Low-altitude monitoring network deployment method and system based on unmanned aerial vehicle nest

Abstract

The invention discloses a low-altitude monitoring network deployment method and system based on an unmanned aerial vehicle nest. The method comprises the following steps: screening out an unmanned aerial vehicle nest pre-selected point position set meeting a nest deployment condition; the method comprises the steps of determining a monitoring area range needing to be covered according to a monitoring task, performing variable-scale gridding processing on the monitoring area range based on terrain and earth surface information, taking a grid unit as a monitoring demand object, and adjusting the grid unit to obtain a monitoring area; constructing an unmanned aerial vehicle nest deployment problem model; based on the unmanned aerial vehicle nest deployment problem model, solving an optimal nest deployment scheme through a heuristic search algorithm; and when the deployment environment is changed, quickly determining and deploying a new unmanned aerial vehicle nest position through an unmanned aerial vehicle nest deployment problem model based on the deployed nest position. According to the invention, the unmanned aerial vehicle nest deployment strategy is optimized, so that the monitoring coverage capability and the response speed to emergencies are greatly improved, and the requirements of low-altitude monitoring tasks are met.

Description

Technical Field

[0001] The present invention relates to the technical field of low-altitude monitoring, and in particular to a method and system for deploying a low-altitude monitoring network based on an unmanned aerial vehicle (UAV) nest. Background Art

[0002] Low-altitude monitoring tasks place extremely high demands on real-time and efficiency. With their high efficiency, flexibility and easy deployment, drones have become an important tool in low-altitude monitoring. However, in practical applications, due to the wide distribution of natural resources and the complexity of terrain, factors such as drone endurance, flight distance and inspection range limit their ability to continuously monitor over a large area. Drone nests provide drones with centralized take-off and landing, charging, maintenance and storage functions, enabling multiple drones to continuously perform aerial monitoring, patrols and mission operations in one area. Due to restrictions such as complex terrain, uneven distribution of buildings and the existence of flight restricted areas, optimizing the deployment of drone nests has become a key challenge. Existing technologies lack a systematic deployment method under complex terrain and limited resources, resulting in low efficiency of monitoring tasks and high operating costs. Therefore, how to optimize the deployment of drone nests so that they can complete efficient coverage of the monitoring area within limited time and resources to meet the needs of natural resource monitoring tasks is a key issue that needs to be overcome in the current technical field. Summary of the invention

[0003] Based on this, the present invention provides a method and system for deploying a low-altitude monitoring network based on drone nests in order to solve the problem of how to optimize the deployment of drone nests so that they can efficiently cover the monitoring area within limited time and resources.

[0004] The first aspect of the present invention provides a method for deploying a low-altitude monitoring network based on a drone nest, comprising:

[0005] Based on the real-life three-dimensional building model and the no-fly zone information, the pre-selected deployment points of the drone nest are obtained, and a set of pre-selected drone nest points that meet the nest deployment conditions are screened out according to the deployment restriction conditions; the deployment restriction conditions include flat roofs, high-rise buildings, surrounding environments, and no-fly zones;

[0006] Determine the scope of the monitoring area to be covered according to the monitoring task, perform variable-scale grid processing on the monitoring area based on the terrain and surface information of the digital elevation model and digital surface model, take the grid unit as the monitoring demand object, consider the adjustment of the grid unit due to the no-fly information and the complexity of the terrain and buildings, and obtain the monitoring area;

[0007] Define a set of demand objects and a set of pre-selected locations for drone nests, set decision variables to indicate whether to deploy nests at pre-selected locations, set decision variables to indicate whether demand objects are monitored by specific nests, and build a drone nest deployment problem model;

[0008] Based on the UAV nest deployment problem model, the optimal nest deployment solution is solved by a heuristic search algorithm;

[0009] Based on the existing set of pre-selected drone nest locations, determine whether there is a change in the deployment environment. If so, quickly determine and deploy a new drone nest location based on the deployed nest location through the drone nest deployment problem model.

