Multi-agent management system and method for collaborative operation of robot and unmanned aerial vehicle

Abstract

The invention discloses a multi-agent management system and method for collaborative operation of a robot and an unmanned aerial vehicle, relates to the technical field of multi-agent management, and solves the technical problems that the prior art lacks collaborative operation capability and is not accurate enough in pest and disease damage identification result. Image data of crops and corresponding environment data are collected through the unmanned aerial vehicle; recognizing the image data of the crops collected in real time based on the trained disease and pest recognition model; constructing a correction model based on the environmental data, and correcting the identified initial pest and disease coverage rate to obtain a target pest and disease coverage rate; the pesticide spraying amount of the pesticide spraying robot is calculated based on the target disease and pest coverage rate; obtaining an optimal path of the pesticide spraying robot through a path planning algorithm; and moving to the disease and insect pest coverage area based on the optimal path, and spraying pesticide to the disease and insect pest coverage area based on the pesticide spraying amount, so that the technical problem is solved.

Description

Technical Field

[0001] The present invention belongs to the field of multi-agent management, and specifically relates to a multi-agent management system and method for collaborative operation of robots and unmanned aerial vehicles (UAVs). Background Art

[0002] In modern agriculture, pest control is an important link to ensure the health and high yield of crops. Traditional pest control methods rely on manual inspections and manual spraying of pesticides, which have significant problems: manual inspections are time-consuming and laborious and it is difficult to comprehensively cover large areas of farmland; manual spraying is prone to uneven spraying, resulting in over-spraying or under-spraying in some areas; the accuracy of manual pest identification is low, and it is easy to miss inspections or make misjudgments.

[0003] Existing technologies mainly use image recognition technology to identify pests and diseases, and monitor and spray pesticides on crops through a single agent (such as a UAV or a pesticide spraying robot). However, a single agent (such as a UAV or a pesticide spraying robot) can usually only complete specific tasks (such as image acquisition or spraying), lacks the ability of collaborative operation, and cannot give full play to their respective advantages. At the same time, although existing technologies can identify pests and diseases, they do not sufficiently consider the influence of environmental factors such as light intensity and air quality, resulting in inaccurate identification results and affecting the formulation of subsequent control strategies.

[0004] Therefore, the present invention proposes a multi-agent management system and method for collaborative operation of robots and UAVs to solve the above problems. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art. For this purpose, the present invention proposes a multi-agent management system and method for collaborative operation of robots and UAVs, which is used to solve the technical problems that a single agent can usually only complete specific tasks, lacks the ability of collaborative operation, cannot give full play to their respective advantages, and at the same time, although existing technologies can identify pests and diseases, they do not sufficiently consider the influence of environmental factors such as light intensity and air quality, resulting in inaccurate identification results and affecting the formulation of subsequent control strategies.

[0006] To achieve the above object, the first aspect of the present invention provides a multi-agent management system for collaborative operation of robots and UAVs, including: a data acquisition module, a data analysis module, and a multi-agent management module.

[0007] The data acquisition module: is used to collect image data of crops and corresponding environmental data in real time.

[0008] The data analysis module: trains an artificial intelligence model based on historical image data to obtain a pest and disease identification model; identifies the image data of crops collected in real time based on the pest and disease identification model to obtain an initial pest and disease coverage rate; and

[0009] Construct a correction model based on environmental data, and correct the initial pest and disease coverage rate to obtain the target pest and disease coverage rate;

[0010] Multi-agent management module: Calculate the pesticide spraying amount of the pesticide spraying robot based on the target pest and disease coverage rate; Obtain the optimal path of the pesticide spraying robot to the pest and disease coverage area through the path planning algorithm; and,

[0011] Move to the pest and disease coverage area based on the optimal path, and spray pesticides on the pest and disease coverage area based on the pesticide spraying amount.

[0012] Preferably, the real-time acquisition of the image data of the crops and the corresponding environmental data includes:

[0013] Divide the farmland into several sub-regions according to a preset ratio; among them, several sub-regions are all rectangles;

[0014] Real-time collect the images of the crops in the sub-regions through the image acquisition device installed on the drone;

[0015] Real-time collect the environmental data of the farmland through the data sensor; among them, the environmental data includes: light intensity and air quality index.

