A method and system for UAV flight path planning based on electromagnetic environment data and 3D maps

Abstract

This application provides a method and system for UAV flight path planning based on electromagnetic environment data and 3D maps. The method involves acquiring 3D real-world images of a target area and constructing a 3D real-world model; locating electromagnetic radiation sources; obtaining electromagnetic radiation signals based on the located sources, analyzing the characteristics of the signals, and matching them with corresponding target electromagnetic radiation source model files; importing the target electromagnetic radiation source model files into the 3D real-world model to construct a comprehensive model; obtaining UAV flight path planning parameters; and performing flight path planning within the comprehensive model based on these parameters to obtain the target flight path. By accurately locating electromagnetic radiation sources and constructing a 3D comprehensive model containing their locations, the invisible electromagnetic field is visualized in real time, providing a clear and intuitive way to obtain the desired electromagnetic information. This method can use BP neural networks to plan detour paths and optimize flight paths based on the electromagnetic radiation source field strength, thereby improving the safety and effectiveness of UAV patrols.

Description

Technical Field

[0001] This application relates to the fields of UAV flight path planning and electromagnetic environment technology, and in particular to a method and system for UAV flight path planning based on electromagnetic environment data and three-dimensional maps. Background Technology

[0002] The electromagnetic environment's impact on UAV flight paths involves multiple critical systems, including navigation, communication, and control. Major hazards include: interference with navigation systems (e.g., strong electromagnetic fields near high-voltage lines or radar stations) or human interference (GPS spoofing) can cause UAVs to receive incorrect satellite signals); communication link interruptions, triggering UAV fail-safe protection mechanisms (e.g., return to home, hovering, or forced landing); and if GPS is also interfered with, complete loss of connection; flight control system malfunctions (e.g., electromagnetic pulses from lightning or military electronic warfare equipment can burn out flight control chips or cause sensors (IMU, barometer) to output abnormal data, leading to incorrect attitude calculations and violent shaking or rolling; and interference with the propulsion system (e.g., strong electric fields near high-voltage lines can interfere with electronic speed controller (ESC) signals, causing abnormal motor speeds and power imbalances, potentially resulting in direct crashes, especially for multi-rotor UAVs.

[0003] Due to limitations in current technology, the distribution of spatial electromagnetic fields in complex terrains and electromagnetic environments is often difficult to accurately grasp, and electromagnetic sources are hard to locate. Furthermore, the electromagnetic environment is invisible and intangible, further increasing the difficulty of exploration.

[0004] Therefore, designing a UAV route planning method based on electromagnetic environment data and 3D maps to visualize invisible electromagnetic fields in real time, obtain the desired electromagnetic information intuitively, and avoid the electromagnetic environment affecting the UAV's patrol route planning is an important research topic for those skilled in the art. Summary of the Invention

[0005] In view of this, it is necessary to provide a method for UAV route planning based on electromagnetic environment data and 3D maps. By accurately locating electromagnetic radiation sources and constructing a 3D comprehensive model containing the location of electromagnetic radiation sources, the invisible electromagnetic field can be visualized in real time, and the desired electromagnetic information can be obtained intuitively. It can use BP neural network to plan detour paths and optimize flight paths according to the field strength of electromagnetic radiation sources, thereby improving the safety and effectiveness of UAV patrols.

[0006] This application provides a method and system for UAV flight path planning based on electromagnetic environment data and 3D maps. The method involves acquiring 3D real-world images of a target area and constructing a 3D real-world model; locating electromagnetic radiation sources; obtaining electromagnetic radiation signals based on the located sources, analyzing the characteristics of the signals, and matching them with corresponding target electromagnetic radiation source model files; importing the target electromagnetic radiation source model files into the 3D real-world model to construct a comprehensive model; obtaining UAV flight path planning parameters; and performing flight path planning within the comprehensive model based on these parameters to obtain the target flight path. By accurately locating electromagnetic radiation sources and constructing a 3D comprehensive model containing their locations, the invisible electromagnetic field is visualized in real time, providing a clear and intuitive way to obtain the desired electromagnetic information. This method can use BP neural networks to plan detour paths and optimize flight paths based on the electromagnetic radiation source field strength, thereby improving the safety and effectiveness of UAV patrols.