[0010] The acquisition of the pre-selected deployment point of the drone nest includes:

[0011] Flat-roofed buildings are identified based on real-life 3D building data, and buildings with a roof slope less than 5° and a roof area greater than 200 square meters are selected as pre-selected deployment points for drone nests;

[0012] Select high-rise buildings higher than 20 meters with power supply and network connection conditions as the pre-selected deployment points for drone nests;

[0013] Evaluate the flight adaptability within 50 meters around the candidate points, and select candidate points without tall obstacles and with an environment suitable for drone take-off, landing and flight as pre-selected deployment points for drone nests;

[0014] Eliminate candidate points that are within the no-fly zone or within 100 meters of the no-fly zone boundary.

[0015] The acquisition of the monitoring area includes:

[0016] After determining the scope of the monitoring area, the monitoring area is gridded, each grid unit is defined as a monitoring requirement object, and the grid division takes terrain characteristics into consideration, and the high terrain or complex terrain area is further divided to obtain the monitoring area.

[0017] The construction of the UAV nest deployment problem model includes:

[0018] Define the required object set I and the drone nest pre-selected point set J, where i∈I, j∈J, and set the coverage radius of the drone nest to r j , combined with the terrain and building features around the drone nest deployment point, the monitoring range of each nest is pre-defined; the decision variable X is introduced j and Y ij , X j ∈{0,1},Y ij ∈{0,1},

[0019]

[0020] Among them, r h ≤r j ≤r max , r h represents the standard minimum coverage radius, r max Indicates the standard maximum coverage radius;

[0021] Based on the decision variable X j and Y ij , the drone nest deployment problem is modeled as an integer linear programming problem, whose goal is to minimize the number of drone nest deployments while achieving full coverage of the monitoring area. The objective function expression is:

[0022]

[0023] in, Indicates the number of nests that need to be selected. For penalty items;

[0024] The addition of the penalty term in the objective function allows the model to prioritize the nests with smaller radius to ensure coverage quality, while allowing the number of nests to be reduced by expanding the radius; if the coverage radius of the nest is set to exceed the standard minimum coverage radius r h , then the penalty term is calculated as:

[0025] P j =λ·(r j -r h )·X j ;

[0026] Among them, λ represents the penalty coefficient.

[0027] The solution of the optimal machine nest deployment plan includes:

[0028] A heuristic search algorithm is used to solve the drone nest deployment model; the heuristic search algorithm continuously iterates and optimizes in the search space until a preset goal is reached and stops, outputting the optimal solution for the drone nest deployment plan.

[0029] The determination and deployment of new drone nest locations includes:

[0030] If the deployment environment changes, the deployment plan needs to be adjusted quickly to restore the monitoring capability. The drone nest deployment problem model simulates and calculates the coverage of the nest with a changed deployment environment to identify the required objects that cannot be effectively covered.

[0031] New pre-selected points are introduced, and their contribution to the restoration of coverage capability is calculated. The heuristic search algorithm is used to solve the optimal new machine nest deployment plan and determine the deployment location of the new machine nest.

[0032] The second aspect of the present invention provides a low-altitude monitoring network deployment system based on a drone nest, comprising:

[0033] The drone nest pre-selected point set screening module is used to obtain the drone nest pre-selected deployment points based on the real-life 3D building model and the no-fly zone information, and screen out the drone nest pre-selected point set that meets the nest deployment conditions according to the deployment restriction conditions;

[0034] The monitoring area acquisition module is used to determine the monitoring area range that needs to be covered according to the monitoring task, and to perform variable-scale grid processing on the monitoring area range based on the terrain and surface information of the digital elevation model and the digital surface model. The grid unit is used as the monitoring demand object, and the grid unit is adjusted considering the no-fly information and the complexity of the terrain and buildings to obtain the monitoring area;

[0035] The module for constructing the model of the drone nest deployment problem is used to define a set of demand objects and a set of pre-selected points for drone nests, set decision variables to indicate whether to deploy drone nests at pre-selected points, set decision variables to indicate whether the demand objects are monitored by specific drone nests, and construct a drone nest deployment problem model;

[0036] An optimal nest deployment solution solving module is used to solve the optimal nest deployment solution through a heuristic search algorithm based on the UAV nest deployment problem model;

[0037] The new drone nest location deployment module is used to determine whether there is a change in the deployment environment based on the existing drone nest pre-selected point set. If so, the new drone nest location is quickly determined and deployed based on the deployed drone nest location through the drone nest deployment problem model.