[0016] It should be noted that the preset ratio is set according to the resolution and clarity of the image acquisition device to ensure that the images of the crops in the collected sub-regions are clear.

[0017] Preferably, the training of the artificial intelligence model based on the historical image data includes:

[0018] Extract the images of the crops in the sub-regions from the historical image data;

[0019] Based on the images of the crops in the sub-regions of the historical image data, obtain the coverage rate of pests and diseases in the corresponding crops in the sub-regions by manual marking, and mark the coverage rate of pests and diseases in the sub-regions as the pest and disease coverage rate;

[0020] Integrate the images of the crops in the sub-regions of the historical image data into standard input data; Integrate the pest and disease coverage rates corresponding to the images of the crops in the sub-regions of the historical image data into standard output data; Train the artificial intelligence model based on the standard input data and the standard output data to obtain a pest and disease recognition model; among them, the artificial intelligence model includes: YOLO model or deep belief network.

[0021] Preferably, the recognition of the real-time collected image data of the crops based on the pest and disease recognition model includes:

[0022] Extract the images of the crops in the sub-regions collected in real time;

[0023] The images of crops in the sub-region collected in real time are identified by the pest and disease identification model to obtain the pest and disease coverage rate corresponding to the images of crops in the sub-region collected in real time, and the pest and disease coverage rate corresponding to the images of crops in the sub-region collected in real time is marked as the initial pest and disease coverage rate.

[0024] Preferably, constructing a correction model based on environmental data and correcting the initial pest and disease coverage rate includes:

[0025] Mark the light intensity as G and the air quality index as K;

[0026] Taking the light intensity and the air quality index as independent variables; taking the corrected pest and disease coverage rate as the dependent variable, and marking it as the target pest and disease coverage rate MP;

[0027] The independent variables and the dependent variable are fitted by polynomial fitting to establish a correction model; where the correction model is specifically: MP = CP × [1 + α / [e^(G / (G + 1))] + β × e^(K / (K + 1))], α and β are proportionality coefficients, and CP is the initial pest and disease coverage rate;

[0028] For the proportionality coefficient α: if G < Gmin or G > Gmax, then 0 < α < 1; if Gmin ≤ G ≤ Gmax, then -1 < α < 0; where Gmin is the minimum value of the optimal light intensity range of the crops, and Gmax is the maximum value of the optimal light intensity range of the crops;

[0029] For the proportionality coefficient β: if K ≤ YK, then -1 < β < 0; if K > YK, then 0 < β < 1; where YK is the preset air quality index threshold;

[0030] Extract the initial pest and disease coverage rate output by the pest and disease identification model, and input the initial pest and disease coverage rate into the correction model to obtain the target pest and disease coverage rate.

[0031] It should be noted that the proportionality coefficient is set by experts in the field according to experience; the preset air quality index threshold is set by experts in the field according to the average value of the air quality index at the acquisition moment corresponding to the image data in the training data of the pest and disease identification model;

[0032] Light intensity has a significant impact on the health of crops and the coverage rate of pests and diseases; when the light intensity is lower than the optimal light intensity, the photosynthesis efficiency of plants decreases, the growth is slow, the stress resistance weakens, and it is easy to be invaded by fungi, bacteria and pests, resulting in an increase in the coverage rate of pests and diseases; when the light intensity exceeds the optimal light intensity, plants will suffer from photoinhibition and photo-damage, the leaf temperature rises, causing a heat stress response, and the damaged tissues are more likely to be infected by pathogens and attract pests, which will also lead to an increase in the coverage rate of pests and diseases; the higher the air quality index, the more serious the air pollution, and the pollutants will damage plants, reduce their photosynthesis efficiency and disease resistance, making plants more vulnerable to pests and diseases, thus leading to an increase in the coverage rate of pests and diseases; on the contrary, fresh air helps the normal growth and metabolism of plants and enhances their pest and disease resistance ability.

[0033] Preferably, calculating the spraying amount of the pesticide spraying robot based on the target pest and disease coverage rate includes:

[0034] Extracting the total area of the sub-region and the corresponding target pest and disease coverage rate;

[0035] Calculating the actual spraying area by multiplying the total area of the sub-region and the corresponding target pest and disease coverage rate;

[0036] Calculating the spraying amount of each sub-region containing pests and diseases by multiplying the spraying amount per unit area and the actual spraying area.

