Agricultural unmanned aerial vehicle operation path planning system and method based on Internet of Things

Abstract

The invention discloses an agricultural unmanned aerial vehicle operation path planning system and method based on the Internet of Things, and belongs to the field of intelligent agriculture. An initial path planning model is constructed, the spraying width and the overlapping coefficient are imported into the initial path planning model to calculate the path distance, and a fog drop motion model is constructed; introducing the initial diameter and mass of the fog drops into a fog drop motion model to evaluate the fog drop settling velocity, constructing a fog drop evaporation and drift model, introducing the environment data, the fog drop diameter and the settling velocity into the fog drop evaporation and drift model to evaluate the fog drop evaporation effect and the fog drop horizontal drift distance, and constructing an unmanned aerial vehicle flight height and path correction model; settlement fog drop data and real-time spraying width are imported into an unmanned aerial vehicle flight height and path correction model to adjust the flight height and path of the unmanned aerial vehicle, a dose control model is constructed, the pest and disease damage degree of each grid is imported into the dose control model to evaluate the pesticide spraying dose of each grid, and the spraying precision is improved.

Description

Technical Field

[0001] This application belongs to the field of smart agriculture, specifically an agricultural UAV operation path planning system and method based on the Internet of Things. Background Art

[0002] With the development of agricultural intelligence, plant protection UAVs have been widely used in agricultural operation scenarios such as pest control and pesticide spraying. Traditional UAV spraying schemes mainly rely on fixed flight altitudes, equal dosages, and regular grid coverage, without fully considering key factors such as wind speed and direction disturbances during the actual spraying process, the influence of environmental factors on the movement behavior of droplets, and the growth status of surface crops.

[0003] In complex environments with high temperatures, low humidity, or strong winds, droplets are prone to evaporation or diffusion. The existing systems lack a droplet evaporation modeling and sedimentation trajectory prediction mechanism, resulting in a decrease in the effectiveness of pesticides landing. Most use a constant nozzle opening and fixed spraying flow rate, without dynamically adjusting the dosage according to the degree of crop pests and diseases, which is not conducive to precision agriculture spraying. This application combines wind speed and direction, droplet movement, real-time image recognition, and dosage control to plan the operation of UAVs, improving the accuracy of pesticide spraying. Summary of the Invention

[0004] In view of the deficiencies of the prior art, this application proposes an agricultural UAV operation path planning system and method based on the Internet of Things.

[0005] To achieve the above object, this application provides the following technical solutions: An agricultural UAV operation path planning system and method based on the Internet of Things, which includes the following specific steps: Construct an initial path planning model, and import the spray width and overlap coefficient into the initial path planning model to calculate the path spacing; Construct a droplet movement model, and import the initial diameter and mass of the droplets into the droplet movement model to evaluate the droplet sedimentation velocity; Construct a droplet evaporation and drift model, and import the environmental data, droplet diameter, and sedimentation velocity into the droplet evaporation and drift model to evaluate the droplet evaporation effect and the horizontal drift distance of the droplets; Construct a UAV flight height and path correction model, and import the sedimented droplet data and real-time spray width into the UAV flight height and path correction model to adjust the UAV flight height and path; Construct a dosage control model, and import the degree of pests and diseases of each grid into the dosage control model to evaluate the pesticide spraying dosage of each grid.

[0006] Preferably, the step of constructing the initial path planning model and importing the spray width and overlap coefficient into the initial path planning model to calculate the path spacing includes the following specific steps: S11. Set the UAV operation area through the electronic map, and rasterize the operation area into a grid map of . Among them, the central coordinates of the i-th unit grid are: , and the adjacent path spacing is: , where W is the spray width of the nozzle, is the overlap coefficient. Each grid cell represents the smallest operation unit that the UAV needs to cover in the spraying task to ensure the overlap coverage rate between spraying areas; S12. Obtain the historical flight parameters and paths, obtain the obstacle grid data through the historical flight data, and use the A* algorithm to perform initial path planning in the grid. Among them, the set of spatial coordinate points of the UAV flight path is: , where is the flight height of the UAV in the i-th grid. Among them, the calculation formula for the spray width of the nozzle is: , where is the fixed atomization angle of the nozzle.

