Path planning method and device for pesticide spraying equipment, equipment and medium

Abstract

The invention discloses a path planning method, device and equipment for pesticide spraying equipment and a medium, and relates to the technical field of path planning, and the method comprises the steps: obtaining a plurality of to-be-sprayed points and a first path number corresponding to a current farmland; and based on the total path length, the total power consumption of the pesticide spraying equipment and the total pesticide consumption, finding a homeward voyage point of the pesticide spraying equipment and a homeward voyage point of the pesticide spraying equipment to obtain a target path. The method and the device are used for solving the problems of long consumed time, low efficiency and poor applicability of pesticide spraying equipment in the prior art during pesticide spraying, and path planning of the pesticide spraying equipment is realized to adapt to various types of farmlands, so that the pesticide spraying equipment completes pesticide spraying operation at the optimal speed and the optimal consumption.

Description

Technical Field

[0001] The present application relates to the field of path planning technology, and in particular to a path planning method, device, equipment and medium for pesticide spraying equipment. Background Art

[0002] In the existing research on the path planning algorithm of plant protection UAV, the grid method is used to divide the farmland plots, and then the walking strategy of the UAV in the grid plots is designed, so that it can perform full coverage path operations in a reciprocating rotation manner and generate an operation simulation path map. In this process, the pesticide spraying points need to be set manually in advance, and the UAV sprays pesticides based on the pre-set spraying points when walking in the grid plots.

[0003] In addition, during the pesticide spraying process, the drone needs to return several times to load pesticides in order to complete the pesticide spraying of the entire farmland. The existing technology requires that a return point be set on the boundary of the operation area in advance so that the drone can return and reload pesticides after reaching the return point. However, this method is only applicable to small farmland areas and is difficult to adapt to large areas, complex terrain or farmland composed of multiple plots; moreover, the overall operation of this method is time-consuming and inefficient. Summary of the invention

[0004] In response to the above-mentioned problems and technical needs, the applicant has proposed a path planning method, device, equipment and medium for pesticide spraying equipment to solve the problems of long time consumption, low efficiency and poor applicability of pesticide spraying equipment in the prior art when spraying pesticides, and to realize path planning of pesticide spraying equipment to adapt to various types of farmland, so that the pesticide spraying equipment can complete the pesticide spraying operation at the optimal speed and optimal consumption.

[0005] The present application embodiment provides a path planning method for pesticide spraying equipment, the method comprising:

[0006] Acquire a plurality of points to be sprayed and the number of first paths corresponding to the current farmland, wherein the points to be sprayed are obtained by identifying crop growth images;

[0007] Arrange the points to be sprayed, and obtain the first number of initial target paths based on the length of the paths after the arrangement process;

[0008] The following processing is performed for each of the initial target paths:

[0009] Determine the path change probability of the initial target path, and calculate the reference result corresponding to the initial target path based on the order of each to-be-sprayed point in the initial target path; calculate the local target path and the global target path in the current state based on the reference result; update the path change probability based on the local target path and the global target path, and perform mutation processing on the initial target path based on the updated path change probability to obtain a new initial target path;

[0010] The reference result includes: the total path length and influencing conditions of the initial target path, and the influencing conditions include: the total power consumption of the pesticide spraying equipment, the total pesticide consumption, the return point of the pesticide spraying equipment, and the return point of the pesticide spraying equipment;

[0011] After each of the initial target paths executes the processing procedure for a preset number of times, a final global target path is determined based on the reference result.

[0012] According to a path planning method for pesticide spraying equipment according to an embodiment of the present application, each of the points to be sprayed is arranged, and based on the length of the path after the arrangement, the first number of initial target paths is obtained, including:

[0013] Arranging the points to be sprayed to obtain a plurality of spraying paths to be determined;

[0014] Performing mutation processing on the spraying paths to be determined to obtain multiple new spraying paths to be determined, and merging the spraying paths to be determined to obtain multiple spraying paths to be processed;

[0015] The path length of each of the to-be-processed spraying paths is calculated, and the to-be-processed spraying paths having the first number of paths whose path lengths are less than the preset path lengths are determined as the initial target paths.

[0016] According to a path planning method for pesticide spraying equipment according to an embodiment of the present application, after calculating the path length of each of the spraying paths to be processed, the method further includes:

[0017] Determine the number of second paths of the spraying path to be processed whose path length is less than the preset path length;

[0018] In the case where it is determined that the number of the second paths is less than the number of the first paths, performing the step of performing mutation processing on the spraying paths to be determined to obtain a plurality of new spraying paths to be determined;

[0019] In the case where it is determined that the second path number is greater than or equal to the first path number, the step of determining the to-be-processed spraying paths of the first path number whose path lengths are less than a preset path length as the initial target paths is performed.