[0037] Preferably, obtaining the optimal path of the pesticide spraying robot to the pest and disease coverage area through the path planning algorithm includes:

[0038] Constructing a planar two-dimensional model of the farmland through a modeling software, and constructing a planar rectangular coordinate system with the center point of the farmland as the origin in the planar two-dimensional model of the farmland;

[0039] Obtaining the positions of the pesticide spraying robot and the target sub-region, and marking them as position information; wherein, the target sub-region refers to the sub-region containing pests and diseases;

[0040] Based on the position information, obtaining the optimal path of the pesticide spraying robot to the target sub-region through the path planning algorithm; wherein, the path planning algorithm includes: A* algorithm or Dijkstra algorithm.

[0041] Preferably, obtaining the positions of the pesticide spraying robot and the target sub-region includes:

[0042] Obtaining the current position of the pesticide spraying robot through the GPS device installed on the pesticide spraying robot, and mapping it to the rectangular coordinate system on the planar two-dimensional model of the farmland to obtain the position coordinates of the pesticide spraying robot;

[0043] Extract the coordinate points of the four vertices of the target sub-region in the rectangular coordinate system on the two-dimensional plane model of the farmland, and mark them as the vertex coordinates of the target sub-region;

[0044] Integrate the position coordinates of the pesticide spraying robot and the vertex coordinates of the target sub-region into position information.

[0045] Preferably, moving to the pest coverage area based on the optimal path and spraying pesticides on the pest coverage area based on the spraying amount, including:

[0046] The pesticide spraying robot moves to the vertex position of the nearest target sub-region based on the optimal path;

[0047] Obtain the area covered by pests in the target sub-region based on computer vision technology; wherein, the computer vision technology includes: edge detection or color segmentation;

[0048] Extract the calculated spraying amount of the target sub-region, and spray pesticides on the area covered by pests in the target sub-region based on the spraying amount of the target sub-region.

[0049] The second aspect of the present invention provides a multi-agent management method for collaborative operation of robots and drones, including:

[0050] Step 1: Real-time collect image data of crops and corresponding environmental data;

[0051] Step 2: Train an artificial intelligence model based on historical image data to obtain a pest identification model; identify the real-time collected image data of crops based on the pest identification model to obtain an initial pest coverage rate;

[0052] Step 3: Construct a correction model based on the environmental data and correct the initial pest coverage rate to obtain a target pest coverage rate;

[0053] Step 4: Calculate the spraying amount of the pesticide spraying robot based on the target pest coverage rate;

[0054] Step 5: Obtain the optimal path of the pesticide spraying robot to the pest coverage area through a path planning algorithm;

[0055] Step 6: Move to the pest coverage area based on the optimal path and spray pesticides on the pest coverage area based on the spraying amount.

[0056] Compared with the prior art, the beneficial effects of the present invention are:

[0057] 1. The present invention obtains high-resolution images and environmental data of crops in real time by using drones, and accurately locates them through GPS devices installed on pesticide spraying robots, ensuring full coverage of large areas of farmland and reducing the time and cost of manual inspections. Secondly, through an artificial intelligence model, the collected images are automatically recognized to obtain the initial pest and disease coverage rate, and a correction model is constructed in combination with environmental factors to further improve the recognition accuracy, solving the problem that although the prior art can identify pests and diseases, it insufficiently considers the influence of environmental factors such as light intensity and air quality, resulting in inaccurate recognition results and affecting the formulation of subsequent prevention and control strategies. Based on the target pest and disease coverage rate, the actual amount of pesticide sprayed in each sub-region is calculated to ensure precise spraying, avoid overuse of pesticides, and reduce resource waste and environmental pollution.