[0007] In a first aspect, embodiments of this application provide a method for UAV route planning based on electromagnetic environment data and a three-dimensional map, the method comprising:

[0008] S1, acquire 3D real-world images of the target area and construct a 3D real-world model;

[0009] S2, Locating electromagnetic radiation sources based on drone scattering signals;

[0010] S3. Obtain electromagnetic radiation signals based on the location of the electromagnetic radiation source, analyze the characteristics of the electromagnetic radiation signals, and match the corresponding target electromagnetic radiation source model file.

[0011] S4. Import the target electromagnetic radiation source model file into the three-dimensional reality model to construct a comprehensive model;

[0012] S5. Obtain the UAV route planning parameters, and perform route planning in the integrated model according to the route planning parameters to obtain the target route.

[0013] Optionally, in one implementation of the first aspect of the present invention, step S1, acquiring a three-dimensional real-scene image of the target area and constructing a three-dimensional real-scene model, includes:

[0014] S1.1, High-resolution depth images captured by drones: By using a drone equipped with a high-resolution camera or oblique photography equipment, multi-view, high-overlap image data of the target area is acquired. The image data must include position and attitude information and positioning data. At the same time, lidar point cloud data is collected to assist in the acquisition of depth information.

[0015] S1.2, Image screening and preprocessing: The high-resolution depth image is screened to remove unqualified images, and qualified images are corrected, denoised, color-balanced, and enhanced.

[0016] S1.3, Image Matching and Adjustment Calculation: Image feature points are extracted using the SIFT algorithm, and corresponding relationships of corresponding points are established through multi-view matching. Combined with ground control point data, exterior orientation elements of each image are calculated through bundle adjustment iterative optimization, and the relative coordinates are transformed to the geodetic coordinate system.

[0017] S1.4, Sparse Point Cloud Denseening: An initial 3D point cloud is generated based on matching corresponding points; a multi-view stereo algorithm is used for pixel-by-pixel matching to generate a high-density point cloud;

[0018] S1.5, TIN Model Construction and Optimization: Dense point clouds are converted into irregular triangular meshes. An initial model is constructed using the Delaunay triangulation algorithm. The density of the triangular mesh is adjusted according to the curvature of the surface. Triangular patches are simplified in flat areas, while details are preserved in complex areas. Abnormal triangles are repaired to ensure the continuity of the triangular mesh structure.

[0019] S1.6, Texture Mapping and Model Generation: Based on the normal direction and spatial position of the TIN patch, the best texture is automatically selected from multi-view images; overlapping textures are uniformly colored and the seams are processed to ensure color consistency; the texture is associated with the geometric model to generate a 3D real-world model with real geographic coordinates and attribute information.

[0020] Optionally, in one implementation of the first aspect of the present invention, step S2, locating the electromagnetic radiation source based on the scattered signal from the UAV, includes:

[0021] By capturing the weak signal scattered by the UAV, the Doppler translation curve is obtained based on the Doppler frequency shift function;

[0022] Based on the Doppler translation curve, the Doppler frequency shift information generated by the UAV during its movement is extracted from the scattered signal;

[0023] By combining the real-time flight status of the UAV, a multi-source data fusion method is used to reverse analyze and determine the location of the ground electromagnetic radiation source.

[0024] Optionally, in one implementation of the first aspect of the present invention, determining the location of the ground electromagnetic radiation source includes:

[0025] Establish a three-dimensional spatial coordinate system, with the electromagnetic radiation source relative to time. The carrier frequency reaching the drone is:

[0026] ;

[0027] The carrier frequency that the drone's scattering reaches the ground receiver is:

[0028] ;

[0029] The Doppler frequency shift function of the electromagnetic radiation source obtained by the ground receiver is:

[0030] ,

[0031] in, The frequency of the electromagnetic radiation source, This indicates the speed at which electromagnetic waves propagate through the air. Indicates the drone's time The velocity vector, This represents the unit vector pointing from the electromagnetic radiation source to the location of the UAV. The unit vector representing the position of the ground receiver pointing to the position of the UAV;