[0020] According to an embodiment of the present application, the path planning method for pesticide spraying equipment further includes:

[0021] The step of performing mutation processing on the spraying path to be determined to obtain a plurality of new spraying paths to be determined is performed to obtain a new global target path;

[0022] When it is determined that the number of consecutive predictions of the new global target path does not change, the new global target path is determined as the final global target path.

[0023] According to a path planning method for pesticide spraying equipment according to an embodiment of the present application, when it is determined that the number of consecutive predictions of the new global target path does not change, the new global target path is determined as the final global target path, including:

[0024] When it is determined that the number of continuous predictions of the new global target path does not change, determining whether the number of iterations reaches a preset number of iterations;

[0025] When it is determined that the number of iterations reaches the preset number of iterations, determining the new global target path as the final global target path;

[0026] When it is determined that the number of iterations has not reached the preset number of iterations, the step of performing the following processing on each of the initial target paths is performed until the number of iterations reaches the preset number of iterations and a final global target path is obtained.

[0027] According to a path planning method for pesticide spraying equipment according to an embodiment of the present application, until the number of iterations reaches the preset number of iterations and a final global target path is obtained, the method includes:

[0028] In the process of determining that the number of iterations reaches the preset number of iterations, there is no situation where the number of consecutive predictions of the new global target path does not change, and the final global target path is determined from the new global target path based on the reference result.

[0029] According to a path planning method for pesticide spraying equipment in one embodiment of the present application, a plurality of to-be-sprayed points corresponding to the current farmland are obtained, including:

[0030] Obtain multiple crop growth images corresponding to the current farmland;

[0031] Identify the pest and disease situation corresponding to each crop growth image, and determine the specific category of the pest and disease based on the pest and disease situation;

[0032] When the required pesticide is determined, the farmland area corresponding to the crop generated image is determined as the point to be sprayed.

[0033] The present application also provides a path planning device for pesticide spraying equipment, including:

[0034] An acquisition module, used for acquiring a plurality of to-be-sprayed points and the number of first paths corresponding to the current farmland, wherein the to-be-sprayed points are obtained by identifying a crop growth image;

[0035] A first processing module is used to arrange the points to be sprayed, and obtain the first number of initial target paths based on the length of the paths after the arrangement process;

[0036] The second processing module is used to perform the following processing on each of the initial target paths:

[0037] Determine the path change probability of the initial target path, and calculate the reference result corresponding to the initial target path based on the order of each to-be-sprayed point in the initial target path; calculate the local target path and the global target path in the current state based on the reference result; update the path change probability based on the local target path and the global target path, and perform mutation processing on the initial target path based on the updated path change probability to obtain a new initial target path;

[0038] The reference result includes: the total path length and influencing conditions of the initial target path, and the influencing conditions include: the total power consumption of the pesticide spraying equipment, the total pesticide consumption, the return point of the pesticide spraying equipment, and the return point of the pesticide spraying equipment;

[0039] A determination module is used to determine a final global target path based on the reference result after each of the initial target paths executes the processing for a predicted number of times.

[0040] An embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the path planning method for pesticide spraying equipment as described in any one of the above items are implemented.

[0041] An embodiment of the present application also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the path planning method for pesticide spraying equipment as described in any of the above items are implemented.

[0042] The path planning method, device, equipment and medium for pesticide spraying equipment provided in the embodiments of the present application obtain multiple points to be sprayed and the number of first paths corresponding to the current farmland. The spraying points of the present application are obtained by identifying the crop growth image, without manual setting. The spraying points obtained by the present application based on the pest and disease conditions of the crops are more accurate and do not need to consider the type of farmland; furthermore, multiple local target paths are determined based on multiple reference points including the path length, the total power consumption of the pesticide spraying equipment, the total pesticide consumption, the return point of the pesticide spraying equipment and the return point of the pesticide spraying equipment; a global target path is determined based on multiple reference points from the multiple local target paths, and the global target path is obtained by the optimal values ​​of the path length, the total power consumption of the pesticide spraying equipment, the total pesticide consumption, the return point of the pesticide spraying equipment and the return point of the pesticide spraying equipment, so as to ensure that the pesticide spraying equipment completes the pesticide spraying operation at the optimal speed and optimal consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0044] Figure 1 It is one of the flow charts of the path planning method for pesticide spraying equipment provided in the embodiment of the present application;