[0038] According to a third aspect of the present invention, there is provided an electronic device, comprising: a processor; and a memory storing a program, wherein the program comprises instructions, which, when executed by the processor, cause the processor to execute the method described above.

[0039] A fourth aspect of the present invention provides a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions implement the above-described method when executed by a processor.

[0040] Beneficial effects: The present invention combines a variety of data such as three-dimensional real-life building models, digital elevation models, digital surface models, and no-fly information to reasonably screen the pre-selected deployment points of drone nests, and improve the adaptability of complex terrain through multi-scale grid division; based on integer linear programming mathematical methods, the drone nest deployment problem model is optimized to build a comprehensive and efficient drone nest deployment plan to ensure full coverage of the monitoring area and minimize the nest deployment cost. Combined with the heuristic search algorithm, the system can quickly solve the optimal deployment plan and quickly generate a new nest deployment plan in an emergency situation to ensure the stability and flexibility of the monitoring network.

[0041] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The accompanying drawings are used to better understand the present invention and do not constitute a limitation of the present invention.

[0043] Figure 1 It is a flow chart of a method for deploying a low-altitude monitoring network of a drone nest provided by the present invention;

[0044] Figure 2a This is a schematic diagram of the deployment of pre-selected points of drone nests provided by the present invention;

[0045] Figure 2b is a schematic diagram of multi-scale grid division processing of the monitoring area provided by the present invention;

[0046] Figure 3 is a schematic diagram of an optimal machine nest deployment solution provided according to the present invention;

[0047] Figure 4a It is a schematic diagram of the impact area after the existing machine nest provided by the present invention is damaged due to unforeseen factors;

[0048] Figure 4b This is a schematic diagram of the new drone nest position deployment effect provided by the present invention;

[0049] Figure 5 This is a schematic diagram of a low-altitude monitoring network deployment system for a drone nest provided by the present invention;

[0050] Figure 6 is a block diagram of an electronic device provided according to the present invention. DETAILED DESCRIPTION

[0051] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0052] The first aspect of the present invention provides a method for deploying a low-altitude monitoring network based on a drone nest, comprising:

[0053] The flow chart of the low-altitude monitoring network deployment method for drone nests is as follows: Figure 1 shown.

[0054] S1: Based on the real-life 3D building model and no-fly zone information, the pre-selected deployment points of the drone nest are obtained, and the set of pre-selected drone nest points that meet the nest deployment conditions are screened out according to the deployment restrictions. It should be noted that:

[0055] The deployment constraints include flat roofs, high-rise buildings, surrounding environments, and no-fly zones;

[0056] The acquisition of the pre-selected deployment point of the drone nest includes:

[0057] ① Screening of flat-roofed buildings: Identify flat-roofed buildings based on real-life 3D building data, and select buildings with a roof slope of less than 5° and a roof area of ​​more than 200 square meters as pre-selected deployment points for drone nests;

[0058] ② High-rise building screening: select high-rise buildings higher than 20 meters with power supply and network connection conditions as the pre-selected deployment points for drone nests;

[0059] ③Surrounding environment screening: Evaluate the flight adaptability within 50 meters around the candidate point, and select the candidate point without tall obstacles and the environment suitable for drone take-off and landing as the pre-selected deployment point of the drone nest;

[0060] ④ Eliminate no-fly zones: Eliminate candidate points within the no-fly zone or within 100 meters of the no-fly zone boundary.

[0061] Figure 2a Schematic diagram of the pre-selected deployment points for drone nests.

[0062] S2: Determine the scope of the monitoring area that needs to be covered according to the monitoring task, perform variable-scale grid processing on the monitoring area based on the terrain and surface information of the digital elevation model and the digital surface model, take the grid unit as the monitoring demand object, consider the adjustment of the grid unit due to the no-fly information and the complexity of the terrain and buildings, and obtain the monitoring area; according to the requirements of the natural resource monitoring task, this embodiment delineates the monitoring area and performs multi-scale grid processing, dynamically adjusts the deployment density of the drone nest, and improves the adaptability to complex terrain and monitoring accuracy. It should be noted that:

[0063] The acquisition of the monitoring area includes:

[0064] After determining the scope of the monitoring area, the monitoring area is gridded, each grid unit is defined as a monitoring requirement object, and the grid division takes terrain characteristics into consideration, and the high terrain or complex terrain area is further divided to obtain the monitoring area. Figure 2b Schematic diagram of multi-scale grid division and processing of the monitoring area.

