Unmanned aerial vehicle nest site selection method, device and equipment and readable storage medium

Abstract

The invention discloses an unmanned aerial vehicle nest site selection method, device and equipment and a readable storage medium, which are applied to the technical field of unmanned aerial vehicles, and comprise the following steps: determining the reachable range of an unmanned aerial vehicle based on the flight range and the inspection point of the unmanned aerial vehicle; determining an initial machine nest point corresponding to each inspection point based on the reachable range, and obtaining an inspection point set corresponding to each initial machine nest point; generating a nest removal priority sequence according to the inspection parameters of each inspection point in the inspection point set corresponding to each initial nest point; and sequentially removing the initial cell points based on the cell removal priority sequence, and performing position adjustment on the remaining cell points after the initial cell points are removed until the remaining cell points cannot meet the full-coverage constraint condition. According to the method, firstly, enough initial machine nest points are arranged to cover all the inspection points, the initial machine nest points are further removed one by one, site selection is carried out on the remaining machine nests again, all the inspection points are covered under the condition that the machine nest points are minimum, and therefore the machine nest site selection efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles (UAVs), and in particular to a method, device, equipment and readable storage medium for selecting a nest site for an UAV. Background Art

[0002] As key infrastructure for automated inspection systems, drone nests perform multiple functions, including mission deployment, charging, and data relay. Currently, in complex forest environments, drone nest deployment relies heavily on manual experience and lacks a scientific, systematic site selection mechanism. This leads to problems such as low site selection efficiency, poor coverage, high energy consumption, and difficult maintenance, hindering the intelligent and scalable development of drone systems.

[0003] Therefore, how to intelligently select the site for drone nests and improve the efficiency of drone nest selection is a technical problem that technicians in this field urgently need to solve. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a method, device, equipment and readable storage medium for selecting a drone nest, which solves the technical problem of low efficiency in drone site selection in the prior art.

[0005] To solve the above technical problems, the present invention provides a method for selecting a drone nest site, comprising:

[0006] Determine the reach of the drone based on its flight range and inspection points;

[0007] Determine an initial machine nest point corresponding to each inspection point based on the reachable range, and obtain a set of inspection points corresponding to each initial machine nest point;

[0008] Generate a machine nest removal priority sequence according to the inspection parameters of each inspection point in the inspection point set corresponding to each initial machine nest point;

[0009] The initial nest points are removed in sequence based on the nest removal priority sequence, and the positions of the remaining nest points are adjusted after the initial nest points are removed until the current remaining nest points cannot meet the full coverage constraint condition, thereby obtaining the target nest point.

[0010] Optionally, determine the drone's reach based on its flight range and inspection points, including:

[0011] The coverage radius of the drone is determined based on the flight range and inspection points of the drone; wherein the reachable range of the drone includes the coverage radius of the drone.

[0012] Optionally, determining an initial machine nest point corresponding to each inspection point based on the reachable range, and obtaining a set of inspection points corresponding to each initial machine nest point, includes:

[0013] Determine K initial machine nest points;

[0014] The K initial nest points are used as cluster centers, and the coverage radius of the drone is used as the distance r for cluster analysis to obtain a set of inspection points corresponding to each initial nest point.

[0015] Optionally, generating a machine nest removal priority sequence according to the inspection parameters of each inspection point in the inspection point set corresponding to each initial machine nest point includes:

[0016] Determine the inspection parameter of each inspection point as the inspection frequency;

[0017] Determine all inspection frequencies corresponding to each of the initial machine nest points, and obtain a removal level parameter corresponding to each of the initial machine nest points based on all the inspection frequencies;

[0018] The initial machine nest points are sorted according to the removal level parameters to obtain the machine nest removal priority sequence.

[0019] Optionally, the initial nest points are removed in sequence based on the nest removal priority sequence, and after the initial nest points are removed, the positions of the remaining nest points are adjusted until the remaining nest points cannot meet the full coverage constraint condition, thereby obtaining the target nest point, including:

[0020] Determine the first machine nest point to be removed based on the machine nest removal priority sequence, and use the inspection point corresponding to the first machine nest point to be removed as the inspection point to be assigned;

[0021] The goal is to minimize the distance between each inspection point to be assigned and the remaining machine nest points, and determine the nearest machine nest point corresponding to each inspection point to be assigned;

[0022] Taking the minimum nest moving distance as the goal, calculate the weighted centroid position of each point covered by the nearest nest point;

[0023] Each of the nearest machine nest points is moved in a direction from its current position to the corresponding weighted center position to obtain the target machine nest point after the movement.

[0024] Optionally, minimizing the distance between each inspection point to be assigned and the remaining machine nest points is taken as the goal, and the nearest machine nest point corresponding to each inspection point to be assigned is determined, including:

[0025] The goal is to minimize the sum of the weighted square distances between each inspection point and the remaining machine nest points, and determine the nearest machine nest point corresponding to each inspection point to be assigned; wherein, in the process of determining the sum of the weighted square distances between the inspection point and the remaining machine nest points, the weighting method is to weight based on the inspection parameters of each inspection point to be assigned.

[0026] Optionally, after determining the initial machine nest point corresponding to each inspection point based on the reachable range and obtaining the inspection point set corresponding to each initial machine nest point, the method further includes:

[0027] Determine the area where the machine nest can be deployed based on the conditions for machine nest deployment, energy supply, communication, and operation and maintenance convenience;

[0028] Determining whether each initial machine nest point is in the area where the machine nest can be arranged;

[0029] If not, the current initial machine nest point is moved to the nearest area where a machine nest can be arranged.

