Control method for unmanned aerial vehicle, unmanned aerial vehicle, swarm collaboration system and processor

Abstract

The embodiments of the present application provide a control method for drones, drones, a swarm collaboration system, and a processor. The control method includes: determining the growing area where crops are located, the growing area including multiple locations to be collected for image acquisition; obtaining the current position and current operating status of each drone, and determining the target drone for each location to be collected; determining the target path of each target drone from the current position to the corresponding location to be collected; determining the intersection path of any two target paths; for each target drone, adjusting the intersection path according to the range of the target path to obtain an adjusted target path; controlling the target drone to fly to the location to be collected according to the adjusted target path to collect images of crops at the location to be collected. By collecting data on the growing area of ​​crops using multiple drones, the efficiency of data collection is improved, and the best time for preventing and controlling weeds is avoided.

Description

Technical Field

[0001] The present application relates to the field of intelligent agricultural equipment, and specifically to a control method for a drone, a drone, a drone swarm collaboration system, a storage medium, and a processor. Background Art

[0002] Drones are small and lightweight, and their control systems have simple interfaces, eliminating the need for complex operating spaces and methods. Small drones also offer a wider range of controllable aerodynamic stability, making them widely used in agriculture. However, existing technologies for single drones operating agriculturally often cannot sustain long-term operations over large farmland due to the numerous tasks they perform and the high power consumption. Summary of the Invention

[0003] The purpose of the embodiments of the present application is to provide a control method for a drone, a drone, a drone swarm collaboration system, a storage medium, and a processor.

[0004] In order to achieve the above objectives, the present application provides a first aspect of a control method for a drone, the control method comprising:

[0005] Determine a growing area of ​​the crop, where the growing area includes a plurality of locations to be imaged;

[0006] Get the current location and current operation status of each drone;

[0007] Determine the target drone at each location to be collected based on the current location and current operation status of each drone;

[0008] Determine the target path of each target UAV from its current position to the corresponding location to be collected;

[0009] Determine the intersection path of any two target paths, where the intersection path refers to the coincidence point and / or coincidence path between the two target paths;

[0010] For each target UAV, the intersection path is adjusted according to the range of the target path to obtain the adjusted target path;

[0011] The target UAV is controlled to fly to the location to be collected according to the adjusted target path to collect crop images at the location to be collected.

[0012] In an embodiment of the present application, adjusting the intersection path according to the range of the target path to obtain an adjusted target path includes: determining the intersection starting position and the intersection ending position of the intersection path of each target UAV; for each target UAV, determining the turning radius of the target UAV between the intersection starting position and the intersection ending position; determining multiple reference tracks for each target UAV from the intersection starting position to the intersection ending position according to the turning radius; for a target UAV whose target path range is greater than a preset range threshold, adjusting the intersection path of the reference track with the shortest range among the multiple reference tracks to obtain the adjusted target path of the target UAV; for a target UAV whose target path range is less than or equal to the preset range threshold, adjusting the intersection path of the reference track with the longest range among the multiple reference tracks to obtain the adjusted target path of the target UAV.

[0013] In an embodiment of the present application, determining the target UAV for each location to be collected based on the current position and current operating status of each UAV includes: for each location to be collected, determining the range between the current position of each UAV and the location to be collected; for each location to be collected, determining the priority order of each UAV in performing collection operations on the location to be collected based on the range corresponding to each UAV and the current operating status of each UAV; for each location to be collected, determining the UAV with the highest priority order as the target UAV for the location to be collected.

[0014] In an embodiment of the present application, determining the target path of each target UAV from the current position to the corresponding position to be collected includes: determining the obstacle position of each target UAV between the current position and the corresponding position to be collected; based on the path planning algorithm, determining the initial path of each target UAV from the current position to the corresponding position to be collected according to the obstacle position; interpolating the position points of the initial path corresponding to each target UAV to generate the target path of each target UAV.