[0065] This embodiment uses Yuhang District of Hangzhou City as the coverage area of ​​the natural resources monitoring task. After determining the regional scope, this embodiment uses a digital elevation model to perform variable-scale grid processing on the study area. Specifically, for areas below 500 meters above sea level, a grid of 1500 meters × 1500 meters is used for division; for mountainous areas above 500 meters above sea level, due to its complex terrain, a grid of 750 meters × 750 meters is used to enhance the monitoring capability of complex terrain. This embodiment defines each divided grid unit as a monitoring requirement object. Special consideration is given to the restrictions of restricted flight zones, and the no-fly zones are excluded from the grid to avoid including the no-fly zones in the monitoring coverage, thereby ensuring the flight safety of the drone.

[0066] S3: Define the set of demand objects and the set of pre-selected locations of drone nests, set decision variables to indicate whether to deploy nests at pre-selected locations, set decision variables to indicate whether the demand objects are monitored by specific nests, and build a model for the deployment of drone nests;

[0067] like Figure 3 Shown is a schematic diagram of the optimal machine nest deployment solution obtained by using the method of the present invention in an exemplary embodiment of the present application.

[0068] The construction of the UAV nest deployment problem model includes:

[0069] Define the required object set I and the drone nest pre-selected point set J, where i∈I, j∈J, and set the coverage radius of the drone nest to r j , combined with the terrain and building features around the drone nest deployment point, the monitoring range of each nest is pre-defined; the decision variable X is introduced j and Yij , X j ∈{0,1},Y ij ∈{0,1},

[0070]

[0071] Among them, r h ≤r j ≤r max , r h represents the standard minimum coverage radius, r max Indicates the standard maximum coverage radius;

[0072] Y ij It can be specifically expressed as a reachability matrix between a demand object and a machine nest:

[0073]

[0074] Among them, m represents the number of demand objects, and n represents the number of pre-selected points of drone nests;

[0075] Furthermore, the accessibility between the drone nest and the grid demand object is determined through distance measurement and GIS geographic analysis. The specific steps of the accessibility analysis are as follows: (1) Determine whether the distance is within the safe working distance: calculate the straight-line distance from the nest to the grid demand object, and determine whether it is within the safe working range. (2) Determine whether there are flight obstacles in the middle: according to the flight altitude and path from the nest to the demand object, check whether there are mountains, buildings and other obstructions through line of sight analysis. If the route is blocked, the path is considered unreachable. If the distance between the drone nest and the grid demand object is within the safe working range and it is confirmed that there are no flight obstacles, then Y is given. ij Assign a value of 1 if it is within the reachable range, otherwise 0.

[0076] Based on the decision variable X j and Y ij , the drone nest deployment problem is modeled as an integer linear programming problem, whose goal is to minimize the number of drone nest deployments while achieving full coverage of the monitoring area. The objective function expression is:

[0077]

[0078] in, Indicates the number of nests that need to be selected. is a penalty term used to balance the number of nests and coverage effect;

[0079] If the coverage radius of the machine nest is set to exceed the standard minimum coverage radius r h , then the penalty term is calculated as:

[0080] Pj =λ·(r j -r h )·X j ;

[0081] Among them, λ represents the penalty coefficient, λ∈[0,1], which is used to control the penalty intensity.

[0082] The addition of a penalty term in the objective function encourages the priority selection of nests with smaller radii to ensure coverage quality, while allowing the number of nests to be reduced by expanding the radius.