[0032] To facilitate determining the location of the electromagnetic radiation source, the coordinate system is simplified as follows:

[0033] Establish a three-dimensional coordinate system with the ground as the reference plane, point O as the center, and the UAV's flight path as the X-axis. Let the UAV's altitude be a fixed value h and its speed be a fixed value v. Then, the UAV's time... The position is represented as The location of the ground receiver is indicated as The location of the electromagnetic radiation source is represented as Then the first The simplified Doppler frequency shift function of the electromagnetic radiation source at time t is:

[0034] ;

[0035] The location of the electromagnetic radiation source was calculated by substituting multiple sets of data into the simplified Doppler frequency shift function. , Indicates that drones are in The X-axis coordinate at time [time].

[0036] Optionally, in one implementation of the first aspect of the present invention, step S3, which involves acquiring an electromagnetic radiation signal based on the location of the electromagnetic radiation source, analyzing the characteristics of the electromagnetic radiation signal, and matching a corresponding target electromagnetic radiation source model file, includes:

[0037] Construct different electromagnetic radiation source model files;

[0038] Electromagnetic radiation signals are obtained based on the location of the electromagnetic radiation source;

[0039] The electromagnetic radiation signal is subjected to feature extraction to obtain electromagnetic fingerprint features;

[0040] The electromagnetic fingerprint features are input into the electromagnetic radiation source identification model to obtain the electromagnetic radiation source type;

[0041] Based on the identified electromagnetic radiation source type, obtain the target electromagnetic radiation source model file.

[0042] Optionally, in one implementation of the first aspect of the present invention, step S4, importing the target electromagnetic radiation source model file into the three-dimensional real-world model to construct a comprehensive model, includes:

[0043] Import the 3D reality model and extract its geometric topology and texture coordinates;

[0044] Obtain the electric field intensity, potential field function, and radiation power density from the target electromagnetic radiation source model file;

[0045] The electric field strength, potential field function, and radiated power density are normalized to texture pixel values ​​and matched with the model vertex coordinates to generate a lookup table for electromagnetic parameters.

[0046] Electromagnetic parameters can be converted into texture colors or transparency through shader programming or software plugins and mapped onto the model surface to obtain a comprehensive model with electromagnetic radiation.

[0047] The mapping methods include dynamic texture overlay and multiphysics coupling;

[0048] If it is necessary to display the dynamic changes of the electromagnetic field, the time variable is incorporated into the texture parameters to generate a dynamic texture sequence; if the mapping method is multi-physics coupling, the electromagnetic simulation field distribution results are directly output as texture maps in the COMSOL modeling software, and the ModelFun tool is used for automated mapping.

[0049] Verify the consistency of the mapping, verify the physical rationality of the electromagnetic texture through electromagnetic field observation data, and ensure that the radiation field distribution meets theoretical expectations;

[0050] Combine and save the geometric topology and texture coordinates with the lookup table.

[0051] Optionally, in one implementation of the first aspect of the present invention, step S5, obtaining UAV route planning parameters and performing route planning in the integrated model based on the route planning parameters to obtain a target route, includes:

[0052] By using multi-sensor fusion and integrated model calculation, it is determined whether the distance between the drone and the electromagnetic field source is within the threshold of a safe range;

[0053] When the drone is in an electromagnetic field environment, the electromagnetic field strength vector is combined with the drone's position and attitude data to calculate the direction of the resultant force of the electromagnetic field on the drone body, and the flight speed is optimized based on the real-time field strength distribution.

[0054] When the drone is outside the electromagnetic field environment, a backpropagation neural network is used to plan a detour path.