[0007] Preferably, the construction of the droplet motion model, and importing the initial diameter and mass of the droplets into the droplet motion model to evaluate the droplet settlement velocity includes the following specific steps: S21. Obtain the real-time wind speed and wind direction through the wind speed and wind direction sensor, obtain the UAV nozzle parameters. The movement of the sprayed droplets in the air is affected by gravity, air resistance and wind force. Substitute the droplet mass into the droplet motion equation to calculate the droplet settlement velocity. Among them, the droplet motion equation is: , where m is the droplet mass, g is the acceleration due to gravity, ρ is the air density, C is the air resistance coefficient, which can be obtained from the table, A is the cross-sectional area of the droplet facing the wind, v is the droplet velocity. Among them, the calculation formula for the droplet mass is: , and the calculation formula for the cross-sectional area of the droplet facing the wind is: , where is the pesticide density, is the initial droplet diameter, and the calculated droplet settlement velocity is: . Establish the droplet motion equation through Newton's second law, considering the actual motion influence of gravity, air resistance and wind force on the droplets.

[0008] Preferably, the construction of the droplet evaporation and drift model, and importing the environmental data, droplet diameter and settlement velocity into the droplet evaporation and drift model to evaluate the droplet evaporation effect and the horizontal drift distance of the droplets includes the following specific steps: S31. Obtain the environmental humidity and temperature. During the process of the droplets being sprayed onto the crop surface, they will be affected by the environment. The square of the droplet diameter decays linearly with time. Among them, the calculation formula for the droplet diameter at time t is: , where K is the evaporation coefficient, and the calculation formula for the evaporation coefficient is: , where is the latent heat, D is the water vapor diffusion coefficient, c is the specific heat capacity of air, P is the saturation vapor pressure, T is the ambient temperature, RH is the relative humidity of air, and the evaporation rate constant is jointly determined by the air temperature, humidity, water vapor diffusion coefficient, latent heat, specific heat capacity of air, and saturation vapor pressure.

[0009] S32. Substitute the crosswind speed into the calculation formula of the horizontal drift distance of fog droplets to calculate the horizontal drift distance of fog droplets. The calculation formula of the horizontal drift distance of fog droplets is: , where is the crosswind speed, is the sedimentation time. The calculation formula of the sedimentation time is: , where is the height of the crops in the i-th grid.

[0010] Preferably, the construction of the UAV flight height and path correction model, and the import of the sedimented fog droplet data and the real-time spray width into the UAV flight height and path correction model to adjust the UAV flight height and path include the following specific steps: S41. Substitute the horizontal drift data of fog droplets and the diameter of the sedimented fog droplets into the height adjustment formula to adjust the UAV flight height. The height adjustment formula is: , where is the adjusted flight height of the i-th grid, is the offset flight height adjustment of the i-th grid, is the flight height adjustment of the spray diameter of the i-th grid. To ensure that the offset does not exceed the maximum allowable distance, the calculation formula of the offset flight height adjustment of the i-th grid is: , where d max is the maximum allowable distance of the horizontal drift of fog droplets. Substitute the sedimentation time into the calculation formula of the fog droplet diameter to calculate the diameter of the sedimented fog droplets. Compare the diameter of the sedimented fog droplets with the fog droplet diameter spraying threshold. If it is within the threshold range, fly at the original height. If it is not within the threshold range, adjust the height. The calculation formula of the flight height adjustment of the spray diameter of the i-th grid is: , where is the fog droplet diameter spraying threshold; S42. Substitute the adjusted flight height into the calculation formula of the real-time spray width to calculate the real-time spray width. The calculation formula of the real-time spray width is: , and automatically adjust the grid spacing of the flight path according to the preset overlap coefficient. The grid spacing adjustment formula of the flight path is: , where is the overlap coefficient. At the same time, the flight path is offset by the same distance in the crosswind direction. The calculation formula of the offset abscissa is: , causing an equal offset of the flight path in the upwind direction, maximizing the accuracy of the fog droplet landing point, and preventing missed spraying and double spraying.

[0011] Preferably, the step of constructing the dosage control model and importing the pest and disease degree of each grid into the dosage control model to evaluate the drug spraying dosage of each grid includes the following specific steps: S51. Collect crop images through a camera carried by a drone, import the crop images taken of each grid into a pre-trained image model, output the pest and disease score value, and substitute the pest and disease score value into the drug spraying dosage calculation formula to calculate the drug spraying dosage. Among them, the drug spraying dosage calculation formula for the i-th grid is: , where is the minimum drug dosage, is the maximum drug dosage, is the pest and disease score value of the i-th grid; S52. Substitute the spraying dosage into the drone spraying flow rate calculation formula to calculate the spraying flow rate of the drone per unit time. Among them, the drone spraying flow rate calculation formula is: , where V is the drone flight speed, and the flow rate of each grid is adjusted by adjusting the opening of the nozzle valve.