[0045] Figure 2 This is the second flow chart of the path planning method for pesticide spraying equipment provided in the embodiment of the present application;

[0046] Figure 3 is a structural schematic diagram of a path planning device for a pesticide spraying device provided in an embodiment of the present application;

[0047] Figure 4 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution 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. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] The present application embodiment provides a path planning method for pesticide spraying equipment. The method can be applied to a smart terminal or a server. Some other descriptions in the present application embodiment are for illustrative purposes only and are not intended to limit the scope of protection of the present application. They will not be described one by one. The specific implementation of the method is as follows: Figure 1 As shown:

[0050] Step 101, obtaining a plurality of points to be sprayed and the number of first paths corresponding to the current farmland.

[0051] The points to be sprayed are obtained by identifying crop growth images.

[0052] Step 102: Arrange the points to be sprayed, and obtain a first number of initial target paths based on the path lengths after the arrangement.

[0053] Step 103, performing the following processing on each initial target path: determining the path change probability of the initial target path, and calculating the reference result corresponding to the initial target path based on the order of each to-be-sprayed point in the initial target path; calculating the local target path and the global target path in the current state based on the reference result; updating the path change probability based on the local target path and the global target path, and performing mutation processing on the initial target path based on the updated path change probability to obtain a new initial target path.

[0054] Among them, the reference results include: the total path length and influencing conditions of the initial target path, and the influencing conditions include: the total power consumption of the pesticide spraying equipment, the total pesticide consumption, the return point of the pesticide spraying equipment, and the return point of the pesticide spraying equipment.

[0055] Step 104 , after each initial target path executes the processing process for a preset number of times, a final global target path is determined based on the reference result.

[0056] The path planning method for pesticide spraying equipment provided in the embodiment of the present application obtains multiple points to be sprayed and the number of first paths corresponding to the current farmland. The spraying points of the present application are obtained by identifying the crop growth image, without manual setting. The spraying points obtained by the present application based on the pest and disease conditions of the crops are more accurate and do not need to consider the type of farmland; furthermore, multiple local target paths are determined based on multiple reference points including the path length, the total power consumption of the pesticide spraying equipment, the total pesticide consumption, the return point of the pesticide spraying equipment, and the return point of the pesticide spraying equipment; a global target path is determined based on multiple reference points from the multiple local target paths, and the global target path is obtained through the optimal values ​​of the path length, the total power consumption of the pesticide spraying equipment, the total pesticide consumption, the return point of the pesticide spraying equipment, and the return point of the pesticide spraying equipment, so as to ensure that the pesticide spraying equipment completes the pesticide spraying operation at the optimal speed and optimal consumption.

[0057] In a specific embodiment, obtaining multiple points to be sprayed corresponding to the current farmland includes:

[0058] Acquire multiple crop growth images corresponding to the current farmland; identify the pest and disease situation corresponding to each crop growth image, and determine the specific category of the pest and disease based on the pest and disease situation; when the required pesticides are determined, determine the farmland area corresponding to the crop generation image as the spraying point.

[0059] Among them, pesticide spraying equipment includes drones.

[0060] Specifically, the three-dimensional terrain reconstruction technology is used to accurately obtain the three-dimensional topographic map of the farmland. The camera device is used to take multiple crop growth images based on a preset size. The high-precision pest and disease area recognition technology is used to identify the pest and disease areas in the farmland, which helps the drone to accurately cover the pest and disease areas when spraying pesticides, thereby improving the efficiency and effectiveness of pesticide use.

[0061] Specifically, after identifying the pest and disease areas in the farmland, the target locations (points to be sprayed) where pesticides need to be sprayed are marked.

[0062] Specifically, the goal of this application is to design an efficient path planning strategy given the coordinates of the drone's starting point (i.e., the final return point), a known series of target point coordinates that must be visited (coordinates of the points to be sprayed), the drone's total power reserve, the amount of power consumed per unit flight distance, and the amount of pesticide application required for each target point.

[0063] This strategy needs to ensure that the drone can start from the starting point, visit all designated target points in sequence, and finally return to the starting point, while meeting the dual constraints of power and pesticides, and minimizing the total distance of the entire flight process. In short, this solution aims to solve the optimal path of the drone under the condition of limited power and pesticide resources, so as to achieve efficient and accurate agricultural operation management.

[0064] Given the constant definition:

[0065] A set of coordinates of the spraying points to be traversed P = {p1, p2, ..., p n}.