[0058] 2. The present invention calculates the amount of pesticide sprayed by the pesticide spraying robot based on the target pest and disease coverage rate. By extracting the total area of the sub-region and the corresponding target pest and disease coverage rate, the actual pesticide spraying area is calculated, and combined with the amount of pesticide sprayed per unit area, the amount of pesticide sprayed in each sub-region is accurately determined, ensuring the precise application of pesticides and avoiding the problems of over-spraying or under-spraying, thereby reducing resource waste and environmental pollution. Secondly, the optimal path from the pesticide spraying robot to the pest and disease coverage area is obtained through a path planning algorithm. A planar two-dimensional model of the farmland is constructed using modeling software, and a rectangular coordinate system is established with the center point of the farmland as the origin to accurately locate the position information of the pesticide spraying robot and the target sub-region, ensuring the accuracy of path planning. The path is optimized through the path planning algorithm, improving the movement efficiency of the pesticide spraying robot and reducing unnecessary movement time and energy consumption. In addition, the real-time position of the pesticide spraying robot is obtained through a GPS device and mapped onto the planar two-dimensional model, combined with the vertex coordinates of the target sub-region, realizing the accurate integration of position information, further enhancing the reliability and operation of the system, not only greatly improving the accuracy and efficiency of pest and disease control, but also effectively reducing labor costs and environmental burdens, providing an efficient and intelligent solution for modern agriculture. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0060] Figure 1 It is a schematic diagram of the system module of the embodiment of the present invention;

[0061] Figure 2 It is a schematic diagram of the specific process of the embodiment of the present invention. Detailed implementation mode

[0062] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative work belong to the protection scope of the present invention.

[0063] Please refer to Figure 1 - Figure 2 , an embodiment of the first aspect of the present invention provides a multi-agent management system for collaborative operation of a robot and a drone, including: a data acquisition module, a data analysis module, and a multi-agent management module;

[0064] The data acquisition module: is used to collect the image data of the crops and the corresponding environmental data in real time;

[0065] The data analysis module: trains an artificial intelligence model based on historical image data to obtain a pest and disease identification model; identifies the image data of the crops collected in real time based on the pest and disease identification model to obtain an initial pest and disease coverage rate; and constructs a correction model based on the environmental data and corrects the initial pest and disease coverage rate to obtain a target pest and disease coverage rate;

[0066] The multi-agent management module: calculates the spraying amount of the pesticide spraying robot based on the target pest and disease coverage rate; obtains the optimal path of the pesticide spraying robot to the pest and disease coverage area through a path planning algorithm; and moves to the pest and disease coverage area based on the optimal path and sprays pesticides on the pest and disease coverage area based on the spraying amount.

[0067] Collecting the image data of the crops and the corresponding environmental data in real time includes:

[0068] Dividing the farmland into several sub-regions according to a preset ratio; among them, several sub-regions are all rectangles;

[0069] Collecting the images of the crops in the sub-regions in real time through the image acquisition device installed on the drone;

[0070] Collecting the environmental data of the farmland in real time through a data sensor; among them, the environmental data includes: light intensity and air quality index.

[0071] Training the artificial intelligence model based on the historical image data includes:

[0072] Extracting the crop images in the sub-regions from the historical image data;

[0073] Based on the crop images in the sub-regions of historical image data, obtain the coverage rate of pests and diseases in the sub-regions of the corresponding crop images through manual marking, and mark the coverage rate of pests and diseases in the sub-regions as the pest and disease coverage rate;

[0074] Integrate the crop images in the sub-regions of historical image data into standard input data; integrate the pest and disease coverage rates corresponding to the crop images in the sub-regions of historical image data into standard output data; train an artificial intelligence model based on the standard input data and the standard output data to obtain a pest and disease recognition model; among them, the artificial intelligence model includes: YOLO model or deep belief network.

[0075] Based on the pest and disease recognition model, identify the image data of the crops collected in real time, including:

[0076] Extract the images of the crops in the sub-regions collected in real time;

[0077] Through the pest and disease recognition model, identify the images of the crops in the sub-regions collected in real time, obtain the pest and disease coverage rate corresponding to the images of the crops in the sub-regions collected in real time, and mark the pest and disease coverage rate corresponding to the images of the crops in the sub-regions collected in real time as the initial pest and disease coverage rate.