[0055] Secondly, embodiments of this application provide a UAV flight path planning system based on electromagnetic environment data and a 3D map, applied to the UAV flight path planning method based on electromagnetic environment data and a 3D map as described in the first aspect, characterized in that it includes:

[0056] 3D Reality Model Construction Module: Acquires 3D reality images of the target area and constructs a 3D reality model;

[0057] Electromagnetic radiation source location module: locates electromagnetic radiation sources based on the scattered signals from UAVs;

[0058] Model file matching module: Obtains electromagnetic radiation signals based on the located electromagnetic radiation source, analyzes the characteristics of the electromagnetic radiation signals, and matches the corresponding target electromagnetic radiation source model file;

[0059] Integrated Model Construction Module: Imports the target electromagnetic radiation source model file into the 3D reality model to construct an integrated model;

[0060] The target route optimization module obtains the UAV route planning parameters and performs route planning in the integrated model based on the route planning parameters to obtain the target route.

[0061] Thirdly, embodiments of this application provide an electronic device, characterized in that it includes:

[0062] processor;

[0063] Memory used to store processor-executable instructions;

[0064] The processor is configured to implement the UAV route planning method based on electromagnetic environment data and three-dimensional map as described in the first aspect when executing the instructions.

[0065] Fourthly, embodiments of this application provide a computer-readable storage medium, characterized in that the computer-readable storage medium stores a program that instructs a device to execute the UAV route planning method based on electromagnetic environment data and a three-dimensional map as described in the first aspect.

[0066] This application provides a method and system for UAV flight path planning based on electromagnetic environment data and 3D maps. The method involves acquiring 3D real-world images of a target area and constructing a 3D real-world model; locating electromagnetic radiation sources; obtaining electromagnetic radiation signals based on the located sources, analyzing the characteristics of the signals, and matching them with corresponding target electromagnetic radiation source model files; importing the target electromagnetic radiation source model files into the 3D real-world model to construct a comprehensive model; obtaining UAV flight path planning parameters; and performing flight path planning within the comprehensive model based on these parameters to obtain the target flight path. By accurately locating electromagnetic radiation sources and constructing a 3D comprehensive model containing their locations, the invisible electromagnetic field is visualized in real time, providing a clear and intuitive way to obtain the desired electromagnetic information. This method can use BP neural networks to plan detour paths and optimize flight paths based on the electromagnetic radiation source field strength, thereby improving the safety and effectiveness of UAV patrols.

[0067] Beneficial effects:

[0068] (1) Accurately locating electromagnetic radiation sources based on the Doppler frequency shift function can improve the accuracy and precision of UAV route planning based on electromagnetic environment data and three-dimensional maps.

[0069] (2) By using three-dimensional visualization technology, the invisible electromagnetic field can be visualized in real time, and the electromagnetic information can be obtained intuitively and vividly.

[0070] (3) Construct a three-dimensional integrated model containing the location of electromagnetic radiation sources. It can use BP neural network to plan detour paths and optimize flight paths based on the field strength of electromagnetic radiation sources, thereby improving the safety and effectiveness of UAV patrols. Attached Figure Description

[0071] Figure 1 This is a schematic flowchart of a UAV route planning method based on electromagnetic environment data and a 3D map, provided as an embodiment of this application.

[0072] Figure 2 A flowchart illustrating the construction of a three-dimensional reality model is provided for one embodiment of this application.

[0073] Figure 3 This is a coordinate diagram provided for an embodiment of this application.

[0074] Figure 4 An electromagnetic field model diagram provided for an embodiment of this application.

[0075] Figure 5 (a)-5 (b) are schematic diagrams of resultant force and resultant velocity provided in an embodiment of this application.

[0076] Figure 6 This is a schematic diagram of a UAV route planning system module based on electromagnetic environment data and a 3D map, provided as an embodiment of this application.

[0077] Figure 7 A schematic diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0078] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them.

[0079] It should be noted that, in the embodiments of this application, "at least one" refers to one or more, and "more than one" refers to two or more. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the specification of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application.