[0012] The agricultural drone operation path planning system based on the Internet of Things is implemented based on the above-mentioned agricultural drone operation path planning method based on the Internet of Things, and specifically includes: The initial path planning module is used to calculate the path spacing through the spraying width and the overlap coefficient; The fog droplet movement evaluation module is used to evaluate the fog droplet sedimentation speed through the initial diameter and mass of the fog droplet; The fog droplet evaporation module is used to evaluate the fog droplet evaporation effect through environmental data and fog droplet diameter; The drift evaluation module is used to evaluate the horizontal drift distance of the fog droplet through the crosswind speed and sedimentation time; The flight height correction module is used to adjust the drone flight height through the fog droplet horizontal drift data and the fog droplet diameter after sedimentation; The path correction module is used to adjust the drone flight path through the real-time spraying width; The dosage control module is used to evaluate the drug spraying dosage of each grid through the pest and disease degree of each grid.

[0013] An electronic device includes: a processor and a memory. Among them, a computer program that can be called by the processor is stored in the memory; The processor executes the above-mentioned agricultural drone operation path planning method based on the Internet of Things by calling the computer program stored in the memory.

[0014] A computer-readable storage medium, characterized in that it stores instructions, which, when run on a computer, cause the computer to execute the above-mentioned method for planning the operation path of an agricultural drone based on the Internet of Things.

[0015] Compared with the prior art, the beneficial effects of this application are as follows: This application constructs an initial path planning model, imports the spray width and overlap coefficient into the initial path planning model to calculate the path spacing, constructs a droplet motion model, imports the initial droplet diameter and mass into the droplet motion model to evaluate the droplet sedimentation velocity, constructs a droplet evaporation and drift model, imports environmental data, droplet diameter and sedimentation velocity into the droplet evaporation and drift model to evaluate the droplet evaporation effect and the horizontal drift distance of the droplets, constructs a drone flight height and path correction model, imports the sedimented droplet data and the real-time spray width into the drone flight height and path correction model to adjust the drone flight height and path, constructs a dosage control model, imports the degree of pests and diseases of each grid into the dosage control model to evaluate the drug spraying dosage of each grid. This application combines wind speed and direction, droplet motion, real-time image recognition and dosage regulation to plan the operation of the drone, improving the accuracy of drug spraying. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a schematic diagram of the overall process of the method for planning the operation path of an agricultural drone based on the Internet of Things in this application; Figure 2 is a flowchart of the adjustment of the drone flight path in this application; Figure 3 is a schematic diagram of the overall framework of the system for planning the operation path of an agricultural drone based on the Internet of Things in this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] Next, the technical solutions in the embodiments of this application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments.

[0018] Embodiment 1 Please refer to Figure 1-2 , an embodiment provided by this application: a method for planning the operation path of an agricultural drone based on the Internet of Things, which includes the following specific steps: Construct an initial path planning model, and import the spray width and overlap coefficient into the initial path planning model to calculate the path spacing; Construct a droplet motion model, and import the initial droplet diameter and mass into the droplet motion model to evaluate the droplet sedimentation velocity; Construct a droplet evaporation and drift model, and import environmental data, droplet diameter and sedimentation velocity into the droplet evaporation and drift model to evaluate the droplet evaporation effect and the horizontal drift distance of the droplets; Build a UAV flight altitude and path correction model, import the sedimentation droplet data and real-time spraying width into the UAV flight altitude and path correction model to adjust the UAV flight altitude and path; Build a dosage control model, import the pest and disease degree of each grid into the dosage control model to evaluate the drug spraying dosage of each grid.