[0015] In an embodiment of the present application, the control method also includes: after collecting the crop image at the location to be collected, inputting the crop image into a weed control model to output the weed type and weed level corresponding to the crop image through the weed control model; determining the herbicide and drug ratio corresponding to the collection location according to the weed type and drug level; controlling the plant protection machine to perform weed control operations on the collection location according to the herbicide and drug ratio; wherein the weed control model has been pre-trained using historical crop images.

[0016] In an embodiment of the present application, the control method also includes a training step of a weed control model, and the training step includes: obtaining multiple historical crop images; extracting the target area in each historical crop image by using a frame difference method; converting the image data corresponding to each target area to obtain converted target image data; determining the weed type data corresponding to each target image data; forming multiple historical image data groups according to each target image data and the weed type data corresponding to each target image data; and inputting the multiple historical image data groups into the weed control model to train the weed control model.

[0017] A second aspect of the present application provides a processor configured to execute the above-mentioned control method for a drone.

[0018] A third aspect of the present application provides a drone, comprising a processor configured to execute the above-mentioned control method for a drone.

[0019] A fourth aspect of the present application provides a drone swarm collaboration system, characterized in that the system includes:

[0020] Multiple drones to collect crop imagery; and

[0021] A processor configured to execute the above-mentioned control method for a drone.

[0022] In an embodiment of the present application, the system further includes: a plant protection machine for performing weed control operations.

[0023] In a fifth aspect, the present application provides a machine-readable storage medium having instructions stored thereon. When the instructions are executed by a processor, the processor is configured to execute the above-mentioned control method for a drone.

[0024] The control method, drone, drone swarm collaboration system, storage medium, and processor for drones are described above. The method determines a crop growth area, where the growth area includes multiple locations to be collected for image acquisition; obtains the current position and current operating status of each drone; determines a target drone for each location to be collected based on the current position and current operating status of each drone; determines a target path for each target drone from its current position to the corresponding location to be collected; determines the intersection path of any two target paths, where the intersection path refers to the overlapping point and / or overlapping path between the two target paths; adjusts the intersection path for each target drone based on the range of the target path to obtain an adjusted target path; and controls the target drone to fly to the location to be collected along the adjusted target path to collect images of the crops at the location to be collected. By collecting data on the crop growth area using multiple drones, data collection efficiency is improved, avoiding missing the optimal time for weed control.

[0025] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present application but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings:

[0027] Figure 1 The following schematically shows a flow chart of a control method for a drone according to an embodiment of the present application;

[0028] Figure 2 A schematic diagram of a drone swarm collaboration system according to an embodiment of the present application is shown schematically;

[0029] Figure 3 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0030] To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the specific implementation methods described herein are only used to illustrate and explain the embodiments of the present application and are not used to limit the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0031] Figure 1 The following schematically shows a flow chart of a control method for a drone according to an embodiment of the present application. Figure 1 As shown, in one embodiment of the present application, a control method for a drone is provided, comprising the following steps:

[0032] S102, determining a growing area where the crops are located, where the growing area includes a plurality of locations to be captured for image capture.

[0033] S104, obtaining the current position and current operation status of each UAV;

[0034] S106, determining a target drone at each location to be collected based on the current location and current operation status of each drone;

[0035] S108, determining a target path for each target UAV from its current position to the corresponding position to be collected;

[0036] S110, determining an intersection path of any two target paths, where the intersection path refers to an overlapping point and / or overlapping path between the two target paths;

[0037] S112, for each target UAV, adjusting the intersection path according to the range of the target path to obtain an adjusted target path;

[0038] S114 , controlling the target UAV to fly to the location to be collected according to the adjusted target path, so as to collect crop images at the location to be collected.