[0078] Based on the environmental data, construct a correction model and correct the initial pest and disease coverage rate, including:

[0079] Mark the light intensity as G and the air quality index as K;

[0080] Take the light intensity and the air quality index as independent variables; take the corrected pest and disease coverage rate as the dependent variable and mark it as the target pest and disease coverage rate MP;

[0081] Through polynomial fitting, fit the independent variables and the dependent variable to establish a correction model; among them, the correction model is specifically: MP = CP × [1 + α / [e ^ (G / (G + 1))] + β × e ^ (K / (K + 1))], where α and β are proportionality coefficients, and CP is the initial pest and disease coverage rate;

[0082] For the proportionality coefficient α: if G < Gmin or G > Gmax, then 0 < α < 1; if Gmin ≤ G ≤ Gmax, then -1 < α < 0; where Gmin is the minimum value of the optimal light intensity range of the crops, and Gmax is the maximum value of the optimal light intensity range of the crops;

[0083] For the proportionality coefficient β: if K ≤ YK, then -1 < β < 0; if K > YK, then 0 < β < 1; where YK is the preset air quality index threshold;

[0084] Extract the initial pest and disease coverage rate output by the pest and disease recognition model, and input the initial pest and disease coverage rate into the correction model to obtain the target pest and disease coverage rate.

[0085] Calculate the pesticide spraying amount of the pesticide spraying robot based on the target pest and disease coverage rate, including:

[0086] Extract the total area of the sub-region and the corresponding target pest and disease coverage rate;

[0087] Obtain the actual spraying area by calculating the product of the total area of the sub-region and the corresponding target pest and disease coverage rate;

[0088] Obtain the pesticide spraying amount of each sub-region containing pests and diseases by calculating the product of the pesticide spraying amount per unit area and the actual spraying area.

[0089] Obtain the optimal path of the pesticide spraying robot to the pest and disease coverage area through the path planning algorithm, including:

[0090] Construct a planar two-dimensional model of the farmland through modeling software, and construct a planar rectangular coordinate system with the center point of the farmland as the origin in the planar two-dimensional model of the farmland;

[0091] Obtain the positions of the pesticide spraying robot and the target sub-region, and mark them as position information; among them, the target sub-region refers to the sub-region containing pests and diseases;

[0092] Based on the position information, obtain the optimal path of the pesticide spraying robot to the target sub-region through the path planning algorithm; among them, the path planning algorithm includes: A* algorithm or Dijkstra algorithm.

[0093] Obtain the positions of the pesticide spraying robot and the target sub-region, including:

[0094] Obtain the current position of the pesticide spraying robot through the GPS device installed on the pesticide spraying robot, and map it to the rectangular coordinate system on the planar two-dimensional model of the farmland to obtain the position coordinates of the pesticide spraying robot;

[0095] Extract the coordinate points of the four vertices of the target sub-region in the rectangular coordinate system on the planar two-dimensional model of the farmland, and mark them as the vertex coordinates of the target sub-region;

[0096] Integrate the position coordinates of the pesticide spraying robot and the vertex coordinates of the target sub-region into position information.

[0097] Move to the pest and disease coverage area based on the optimal path, and spray pesticides on the pest and disease coverage area based on the pesticide spraying amount, including:

[0098] The pesticide spraying robot moves to the vertex position of the nearest target sub-region based on the optimal path;

[0099] Obtain the area covered by pests and diseases in the target sub-region based on computer vision technology; wherein, the computer vision technology includes: edge detection or color segmentation;

[0100] Extract the amount of pesticide spraying for the calculated target sub-region, and spray pesticides on the area covered by pests and diseases in the target sub-region based on the amount of pesticide spraying in the target sub-region.

[0101] For example: Suppose there is a large farmland of 1 hectare that needs pest and disease control; in order to achieve efficient and precise pest and disease control, a multi-agent management system and method for collaborative operation of a robot and a drone proposed by the present invention will be used, specifically as follows:

[0102] 1. Data acquisition module;

[0103] Step 1: Divide the farmland into sub-regions;

[0104] Divide the farmland into several rectangular sub-regions according to a preset ratio, and the area of each sub-region is 10 square meters.

[0105] Use a drone equipped with a high-resolution camera to collect image data of crops in each sub-region in real time, and collect environmental data (such as light intensity and air quality index) in real time through sensors.

[0106] Example data:

[0107] Total number of sub-regions: 1000;

[0108] Area of each sub-region: 10 square meters;

[0109] Light intensity: 60000 lux;

[0110] Air quality index: 100;

[0111] 2. Data analysis module;

[0112] Step 2: Train the artificial intelligence model;

[0113] Based on the historical image data (including pest and disease markings) and corresponding environmental data accumulated in the past few years, use the YOLO model for training to obtain a preliminary pest and disease recognition model;

[0114] Extract the sub-region crop images in the historical image data, and obtain the corresponding pest and disease coverage rate through manual marking.