[0030] An embodiment of the present invention further provides a device for selecting a nest site for a drone, comprising:

[0031] A reach determination module is used to determine the reach of the drone based on the drone's flight range and inspection points;

[0032] An initial machine nest point determination module is used to determine the initial machine nest point corresponding to each inspection point based on the reachable range, and obtain a set of inspection points corresponding to each initial machine nest point;

[0033] A machine nest removal priority sequence determination module, configured to generate a machine nest removal priority sequence according to the inspection parameters of each inspection point in the inspection point set corresponding to each initial machine nest point;

[0034] The machine nest point position adjustment module is used to remove the initial machine nest point in sequence based on the machine nest removal priority sequence, and adjust the positions of the remaining machine nest points after removing the initial machine nest point until the current remaining machine nest points cannot meet the full coverage constraint condition, thereby obtaining the target machine nest point.

[0035] An embodiment of the present invention further provides a drone nest site selection device, comprising:

[0036] Memory for storing computer programs;

[0037] A processor is used to execute the computer program to implement the steps of the above-mentioned drone nest site selection method.

[0038] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the above-mentioned drone nest site selection method are implemented.

[0039] The present invention also provides a computer program product, comprising a computer program / instruction, which, when executed by a processor, implements the steps of the above-mentioned drone nest site selection method.

[0040] It can be seen that the present invention determines the reachable range of the drone based on the flight range and inspection points of the drone; determines the initial nest point corresponding to each inspection point based on the reachable range, and obtains the inspection point set corresponding to each initial nest point; generates a nest removal priority sequence based on the inspection parameters of each inspection point in the inspection point set corresponding to each initial nest point; removes the initial nest points in sequence based on the nest removal priority sequence, and adjusts the positions of the remaining nest points after removing the initial nest points until the current remaining nest points cannot meet the full coverage constraint condition, thereby obtaining the target nest point. The current deployment of nest points mostly relies on manual experience and lacks a scientific and systematic site selection mechanism. There are problems such as low site selection efficiency, poor coverage capability, high energy consumption, and difficult maintenance. In comparison, the present invention adopts an efficient two-stage nest site selection method. In the first stage, enough initial nest points are arranged to cover all inspection points; in the second stage, the initial nest points are removed and the remaining nests are relocated until no more nests can be removed, so as to cover all inspection points with the minimum number of nest points, thereby improving the efficiency and accuracy of drone nest site selection while reducing energy consumption.

[0041] In addition, the present invention also provides a drone nest site selection device, equipment and readable storage medium, which also have the above-mentioned beneficial effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0043] Figure 1 A flowchart of a method for selecting a drone nest site according to an embodiment of the present invention;

[0044] Figure 2 A flowchart illustrating a method for selecting a drone nest site according to an embodiment of the present invention;

[0045] Figure 3 A flowchart illustrating a method for determining an initial machine nest point provided by an embodiment of the present invention;

[0046] Figure 4 A schematic structural diagram of a drone nest site selection device provided by an embodiment of the present invention;

[0047] Figure 5 A schematic structural diagram of a drone nest site selection device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0049] Please refer to Figure 1 , Figure 1 This is a flow chart of a method for selecting a drone nest site according to an embodiment of the present invention. The method may include:

[0050] S101, determining the reachable range of the drone based on the flight range and inspection points of the drone.

[0051] The executor of this embodiment is an electronic device. The electronic device in this embodiment can be a computer, a mobile phone, etc. This embodiment does not limit the specific application scenario of the present invention. For example, the application scenario of this embodiment can be a forest or a city. The flight range of the drone in this embodiment refers to the theoretical maximum flight distance of the drone after a single charge. The reachable range in this embodiment is the actual three-dimensional space boundary within which the drone can safely travel back and forth from the inspection point and complete the operation from the nest point. The inspection point in this embodiment refers to a fixed location that requires periodic inspection. The drone in this embodiment is a drone that needs to patrol the inspection point. This embodiment does not limit the specific form of the reachable range. For example, the reachable range in this embodiment can be abstracted as a radius. Since the horizontal movement distance of the drone is much greater than the vertical movement distance, it can be simplified to the radius of a two-dimensional plane; or the reachable range in this embodiment can also be a specific area range.

[0052] It should be further explained that, based on any of the above embodiments, the above determination of the reachable range of the drone based on the flight range and inspection points of the drone may include: determining the coverage radius of the drone based on the flight range and inspection points of the drone; wherein, the reachable range of the drone includes the coverage radius of the drone. This embodiment considers the impact of the coverage radius constraint of the drone on the site selection of the machine nest. For each machine nest, it is only responsible for the inspection point targets within its coverage radius (for example, specific geographical locations in forest areas that require drones to focus on monitoring, shooting or collecting data, such as fire monitoring areas, pest and disease observation areas, facility inspection areas, etc.). This constraint can be expressed using Euclidean distance as Where Gather for the inspection point, is the set of candidate machine nest points (initial machine nest points), is the coverage radius of the drone.

[0053] It should be further explained that, based on any of the above embodiments, in order to improve the efficiency of determining the inspection point set corresponding to the initial machine nest point, the above determination of the initial machine nest point corresponding to each inspection point based on the reachable range, and obtaining the inspection point set corresponding to each initial machine nest point, may include:

[0054] S1011, determine K initial machine nest points;

[0055] S1012: Perform cluster analysis using the K initial nest points as cluster centers and the coverage radius of the drone as the distance r to obtain a set of inspection points corresponding to each initial nest point.