[0019] In this embodiment, it should be specifically noted that building an initial path planning model and importing the spraying width and overlap coefficient into the initial path planning model to calculate the path spacing includes the following specific steps: S11. Set the UAV operation area through the electronic map, and rasterize the operation area into a grid map, where the central coordinates of the i-th unit grid are: , and the adjacent path spacing is: , where W is the nozzle spraying width, is the overlap coefficient, and each grid cell represents the smallest operation unit that the UAV needs to cover in the spraying task to ensure the overlap coverage rate between spraying areas; Exemplarily, in this embodiment, the overlap coefficient is defaulted to 0.8; S12. Obtain the historical flight parameters and paths, obtain the obstacle grid data through the historical flight data, and use the A* algorithm to perform initial path planning in the grid. Among them, the UAV flight path space coordinate point set is: , where is the UAV flight altitude of the i-th grid. Among them, the nozzle spraying width calculation formula is: , where is the fixed atomization angle of the nozzle.

[0020] In this embodiment, it should be specifically noted that building a droplet movement model and importing the initial droplet diameter and mass into the droplet movement model to evaluate the droplet sedimentation speed includes the following specific steps: S21. Obtain the real-time wind speed and wind direction through the wind speed and wind direction sensor, obtain the UAV nozzle parameters, and the movement of the sprayed droplets in the air is affected by gravity, air resistance and wind force. Substitute the droplet mass into the droplet movement equation to calculate the droplet sedimentation speed. Among them, the droplet movement equation is: , where m is the droplet mass, g is the acceleration due to gravity, ρ is the air density, C is the air resistance coefficient, which can be obtained from the table, A is the droplet frontal area, v is the droplet speed. Among them, the droplet mass calculation formula is: , and the droplet frontal area calculation formula is: , where is the pesticide density, is the initial droplet diameter, and the calculated droplet sedimentation speed is: The motion equation of the droplets is established through Newton's second law, considering the actual motion effects of gravity, air resistance, and wind force on the droplets.

[0021] It should be noted that in this embodiment, the selection of the droplet size is based on the size distribution parameters provided by the nozzle manufacturer, and the volume median diameter is used as a representative value for droplet motion calculation.

[0022] Specifically in this embodiment, a droplet evaporation and drift model is constructed. Importing environmental data, droplet diameter, and sedimentation velocity into the droplet evaporation and drift model to evaluate the droplet evaporation effect and the horizontal drift distance of the droplets includes the following specific steps: S31. Obtain the environmental humidity and temperature. During the process of spraying droplets onto the crop surface, the droplets are affected by the environment, and the square of the droplet diameter decays linearly with time. Among them, the calculation formula for the droplet diameter at time t is: , where K is the evaporation coefficient, and the calculation formula for the evaporation coefficient is: , where is the latent heat ( ), D is the water vapor diffusion coefficient ( ), c is the specific heat capacity of air, P is the saturated vapor pressure. The specific heat capacity of air and the saturated vapor pressure are obtained by looking up the table according to the environmental temperature. T is the environmental temperature, RH is the relative humidity of air, and the evaporation rate constant is jointly determined by the air temperature, humidity, water vapor diffusion coefficient, latent heat, specific heat capacity of air, and saturated vapor pressure.

[0023] Exemplarily, in this embodiment, the latent heat is , and the water vapor diffusion coefficient is ; S32. Substitute the crosswind speed into the calculation formula for the horizontal drift distance of the droplets to calculate the horizontal drift distance of the droplets. Among them, the calculation formula for the horizontal drift distance of the droplets is: , where is the crosswind speed, is the sedimentation time. Among them, the calculation formula for the sedimentation time is: , where is the crop height in the i-th grid.

[0024] Specifically in this embodiment, a UAV flight height and path correction model is constructed. Importing the sedimented droplet data and the real-time spraying width into the UAV flight height and path correction model to adjust the UAV flight height and path includes the following specific steps: S41. Substitute the horizontal drift data of the droplets and the diameter of the sedimented droplets into the height adjustment formula to adjust the UAV flight height. Among them, the height adjustment formula is: , where is the adjusted flight height of the i-th grid, is the adjusted offset flight height of the i-th grid, is the adjusted flight height of the spray diameter of the i-th grid. To ensure that the offset does not exceed the maximum allowable distance, the calculation formula for the adjusted offset flight height of the i-th grid is: , where d max is the maximum allowable horizontal drift distance of the droplets. Substitute the sedimentation time into the droplet diameter calculation formula to calculate the droplet diameter after sedimentation. Compare the sedimented droplet diameter with the droplet diameter spraying threshold. If it is within the threshold range, fly at the original height. If it is not within the threshold range, adjust the height. The calculation formula for the adjusted flight height of the spray diameter of the i-th grid is: , where is the droplet diameter spraying threshold; S42. Substitute the adjusted flight height into the real-time spray width calculation formula to calculate the real-time spray width. The real-time spray width calculation formula is: , and automatically adjust the grid spacing of the flight path according to the preset overlap coefficient. The grid spacing adjustment formula for the flight path is: , where is the overlap coefficient. At the same time, the flight path is offset by the same distance in the crosswind direction. The calculation formula for the abscissa after offset is: , so that the flight path is offset equally in the upstream direction of the wind, maximizing the accuracy of the droplet landing point and preventing missed spraying and double spraying.