[0115] Integrate the historical image data into standard input data, and integrate the pest and disease coverage rate into standard output data, and train the YOLO model as the pest and disease recognition model.

[0116] Step 3: Identify pests and diseases and correct the coverage rate;

[0117] Use the trained YOLO model to identify the crop images in the sub-region collected in real time, and obtain the initial pest and disease coverage rate.

[0118] Construct a correction model by combining the light intensity and the air quality index to further improve the recognition accuracy.

[0119] Example data:

[0120] Initial pest and disease coverage rate: 50%;

[0121] Light intensity: 60000 lux;

[0122] Air quality index: 100;

[0123] Assume that the preset air quality index threshold is 70;

[0124] Since the air quality index K (100) is greater than the preset air quality index threshold YK (70), then 0 < β < 1;

[0125] Assume that the optimal light intensity range for the crop is 40000 lux to 50000 lux; then the minimum value Gmin of the optimal light intensity range for the crop is 40000 lux, and the maximum value Gmax of the optimal light intensity range for the crop is 50000 lux;

[0126] Since the light intensity G (60000 lux) is greater than the maximum value Gmax (50000 lux) of the optimal light intensity range for the crop, the value range of the proportionality coefficient α is 0 < α < 1;

[0127] Correction model formula: MP = CP × [1 + α / [e ^ (G / (G + 1))] + β × e ^ (K / (K + 1))];

[0128] Assume that the proportionality coefficient α = 0.5 and β = 0.06;

[0129] Calculate the target pest and disease coverage rate: Substitute the data to get MP ≈ 67.25%;

[0130] 3. Multi-agent management module;

[0131] Step 4: Calculate the amount of pesticide spraying;

[0132] Extract the total area of the sub-region and the corresponding target pest and disease coverage rate, and calculate the actual pesticide spraying area.

[0133] Combine the amount of pesticide spraying per unit area (assuming 0.5 liters of pesticide is required per square meter) to calculate the amount of pesticide spraying for each sub-region.

[0134] Example data:

[0135] Sub - area area: 10 square meters;

[0136] Target pest coverage rate: 67.25%;

[0137] Pesticide spraying amount per unit area: 0.5 liters / square meter;

[0138] Actual spraying area: 10 square meters × 67.25% = 6.725 square meters;

[0139] Total spraying amount: 6.725 square meters × 0.5 liters / square meter = 3.3625 liters;

[0140] Step 5: Path planning;

[0141] Construct a two - dimensional planar model of the farmland and establish a rectangular coordinate system with the center point of the farmland as the origin.

[0142] Obtain the position information of the pesticide spraying robot and the target sub - area, and use the A* algorithm or Dijkstra algorithm to calculate the optimal path.

[0143] Example data:

[0144] Coordinates of the center point of the farmland: (0, 0);

[0145] Current position coordinates of the pesticide spraying robot: (500, 500);

[0146] Vertex coordinates of the target sub - area: (1000, 1000), (1000, 1100), (1100, 1000), (1100, 1100);

[0147] The optimal path is calculated by the A* algorithm;

[0148] Step 6: Movement and spraying;

[0149] The pesticide spraying robot moves to the position of the vertex of the target sub - area closest to it based on the optimal path.

[0150] Use computer vision technology (such as edge detection or color segmentation) to obtain the specific areas covered by pests and diseases in the target sub - area, and perform precise spraying according to the calculated spraying amount (3.3625 liters).

[0151] As can be seen from the above examples, the present invention automatically identifies the coverage rate of pests and diseases through a deep learning model (such as YOLO), and constructs a correction model in combination with environmental factors (light intensity and air quality index), improving the recognition accuracy and ensuring the accuracy of subsequent prevention and control strategies; accurately calculates the amount of pesticides sprayed according to the target pest and disease coverage rate and the sub-region area, avoiding the problems of over-spraying or under-spraying, reducing resource waste and environmental pollution; optimizes the moving path of the pesticide spraying robot through the A* or Dijkstra algorithm, reducing unnecessary moving time and energy consumption, and improving the overall operation efficiency; uses drones to collect image data and environmental data in real time, combined with precise positioning by GPS devices, achieving full coverage and automated operation of large areas of farmland, and significantly reducing the time and cost of manual inspections.