[0056] In this embodiment, K can be set manually according to the needs. In this embodiment, the sub-category set is obtained. (The set of inspection points corresponding to each initial machine nest point), the specific process can be:

[0057] 1) Initialize list S, s; (The initialization set S is used to store all sub-sets, and s is temporarily used to store the target point set corresponding to the current origin)

[0058] 2) For P in B; (traverse each initial nest point)

[0059] 3) Clear s; (clear the temporary collection s)

[0060] 4) for p in A; (traverse each inspection point)

[0061] 5) if distance(p,P)≤r; (If the distance from the machine nest point P to the inspection point p is less than or equal to the radius r;

[0062] 6) s.append(p); (add this inspection point p to the temporary set s)

[0063] 7) S.append(s); (After the current nest P is processed, its corresponding subset s is added to the total set S)

[0064] 8) return S. (Finally, return the set of reachable target points corresponding to all origins)

[0065] This embodiment provides a method of clustering based on the coverage radius of the drone to obtain the inspection point set corresponding to each initial machine nest point, thereby improving the accuracy of determining the inspection point set corresponding to each initial machine nest point based on the coverage radius of the drone.

[0066] S102: Determine the initial machine nest point corresponding to each inspection point based on the reachable range, and obtain the inspection point set corresponding to each initial machine nest point.

[0067] The logic of this embodiment for determining the initial nest point corresponding to each inspection point based on the reachable range is that it is essentially a constrained spatial problem, with satisfying the reachable range of the drone as the core constraint. This embodiment does not limit the specific process of determining the initial nest point corresponding to each inspection point based on the reachable range and obtaining the set of inspection points corresponding to each initial nest point. For example, this embodiment can perform cluster analysis based on the reachable range and the initial nest point to obtain the set of inspection points corresponding to each initial nest point; or this embodiment can also construct a topological map of the inspection points, calculate the actual path distance between the inspection points, divide the area with the initial nest point as the center, and ensure that the distance from the inspection point to the initial nest point is less than or equal to the reachable range. It should be further explained that to ensure the feasibility of the initial nest site design, the initial nest site selection must comply with site selection rules. For example, 1) the nest deployment area should be away from locations susceptible to external interference, such as high-wind areas, animal habitats, and areas prone to landslides, to ensure the stability and safety of drones during takeoff, landing, and standby. 2) Given that drone nests typically require functions such as charging, environmental control, and data communication, the deployment area should be close to nodes with access to the power grid or have the basic conditions for installing renewable energy systems such as solar panels to ensure a continuous and reliable energy supply. 3) The drone nest must support stable communication with the command center to enable remote control, data upload, and status feedback. Therefore, the site selection area must have a strong cellular communication network signal (such as 4G / 5G) or be able to access a dedicated wireless communication base station. 4) The nest site selection should take into account the convenience of subsequent operation and maintenance, with priority given to areas close to forest roads, forest ranger stations, or management centers to facilitate the deployment, inspection, and maintenance of personnel and equipment. Therefore, by combining geographic information systems and multi-source data, the present invention prioritizes initial machine nest locations within forest management land or forest control points with access to power, good communication signals, relatively flat terrain, and convenient operation and maintenance, maximizing the balance between mission performance and deployment feasibility. Alternatively, this embodiment can determine whether the machine nest deployment requirements, energy supply requirements, communication requirements, and operational and maintenance convenience requirements are met after determining the initial machine nest location.

[0068] It should be further explained that, based on any of the above embodiments, in order to ensure the feasibility, safety, and sustainability of the machine nest point deployment, after determining the initial machine nest point corresponding to each inspection point based on the reachable range and obtaining the inspection point set corresponding to each initial machine nest point, the following steps may also be included:

[0069] S1021, determining an area where a machine nest can be deployed based on machine nest deployment conditions, energy supply conditions, communication conditions, and operation and maintenance convenience conditions;

[0070] S1022, determining whether each initial machine nest point is in an area where a machine nest can be deployed;

[0071] S1023: If not, move the current initial machine nest point to the nearest area where a machine nest can be arranged.

[0072] This embodiment determines the area where machine nests can be deployed based on machine nest deployment conditions, energy supply conditions, communication conditions, and operation and maintenance convenience conditions, ensuring the feasibility, safety, and sustainability of machine nest deployment. If the preset initial machine nest point is not in an area where machine nests can be deployed, this embodiment will move the initial machine nest point to the nearest area where machine nests can be deployed. If it is in an area where machine nests can be deployed, the initial machine nest point will not be processed.

[0073] S103 , generating a machine nest removal priority sequence according to the inspection parameters of each inspection point in the inspection point set corresponding to each initial machine nest point.

[0074] This embodiment does not limit specific inspection parameters. For example, the inspection parameter in this embodiment can be the safety factor of the inspection point. It is understood that when the safety factor of a certain inspection point is low, it means that the point is a low-priority inspection target, and the corresponding initial machine nest point is more likely to be removed. Alternatively, the inspection parameter in this embodiment can be the inspection demand. It is understood that the lower the inspection demand, the more likely the initial machine nest point is to be removed. Alternatively, the inspection detection in this embodiment can be safety parameters and inspection demand. In this embodiment, the machine nest removal priority sequence can determine the order in which the initial machine nest points are removed.