[0066] The coordinates of the starting point (also the return point) are O.

[0067] The total power reserve of the drone is E total .

[0068] The amount of electricity consumed per unit flight distance w.

[0069] The total amount of pesticides carried by the drone P total .

[0070] The amount of pesticide required for each spraying point p need (same for every point).

[0071] The power consumption of each spraying point w need (same for every point).

[0072] Define the variable:

[0073] x ij : Indicates whether the drone flies from point i to point j, x ij ∈{0,1}.

[0074] d ij : The distance from point i to point j.

[0075] E i : The remaining battery power of the drone when it reaches point i.

[0076] P i : The amount of pesticide remaining when the UAV arrives at point i.

[0077] d j0 : represents the distance from point j to the starting point.

[0078] Set the impact condition:

[0079] Power constraint: When reaching the target point i, determine whether the drone has enough power to fly to the next target point j. If E i <(d j0 +d ij )×w+w need , the drone must return to the starting point to charge and return to the target point j, x i0 With x 0j Set to 1.

[0080] Pesticide constraint: For target point i, if P i <p need , the drone must return to the starting point to replenish pesticides and return to the target point j, x before that. i0 With x 0j Set to 1.

[0081] Each point must be visited once and only once, and the starting point and the end point (return point) are the same.

[0082] Set the objective function, see formula (1):

[0083]

[0084] Where L represents the minimum total flight distance.

[0085] In a specific embodiment, each to-be-sprayed point is arranged, and based on the path length after the arrangement, a first number of initial target paths are obtained, including:

[0086] The points to be sprayed are arranged to obtain a plurality of spray paths to be determined; the spray paths to be determined are mutated to obtain a plurality of new spray paths to be determined, and the spray paths to be determined are merged to obtain a plurality of spray paths to be processed; the path length of each spray path to be processed is calculated, and the spray paths to be processed whose path length is less than the first path number of the preset path length are determined as the initial target paths.

[0087] In a specific embodiment, after calculating the path length of each spray path to be processed, the method further includes:

[0088] Determine the number of second paths of the spraying paths to be processed whose path length is less than the preset path length; when it is determined that the number of second paths is less than the number of first paths, perform a step of mutating the spraying paths to be determined to obtain multiple new spraying paths to be determined; when it is determined that the number of second paths is greater than or equal to the number of first paths, perform a step of determining the spraying paths to be processed whose path length is less than the preset path length of the first path as the initial target path.

[0089] Specifically, the discrete brainstorming algorithm (DBSO) can be used to randomly generate paths, and then the paths can be continuously optimized through mutation and selection mechanisms to find the shortest path.

[0090] Specifically, a spray point set and the first number of paths are input, and each to-be-sprayed point in the spray point set is randomly arranged by DBSO to generate multiple to-be-determined spray paths. A to-be-determined path set and a preset number of mutations are input, and each to-be-determined spray path is mutated, and two points in the to-be-determined spray path are randomly selected for exchange to obtain a new to-be-determined spray path until the number of mutations reaches the preset number of mutations. The path length of each to-be-determined spray path is calculated, and the to-be-determined spray path of the first number of paths whose path length is less than the preset path length is determined as the initial target path.

[0091] Determine the number of second paths of the initial target path at this time, and judge whether the number of second paths is greater than or equal to the number of first paths; if so, arbitrarily select the number of initial target paths with the first path; otherwise, retain the spraying paths to be processed whose path length is less than the preset path length, and return to perform the mutation operation until the number of second paths is greater than or equal to the number of first paths.

[0092] The spraying point set includes: each to-be-sprayed point; the to-be-determined path set includes: multiple to-be-determined spraying paths.

[0093] Specifically, the particle swarm optimization method (PSO) can be used to obtain the global target path. The initial target path set is input, and each initial target path is used as a particle. The local target path is obtained based on the influencing conditions, including: the total power consumption of the local target path, the total pesticide consumption, each return point, and each return point. Then, the global target path is determined from multiple local target paths based on the influencing conditions.

[0094] The initial target path set includes multiple initial target paths.

[0095] In a specific embodiment, obtaining the final global target path based on the reference result further includes:

[0096] The step of performing mutation processing on the spraying path to be determined to obtain multiple new spraying paths to be determined is performed to obtain a new global target path; when the number of consecutive predictions of the new global target path does not change, the new global target path is determined as the final global target path.