[0083] Furthermore, the constraints of the drone nest deployment problem model are as follows:

[0084]

[0085] in, is the coverage constraint, ensuring that all required objects i can be covered by at least one drone nest deployed at the pre-selected point j to ensure full coverage of the monitoring area; r j +(1-Y ij )·M≥d ij is the radius constraint, which means that when the machine nest deployment point j is selected to monitor the demand object i (i.e. Y ij =1) Covering radius r j It must be ensured to be greater than the distance d from the required object i to the machine nest j ij , M is a sufficiently large constant to ensure that the constraint does not affect the result when the machine nest is not selected; X j ∈{0,1} and Y ij ∈{0,1} is a parameter constraint, for X j and Y ij The value of is constrained to ensure the integrity and operability of the model; 0≤P j ≤1 constrains the penalty term to ensure that its value is between 0 and 1.

[0086] The model takes into account the actual needs of drone nest deployment and performs reasonable modeling. By introducing coverage constraints, the comprehensiveness of the monitoring task is ensured. The design of the objective function enables the model to optimize the selection of nests as much as possible while ensuring coverage requirements, and reasonably balance the number of nests and coverage effects, thereby achieving more efficient resource allocation.

[0087] S4: Based on the UAV nest deployment problem model, solving the optimal nest deployment solution through a heuristic search algorithm;

[0088] The solution of the optimal machine nest deployment plan includes:

[0089] A heuristic search algorithm is used to solve the drone nest deployment model; the heuristic search algorithm continuously iterates and optimizes in the search space until a preset goal is reached and stops, outputting the optimal solution for the drone nest deployment plan.

[0090] The heuristic search algorithm first gives priority to those points that can cover more demand objects as the initial points. Secondly, through the iterative process of heuristic search, local adjustments are continuously made, such as adding or removing points to optimize the coverage effect and deployment quantity. After each adjustment, the objective function value is recalculated, and a better solution is found near the current solution through neighborhood search, and the solution with the best objective function value is continuously selected for optimization. The algorithm stops after reaching the preset goal (all constraints are met, and the objective function value does not improve after multiple iterations), outputs the current optimal solution, and determines the best machine nest deployment plan.

[0091] A heuristic search algorithm is used to solve the optimal machine nest deployment plan. The specific process is as follows.

[0092] (1) Initial solution setting

[0093] In the complex search space, the pre-selected points that can cover more demand objects are preferentially selected as the initial solution, and the initial radius of the drone nest is uniformly set to the standard minimum coverage radius r h , as the initial solution (x (0) ,r (0) );

[0094] (2) Iterative Update

[0095] In each iteration, update the current solution and select the current optimal nest position x (k) And coverage radius r (k) ; The optimization process can be expressed as:

[0096]

[0097] Among them, x (k) represents the optimal solution selected in the kth iteration, f(x j ,r j ) represents the objective function, (x j ,r j ) represents the location of the machine nest and the corresponding coverage radius that can minimize the objective function under the premise of satisfying all constraints;

[0098] If the current configuration meets all constraints, continue to optimize; otherwise, adjust the drone nest position or coverage radius to improve the coverage effect; use the neighborhood search method to continue to explore possible better solutions in the neighborhood of the current solution to ensure local optimization and gradually approach the global optimal solution;

[0099] (3) Evaluate the current solution

[0100] After each local adjustment iteration, the objective function value of the current solution is evaluated:

[0101] Z k =f(x (k) ,r (k) );

[0102] Among them, Z k represents the objective function value of the kth iteration, f(x (k) ,r (k) ) represents the current solution x (k) and r (k) The corresponding objective function;

[0103] (4) Termination conditions

[0104] The iterative process of the heuristic search algorithm will continue until the following preset termination conditions are met: Constraints are all satisfied, and the objective function value no longer improves after multiple iterations:

[0105] |Z (k+1) -Z (k) |<∈;

[0106] Among them, |Z (k+1) -Z (k) | represents the difference between the objective function values ​​of the k+1th and kth iterations, ∈ is a small threshold indicating the allowable error; when |Z (k+1) -Z (k) When the value of | is less than ∈, it means that the objective function value has stabilized and the heuristic search algorithm can be terminated; the heuristic search algorithm stops after reaching the optimization goal and outputs the final optimal machine nest deployment plan. Through the above steps (1) to (4), the heuristic search algorithm can efficiently search and find the optimal or approximately optimal solution that meets the objectives and constraints.