[0080] It should be noted that in the embodiments of this application, the terms "first," "second," etc., are used only for descriptive purposes and should not be construed as indicating or implying relative importance, nor as indicating or implying order. Features specified as "first" or "second" may explicitly or implicitly include one or more of the stated features. In the description of the embodiments of this application, words such as "exemplary" or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0081] Based on the embodiments described in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0082] Example 1

[0083] This application provides a method and system for UAV flight path planning based on electromagnetic environment data and 3D maps. The method involves acquiring a 3D real-world image of a target area and constructing a 3D real-world model; locating electromagnetic radiation sources based on UAV scattering signals; acquiring electromagnetic radiation signals based on the located electromagnetic radiation sources, analyzing the characteristics of the electromagnetic radiation signals, and matching corresponding target electromagnetic radiation source model files; importing the target electromagnetic radiation source model files into the 3D real-world model to construct a comprehensive model; acquiring UAV flight path planning parameters, and performing flight path planning in the comprehensive model based on the flight path planning parameters to obtain the target flight path. By accurately locating electromagnetic radiation sources and constructing a 3D comprehensive model containing the location of electromagnetic radiation sources, the method can use a BP neural network to plan detour paths and optimize flight paths based on the electromagnetic radiation source field strength, thereby improving the safety and effectiveness of UAV patrols.

[0084] Figure 1 This is a schematic flowchart of a UAV route planning method based on electromagnetic environment data and a 3D map, provided as an embodiment of this application.

[0085] like Figure 1 As shown, a method for UAV flight path planning based on electromagnetic environment data and 3D maps includes:

[0086] S1, acquire 3D real-world images of the target area and construct a 3D real-world model.

[0087] Figure 2 This is a flowchart illustrating the construction of a 3D reality model according to an embodiment of this application. Figure 2 As shown, it can be understood that in this embodiment, step S1, acquiring a 3D real-world image of the target area and constructing a 3D real-world model, includes:

[0088] S1.1, High-resolution depth images captured by drones: By using a drone equipped with a high-resolution camera or oblique photography equipment, multi-view, high-overlap image data of the target area is acquired. The image data must include position and attitude information and positioning data. At the same time, lidar point cloud data is collected to assist in the acquisition of depth information.

[0089] S1.2, Image screening and preprocessing: The high-resolution depth image is screened to remove unqualified images, and qualified images are corrected, denoised, color-balanced, and enhanced.

[0090] S1.3, Image Matching and Adjustment Calculation: Image feature points are extracted using the SIFT algorithm, and corresponding relationships of corresponding points are established through multi-view matching. Combined with ground control point data, exterior orientation elements of each image are calculated through bundle adjustment iterative optimization, and the relative coordinates are transformed to the geodetic coordinate system.

[0091] S1.4, Sparse Point Cloud Denseening: An initial 3D point cloud is generated based on matching corresponding points; a multi-view stereo algorithm is used for pixel-by-pixel matching to generate a high-density point cloud;

[0092] S1.5, TIN Model Construction and Optimization: Dense point clouds are converted into irregular triangular meshes. An initial model is constructed using the Delaunay triangulation algorithm. The density of the triangular mesh is adjusted according to the curvature of the surface. Triangular patches are simplified in flat areas, while details are preserved in complex areas. Abnormal triangles are repaired to ensure the continuity of the triangular mesh structure.

[0093] S1.6, Texture Mapping and Model Generation: Based on the normal direction and spatial position of the TIN patch, the best texture is automatically selected from multi-view images; overlapping textures are uniformly colored and the seams are processed to ensure color consistency; the texture is associated with the geometric model to generate a 3D real-world model with real geographic coordinates and attribute information.

[0094] Specifically, drones equipped with high-resolution cameras or oblique photography equipment acquire multi-view, highly overlapping image data of the target area. The image data must include position and attitude information (such as POS data), and in some cases, GNSS positioning (such as RTK technology) is used to improve accuracy. Some solutions also simultaneously collect LiDAR point cloud data to assist in acquiring depth information.

[0095] Specifically, the original images are screened, removing blurry, occluded, or poorly lit images. Qualified images undergo the following processing: Geometric correction: eliminating lens distortion (such as radial and tangential distortion). Denoising and color equalization: reducing image noise and unifying tonal differences under different lighting conditions using algorithms. Enhancement processing: improving image contrast and detail clarity to facilitate subsequent feature extraction.