[0097] In order to avoid the error caused by an iterative result, after obtaining the global target path, the application returns to execute the mutation processing of the spraying path to be determined, obtains multiple new spraying paths to be determined, and then obtains a new global target path. When the number of consecutive predictions of the new global target path does not change, it is used as the final global target path, thereby ensuring the accuracy of the global target path.

[0098] In a specific embodiment, when it is determined that the number of consecutive predictions of the new global target path does not change, the specific implementation of determining the new global target path as the final global target path includes:

[0099] When it is determined that the number of continuous predictions of the new global target path does not change, determine whether the number of iterations reaches the preset number of iterations; when it is determined that the number of iterations reaches the preset number of iterations, determine the new global target path as the final global target path; when it is determined that the number of iterations does not reach the preset number of iterations, execute the steps of the following processing process for each initial target path until the number of iterations reaches the preset number of iterations and the final global target path is obtained.

[0100] Specifically, in the process of determining the global target path, if the same path is obtained multiple times, stagnation may occur. At this time, the execution returns to perform mutation processing on the spraying path to be determined, and multiple new spraying paths to be determined are obtained, and then a new global target path is obtained. At this time, the iteration continues until the number of iterations reaches the preset number of iterations, thereby ensuring the accuracy of the global target path.

[0101] In a specific embodiment, until the number of iterations reaches a preset number of iterations and the final global target path is obtained, the specific implementation includes:

[0102] In the process of determining that the number of iterations reaches the preset number of iterations, there is no situation where the number of consecutive predictions of the new global target path does not change, and the final global target path is determined from the new global target path based on the reference result.

[0103] Or determine the final global target path from the new global target path based on the influencing conditions.

[0104] In this article, the implementation steps based on the reference results can also be implemented based on the belonging condition.

[0105] Next, through Figure 2 The following is a detailed description of this application:

[0106] Step 201, obtaining each point to be sprayed and its influencing conditions.

[0107] Step 202: randomly sort the spraying points to obtain a plurality of spraying paths to be determined.

[0108] Step 203, performing mutation processing on the spraying path to be determined to obtain a new spraying path to be determined.

[0109] Step 204 , calculating the path length of each spraying path to be determined, and determining the spraying path to be processed whose path length is less than the preset path length as the initial target path.

[0110] Step 205, executing a processing process on each initial target path to obtain multiple local target paths.

[0111] Step 206 , determining a global target path from multiple local target paths based on the influencing conditions, and returning to execute step 205 .

[0112] Step 207, determining whether the above-mentioned number of iterations reaches a preset number of iterations, if so, executing step 206, otherwise, executing step 208.

[0113] Step 208, determine whether stagnation occurs, if so, return to step 203, otherwise, execute step 205.

[0114] The following is a specific example to illustrate:

[0115] Under the influence of a set of known points in the rice fields that need to be sprayed with pesticides (i.e., key areas or areas with high incidence of pests and diseases in the rice fields), the coordinates of the starting point (also the end point) of the drone, the total power of the drone, the power consumed per unit flight distance, the total pesticide stock of the drone, and the amount of pesticide required for each point, the shortest path for the drone to start from the starting point, traverse all designated points, and return to the starting point is planned to ensure that the drone can complete the pesticide spraying task efficiently and accurately.

[0116] (1) Collect and preprocess data.

[0117] Through 3D point cloud reconstruction, we constructed a topographic map of the rice field in the computer. The points where pests and diseases were identified were marked on the map. The coordinate information of the points in the rice field where pesticides need to be sprayed was obtained, as well as the amount of pesticides required for these points (fixed as a square of 25m*25m).

[0118] Determine the coordinates of the drone's starting point (also the end point), total power, power consumed per unit flight distance, and total pesticide inventory.

[0119] Preprocess the collected data to ensure its accuracy and completeness.

[0120] (2) Algorithm parameter initialization processing.

[0121] According to the actual situation, the relevant parameters of discrete brainstorming algorithm (DBSO) and particle swarm optimization algorithm (PSO) are set.

[0122] A set of initial paths are randomly generated, ensuring that the starting points are used as the start and end points of the paths.

[0123] (3) Path planning processing.

[0124] The DBSO algorithm continuously generates new paths through selection and mutation operations, and updates the path set to maintain its diversity. During the mutation process, the constraints of power and pesticide dosage are considered to ensure that the generated paths meet these conditions.

[0125] PSO algorithm, initialize the particle (path) speed and position. Update the particle (path) state according to the PSO rules, while considering the continuity of the path and the power and pesticide constraints. Calculate the total flight distance of the particle (path) and check whether the influencing conditions are met.