[0075] It should be further explained that, based on any of the above embodiments, generating the machine nest removal priority sequence according to the inspection parameters of each inspection point in the inspection point set corresponding to each initial machine nest point may include:

[0076] S1031, determining the inspection parameter of each inspection point as the inspection frequency;

[0077] S1032, determining all inspection frequencies corresponding to each initial machine nest point, and obtaining a removal level parameter corresponding to each initial machine nest point based on all inspection frequencies;

[0078] S1033 , sorting the initial machine nest points according to the removal level parameters to obtain a machine nest removal priority sequence.

[0079] The inspection parameter in this embodiment is the inspection frequency of each inspection point. Increase inspection frequency , a removal metric is proposed for each inspection point p ,The proposed removal metric is used to describe the removal level of each machine nest point. Inspection points need to be assigned to machine nest points. The assignment is based on distance, that is, if the inspection points are Closer to the nest than other nests , then assign it to the machine nest .set up Represents the set of inspection points that meet the above conditions, Indicates the machine nest The removal level (the removal metric can also be defined as ), When the removal metric is hour, The larger the initial nest point, the larger the removal level parameter, and the order is from large to small; when the removal metric is hour, The smaller the initial nest point, the larger the removal level parameter. In this case, the order is from small to large, that is, the smaller the initial nest point, the higher the removal priority of the initial nest. This embodiment provides a specific process for determining the nest removal priority sequence based on the inspection frequency, which improves the accuracy of determining the nest removal priority sequence.

[0080] S104, removing the initial nest point in sequence based on the nest removal priority sequence, adjusting the positions of the remaining nest points after removing the initial nest point, until the current remaining nest points cannot meet the full coverage constraint condition, and obtaining the target nest point.

[0081] This embodiment can remove initial machine nest points from high to low, or from low to high, as long as the initial machine nest points that cover a large number of low-importance inspection points are removed first, as their contribution to the overall inspection task of the system is relatively small. This embodiment does not limit the specific method for adjusting the position of the remaining machine nest points. For example, this embodiment can solve a constrained function based on minimizing the weighted sum of squared distances; or this embodiment can minimize the maximum distance from each inspection point to the machine nest.

[0082] It should be further explained that, based on any of the above embodiments, the above-mentioned process of sequentially removing the initial nest points based on the nest removal priority sequence, adjusting the positions of the remaining nest points after removing the initial nest points until the remaining nest points fail to meet the full coverage constraint condition, and obtaining the target nest point, may include:

[0083] S1041, determining the first machine nest point to be removed based on the machine nest removal priority sequence, and using the inspection point corresponding to the first machine nest point to be removed as the inspection point to be assigned;

[0084] S1042, minimizing the distance between each inspection point to be assigned and the remaining machine nest points as a goal, and determining the nearest machine nest point corresponding to each inspection point to be assigned;

[0085] S1043, taking the minimum nest movement distance as the goal, calculate the weighted centroid position of the points covered by each nearest nest point;

[0086] S1044: Move each nearest nest point in a direction from its current position to the corresponding weighted center position to obtain the target nest point after the movement.

[0087] In this embodiment, the first nest point removed is the nest point with the highest removal priority. In this embodiment, the inspection point corresponding to the first nest point removed is used as the inspection point to be assigned. In this embodiment, minimizing the distance between each inspection point to be assigned and the remaining nest points is the goal. The process of determining the nearest nest point corresponding to each inspection point to be assigned can be understood as: Indicates the remaining after removing the first nest point The location of the machine nest point. ,set up for The distance between the nearest nest and the nearest nest, where . This embodiment can obtain the nearest nest point corresponding to the current inspection point to be assigned by minimizing the distance between each inspection point to be assigned and the remaining nest points. If multiple nearest nest points are obtained in this embodiment, they can be assigned to any nest point, or a function of minimizing the average distance can be constructed to obtain the nearest nest point with the smallest average distance by minimizing the average distance function. The function of minimizing the average distance can be determined based on the target distance between the inspection point to be assigned and the nearest nest point, and the removal level parameter corresponding to the nearest nest point. For ease of understanding, for example, the objective function of relocating the remaining nest points (nest points other than the first removed nest point) can be expressed as: This objective function reflects the average distance between the inspection point and its nearest deployment nest. The internal optimization problem is formulated as follows:

[0088] Here Refers to multiple initial machine nest points that are at the same distance from the inspection point. Based on the above function, the nearest machine nest point with the closest average distance among the multiple nearest machine nest points can be actually found. That is, when multiple nearest machine nests are at the same distance from the inspection point, the globally optimal allocation scheme is selected to minimize the overall cost of the system. This embodiment takes the minimum machine nest movement distance as the goal, calculates the weighted centroid position of the points covered by each nearest machine nest point, thereby minimizing the movement distance and improving the efficiency of movement. This embodiment takes the minimum machine nest movement distance as the goal, and can be based on minimizing the sum of the squares of the distances between each inspection point and the remaining machine nest points as the goal, or can also be based on minimizing the sum of the squares of the weighted distances between each inspection point and the remaining machine nest points as the goal.