[0107] S5: Based on the existing set of pre-selected drone nest locations, determine whether there is a change in the deployment environment. If so, quickly determine and deploy a new drone nest location based on the deployed nest location through the drone nest deployment problem model.

[0108] The determination and deployment of new drone nest locations includes:

[0109] If the deployment environment changes, the deployment plan needs to be adjusted quickly to restore the monitoring capability. The drone nest deployment problem model simulates and calculates the coverage of the nest with a changed deployment environment to identify the required objects that cannot be effectively covered.

[0110] New pre-selected points are introduced, and their contribution to the restoration of coverage capability is calculated. The heuristic search algorithm is used to solve the optimal new machine nest deployment plan and determine the deployment location of the new machine nest.

[0111] Figure 4a The area affected by the damage of the existing engine nest due to unforeseen factors. Figure 4b This is an illustration of the new drone nest deployment effect.

[0112] This embodiment first simulates the coverage of the machine nest with a changed deployment environment, and calculates the required objects that cannot be covered due to the change in the deployment environment, such as Figure 4a As shown. Based on the existing nest, by introducing new pre-selected points for analysis, the potential contribution of each new point to the restoration of coverage is calculated. Combined with the original undamaged nest position, the new nest candidate points that can maximize the restoration of coverage are quickly screened out, such as Figure 4b As shown. In this process, this embodiment does not need to globally solve the overall solution, but adopts a local optimization strategy to give priority to those points that can restore the coverage of key areas the fastest. Through rapid iteration, the coverage effect of each newly added point is locally adjusted, and efficient solutions are deployed preferentially according to the needs of the affected area. This optimization method can provide a quick recovery solution for damage in a short time.

[0113] This embodiment uses Yuhang District of Hangzhou as the experimental area, with a total monitoring range of 942 square kilometers. The original data used in the experiment include urban three-dimensional building models, construction land and cultivated land range vector data, drone no-fly zone range vector data and digital elevation model (DEM) data. In order to verify the superiority of the method of the present invention, the algorithm proposed in the present invention is experimentally compared with the traditional manual deployment method based on empirical rules. The evaluation indicators of the deployment results include the required number of nests, regional coverage, average effective coverage area of ​​each nest, boundary blind area, coverage redundancy rate, etc. The specific results are shown in Table 1.

[0114] Table 1 Comparison of the effects of manual deployment and algorithm deployment methods

[0115]

[0116] The comparative experimental results show that the deployment method proposed in the present invention is significantly superior to the traditional manual deployment method in terms of multiple key indicators. Specifically, while reducing the number of drone nests, this method increases the regional coverage rate to 100%, increases the effective coverage area by 17.8%, and completely eliminates the monitoring blind spots, greatly improving the comprehensiveness and accuracy of monitoring. The coverage redundancy rate is reduced from 24% to 13%, significantly optimizing the resource utilization efficiency. The experimental results demonstrate the advantages of the algorithm deployment method in terms of economy, monitoring performance, and resource allocation, and provide strong support for the scientific deployment of the UAV low-altitude monitoring network.

[0117] In a second aspect, the present invention provides a low-altitude monitoring network deployment system based on a drone nest (such as Figure 5 shown), including:

[0118] The drone nest pre-selected point set screening module 1 is used to obtain the drone nest pre-selected deployment points based on the real-life three-dimensional building model and the no-fly zone information, and screen out the drone nest pre-selected point set that meets the nest deployment conditions according to the deployment restriction conditions;

[0119] Monitoring area acquisition module 2 is used to determine the scope of the monitoring area to be covered according to the monitoring task, perform variable-scale grid processing on the monitoring area based on the terrain and surface information of the digital elevation model and the digital surface model, take the grid unit as the monitoring requirement object, consider the adjustment of the grid unit due to the no-fly information and the complexity of the terrain and buildings, and obtain the monitoring area;

[0120] The drone nest deployment problem model building module 3 is used to define a set of demand objects and a set of pre-selected points for drone nests, set decision variables to indicate whether to deploy drone nests at pre-selected points, set decision variables to indicate whether the demand objects are monitored by specific drone nests, and build a drone nest deployment problem model;

[0121] The optimal nest deployment solution solving module 4 is used to solve the optimal nest deployment solution through a heuristic search algorithm based on the drone nest deployment problem model;

[0122] The new drone nest location deployment module 5 is used to determine whether there is a change in the deployment environment based on the existing drone nest pre-selected point set. If so, the new drone nest location is quickly determined and deployed based on the deployed nest location through the drone nest deployment problem model.