[0126] The elite paths generated by the DBSO algorithm are used as particles of the PSO for iterative optimization to continuously improve the path quality. In each iteration, the local optimal and global optimal paths are updated according to the evaluation results.

[0127] Repeat the optimization process until the preset number of iterations is reached or a path that meets the conditions is found. During the iteration process, the algorithm parameters can be adjusted as needed to optimize the search efficiency. If the optimization is stagnant, the elite path is selected through DBSO, and the path set is updated to repeat the PSO optimization process.

[0128] (4) Path selection and execution processing.

[0129] The algorithm is terminated based on the termination condition. The algorithm terminates when the maximum number of iterations is reached or a path that satisfies the power and pesticide constraints and has the shortest total flight distance is found.

[0130] Output the optimal path and its total flight distance. This path is the best flight route for the drone to spray pesticides.

[0131] The optimal path and its related information (such as the order of passing points, coordinates, changes in drone power and pesticide dosage, etc.) are provided to the drone flight control system to guide the drone to fly and spray pesticides according to the planned route.

[0132] (5) Real-time monitoring and adjustment processing.

[0133] When the drone is performing spraying tasks, its battery power and pesticide dosage changes are monitored in real time.

[0134] If it is found that the drone’s battery power or pesticide amount is insufficient to complete the remaining task, the drone will be promptly commanded to return to the starting point for charging or replenishing pesticides.

[0135] Adjust the flight speed and spraying volume of the drone according to actual conditions to ensure the uniformity and effectiveness of pesticide spraying.

[0136] The drone of this application can efficiently and accurately complete the task of spraying pesticides on rice fields. While ensuring the spraying effect, the flight distance of the drone and the amount of pesticides used are minimized, reducing costs and environmental impact. At the same time, through real-time monitoring and adjustment, the safety and stability of the drone during flight are ensured.

[0137] This application makes full use of 3D terrain reconstruction technology to accurately obtain the 3D terrain features of farmland. This enables the drone to know the specific coordinates of the target points for pesticide spraying in the rice fields in advance, so as to accurately and quickly plan the path and perform intelligent cruising.

[0138] Through advanced path planning algorithms, this application can provide efficient pesticide spraying paths for large-scale, multi-plot rice fields, significantly improving the operating efficiency of drones and reducing unnecessary flight time and energy consumption. At the same time, high-precision pest and disease area recognition technology ensures that drones can accurately cover pest and disease areas, improving the efficiency and effectiveness of pesticide use and reducing pesticide waste.

[0139] This application can be applied to rice fields of different sizes and has strong adaptability. In addition, the high flexibility of the algorithm enables this application to be adaptively adjusted according to the actual conditions of different farmland areas, ensuring that the drone can always remain in the optimal operating state. By building an intelligent decision-making and scheduling system, this application can make the best decision based on real-time conditions. This includes decision-making and scheduling in terms of drone takeoff, flight path, spraying strategy, etc., ensuring that the drone can complete tasks efficiently and accurately in actual operations. The introduction of an intelligent decision-making system also reduces the degree of manual intervention, reduces the burden on operators, and improves the safety and reliability of operations. By optimizing path planning and improving operating efficiency, this technical solution reduces the flight time and energy consumption of drones, helping to reduce carbon emissions and environmental pollution. At the same time, high-precision pesticide spraying technology reduces the waste and residue of pesticides, which is of great significance to protecting the ecological environment and the quality of agricultural products.

[0140] The implementation of this application will promote the improvement of agricultural intelligence and provide strong support for agricultural modernization. By introducing advanced drone technology and intelligent decision-making systems, agricultural production will become more efficient, intelligent and sustainable. In addition, it will also help energy conservation, emission reduction and environmental protection, improve the level of agricultural intelligence, and is of great significance to agricultural modernization and sustainable development.

[0141] The present application also provides a path planning device for a pesticide spraying device. The specific implementation of the device can refer to the description of the path planning method for a pesticide spraying device, and the repetitive parts will not be repeated. Figure 3 As shown, the device comprises:

[0142] An acquisition module 301 is used to acquire a plurality of to-be-sprayed points and the number of first paths corresponding to the current farmland, wherein the to-be-sprayed points are obtained by identifying a crop growth image;

[0143] The first processing module 302 is used to arrange the points to be sprayed, and obtain a first number of initial target paths based on the path length after the arrangement process;

[0144] The second processing module 303 is used to perform the following processing on each initial target path:

[0145] Determine the path change probability of the initial target path, and calculate the reference result corresponding to the initial target path based on the order of each to-be-sprayed point in the initial target path; calculate the local target path and the global target path in the current state based on the reference result; update the path change probability based on the local target path and the global target path, and perform mutation processing on the initial target path based on the updated path change probability to obtain a new initial target path;

[0146] The reference result includes: the total path length and influencing conditions of the initial target path, and the influencing conditions include: the total power consumption of the pesticide spraying equipment, the total pesticide consumption, the return point of the pesticide spraying equipment, and the return point of the pesticide spraying equipment;

[0147] The determination module 304 is used to determine a final global target path based on the reference result after each of the initial target paths executes the processing procedure for a preset number of times.