[0152] The second aspect of the embodiments of the present invention provides a multi-agent management method for the collaborative operation of robots and drones, including:

[0153] Step 1: Collect image data of crops and corresponding environmental data in real time;

[0154] Step 2: Train an artificial intelligence model based on historical image data to obtain a pest and disease recognition model; identify the real-time collected image data of crops based on the pest and disease recognition model to obtain the initial pest and disease coverage rate;

[0155] Step 3: Construct a correction model based on environmental data and correct the initial pest and disease coverage rate to obtain the target pest and disease coverage rate;

[0156] Step 4: Calculate the amount of pesticides sprayed by the pesticide spraying robot based on the target pest and disease coverage rate;

[0157] Step 5: Obtain the optimal path of the pesticide spraying robot to the pest and disease coverage area through a path planning algorithm;

[0158] Step 6: Move to the pest and disease coverage area based on the optimal path and spray pesticides on the pest and disease coverage area based on the amount of pesticides sprayed.

[0159] Some of the data in the above formula are calculated by removing the dimension and taking their numerical values. The formula is obtained by software simulation of a large amount of collected data to get a formula closest to the real situation; the preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0160] The above embodiments are only used to illustrate the technical method of the present invention and not to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A multi-agent management system for collaborative operation of robots and drones, characterized in that: include: Data collection module, data analysis module, multi-agent management module; Data acquisition module: used to collect image data of crops and corresponding environmental data in real time; Data analysis module: train the artificial intelligence model based on historical image data to obtain the pest and disease recognition model; identify the image data of crops collected in real time based on the pest and disease recognition model to obtain the initial pest and disease coverage rate; as well as, A correction model is constructed based on environmental data, and the initial pest and disease coverage rate is corrected to obtain the target pest and disease coverage rate; Multi-agent management module: calculates the spraying amount of the pesticide spraying robot based on the target pest and disease coverage rate; obtains the optimal path from the pesticide spraying robot to the pest and disease coverage area through the path planning algorithm; and, Move to the pest-covered area based on the optimal path, and spray pesticides on the pest-covered area based on the spraying amount.

2. A multi-agent management system for collaborative operation of robots and drones according to claim 1, characterized in that: The real-time collection of crop image data and corresponding environmental data includes: The farmland is divided into a number of sub-areas according to a preset ratio; wherein the sub-areas are all rectangular; The images of crops in the sub-areas are collected in real time by an image acquisition device mounted on a UAV; The environmental data of farmland is collected in real time through data sensors; the environmental data includes: light intensity and air quality index.

3. A multi-agent management system for collaborative operation of robots and drones according to claim 1, characterized in that: The training of the artificial intelligence model based on historical image data includes: Extracting crop images of sub-regions in historical image data; Based on the crop images of the sub-regions in the historical image data, the coverage rate of pests and diseases in the sub-regions in the corresponding crop images is obtained by manual marking, and the coverage rate of pests and diseases in the sub-regions is marked as the pest and disease coverage rate; The method integrates the crop images of sub-regions in the historical image data as standard input data; integrates the pest and disease coverage rates corresponding to the crop images of sub-regions in the historical image data as standard output data; trains an artificial intelligence model based on the standard input data and the standard output data to obtain a pest and disease recognition model; wherein the artificial intelligence model includes: a YOLO model or a deep belief network.

4. A multi-agent management system for collaborative operation of robots and drones according to claim 1, characterized in that: The method of identifying the crop image data collected in real time based on the pest and disease identification model includes: Extracting images of crops in sub-areas collected in real time; The images of crops in the sub-area collected in real time are recognized by the pest and disease recognition model to obtain the pest and disease coverage rate corresponding to the images of crops in the sub-area collected in real time, and the pest and disease coverage rate corresponding to the images of crops in the sub-area collected in real time is marked as the initial pest and disease coverage rate.