[0096] Specifically, image matching and adjustment calculations include: Connectivity point extraction and matching: Image feature points are extracted using algorithms such as SIFT and SURF, and corresponding relationships between corresponding points are established through multi-view matching. Regional network adjustment: Combining ground control points (GCPs) or POS data, iterative optimization using bundle adjustment is employed to calculate the exterior orientation elements (i.e., camera position and attitude parameters) of each image, and the relative coordinates are transformed to a geodetic coordinate system (such as CGCS2000). Accuracy verification: The horizontal and vertical residuals after adjustment must be controlled within the millimeter level (e.g., 0.12cm horizontal residual) to ensure model accuracy.

[0097] Specifically, sparse point cloud densification includes sparse point cloud generation: generating an initial 3D point cloud based on matched corresponding points. Dense matching: using multi-view stereo algorithms (such as PMVS, MVS) for pixel-by-pixel matching to generate a high-density point cloud. Some techniques introduce parallel computing or consistency constraints (such as multi-frame depth map filtering) to improve efficiency and accuracy. Data block processing: dividing the large-scale point cloud into blocks to adapt to computational resource constraints.

[0098] Specifically, TIN model construction and optimization include: Triangulation generation: converting dense point clouds into irregular triangular meshes (TINs), and constructing an initial model using algorithms such as Delaunay triangulation. Smoothing and optimization: Geometric optimization: adjusting the density of the triangular mesh according to the curvature of the surface, simplifying triangular faces in flat areas, and preserving details in complex areas. Topology optimization: repairing abnormal triangles (such as narrow triangles) to ensure the continuity of the triangular mesh structure. Blocking and LOD construction: processing large-scale TIN models in blocks and generating multiple levels of detail (LODs) to improve rendering efficiency. Texture mapping and model generation include: Texture matching: automatically selecting the best texture from multi-view images (such as the smallest viewing angle or the highest resolution image) based on the normal direction and spatial position of the TIN facets. Texture blending: uniformizing and seam processing of overlapping textures to ensure color consistency. Semantic assignment: associating textures with geometric models to generate 3D reality models with real geographic coordinates and attribute information.

[0099] S2, locating electromagnetic radiation sources based on drone scattering signals.

[0100] It is understood that in this embodiment, S2, locating the electromagnetic radiation source based on the scattered signal from the UAV, includes:

[0101] By capturing the weak signal scattered by the UAV, the Doppler translation curve is obtained based on the Doppler frequency shift function;

[0102] Based on the Doppler translation curve, the Doppler frequency shift information generated by the UAV during its movement is extracted from the scattered signal;

[0103] By combining the real-time flight status of the UAV, a multi-source data fusion method is used to reverse analyze and determine the location of the ground electromagnetic radiation source.

[0104] Specifically, signal acquisition techniques mainly employ wideband receivers and high-sensitivity RF front-ends, combined with adaptive filtering algorithms to suppress environmental noise. For low signal-to-noise ratio signals, cyclostationarity analysis can be applied to extract periodic features, or the pseudo-Doppler principle can be used to enhance signal detectability.

[0105] Doppler frequency shift extraction includes time-frequency analysis: by generating time-spectrum maps through short-time Fourier transform (STFT) or wavelet transform, the frequency shift curves of the UAV approaching, crossing the baseline, and moving away are identified.

[0106] Specifically, determining the location of the ground electromagnetic radiation source includes:

[0107] Establish a three-dimensional spatial coordinate system, with the electromagnetic radiation source relative to time. The carrier frequency reaching the drone is:

[0108] ;

[0109] The carrier frequency that the drone's scattering reaches the ground receiver is:

[0110] ;

[0111] The Doppler frequency shift function of the electromagnetic radiation source obtained by the ground receiver is:

[0112] ,

[0113] in, The frequency of the electromagnetic radiation source, This indicates the speed at which electromagnetic waves propagate through the air. Indicates the drone's time The velocity vector, This represents the unit vector pointing from the electromagnetic radiation source to the location of the UAV. The unit vector representing the position of the ground receiver pointing to the position of the UAV;

[0114] To facilitate determining the location of the electromagnetic radiation source, the coordinate system is simplified. Figure 3 This is a coordinate diagram provided for one embodiment of this application. Figure 3 As shown, specifically:

[0115] Establish a three-dimensional coordinate system with the ground as the reference plane, point O as the center, and the UAV's flight path as the X-axis. Let the UAV's altitude be a fixed value h and its speed be a fixed value v. Then, the UAV's time... The position is represented as The location of the ground receiver is indicated as The location of the electromagnetic radiation source is represented as Then the first The simplified Doppler frequency shift function of the electromagnetic radiation source at time t is:

[0116] ;

[0117] The location of the electromagnetic radiation source was calculated by substituting multiple sets of data into the simplified Doppler frequency shift function. , Indicates that drones are in The X-axis coordinate at time [time].

[0118] S3. Obtain electromagnetic radiation signals based on the location of the electromagnetic radiation source, analyze the characteristics of the electromagnetic radiation signals, and match the corresponding target electromagnetic radiation source model file.

[0119] It is understood that in this embodiment, step S3, which involves acquiring electromagnetic radiation signals based on the location of the electromagnetic radiation source, analyzing the characteristics of the electromagnetic radiation signals, and matching the corresponding target electromagnetic radiation source model file, includes:

[0120] Construct different electromagnetic radiation source model files;

[0121] Electromagnetic radiation signals are obtained based on the location of the electromagnetic radiation source;

[0122] The electromagnetic radiation signal is subjected to feature extraction to obtain electromagnetic fingerprint features;

[0123] The electromagnetic fingerprint features are input into the electromagnetic radiation source identification model to obtain the electromagnetic radiation source type;

[0124] Based on the identified electromagnetic radiation source type, obtain the target electromagnetic radiation source model file.

[0125] Specifically, Figure 4 This is a diagram of an electromagnetic field model provided in one embodiment of this application. Figure 4 The diagram shows a schematic representation of a three-dimensional electromagnetic field model under ideal conditions. The model is generated from a data file composed of discrete points in space.

[0126] S4. Import the target electromagnetic radiation source model file into the three-dimensional reality model to construct a comprehensive model.

[0127] It is understood that in this embodiment, step S4, importing the target electromagnetic radiation source model file into the three-dimensional reality model to construct a comprehensive model, includes:

[0128] Import the 3D reality model and extract its geometric topology and texture coordinates;

[0129] Obtain the electric field intensity, potential field function, and radiation power density from the target electromagnetic radiation source model file;

[0130] The electric field strength, potential field function, and radiated power density are normalized to texture pixel values ​​and matched with the model vertex coordinates to generate a lookup table for electromagnetic parameters.

[0131] Electromagnetic parameters can be converted into texture colors or transparency through shader programming or software plugins and mapped onto the model surface to obtain a comprehensive model with electromagnetic radiation.

[0132] Specifically, importing a 3D reality model and extracting its geometric topology and texture coordinates requires ensuring that the 3D model meets the requirements of a unified coordinate system and elevation accuracy. The model's axis center point is defined as the center point of the bottom surface, and the format must conform to the standard (such as OSGB format). Use 3D modeling software (such as MultiGen Creator) to import the model, and extract the geometric topology and texture coordinates through dense matching and texture mapping processes to ensure the model structure is complete and free from issues such as coplanarity or gaps. The texture must be consistent with the actual landscape, with a resolution of no less than 0.03 meters per pixel, a single texture surface not exceeding 1024 pixels, and a color depth of 8 bits.

[0133] When obtaining the model parameters of the target electromagnetic radiation source, parameters such as electric field strength, potential field function, and radiated power density are extracted from the radiation source model. These parameters are based on the mathematical model of the radiation source, including characteristics such as location, frequency, polarization mode, and direction function. For multi-radiation source scenarios, the spatial composite field strength needs to be calculated, for example, using a radar radiation source detection range model and field strength synthesis algorithm. Parameters are normalized and an electromagnetic parameter lookup table is generated, normalizing parameters such as electric field strength to texture pixel values ​​of 0-255. Referring to the method of quantizing radiation intensity into grayscale values ​​in infrared scene simulation, parameter standardization is achieved using the radiance calculation formula. A lookup table (LUT) for electromagnetic parameters is generated by matching the normalized data with the model vertex coordinates. Similar to the process of calculating the electromagnetic radiation spatial field layer by layer using grid points in the LRBF method, this ensures that the data accurately corresponds to the geometric structure. It also includes electromagnetic parameter visualization mapping, using shader programming or software plugins, and using shaders from graphics libraries such as OpenGL to convert the electromagnetic parameters in the lookup table into RGB colors or transparency values. For example, interval mapping combined with color rendering capabilities can be used to display the field strength distribution. You can also use CST electromagnetic simulation software to perform radiation field analysis, directly mapping parameters such as power density and radiation pattern onto the model surface, or use Vega's Sensor Vision module to read material files to achieve dynamic rendering.