[0123] According to a third aspect of the present invention, there is provided an electronic device, comprising: a processor; and a memory storing a program, wherein the program comprises instructions, which, when executed by the processor, cause the processor to execute the method described above.

[0124] like Figure 6 As shown, the electronic device 100 is the core processing unit of the system, which undertakes the key tasks of data processing and algorithm execution. The device is mainly composed of a processor 101 and a memory 103, which are connected via a bus 102 to achieve efficient information transmission and data processing. The structure of the electronic device 100 does not constitute a limitation of the embodiments of the present application.

[0125] The processor 101 can be a CPU, DSP, ASIC, FPGA or other programmable logic device, which is specially designed to execute the logical framework and algorithm related to the deployment of drone nests. Its functions include real-time data analysis, monitoring area division, and solution of the best deployment plan, etc., to ensure the efficient operation of the drone nest low-altitude monitoring network in a complex environment.

[0126] The bus 102 is used to transmit information between the processor 101 and the memory 103. It can be a PCI bus or an EISA bus, and supports multiple data transmission modes, including address, data, and control signals. This design ensures real-time data processing and feedback, so that the system can quickly respond to changes in monitoring tasks and optimize the deployment strategy of the drone nest. For ease of representation, Figure 6 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0127] The memory 103 may include various types of storage devices such as ROM, RAM, or any other medium that can be used to store program codes in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 103 is used to store static information and dynamic data required for the deployment of the drone nest low-altitude monitoring network. It can store algorithms, model parameters, flight paths, and deployment strategies related to the monitoring tasks to ensure that the system can efficiently call and process this information during execution.

[0128] A fourth aspect of the present invention provides a computer-readable storage medium having computer program instructions stored thereon, wherein the computer program instructions implement the above-described method when executed by a processor.

[0129] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the modules or units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed.

[0130] The units may or may not be physically separated, and the components displayed as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0131] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0132] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program codes.

[0133] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for deploying a low-altitude monitoring network based on a drone nest, characterized in that: include: Based on the real-life three-dimensional building model and the no-fly zone information, the pre-selected deployment points of the drone nest are obtained, and a set of pre-selected drone nest points that meet the nest deployment conditions are screened out according to the deployment restriction conditions; the deployment restriction conditions include flat roofs, high-rise buildings, surrounding environments, and no-fly zones; Determine the scope of the monitoring area to be covered according to the monitoring task, perform variable-scale grid processing on the monitoring area based on the terrain and surface information of the digital elevation model and digital surface model, take the grid unit as the monitoring demand object, consider the adjustment of the grid unit due to the no-fly information and the complexity of the terrain and buildings, and obtain the monitoring area; Define a set of demand objects and a set of pre-selected locations for drone nests, set decision variables to indicate whether to deploy nests at pre-selected locations, set decision variables to indicate whether demand objects are monitored by specific nests, and build a drone nest deployment problem model; Based on the UAV nest deployment problem model, the optimal nest deployment solution is solved by a heuristic search algorithm; Based on the existing set of pre-selected drone nest locations, determine whether there is a change in the deployment environment. If so, quickly determine and deploy a new drone nest location based on the deployed nest location through the drone nest deployment problem model.

2. The method for deploying a low-altitude monitoring network based on a drone nest according to claim 1 is characterized in that: The acquisition of the pre-selected deployment point of the drone nest includes: Flat-roofed buildings are identified based on real-life 3D building data, and buildings with a roof slope less than 5° and a roof area greater than 200 square meters are selected as pre-selected deployment points for drone nests; Select high-rise buildings higher than 20 meters with power supply and network connection conditions as the pre-selected deployment points for drone nests; Evaluate the flight adaptability within 50 meters around the candidate points, and select candidate points without tall obstacles and with an environment suitable for drone take-off, landing and flight as pre-selected deployment points for drone nests; Eliminate candidate points that are within the no-fly zone or within 100 meters of the no-fly zone boundary.