[0089] It should be further explained that, based on any of the above embodiments, minimizing the distance between each inspection point to be assigned and the remaining machine nest points is taken as a goal, and determining the nearest machine nest point corresponding to each inspection point to be assigned may include: minimizing the sum of the weighted square distances between each inspection point and the remaining machine nest points is taken as a goal, and determining the nearest machine nest point corresponding to each inspection point to be assigned; wherein, in the process of determining the sum of the weighted square distances between the inspection point and the remaining machine nest points, the weighting method is to perform weighting based on the inspection parameters of each inspection point to be assigned. It can be understood that the above-mentioned movement process can be understood as local movement, and the local movement method is described as follows. Since a machine nest point is removed, there will be some inspection points that are not covered. Then, these inspection points are assigned to the nearest machine nest. Assume Indicates that it is assigned to the machine nest The inspection point subset ( If there are two or more nests with the same distance from the inspection point, the inspection point can be assigned to any of the nests (for example, to the nest with the lower index). Introducing a virtual force The virtual force is modeled as follows: ; is pointing to arrive The vector of Playing the role of weight, this embodiment can introduce the inspection frequency of the inspection point to construct the weight, similar to the center of gravity and density. Movement along the joint virtual force Where for The center of gravity, Defines a point to direction, moving in this direction will result in Towards Move, p is a vector, representing the inspection point location coordinates (x, y), P is also a vector, representing the nest location; the desired new nest location = the old nest location + the joint virtual force. This embodiment provides a specific method for moving the nearest nest point, improving the accuracy of nest movement. It is understandable that after moving the first mobile nest point, the second mobile nest point (the nest point with the second largest horizontal parameter) can be moved. Removing this station does not satisfy the continuity constraint. (full coverage constraint), where Calculate the distance between two nest points. It is based on a given threshold of the flight distance of the drone when fully charged, and will not be removed for now.

[0090] A method for selecting a drone nest site provided by an embodiment of the present invention may include: S101, determining the reachable range of the drone based on the flight range and inspection points of the drone; S102, determining the initial nest point corresponding to each inspection point based on the reachable range, and obtaining a set of inspection points corresponding to each initial nest point; S103, generating a nest removal priority sequence based on the inspection parameters of each inspection point in the set of inspection points corresponding to each initial nest point; S104, removing the initial nest points in sequence based on the nest removal priority sequence, and adjusting the positions of the remaining nest points after removing the initial nest points until the current remaining nest points cannot meet the full coverage constraint condition, and obtaining the target nest point. The current deployment of machine nest points mostly relies on manual experience and lacks a scientific and systematic site selection mechanism. There are problems such as low site selection efficiency, poor coverage, high energy consumption, and difficult maintenance. The present invention adopts an efficient two-stage machine nest site selection method. In the first stage, enough initial machine nest points are arranged to cover all inspection points; in the second stage, the initial machine nest points are removed and the remaining machine nest points are re-located until the machine nest points can no longer be removed, so that all inspection points are covered with the lowest number of machine nest points, thereby improving the efficiency and accuracy of drone nest site selection while reducing energy consumption.

[0091] The purpose of this invention is to provide a method for selecting a nest for inspection drones by using multi-source data and optimization algorithms, taking into account multiple factors such as terrain characteristics, communication conditions, power supply resources, and inspection coverage efficiency, so as to improve the automation level, deployment efficiency, and operational performance of the inspection system. Figure 2 , Figure 2 An example flow chart of a method for selecting a drone nest site is provided in an embodiment of the present invention, which may specifically include:

[0092] S201, determining an area where a machine nest can be arranged based on machine nest deployment conditions, energy supply conditions, communication conditions, and operation and maintenance convenience conditions.

[0093] The technical approach of this embodiment is that when determining the initial nest point, it is necessary to determine the area where the nest can be arranged based on the regional division of the geographic information system. Then, based on the nest deployment conditions, energy supply conditions, communication conditions, and operation and maintenance convenience conditions, the initial nest points are set for cluster analysis to obtain the inspection point set corresponding to each initial nest point. After that, the initial nest points are removed. Removal is to optimize the number of nest points, remove the initial nest points with the smallest inspection requirements, and then determine the nearest nest point corresponding to each inspection point to be assigned. When each nearest nest point is moved to cover all inspection points, the method of moving the nearest nest point is determined to minimize the moving distance. Then, the next nest point is removed. The removal is stopped until the current initial nest point cannot meet the continuity constraint and the conditions of covering all inspection points.

[0094] S202: Determine the reachable range of the drone based on the flight range and inspection points of the drone.

[0095] S203: Setting an initial nest point based on the reachable range of the UAV and the area where nests can be arranged.

[0096] S204, perform cluster analysis with the drone coverage radius as the radius and the number of initial drone nest points as the number of cluster centers. If the current number of drone nest points cannot cover all inspection points, the number of drone nest points will be automatically increased until the full coverage requirement is met, and the inspection point set corresponding to each initial drone nest point is obtained.

[0097] The process of determining the inspection point set corresponding to each initial machine nest point in this embodiment may include:

[0098] 1) Use ArcGIS (geographic mapping software) to create a single layer for each of the four principle requirements (machine nest deployment conditions, energy supply conditions, communication conditions, and operation and maintenance convenience). For each principle, determine whether the area is suitable. Use ArcGIS Toolbox to assign a value of 1 to suitable areas and a value of 0 to unsuitable areas.

[0099] 2) Overlay evaluation: To obtain a comprehensive evaluation result, the above layers are overlaid by setting an average weight. Based on the value of the overlaid comprehensive layer, a judgment is made, a threshold is set, and the area where the machine nest can be deployed is divided.