[0025] It should be specifically noted in this embodiment that to construct a dose control model and import the pest and disease degree of each grid into the dose control model to evaluate the drug spraying dose of each grid, the following specific steps are included: S51. Use a drone equipped with a camera to collect crop images. Import the crop images taken of each grid into a pre-trained image model to output a pest and disease score value. Substitute the pest and disease score value into the spraying dose calculation formula to calculate the spraying dose. The calculation formula for the spraying dose of the i-th grid is: , where is the minimum drug dose, is the maximum drug dose, is the pest and disease score value of the i-th grid; Exemplarily, in this embodiment, the pest and disease score value of the i-th grid , 0–0.3 indicates minor pests and diseases, 0.3–0.6 indicates moderate pests and diseases, and 0.6–1.0 indicates severe pests and diseases; S52. Substitute the spraying dose into the drone spraying flow rate calculation formula to calculate the spraying flow rate per unit time of the drone. The drone spraying flow rate calculation formula is: , where V is the flight speed of the drone, and the flow rate of each grid is adjusted by adjusting the opening of the nozzle valve.

[0026] Specifically, the flow sensor monitors the actual flow rate of the pesticide in real time and feeds the data back to the controller. The controller compares the actual flow rate with the preset target flow rate, and then adjusts the flow rate by adjusting the opening of the nozzle valve and changing the rotation speed of the pump to make it reach the preset value, so as to accurately control the spraying dose.

[0027] It should be noted that the value-taking method of various setting parameters in this embodiment is as follows: obtain representative historical drone spraying process data, and at the same time obtain historical spraying effect data. Hire experts to manually judge whether the drone spraying effect meets the requirements. At the same time, substitute the obtained historical data into the calculation results and judgment results of each step in this embodiment into the fitting software, and output the value-taking of various setting parameters that meet the highest judgment accuracy rate; The advantages of this embodiment over the prior art are: In this embodiment, an initial path planning model is constructed. The spray width and overlap coefficient are imported into the initial path planning model to calculate the path spacing. A droplet motion model is constructed, and the initial droplet diameter and mass are imported into the droplet motion model to evaluate the droplet sedimentation speed. A droplet evaporation and drift model is constructed, and the environmental data, droplet diameter, and sedimentation speed are imported into the droplet evaporation and drift model to evaluate the droplet evaporation effect and the horizontal drift distance of the droplets. A drone flight height and path correction model is constructed, and the sedimented droplet data and the real-time spray width are imported into the drone flight height and path correction model to adjust the drone flight height and path. A dose control model is constructed, and the pest and disease degree of each grid is imported into the dose control model to evaluate the drug spraying dose of each grid. This application combines wind speed and direction, droplet motion, real-time image recognition, and dose regulation to plan the operation of the drone, improving the drug spraying accuracy.

[0028] Embodiment 2 Such as Figure 3As shown, the agricultural drone operation path planning system based on the Internet of Things is implemented based on the above-mentioned agricultural drone operation path planning based on the Internet of Things. It specifically includes an initial path planning module, a droplet movement evaluation module, a droplet evaporation module, a drift evaluation module, a flight altitude correction module, a path correction module, and a dosage control module. The initial path planning module is used to calculate the path spacing through the spray width and the overlap coefficient; the droplet movement evaluation module is used to evaluate the droplet sedimentation speed through the initial diameter and mass of the droplets; the droplet evaporation module is used to evaluate the droplet evaporation effect through environmental data and droplet diameter; the drift evaluation module is used to evaluate the horizontal drift distance of the droplets through the crosswind speed and sedimentation time; the flight altitude correction module is used to adjust the flight altitude of the drone through the horizontal drift data of the droplets and the droplet diameter after sedimentation; the path correction module is used to adjust the flight path of the drone through the real-time spray width; the dosage control module is used to evaluate the drug spraying dosage of each grid through the pest and disease degree of each grid.