[0039] The processor can determine the crop growing area. The growing area can be a single crop field or multiple crop fields within a single area. The target location refers to the location within the crop growing area where the drone is required to perform image acquisition. Typically, a single crop field contains multiple target locations. For multiple drones performing image acquisition at multiple target locations, the processor can first obtain the current location and current operating status of each drone. The drone's current location refers to its latitude and longitude at the current moment. The current operating status includes at least one of whether there is a task to acquire images at the target location, the range between the drone's current location and the target location corresponding to the current task, if a task exists, and the drone's battery level. The processor can then analyze and process the current location and current operating status to determine a target drone for each target location. For each target location, the target drone refers to the drone that will perform the image acquisition task at that target location. The processor can then determine the target path for each target drone from its current location to the corresponding target location. The target path refers to the flight path that the target drone will take from its current location to the corresponding target location, avoiding obstacles. For any two target paths, the processor can determine whether they intersect. If so, the processor can adjust the intersecting path based on the target path's range to obtain an adjusted target path. The processor can then control the target drone to fly along the adjusted target path to the desired collection location to capture crop images at that location. Crop images contain images of both crops and weeds. For example, if there are 100 locations to be collected in a crop growing area and 10 drones are dispatched for the collection mission, each drone can capture crop images at multiple locations, significantly improving collection efficiency.

[0040] In one embodiment, adjusting the intersection path according to the range of the target path to obtain an adjusted target path includes: determining the intersection starting position and the intersection ending position of the intersection path of each target UAV; for each target UAV, determining the turning radius of the target UAV between the intersection starting position and the intersection ending position; determining multiple reference tracks for each target UAV from the intersection starting position to the intersection ending position according to the turning radius; for a target UAV whose target path has a range greater than a preset range threshold, adjusting the intersection path of the reference track with the shortest range among the multiple reference tracks to obtain the adjusted target path of the target UAV; for a target UAV whose target path has a range less than or equal to the preset range threshold, adjusting the intersection path of the reference track with the longest range among the multiple reference tracks to obtain the adjusted target path of the target UAV.

[0041] For any two target paths with intersecting paths, if the intersecting path is a section of the path that overlaps the two target paths, the processor can determine the intersection starting position and intersection ending position of the intersection path of each target UAV. According to the movement direction of the target path of the target UAV, the intersection starting position is the flight starting point of the intersection path, and the intersection ending position is the flight ending point of the intersection path. The processor can then determine the turning radius of the target UAV based on the target UAV's intersection starting position, intersection ending position, and the movement direction at these two positions. The turning radius refers to the minimum radius corresponding to the inscribed circle between the intersection starting position and the intersection ending position. The processor can then determine multiple reference tracks for each target UAV from the intersection starting position to the intersection ending position based on the turning radius. The reference track refers to the detour route from the intersection starting position to the intersection ending position generated based on the Dubins path algorithm. Then, for any two target paths that have intersecting paths, the processor can replace the intersecting path of the target drone whose target path's range exceeds a preset range threshold with the reference track with the shortest range among the multiple reference tracks, and replace the intersecting path of the target drone whose target path's range exceeds the preset range threshold with the reference track with the longest range among the multiple reference tracks. Thus, any two target paths that have intersecting paths can be adjusted using the reference tracks. The adjusted intersecting path of the two target paths, due to the change in flight path and range, can reduce the probability of a collision between the two target drones.

[0042] In one embodiment, determining the target UAV for each location to be collected based on the current position and current operating status of each UAV includes: for each location to be collected, determining the range between the current position of each UAV and the location to be collected; for each location to be collected, determining the priority order of each UAV in performing collection operations for the location to be collected based on the range corresponding to each UAV and the current operating status of each UAV; for each location to be collected, determining the UAV with the highest priority order as the target UAV for the location to be collected.

[0043] When assigning a target drone to perform a collection task to each location to be collected, the processor can determine the current location and current operating status of each drone. The current operating status includes at least one of whether there is a collection task to go to the location to be collected for image collection, the range between the drone's current position and the location to be collected corresponding to the current collection task if there is a collection task, and the drone's battery level. Then, the processor can determine the range between the current position of each drone and the location to be collected. Specifically, the AStar algorithm can be used to plan the flight path between the current position and the location to be collected. Then, the processor can construct an objective function matrix for the range and current operating status of all drones based on the wolf pack algorithm (WPA). The drones are prioritized based on the objective function matrix. For each location to be collected, the processor can determine the drone with the highest priority calculated by the wolf pack algorithm (WPA) as the target drone for the location to be collected.