[0100] 3) Cluster analysis: Using the K-means algorithm (K-means clustering algorithm) based on Euclidean distance, determine K cluster centers (based on the K initial machine nest points set in the available machine nest area) with a radius distance r. If the current number of clusters cannot cover all points, the number of cluster centers K is automatically increased until full coverage is achieved.

[0101] 4) Obtain the initial nest location. Based on the clustering results, obtain the actual location coordinates on the GIS map.

[0102] The above process corresponds to Figure 3 , Figure 3 This is a flowchart illustrating a method for determining an initial machine nest point provided by an embodiment of the present invention.

[0103] S205 , determining the inspection parameters corresponding to each inspection point, and determining the removal level parameters corresponding to each initial machine nest point based on the inspection parameters corresponding to the inspection points in each inspection point set.

[0104] The inspection parameters in this embodiment are determined based on the inspection requirements.

[0105] S206 : Determine a machine nest removal priority sequence based on the removal level parameter of each initial machine nest point.

[0106] S207 , determining a first machine nest point to be removed based on the machine nest removal priority sequence, and determining a to-be-allocated inspection point corresponding to the first machine nest point to be removed.

[0107] S208 , minimizing the sum of the squares of the weighted distances between all inspection points to be assigned and the remaining machine nest points is used as a goal, and determining the nearest machine nest point corresponding to each inspection point to be assigned.

[0108] S209, taking the minimum moving distance of the nearest nest point as the goal, calculate the weighted centroid position of the points covered by each nearest nest point.

[0109] S210, move each nearest machine nest point in the direction of its current position to the corresponding weighted center position, and after the movement is completed, move the next initial machine nest point with the largest removal level until the current remaining machine nest points cannot meet the full coverage constraint condition, and obtain the inspection point set corresponding to the target machine nest point.

[0110] This invention employs an efficient two-stage nest selection method. In the first stage, cluster analysis based on multi-source data is used to deploy sufficient nests outside of unsuitable deployment areas to cover all inspection points. In the second stage, initial nests are removed sequentially based on a nest removal priority series, and the remaining nests are relocated until no more nests can be removed. The basic idea of ​​the proposed method is to first deploy a sufficient number of nests to encompass all inspection points, and then recursively remove some nests by relocating the remaining nests to cover all inspection points with the minimum number of nests.

[0111] Beneficial effects may specifically include:

[0112] 1) Supports automatic deployment of initial machine nest points in large and complex forest areas.

[0113] 2) Comprehensively consider terrain adaptation, communication links, energy factors and flight performance.

[0114] 3) Evaluate the path accessibility and operation stability of deployment points through simulation.

[0115] 4) Improve the operational autonomy and deployment efficiency of drone systems.

[0116] The following is an introduction to the drone nest site selection device provided by an embodiment of the present invention. The drone nest site selection device described below and the drone nest site selection method described above can be referenced to each other.

[0117] Please refer to Figure 4 , Figure 4 A schematic structural diagram of a drone nest site selection device provided in an embodiment of the present invention may include:

[0118] A reachable range determination module 100 is used to determine the reachable range of the drone based on the drone's flight range and inspection points;

[0119] An initial machine nest point determination module 200 is configured to determine an initial machine nest point corresponding to each inspection point based on the reachable range, and obtain an inspection point set corresponding to each initial machine nest point;

[0120] The machine nest removal priority sequence determination module 300 is used to generate a machine nest removal priority sequence according to the inspection parameters of each inspection point in the inspection point set corresponding to each initial machine nest point;

[0121] The machine nest point position adjustment module 400 is used to remove the initial machine nest point in sequence based on the machine nest removal priority sequence, and adjust the positions of the remaining machine nest points after removing the initial machine nest point until the current remaining machine nest points cannot meet the full coverage constraint condition, thereby obtaining the target machine nest point.

[0122] Further, based on any of the above embodiments, the reachable range determination module 100 may include:

[0123] The UAV coverage radius determination unit is used to determine the UAV coverage radius based on the UAV's flight range and inspection points; wherein the reachable range of the UAV includes the UAV coverage radius.

[0124] Further, based on any of the above embodiments, the initial machine nest point determination module 200 may include:

[0125] An initial machine nest point determination unit, used to determine K initial machine nest points;

[0126] The initial nest point determination unit is used to perform cluster analysis using the K initial nest points as cluster centers and the coverage radius of the drone as the distance r to obtain a set of inspection points corresponding to each initial nest point.

[0127] Further, based on any of the above embodiments, the nest removal priority sequence determination module 300 may include:

[0128] An inspection frequency determination unit, used to determine an inspection parameter of each inspection point as an inspection frequency;

[0129] a removal level parameter determination unit, configured to determine all inspection frequencies corresponding to each of the initial machine nest points, and obtain a removal level parameter corresponding to each of the initial machine nest points based on all the inspection frequencies;

[0130] The machine nest removal priority sequence determining unit is configured to sort the initial machine nest points according to the removal level parameter to obtain the machine nest removal priority sequence.