[0148] In a specific embodiment, the first processing module 302 is used to arrange the points to be sprayed to obtain multiple spray paths to be determined; perform mutation processing on the spray paths to be determined to obtain multiple new spray paths to be determined, and merge the spray paths to be determined to obtain multiple spray paths to be processed; calculate the path length of each spray path to be processed, and determine the spray paths to be processed whose path length is less than the first number of paths of the preset path length as the initial target path.

[0149] In a specific embodiment, the first processing module 302 is used to determine the number of second paths of the spraying paths to be processed whose path length is less than the preset path length; when it is determined that the number of second paths is less than the number of first paths, the step of performing mutation processing on the spraying paths to be determined to obtain multiple new spraying paths to be determined is performed; when it is determined that the number of second paths is greater than or equal to the number of first paths, the step of determining the spraying paths to be processed whose path length is less than the preset path length and the first path number as the initial target path is performed.

[0150] In a specific embodiment, the second processing module 303 is used to perform a step of performing a variation process on the spraying path to be determined, obtaining multiple new spraying paths to be determined, and obtaining a new global target path; when the number of consecutive predictions of the new global target path does not change, the new global target path is determined as the final global target path.

[0151] In a specific embodiment, the second processing module 303 is used to determine whether the number of iterations reaches a preset number of iterations when it is determined that the number of consecutive predictions of the new global target path does not change; when it is determined that the number of iterations reaches the preset number of iterations, the new global target path is determined as the final global target path; when it is determined that the number of iterations does not reach the preset number of iterations, the steps of performing the following processing process on each initial target path are performed until the number of iterations reaches the preset number of iterations, and the final global target path is obtained.

[0152] In a specific embodiment, the second processing module 303 is used to determine the final global target path from the new global target path based on the reference result in the process of determining that the number of iterations reaches a preset number of iterations and there is no situation where the number of consecutive predictions of the new global target path does not change.

[0153] In a specific embodiment, the acquisition module 301 is used to acquire multiple crop growth images corresponding to the current farmland; identify the pest and disease conditions corresponding to each crop growth image, and determine the specific category of the pest and disease based on the pest and disease conditions; when the required pesticides are determined, the farmland area corresponding to the crop generation image is determined as the spraying point.

[0154] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 401, a communications interface 402, a memory 403 and a communication bus 404, wherein the processor 401, the communications interface 402 and the memory 403 communicate with each other via the communication bus 404. The processor 401 may call the logic instructions in the memory 403 to execute the path planning method of the pesticide spraying equipment.

[0155] In addition, the logic instructions in the above-mentioned memory 403 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0156] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the path planning method for the pesticide spraying equipment provided by the above-mentioned methods.

[0157] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the path planning method for the pesticide spraying equipment provided in the above-mentioned embodiments.

[0158] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0159] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0160] Finally, it should be noted that the above is only the preferred implementation of the present application, and the present application is not limited to the above embodiments. It is understood that other improvements and changes directly derived or associated by those skilled in the art without departing from the spirit and concept of the present application should be considered to be included in the scope of protection of the present application.

Claims

1. A path planning method for pesticide spraying equipment, characterized in that: The method comprises: Acquire a plurality of points to be sprayed and the number of first paths corresponding to the current farmland, wherein the points to be sprayed are obtained by identifying crop growth images; Arrange the points to be sprayed, and obtain the first number of initial target paths based on the length of the paths after the arrangement process; The following processing is performed for each of the initial target paths: Determine the path change probability of the initial target path, and calculate the reference result corresponding to the initial target path based on the order of each to-be-sprayed point in the initial target path; calculate the local target path and the global target path in the current state based on the reference result; update the path change probability based on the local target path and the global target path, and perform mutation processing on the initial target path based on the updated path change probability to obtain a new initial target path; The reference result includes: the total path length and influencing conditions of the initial target path, and the influencing conditions include: the total power consumption of the pesticide spraying equipment, the total pesticide consumption, the return point of the pesticide spraying equipment, and the return point of the pesticide spraying equipment; After each of the initial target paths executes the processing procedure for a preset number of times, a final global target path is determined based on the reference result.