[0044] In one embodiment, determining a target path for each target UAV from a current position to a corresponding position to be collected includes: determining the position of obstacles between each target UAV from the current position to the corresponding position to be collected; determining an initial path for each target UAV from the current position to the corresponding position to be collected according to the obstacle positions based on a path planning algorithm; and interpolating position points of the initial path corresponding to each target UAV to generate a target path for each target UAV.

[0045] The processor can obtain map information of the growth area, and the map information includes multiple obstacles and the locations of the multiple obstacles. The processor can determine the obstacle position of each target UAV from the current position to the corresponding position to be collected. Then, based on the path planning algorithm, the processor can determine the initial path of each target UAV from the current position to the corresponding position to be collected according to the obstacle position. The initial path refers to the shortest path from the current position to the corresponding position to be collected that avoids obstacles. Among them, the path planning algorithm can be an AStar algorithm. Furthermore, according to the cubic B-spline curve algorithm, the position points of the initial path can be interpolated, so that the initial path can be smoothed to generate a flyable target path that meets the constraints.

[0046] In one embodiment, the control method further includes: after collecting the crop image at the location to be collected, inputting the crop image into a weed control model to output the weed type and weed level corresponding to the crop image through the weed control model; determining the herbicide and agent ratio corresponding to the collection location according to the weed type and weed level; controlling the plant protection machine to perform weed control operations on the collection location according to the herbicide and agent ratio; wherein the weed control model has been pre-trained using historical crop images.

[0047] After the target drone captures crop images at the target location, the processor can input the crop images into the weed control model, which then outputs the corresponding weed damage type and damage level. The weed damage type refers to the biological species of the weed, while the weed damage level refers to the degree of damage to crop growth. Specifically, the weed damage level can be determined by the leaf area index of the weed. Based on the weed damage type and damage level, the processor can determine the corresponding herbicide and herbicide ratio. The processor can then control the plant protection machine to perform weed control operations based on the herbicide and herbicide ratio.

[0048] In one embodiment, the control method also includes a training step of a weed control model, the training step including: acquiring a plurality of historical crop images; extracting a target area in each historical crop image by a frame difference method; converting the image data corresponding to each target area to obtain converted target image data; determining weed type data corresponding to each target image data; forming a plurality of historical image data groups according to each target image data and the weed type data corresponding to each target image data; and inputting the plurality of historical image data groups into the weed control model to train the weed control model.

[0049] During the weed control model training process, the processor can use a frame difference method to extract a target area for each historical crop image. The target area includes the image locations of weeds in the historical crop images. Furthermore, the processor can convert the format of the image data corresponding to each target area into target image data for model training. For each historical crop image, each image can be labeled to distinguish the weed type corresponding to its target image data. The weed type data refers to the label data for each historical crop image. The processor can then combine each target image data and the corresponding weed type data into a historical image data set. The processor can then generate multiple historical image data sets based on multiple historical crop images. After inputting these multiple historical image data sets into the weed control model, these data sets can be divided into training and validation sets to train the weed control model and obtain a fully trained weed control model.

[0050] The control method, drone, drone swarm collaboration system, storage medium, and processor for drones are described above. The method determines a crop growth area, where the growth area includes multiple locations to be collected for image acquisition; obtains the current position and current operating status of each drone; determines a target drone for each location to be collected based on the current position and current operating status of each drone; determines a target path for each target drone from its current position to the corresponding location to be collected; determines the intersection path of any two target paths, where the intersection path refers to the overlapping point and / or overlapping path between the two target paths; adjusts the intersection path for each target drone based on the range of the target path to obtain an adjusted target path; and controls the target drone to fly to the location to be collected along the adjusted target path to collect images of the crops at the location to be collected. By using multiple drones to collect data on the crop growth area, data collection efficiency is improved. By feeding crop images from multiple locations into a weed control model, the type and severity of weed damage at each location can be determined. This allows the herbicide spraying and herbicide ratio to be controlled based on the infestation situation. This improves the efficiency of spraying targeted areas of rice fields and avoids missing the optimal time for weed control. This also reduces labor and effectively addresses issues such as pesticide pollution and waste.

