technical features having similar functions applied in the present application (but not limited to) to form technical solutions.
Claims
1. A method for allocating tasks to unmanned aerial vehicles, characterized in that: include: Obtaining the current state models of the tasks to be assigned and all drones, where the current state model of each drone includes the current location, remaining battery power, sensor type, observation capability, and information about the tasks to be performed; Structuring the tasks to be assigned to obtain a task data structure of the tasks to be assigned, wherein the task data structure includes a task type, a task name, a task priority, target area information, and observation requirements, wherein the task type is point continuous monitoring, line continuous observation, single polygonal area imaging, discretely distributed multiple polygonal area imaging, or annular area imaging; Determining, based on current state models of all the drones, a plurality of first drones that meet the mission type and the observation requirement from among all the drones; Determining at least one second drone to perform the task to be assigned from each of the first drones based on the task data structure of the task to be assigned, current state models of all first drones, and a preset task assignment rule; Allocate tasks to all the second UAVs based on the task data structure of the tasks to be assigned; The step of determining at least one second drone to execute the task to be assigned based on the task data structure of the task to be assigned, current state models of all first drones, and a preset task assignment rule includes: Step S41: judging whether one of the first UAVs can complete the task to be assigned based on the target area information; Step S42: If one of the first UAVs can complete the task to be assigned, then based on the task data structure of the task to be assigned, the current state models of all the first UAVs, and a preset particle swarm algorithm, a second UAV that meets set requirements is determined, where the set requirements are that the flight path of each first UAV meets a set path requirement and the energy consumption meets a set energy consumption requirement; Step S43: If a drone cannot complete the task to be assigned, the target area information of the task to be assigned is divided based on a preset area division rule to obtain a plurality of block areas, and a corresponding block task is determined based on each of the block areas, each of which includes a block task data structure; Step S44 : For each of the block tasks, based on the block task data structure corresponding to the block task, the current state models of all first UAVs, and a preset particle swarm algorithm, determine a second UAV that meets the set requirements.
2. A method for allocating UAV tasks according to claim 1, characterized in that: The determining of a plurality of first drones based on the mission type, the observation requirement, and current state models of all drones includes: Determining the sensor type, observation capability, and power requirement of the drone to perform the task according to the task type and observation requirements of the task to be assigned; Determine the first set of drones based on the sensor types, observation capabilities, and power requirements of the required drones; Determining, based on information about pending tasks of each drone in the first drone set, a second drone set that meets the task priorities of the tasks to be assigned; Obtaining historical completion efficiency of each drone in the second drone set in performing tasks of the task type; Determining, based on the historical completion efficiency of each drone in the second drone set, a third drone set that meets the efficiency threshold corresponding to the task priority of the task to be assigned; All drones in the third drone set are used as first drones.
3. The method for allocating UAV tasks according to claim 1, wherein: The determining of a second UAV that meets set requirements based on the task data structure of the task to be assigned, the current state models of all first UAVs, and a preset particle swarm algorithm includes: Initializing a particle swarm based on the task data structure of the task to be assigned and the current state models of all first UAVs, the particle swarm comprising a plurality of particles, each of the particles representing a task assignment scheme, and the task assignment scheme representing a UAV flight path; Based on the preset objective function, calculate the fitness value of each particle; Based on the fitness value, current position and current speed of each particle, updating the speed and position of each particle; The updated speed and position of each particle are used as the current speed and current position of each particle in the particle swarm of the next iteration and the cycle is repeated until the fitness value is less than the set threshold. The task allocation scheme corresponding to the particle that meets the set path requirements and energy consumption requirements is selected from the particle swarm of the current iteration cycle as the target task allocation scheme; Based on the target task allocation plan, a first UAV that executes the target task allocation plan is selected as the second UAV.
4. The method for allocating UAV tasks according to claim 1, wherein: The assigning of tasks to all the second UAVs based on the task data structure of the tasks to be assigned includes: For any of the second UAVs, determining a task execution order of the second UAV based on the task priority of the to-be-assigned task and the priority of the to-be-executed task information of the second UAV; For any of the second drones, tasks are assigned to the second drone based on the task execution order.
5. The method for allocating UAV tasks according to claim 1, wherein: After allocating tasks to all the second UAVs based on the task data structure to be assigned, the method further includes: Obtaining flight status information and current mission information of each second UAV; For any second UAV, determining a safe flight threshold of the second UAV based on the currently executed mission information; For any second UAV, comparing the flight status information of the second UAV with a corresponding safe flight threshold; For any of the second UAVs, if the flight status information of the second UAV exceeds the corresponding safe flight threshold, an alarm message is sent to the command center.
6. A method for allocating UAV tasks according to claim 5, characterized in that: The obtaining of the flight status information of each second UAV includes: For any second drone, obtain the drone's position signal information, posture information, flight speed information, device operation information, and device configuration information through sensors on the second drone; For any second UAV, a flight status assessment is performed based on the position signal information, posture information, flight speed information, device operation information, and device configuration information to determine the flight status information of the UAV.
7. A UAV task allocation device, characterized in that: include: An acquisition module is used to obtain the current state models of the tasks to be assigned and all drones, where the current state model of each drone includes the current location, remaining battery power, sensor type, observation capability, and information about the tasks to be performed; a structured processing module, configured to perform structured processing on the task to be assigned to obtain a task data structure of the task to be assigned, wherein the task data structure includes a task type, a task name, a task priority, target area information, and observation requirements, wherein the task type is point continuous monitoring, line continuous observation, single polygonal area imaging, discretely distributed multiple polygonal area imaging, or annular area imaging; A first determining module is configured to determine, based on current state models of all the drones, a plurality of first drones that meet the mission type and the observation requirement from among all the drones; a second determining module, configured to determine at least one second UAV to perform the task to be assigned from among the first UAVs based on the task data structure of the task to be assigned, current state models of all the first UAVs, and a preset task assignment rule; a task assignment module, configured to assign tasks to all the second UAVs based on the task data structure of the tasks to be assigned; The second determining module is specifically configured to: Step S41: judging whether one of the first UAVs can complete the task to be assigned based on the target area information; Step S42: If one of the first UAVs can complete the task to be assigned, then based on the task data structure of the task to be assigned, the current state models of all the first UAVs, and a preset particle swarm algorithm, a second UAV that meets set requirements is determined, where the set requirements are that the flight path of each first UAV meets a set path requirement and the energy consumption meets a set energy consumption requirement; Step S43: If a drone cannot complete the task to be assigned, the target area information of the task to be assigned is divided based on a preset area division rule to obtain a plurality of block areas, and a corresponding block task is determined based on each of the block areas, each of which includes a block task data structure; Step S44 : For each of the block tasks, based on the block task data structure corresponding to the block task, the current state models of all first UAVs, and a preset particle swarm algorithm, determine a second UAV that meets the set requirements.
8. An electronic device, characterized in that: comprising a processor coupled to a memory; The processor is configured to execute the computer program stored in the memory, so that the electronic device performs the method according to any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that The method comprises a computer program or an instruction, which, when executed on a computer, causes the computer to execute the method according to any one of claims 1 to 6.
Citation Information
Patent Citations
Task allocation method, device and equipment, unmanned aerial vehicle nest and storage medium
CN117540973A