2. The path planning method for pesticide spraying equipment according to claim 1, characterized in that: Arrange the points to be sprayed, and obtain the first number of initial target paths based on the path length after the arrangement process, including: Arranging the points to be sprayed to obtain a plurality of spraying paths to be determined; Performing mutation processing on the spraying paths to be determined to obtain multiple new spraying paths to be determined, and merging the spraying paths to be determined to obtain multiple spraying paths to be processed; The path length of each of the to-be-processed spraying paths is calculated, and the to-be-processed spraying paths having the first number of paths whose path lengths are less than the preset path lengths are determined as the initial target paths.

3. The path planning method for pesticide spraying equipment according to claim 2, characterized in that: After calculating the path length of each of the spray paths to be processed, the method further includes: Determine the number of second paths of the spraying path to be processed whose path length is less than the preset path length; In the case where it is determined that the number of the second paths is less than the number of the first paths, performing the step of performing mutation processing on the spraying paths to be determined to obtain a plurality of new spraying paths to be determined; In the case where it is determined that the second path number is greater than or equal to the first path number, the step of determining the to-be-processed spraying paths of the first path number whose path lengths are less than a preset path length as the initial target paths is performed.

4. The path planning method for pesticide spraying equipment according to claim 2, characterized in that: After obtaining the final global target path based on the reference result, the method further includes: The step of performing mutation processing on the spraying path to be determined to obtain a plurality of new spraying paths to be determined is performed to obtain a new global target path; When it is determined that the number of consecutive predictions of the new global target path does not change, the new global target path is determined as the final global target path.

5. The path planning method for pesticide spraying equipment according to claim 4, characterized in that: When it is determined that the number of consecutive predictions of the new global target path does not change, the new global target path is determined as the final global target path, including: When it is determined that the number of continuous predictions of the new global target path does not change, determining whether the number of iterations reaches a preset number of iterations; When it is determined that the number of iterations reaches the preset number of iterations, determining the new global target path as the final global target path; When it is determined that the number of iterations has not reached the preset number of iterations, the step of performing the following processing on each of the initial target paths is performed until the number of iterations reaches the preset number of iterations and a final global target path is obtained.

6. The path planning method for pesticide spraying equipment according to claim 5, characterized in that: Until the number of iterations reaches the preset number of iterations and the final global target path is obtained, including: In the process of determining that the number of iterations reaches the preset number of iterations, there is no situation where the number of consecutive predictions of the new global target path does not change, and the final global target path is determined from the new global target path based on the reference result.

7. The path planning method for pesticide spraying equipment according to any one of claims 1 to 6, characterized in that: Get multiple spraying points corresponding to the current farmland, including: Obtain multiple crop growth images corresponding to the current farmland; Identify the pest and disease situation corresponding to each crop growth image, and determine the specific category of the pest and disease based on the pest and disease situation; When the required pesticide is determined, the farmland area corresponding to the crop generated image is determined as the point to be sprayed.

8. A path planning device for pesticide spraying equipment, characterized in that: The device comprises: An acquisition module, used for acquiring a plurality of to-be-sprayed points and the number of first paths corresponding to the current farmland, wherein the to-be-sprayed points are obtained by identifying a crop growth image; A first processing module is used to arrange the points to be sprayed, and obtain the first number of initial target paths based on the length of the paths after the arrangement process; The second processing module is used to perform the following processing on each of the initial target paths: Determine the path change probability of the initial target path, and calculate the reference result corresponding to the initial target path based on the order of each to-be-sprayed point in the initial target path; calculate the local target path and the global target path in the current state based on the reference result; update the path change probability based on the local target path and the global target path, and perform mutation processing on the initial target path based on the updated path change probability to obtain a new initial target path; The reference result includes: the total path length and influencing conditions of the initial target path, and the influencing conditions include: the total power consumption of the pesticide spraying equipment, the total pesticide consumption, the return point of the pesticide spraying equipment, and the return point of the pesticide spraying equipment; A determination module is used to determine a final global target path based on the reference result after each of the initial target paths executes the processing for a predicted number of times.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the path planning method for the pesticide spraying equipment as described in any one of claims 1 to 7 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the path planning method for pesticide spraying equipment as described in any one of claims 1 to 7 are implemented.

Images