[0051] Figure 1 FIG. 1 is a flow chart of a control method for a drone in one embodiment. It should be understood that although Figure 1 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0052] In one embodiment, a drone is provided, comprising a processor configured to implement the aforementioned drone control method. Each drone includes a positioning device, an image acquisition device, and a processor, which can be used to determine the drone's current location in real time. When the drone arrives at the corresponding location to be collected, it can capture images of the location to obtain crop images. Specifically, the processor includes a quantum computing platform. The quantum computing platform is used for data processing and analysis. Quantum computing can extract effective information from large amounts of data and process it to generate new and useful information. Traditional computing platforms are often susceptible to virus attacks, causing computer crashes and potentially leaking personal information. However, quantum computing platforms, due to the principle of quantum non-cloning, can effectively avoid these issues. Furthermore, quantum computing has powerful parallel computing capabilities, capable of analyzing large amounts of different data simultaneously, with computing speeds far exceeding those of traditional computing platforms.

[0053] In one embodiment, Figure 2 As shown, a UAV swarm collaboration system is provided, comprising:

[0054] Multiple drones for collecting crop images;

[0055] The processor is configured to implement the above-mentioned control method for a drone.

[0056] The processor can determine the growing area of ​​the crops. The multiple drones can be drone 1, drone 2, and drone N. For multiple drones to capture images of multiple locations to be captured, the processor can first obtain the current location and current operating status of each drone. The drone's current location refers to its latitude and longitude at the current moment. The current operating status includes at least one of whether there is a mission to capture images at the location to be captured, the range between the drone's current location and the location to be captured corresponding to the current mission (if a mission exists), and the drone's battery level. The processor can then analyze and process the current location and operating status to determine a target drone for each location to be captured. For each location to be captured, the target drone refers to the drone that is performing the image capture mission at that location. The processor can then determine a target path for each target drone from its current location to the corresponding location to be captured. The target path refers to the flight path that the target drone takes from its current location to the corresponding location to be captured, avoiding obstacles. For any two target paths, the processor can determine whether the two target paths intersect. If so, the processor can adjust the intersecting path based on the target path's range to obtain an adjusted target path. The processor can then control the target drone to fly along the adjusted target path to the desired location to capture crop images at that location. This allows multiple drones to work together to capture crop images at multiple locations across a growing area, improving data collection efficiency and preventing weed control efforts from being missed.

[0057] In one embodiment, Figure 2 As shown, the UAV swarm collaboration system also includes: a plant protection drone for performing weed control operations.

[0058] After multiple drones capture crop images, the processor can input these images into a weed control model, which then outputs the corresponding weed damage type and damage level. Based on the damage type and damage level, the processor can then determine the appropriate herbicide and herbicide ratio for the captured location, controlling the plant protection aircraft to perform weed control operations at the captured location. The processor can also control the plant protection aircraft to generate a corresponding route map for path planning, which it then uses to perform spraying operations.

[0059] The processor contains a kernel, which retrieves the corresponding program unit from the memory. There can be one or more kernels, and the control method for the drone can be implemented by adjusting the kernel parameters.

[0060] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0061] An embodiment of the present application provides a storage medium having a program stored thereon, which, when executed by a processor, implements the above-mentioned control method for a drone.

[0062] An embodiment of the present application provides a processor, which is used to run a program, wherein the program executes the above-mentioned control method for a drone when running.

[0063] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor A01, a network interface A02, a memory (not shown in the figure) and a database (not shown in the figure) connected via a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02 and a database (not shown in the figure). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A04. The database of the computer device is used to store data for a control method for a drone. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program B02 is executed by the processor A01, a control method for a drone is implemented.