[0131] Further, based on any of the above embodiments, the machine nest point position adjustment module 400 may include:

[0132] A to-be-allocated inspection point determination unit, configured to determine a first removed machine nest point based on the machine nest removal priority sequence, and use the inspection point corresponding to the first removed machine nest point as the to-be-allocated inspection point;

[0133] The nearest machine nest point determination unit is used to determine the nearest machine nest point corresponding to each inspection point to be assigned, with the goal of minimizing the distance between each inspection point to be assigned and the remaining machine nest points;

[0134] A weighted center position determination unit, configured to calculate the weighted center position of each point covered by the nearest nest point, with the minimum nest movement distance as the goal;

[0135] The moving unit is used to move each of the nearest machine nest points in a direction from its current position to the corresponding weighted center position to obtain the target machine nest point after the movement.

[0136] Furthermore, based on the above embodiment, the nearest nest point determination unit may include:

[0137] The nearest machine nest point determination subunit is used to determine the nearest machine nest point corresponding to each inspection point to be assigned with the goal of minimizing the weighted sum of squared distances between each inspection point and the remaining machine nest points; wherein, in the process of determining the weighted sum of squared distances between the inspection point and the remaining machine nest points, the weighting method is to perform weighting based on the inspection parameters of each inspection point to be assigned.

[0138] Furthermore, based on any of the above embodiments, the drone nest site selection device may further include:

[0139] A module for determining the area where a machine nest can be deployed, which is used to determine the area where a machine nest can be deployed based on the conditions for machine nest deployment, energy supply, communication, and operation and maintenance convenience;

[0140] A judgment module, configured to determine whether each initial machine nest point is located in the area where the machine nest can be arranged;

[0141] The module for moving to an area where a machine nest can be arranged is used to move the current initial machine nest point to the nearest area where a machine nest can be arranged if it is not already there.

[0142] It should be noted that the order of the modules and units in the above-mentioned drone nest site selection device can be changed without affecting the logic.

[0143] The drone nest site selection device provided by the embodiment of the present invention may include: a reachable range determination module 100, configured to determine the reachable range of the drone based on the drone's flight range and inspection points;

[0144] An initial machine nest point determination module 200 is configured to determine an initial machine nest point corresponding to each inspection point based on the reachable range, and obtain an inspection point set corresponding to each initial machine nest point;

[0145] The machine nest removal priority sequence determination module 300 is used to generate a machine nest removal priority sequence according to the inspection parameters of each inspection point in the inspection point set corresponding to each initial machine nest point;

[0146] The machine nest point location adjustment module 400 is used to remove the initial machine nest points in sequence based on the machine nest removal priority sequence, and adjust the positions of the remaining machine nest points after removing the initial machine nest points until the remaining machine nest points cannot meet the full coverage constraint condition, thereby obtaining the target machine nest point. The current deployment of machine nest points mostly relies on manual experience and lacks a scientific and systematic site selection mechanism. There are problems such as low site selection efficiency, poor coverage capability, high energy consumption, and difficult maintenance. The present invention adopts an efficient two-stage machine nest site selection method. In the first stage, enough initial machine nest points are arranged to cover all inspection points; in the second stage, the initial machine nest points are removed and the remaining machine nest points are re-located until no more machine nest points can be removed, thereby covering all inspection points with the lowest number of machine nest points, thereby improving the efficiency and accuracy of drone nest site selection on the basis of reducing energy consumption.

[0147] The following is an introduction to a drone nest site selection device provided by an embodiment of the present invention. The drone nest site selection device described below and the drone nest site selection method described above can be referenced to each other.

[0148] Please refer to Figure 5 , Figure 5 A schematic structural diagram of a drone nest site selection device provided in an embodiment of the present invention may include:

[0149] Memory 10, for storing computer programs;

[0150] The processor 20 is used to execute a computer program to implement the above-mentioned drone nest site selection method.

[0151] The memory 10 , the processor 20 , and the communication interface 30 all communicate with each other via a communication bus 40 .

[0152] In the embodiment of the present invention, the memory 10 is used to store one or more programs. The program may include program code, and the program code includes computer operation instructions. In the embodiment of the present invention, the memory 10 may store programs for implementing the following functions:

[0153] Determine the reach of the drone based on its flight range and inspection points;

[0154] Determine the initial machine nest point corresponding to each inspection point based on the reachable range, and obtain the inspection point set corresponding to each initial machine nest point;

[0155] Generate a machine nest removal priority sequence based on the inspection parameters of each inspection point in the inspection point set corresponding to each initial machine nest point;

[0156] The initial nest points are removed in sequence based on the nest removal priority sequence. After removing the initial nest points, the positions of the remaining nest points are adjusted until the current remaining nest points cannot meet the full coverage constraint condition, and the target nest point is obtained.

[0157] In one possible implementation, the memory 10 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and applications required for at least one function, etc.; the data storage area may store data created during use.

[0158] In addition, the memory 10 may include a read-only memory and a random access memory, and provides instructions and data to the processor. A portion of the memory may also include NVRAM. The memory stores an operating system and operating instructions, executable modules or data structures, or a subset or an extended set thereof. The operating instructions may include various operating instructions for implementing various operations. The operating system may include various system programs for implementing various basic tasks and processing hardware-based tasks.

[0159] The processor 20 may be a central processing unit (CPU), an application-specific integrated circuit, a digital signal processor, a field programmable gate array, or other programmable logic device. The processor 20 may be a microprocessor or any conventional processor. The processor 20 may call a program stored in the memory 10 .

[0160] The communication interface 30 may be an interface of a communication module, and is used to connect to other devices or systems.

[0161] Of course, it needs to be explained that Figure 5 The structure shown does not constitute a limitation on the drone nest site selection device in the embodiment of the present invention. In actual applications, the drone nest site selection device may include Figure 5 More or fewer components than shown, or combinations of certain components.