[0029] Embodiment 3 This embodiment provides an electronic device, including: a processor and a memory, wherein, a computer program that can be called by the processor is stored in the memory; The processor executes the above-mentioned agricultural drone operation path planning method based on the Internet of Things by calling the computer program stored in the memory.

[0030] This electronic device may have relatively large differences due to different configurations or performances, and can include one or more processors (Central Processing Units, CPUs) and one or more memories. Among them, at least one computer program is stored in the memory, and this computer program is loaded and executed by the processor to implement the agricultural drone operation path planning method provided by the above method embodiment. This electronic device can also include other components for implementing device functions. For example, this electronic device can also have components such as wired or wireless network interfaces and input / output interfaces for data input and output. This embodiment will not be elaborated here.

[0031] Embodiment 4 This embodiment proposes a computer-readable storage medium, on which a rewritable computer program is stored; When the computer program runs on a computer device, it causes the computer device to execute the above-mentioned agricultural drone operation path planning method based on the Internet of Things.

[0032] For example, a computer-readable storage medium can be a Read-Only Memory (ROM for short), a Random Access Memory (RAM for short), a Compact Disc Read-Only Memory (CD-ROM for short), magnetic tape, floppy disk, optical data storage device, etc.

[0033] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions according to the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that the computer can access or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

Claims

1. The path planning method for agricultural drone based on the Internet of Things is characterized by: It includes the following specific steps: Construct an initial path planning model, import the spray width and overlap coefficient into the initial path planning model to calculate the path spacing; Construct a droplet motion model, and import the initial droplet diameter and mass into the droplet motion model to evaluate the droplet settling velocity; Construct a droplet evaporation and drift model, import environmental data, droplet diameter and settling velocity into the droplet evaporation and drift model to evaluate the droplet evaporation effect and droplet horizontal drift distance; Construct a UAV flight altitude and path correction model, import the precipitation droplet data and real-time spray width into the UAV flight altitude and path correction model to adjust the UAV flight altitude and path; A dosage control model was constructed, and the degree of pests and diseases in each grid was imported into the dosage control model to evaluate the drug spraying dosage of each grid.

2. The method for planning the path of an agricultural UAV based on the Internet of Things according to claim 1, characterized in that: The construction of the initial path planning model and the importation of the spray width and the overlap coefficient into the initial path planning model to calculate the path spacing include the following specific steps: The UAV operation area is set through the electronic map, and the operation area is rasterized into The grid diagram is used to calculate the spacing G between adjacent paths according to the nozzle spray width and the overlap coefficient; Obtain historical flight parameters and paths, obtain obstacle grid data through historical flight data, mark the obstacle grids in the operating area, use the A* algorithm to perform initial path planning in the grid, generate a set of flight path coordinate points from the starting point to the end point of the drone, and assign flight altitude values ​​to each grid.

3. The method for agricultural UAV operation path planning based on the Internet of Things as claimed in claim 2, characterized in that: The construction of the droplet motion model and the introduction of the initial droplet diameter and mass into the droplet motion model to evaluate the droplet settling velocity include the following specific steps: The real-time wind speed and direction are obtained through the wind speed and direction sensor, the parameters of the drone nozzle are obtained, and the droplet mass is substituted into the droplet motion equation to calculate the droplet settling speed, where the droplet motion equation is: , where m is the mass of the droplet, g is the acceleration of gravity, ρ is the air density, C is the air resistance coefficient, A is the windward area of ​​the droplet, and v is the droplet velocity. The droplet mass calculation formula is: , the calculation formula for the windward area of ​​the droplet is: ,in, is the pesticide density, is the initial droplet diameter, and the droplet settling velocity is calculated as: .