3. A method for deploying a low-altitude monitoring network based on a drone nest according to claim 1 or 2, characterized in that: The acquisition of the monitoring area includes: After determining the scope of the monitoring area, the monitoring area is gridded, each grid unit is defined as a monitoring requirement object, and the grid division takes terrain characteristics into consideration, and the high terrain or complex terrain area is further divided to obtain the monitoring area.

4. The method for deploying a low-altitude monitoring network based on a drone nest according to claim 3 is characterized in that: The construction of the UAV nest deployment problem model includes: Define the required object set I and the drone nest pre-selected point set J, where i∈I, j∈J, and set the coverage radius of the drone nest to r j , combined with the terrain and building features around the drone nest deployment point, the monitoring range of each nest is pre-defined; the decision variable X is introduced j and Y ij , X j ∈{0,1},Y ij ∈{0,1}, Among them, r h ≤r j ≤r max , r h represents the standard minimum coverage radius, r max Indicates the standard maximum coverage radius; Based on the decision variable X j and Y ij , the drone nest deployment problem is modeled as an integer linear programming problem, whose goal is to minimize the number of drone nest deployments while achieving full coverage of the monitoring area. The objective function expression is: in, Indicates the number of nests that need to be selected. For penalty items; If the coverage radius of the machine nest is set to exceed the standard minimum coverage radius r h , then the penalty term is calculated as: P j =λ·(r j -r h )·X j ; Among them, λ represents the penalty coefficient.

5. The method for deploying a low-altitude monitoring network based on a drone nest according to claim 4 is characterized in that: The solution of the optimal machine nest deployment plan includes: A heuristic search algorithm is used to solve the drone nest deployment model; the heuristic search algorithm continuously iterates and optimizes in the search space until a preset goal is reached and stops, outputting the optimal solution for the drone nest deployment plan.

6. The method for deploying a low-altitude monitoring network based on a drone nest according to claim 5 is characterized in that: The determination and deployment of new drone nest locations includes: If there is a change in the deployment environment, the deployment plan needs to be adjusted quickly to restore the monitoring capability. The drone nest deployment problem model simulates and calculates the coverage of the nest with a changed deployment environment to identify the required objects that cannot be effectively covered; New pre-selected points are introduced, and their contribution to the restoration of coverage capability is calculated. The heuristic search algorithm is used to solve the optimal new machine nest deployment plan and determine the deployment location of the new machine nest.

7. A system using the method for deploying a low-altitude monitoring network based on a drone nest as described in claims 1-6, characterized in that: include: The drone nest pre-selected point set screening module is used to obtain the drone nest pre-selected deployment points based on the real-life 3D building model and the no-fly zone information, and screen out the drone nest pre-selected point set that meets the nest deployment conditions according to the deployment restriction conditions; The monitoring area acquisition module is used to determine the monitoring area range that needs to be covered according to the monitoring task, and to perform variable-scale grid processing on the monitoring area range based on the terrain and surface information of the digital elevation model and the digital surface model. The grid unit is used as the monitoring demand object, and the grid unit is adjusted considering the no-fly information and the complexity of the terrain and buildings to obtain the monitoring area; The module for constructing the model of the drone nest deployment problem is used to define a set of demand objects and a set of pre-selected points for drone nests, set decision variables to indicate whether to deploy drone nests at pre-selected points, set decision variables to indicate whether the demand objects are monitored by specific drone nests, and construct a drone nest deployment problem model; An optimal nest deployment solution solving module is used to solve the optimal nest deployment solution through a heuristic search algorithm based on the UAV nest deployment problem model; The new drone nest location deployment module is used to determine whether there is a change in the deployment environment based on the existing drone nest pre-selected point set. If so, the new drone nest location is quickly determined and deployed based on the deployed drone nest location through the drone nest deployment problem model.

8. An electronic device comprising: processor; and a memory storing a program, wherein the program comprises instructions, which, when executed by the processor, cause the processor to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images