[0162] The following introduces the computer-readable storage medium (readable storage medium) provided in an embodiment of the present invention. The computer-readable storage medium described below and the drone nest site selection method described above can be referenced to each other.

[0163] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned drone nest site selection method are implemented.

[0164] The computer-readable storage medium may include: 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, etc., which can store program codes.

[0165] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. Reference can be made to the descriptions of the identical or similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and the relevant parts can be referred to the descriptions of the methods.

[0166] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0167] Finally, it should be noted that, in this document, relationships such as first and second, etc., are used solely to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0168] The above is a detailed introduction to the drone nest site selection method, device, equipment and readable storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for selecting a drone nest location, characterized in that: include: Determine the reach of the drone based on its flight range and inspection points; Determine an initial machine nest point corresponding to each inspection point based on the reachable range, and obtain a set of inspection points corresponding to each initial machine nest point; Generate a machine nest removal priority sequence according to the inspection parameters of each inspection point in the inspection point set corresponding to each initial machine nest point; The initial nest points are removed in sequence based on the nest removal priority sequence, and the positions of the remaining nest points are adjusted after the initial nest points are removed until the current remaining nest points cannot meet the full coverage constraint condition, thereby obtaining the target nest point.

2. The method for selecting a drone nest site according to claim 1, wherein: Determine the reach of the drone based on its flight range and inspection points, including: The coverage radius of the drone is determined based on the flight range and inspection points of the drone; wherein the reachable range of the drone includes the coverage radius of the drone.

3. The method for selecting a drone nest site according to claim 2, wherein: Determine an initial machine nest point corresponding to each inspection point based on the reachable range, and obtain a set of inspection points corresponding to each initial machine nest point, including: Determine K initial machine nest points; The K initial nest points are used as cluster centers, and the coverage radius of the drone is used as the distance r for cluster analysis to obtain a set of inspection points corresponding to each initial nest point.

4. The method for selecting a drone nest site according to any one of claims 1 to 3, wherein: Generate a machine nest removal priority sequence according to the inspection parameters of each inspection point in the inspection point set corresponding to each initial machine nest point, including: Determine the inspection parameter of each inspection point as the inspection frequency; Determine all inspection frequencies corresponding to each of the initial machine nest points, and obtain a removal level parameter corresponding to each of the initial machine nest points based on all the inspection frequencies; The initial machine nest points are sorted according to the removal level parameters to obtain the machine nest removal priority sequence.

5. The method for selecting a drone nest site according to claim 1, wherein: The initial nest points are removed in sequence based on the nest removal priority sequence. After the initial nest points are removed, the positions of the remaining nest points are adjusted until the remaining nest points cannot meet the full coverage constraint condition, thereby obtaining the target nest point, including: Determine the first machine nest point to be removed based on the machine nest removal priority sequence, and use the inspection point corresponding to the first machine nest point to be removed as the inspection point to be assigned; The goal is to minimize the distance between each inspection point to be assigned and the remaining machine nest points, and determine the nearest machine nest point corresponding to each inspection point to be assigned; Taking the minimum nest moving distance as the goal, calculate the weighted centroid position of each point covered by the nearest nest point; Each of the nearest machine nest points is moved in a direction from its current position to the corresponding weighted center position to obtain the target machine nest point after the movement.

6. The method for selecting a drone nest site according to claim 5, wherein: The goal is to minimize the distance between each inspection point to be assigned and the remaining machine nest points, and determine the nearest machine nest point corresponding to each inspection point to be assigned, including: The goal is to minimize the sum of the weighted square distances between each inspection point and the remaining machine nest points, and determine the nearest machine nest point corresponding to each inspection point to be assigned; wherein, in the process of determining the sum of the weighted square distances between the inspection point and the remaining machine nest points, the weighting method is to weight based on the inspection parameters of each inspection point to be assigned.

7. The method for selecting a drone nest site according to claim 1, wherein: After determining the initial machine nest point corresponding to each inspection point based on the reachable range and obtaining the inspection point set corresponding to each initial machine nest point, the method further includes: Determine the area where the machine nest can be deployed based on the conditions for machine nest deployment, energy supply, communication, and operation and maintenance convenience; Determining whether each initial machine nest point is in the area where the machine nest can be arranged; If not, the current initial machine nest point is moved to the nearest area where a machine nest can be arranged.

8. A drone nest site selection device, characterized in that: include: A reach determination module is used to determine the reach of the drone based on the drone's flight range and inspection points; An initial machine nest point determination module is used to determine the initial machine nest point corresponding to each inspection point based on the reachable range, and obtain a set of inspection points corresponding to each initial machine nest point; A machine nest removal priority sequence determination module, configured to generate a machine nest removal priority sequence according to the inspection parameters of each inspection point in the inspection point set corresponding to each initial machine nest point; The machine nest point position adjustment module is used to remove the initial machine nest point in sequence based on the machine nest removal priority sequence, and adjust the positions of the remaining machine nest points after removing the initial machine nest point until the current remaining machine nest points cannot meet the full coverage constraint condition, thereby obtaining the target machine nest point.

9. A drone nest site selection device, characterized in that: include: Memory for storing computer programs; A processor, configured to execute the computer program to implement the steps of the drone nest site selection method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the drone nest site selection method according to any one of claims 1 to 7.

Images