[0064] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0065] An embodiment of the present application provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, steps of a control method for a drone are implemented.

[0066] The present application also provides a computer program product that, when executed on a data processing device, is suitable for executing a program that initializes the steps of a control method for an unmanned aerial vehicle. Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a fully hardware embodiment, a fully software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0067] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0068] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0069] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps for the function specified in one or more boxes.

[0070] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0071] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0072] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0073] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0074] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A control method for a drone, characterized in that: The control method includes: Determining a growing area of ​​the crops, wherein the growing area includes a plurality of locations to be captured for image capture; Get the current location and current operation status of each drone; For each location to be collected, determining the range between the current location of each drone and the location to be collected; For each location to be collected, determine the priority order of each drone in performing the collection operation on the location to be collected based on the flight range corresponding to each drone and the current operation status of each drone; For each location to be collected, the UAV with the highest priority is determined as the target UAV for the location to be collected; Determine the target path of each target UAV from its current position to the corresponding location to be collected; Determine an intersection path of any two target paths, where the intersection path refers to an overlapping point and / or an overlapping path between the two target paths; For each target UAV, adjusting the intersection path according to the range of the target path to obtain an adjusted target path; Controlling the target UAV to fly to the location to be collected according to the adjusted target path to collect crop images at the location to be collected; The adjusting the intersecting path according to the range of the target path to obtain an adjusted target path includes: Determine the intersection start position and the intersection end position of the intersection path of each target UAV; For each target UAV, determining a turning radius of the target UAV between the intersection start position and the intersection end position; Determine a plurality of reference tracks for each target UAV from the intersection starting position to the intersection ending position according to the turning radius; For a target UAV whose range of the target path is greater than a preset range threshold, adjusting the intersection path by using the reference track with the shortest range among the multiple reference tracks to obtain an adjusted target path for the target UAV; For a target UAV whose range of the target path is less than or equal to a preset range threshold, the reference track with the longest range among multiple reference tracks is adjusted to the intersection path to obtain the adjusted target path of the target UAV.

2. The control method for a drone according to claim 1, characterized in that: Determining the target path of each target drone from its current position to the corresponding location to be collected includes: Determine the obstacle position between each target drone's current position and the corresponding location to be collected; Based on the path planning algorithm, determine the initial path of each target UAV from the current position to the corresponding position to be collected according to the obstacle position; The position points of the initial path corresponding to each target UAV are interpolated to generate the target path of each target UAV.

3. The control method for a drone according to claim 1, characterized in that: The control method further includes: After collecting the crop image at the location to be collected, inputting the crop image into a weed control model, so that the weed control model outputs the weed type and weed level corresponding to the crop image; determining the herbicide and the herbicide ratio corresponding to the collection location according to the weed damage type and the weed damage level; controlling the plant protection machine to perform weed control operations at the collection location according to the herbicide and the herbicide ratio; The weed control model is pre-trained using historical crop images.

4. The control method for a drone according to claim 3, characterized in that: The control method further comprises a training step of a weed control model, wherein the training step comprises: Acquire multiple historical crop images; The target area in each historical crop image is extracted by frame difference method; Converting the image data corresponding to each target area into a format to obtain converted target image data; Determining weed damage type data corresponding to each target image data; forming a plurality of historical image data groups according to each target image data and the weed damage type data corresponding to each target image data; The plurality of historical image data sets are input into the weed control model to train the weed control model.

5. A processor, characterized in that: The method is configured to execute the control method for a drone according to any one of claims 1 to 4.

6. A drone, characterized in that: comprising the processor of claim 5.

7. A drone swarm collaboration system, characterized in that: The system comprises: Multiple drones to collect crop imagery; and The processor of claim 5.

8. The UAV swarm collaboration system according to claim 7, characterized in that: The system further comprises: Plant protection machine, used for weed control operations.

9. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the control method for a drone according to any one of claims 1 to 4.

Images