5. A multi-agent management system for collaborative operation of robots and drones according to claim 1, characterized in that: The correction model is constructed based on environmental data, and the initial pest and disease coverage rate is corrected, including: Label the light intensity as G and the air quality index as K; Light intensity and air quality index are used as independent variables; the corrected pest coverage is used as the dependent variable and is marked as target pest coverage MP; The independent variables and dependent variables were fitted by polynomial fitting to establish a correction model; the correction model was specifically: MP = CP × [1 + α / [e^(G / (G+1))] + β × e^(K / (K+1))], α and β are proportional coefficients, and CP is the initial pest and disease coverage rate; For the proportionality coefficient α: if G<Gmin or G>Gmax, then 0<α<1; if Gmin≤G≤Gmax, then -1<α<0; where Gmin is the minimum value of the optimal light intensity range for crops, and Gmax is the maximum value of the optimal light intensity range for crops; For the proportionality coefficient β: if K≤YK, then -1<β<0; if K>YK, then 0<β<1; where YK is the preset air quality index threshold; The initial pest and disease coverage rate output by the pest and disease identification model is extracted, and the initial pest and disease coverage rate is input into the correction model to obtain the target pest and disease coverage rate.

6. A multi-agent management system for collaborative operation of robots and drones according to claim 1, characterized in that: The method of calculating the spraying amount of the pesticide spraying robot based on the target pest and disease coverage rate includes: Extract the total area of ​​the sub-region and the corresponding target pest and disease coverage; The actual spraying area is obtained by calculating the product of the total area of ​​the sub-region and the corresponding target pest and disease coverage rate; The spraying amount for each sub-area containing pests and diseases is obtained by calculating the product of the spraying amount per unit area and the actual sprayed area.

7. A multi-agent management system for collaborative operation of robots and drones according to claim 1, characterized in that: The method of obtaining the optimal path of the pesticide spraying robot to the pest and disease coverage area through a path planning algorithm includes: A two-dimensional plane model of the farmland is constructed by using modeling software, and a plane rectangular coordinate system is constructed in the two-dimensional plane model of the farmland with the center point of the farmland as the origin; Obtain the positions of the pesticide spraying robot and the target sub-area and mark them as position information; wherein the target sub-area refers to the sub-area containing pests and diseases; Based on the position information, the optimal path from the pesticide spraying robot to the target sub-area is obtained through a path planning algorithm; wherein the path planning algorithm includes: A* algorithm or Dijkstra algorithm.

8. A multi-agent management system for collaborative operation of robots and drones according to claim 7, characterized in that: The obtaining of the positions of the pesticide spraying robot and the target sub-area comprises: The current position of the pesticide spraying robot is obtained by using the GPS device installed on the pesticide spraying robot, and is mapped to the rectangular coordinate system on the plane two-dimensional model of the farmland to obtain the position coordinates of the pesticide spraying robot; Extract the coordinate points of the four vertices of the target sub-region in the rectangular coordinate system on the plane two-dimensional model of the farmland, and mark them as the vertex coordinates of the target sub-region; The position coordinates of the pesticide spraying robot and the vertex coordinates of the target sub-area are integrated into the position information.

9. A multi-agent management system for collaborative operation of robots and drones according to claim 1, characterized in that: The moving to the pest-covered area based on the optimal path and spraying pesticides on the pest-covered area based on the spraying amount includes: The pesticide spraying robot moves to the vertex position of the nearest target sub-area based on the optimal path; Obtaining the area covered by pests and diseases in the target sub-area based on computer vision technology; wherein the computer vision technology includes: edge detection or color segmentation; The calculated spraying amount of the target sub-area is extracted, and pesticides are sprayed on the area covered by pests and diseases in the target sub-area based on the spraying amount of the target sub-area.

10. A multi-agent management method for collaborative operation of robots and drones, applied to a multi-agent management system for collaborative operation of robots and drones as claimed in any one of claims 1 to 9, characterized in that: include: Step 1: Collect image data of crops and corresponding environmental data in real time; Step 2: Train an artificial intelligence model based on historical image data to obtain a pest and disease recognition model; identify the image data of crops collected in real time based on the pest and disease recognition model to obtain the initial pest and disease coverage rate; Step 3: Build a correction model based on environmental data and correct the initial pest and disease coverage rate to obtain the target pest and disease coverage rate; Step 4: Calculate the spraying amount of the pesticide spraying robot based on the target pest and disease coverage rate; Step 5: Obtain the optimal path for the pesticide spraying robot to the pest and disease coverage area through a path planning algorithm; Step 6: Move to the pest-covered area based on the optimal path, and spray pesticides on the pest-covered area based on the spraying amount.

Images