4. The method for planning the path of an agricultural UAV based on the Internet of Things as claimed in claim 3, characterized in that: The construction of the droplet evaporation and drift model, importing environmental data, droplet diameter and settling velocity into the droplet evaporation and drift model to evaluate the droplet evaporation effect and droplet horizontal drift distance includes the following specific steps: Obtain the ambient humidity and temperature, substitute the initial droplet diameter and environmental parameters into the droplet diameter calculation formula to calculate the droplet diameter after a period of time. The droplet diameter calculation formula at time t is: , where K is the evaporation coefficient, and the calculation formula of the evaporation coefficient is: ,in, is latent heat, D is water vapor diffusion coefficient, c is air specific heat capacity, P is saturated vapor pressure, T is ambient temperature, RH is relative humidity of air; Substitute the crosswind speed into the calculation formula of the horizontal drift distance of the droplets to calculate the horizontal drift distance of the droplets, where the calculation formula of the horizontal drift distance of the droplets is: ,in, is the crosswind speed, is the sedimentation time, where the calculation formula for the sedimentation time is: ,in, is the height of crops in the grid, is the flight altitude within the grid.

5. The method for planning the path of an agricultural UAV based on the Internet of Things as claimed in claim 4, characterized in that: The construction of the UAV flight altitude and path correction model, importing the precipitation droplet data and the real-time spray width into the UAV flight altitude and path correction model to adjust the UAV flight altitude and path includes the following specific steps: Substitute the droplet horizontal drift data and the droplet diameter after settling into the height adjustment formula to adjust the UAV flight height. The height adjustment formula is: ,in, is the adjusted flight height of the ith grid, Offset flight altitude adjustment for the grid, is the grid spray diameter flight height adjustment, where the grid offset flight height adjustment calculation formula is: , where d max is the maximum distance of horizontal drift of droplets. Substitute the settling time into the droplet diameter calculation formula to calculate the droplet diameter after settling. Compare the droplet diameter after settling with the droplet diameter spraying threshold. If it is within the threshold range, fly at the original height. If it is not within the threshold range, adjust the height. The calculation formula for the grid spray diameter flight height adjustment is: ,in, is the spraying threshold of droplet diameter; Substitute the adjusted flight height into the real-time spray width calculation formula to calculate the real-time spray width, where the real-time spray width calculation formula is: , according to the preset overlap coefficient, the flight path grid spacing is automatically adjusted, where the flight path grid spacing adjustment formula is: ,in, Fixed atomization angle for the nozzle. is the overlap coefficient, and the flight path is offset by the same distance in the crosswind direction. The calculation formula of the horizontal coordinate after the offset is: , is the horizontal coordinate of the center of the i-th unit grid.

6. The method for agricultural UAV operation path planning based on the Internet of Things as claimed in claim 5, characterized in that: The construction of the dosage control model and the introduction of the pest and disease degree of each grid into the dosage control model to evaluate the drug spraying dosage of each grid include the following specific steps: The crop images are collected by the camera carried by the drone, and the crop images taken by each grid are imported into the pre-trained image model to output the pest and disease score value. The pest and disease score value is substituted into the spray dosage calculation formula to calculate the spray dosage. The spray dosage calculation formula of the grid is: ,in, The lowest dose of the drug, The highest dose of the drug, Give the grid pest and disease score value; Substitute the spraying dosage into the UAV spraying flow rate calculation formula to calculate the UAV spraying flow rate per unit time. The UAV spraying flow rate calculation formula is: , where V is the flight speed of the drone, and the flow rate of each grid is adjusted by adjusting the opening of the nozzle valve.

7. An agricultural UAV operation path planning system based on the Internet of Things, which is implemented based on the agricultural UAV operation path planning method based on the Internet of Things as claimed in any one of claims 1 to 6, characterized in that: Specifically include: The initial path planning module is used to calculate the path spacing by spray width and overlap coefficient; The droplet motion evaluation module is used to evaluate the droplet settling velocity based on the initial droplet diameter and mass; The droplet evaporation module is used to evaluate the droplet evaporation effect through environmental data and droplet diameter; Drift assessment module, used to assess the horizontal drift distance of droplets based on crosswind speed and settling time; The flight altitude correction module is used to adjust the flight altitude of the drone based on the horizontal drift data of the droplets and the diameter of the droplets after settling; Path correction module, used to adjust the flight path of the drone through real-time spray width; The dosage control module is used to evaluate the drug spraying dosage of each grid according to the degree of pests and diseases in each grid.

8. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; It is characterized in that the processor executes the agricultural drone operation path planning method based on the Internet of Things as described in any one of claims 1 to 6 by calling the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes the agricultural UAV operation path planning method based on the Internet of Things as described in any one of claims 1-6.

Images