[0134] Specifically, technical verification and optimization can utilize verification models, taking into account the relationship between geometric dimensions and wavelength to avoid excessively large simulation domains that could lead to a surge in computational load. A simplified symmetric plane model can be employed, and the accuracy of the field strength distribution can be verified using ray tracing. In complex scenarios, propagation loss calculations (such as those influenced by terrain) and received power synthesis algorithms must be combined to ensure that the spatiotemporal superposition of electromagnetic environment signals conforms to reality.

[0135] The mapping methods include dynamic texture overlay and multiphysics coupling;

[0136] If it is necessary to display the dynamic changes of the electromagnetic field, the time variable is incorporated into the texture parameters to generate a dynamic texture sequence; if the mapping method is multi-physics coupling, the electromagnetic simulation field distribution results are directly output as texture maps in the COMSOL modeling software, and the ModelFun tool is used for automated mapping.

[0137] Verify the consistency of the mapping, verify the physical rationality of the electromagnetic texture through electromagnetic field observation data, and ensure that the radiation field distribution meets theoretical expectations;

[0138] The geometric topology and texture coordinates are combined with a lookup table and saved together. The saved file can be directly opened the next time it is used to generate a 3D model visualization carrying electromagnetic fields.

[0139] S5. Obtain the UAV route planning parameters, and perform route planning in the integrated model according to the route planning parameters to obtain the target route.

[0140] It is understood that in this embodiment, step S5, obtaining UAV route planning parameters and performing route planning in the integrated model based on the route planning parameters to obtain the target route, includes:

[0141] By using multi-sensor fusion and integrated model calculation, it is determined whether the distance between the drone and the electromagnetic field source is within the threshold of a safe range;

[0142] When the drone is in an electromagnetic field environment, the electromagnetic field strength vector is combined with the drone's position and attitude data to calculate the direction of the resultant force of the electromagnetic field on the drone body, and the flight speed is optimized based on the real-time field strength distribution.

[0143] When the drone is outside the electromagnetic field environment, a backpropagation neural network is used to plan a detour path.

[0144] In complex electromagnetic environments, UAV sensors and communication links may be interfered with, requiring more robust algorithms (such as APSO-BP or DRNN). However, outside the electromagnetic field range, path planning in normal environments has relatively lower real-time requirements, and the performance of BP neural networks can meet the needs in this case.

[0145] Backpropagation (BP) neural networks (BPNNs) take the linear motion parameters of a UAV (displacement, angular velocity, etc.) and external environmental information (such as wind direction) as inputs and output 4D trajectory predictions. Their three-layer structure (input layer, hidden layer, and output layer) effectively handles nonlinear mapping problems, providing a theoretical basis for detour path planning. A typical BPNN employs a three-layer structure: an input layer, hidden layers (4-13 nodes), and an output layer. Input parameters include the UAV's motion state and environmental data, while the output is the displacement and angle of the detour path. To improve efficiency, BPNNs are typically trained offline (e.g., parameter pre-training for agricultural UAV control systems) and then adjusted online using real-time data to handle dynamic obstacles. In the third stage of obstacle avoidance (path planning stage), the BPNN can be combined with terrain data and GNSS signals to generate the optimal path around static obstacles (such as cranes and bridges).

[0146] Specifically, if the drone is within the electromagnetic field safety threshold, its flight speed needs to be optimized to avoid electromagnetic interference. The direction of the resultant force of the electromagnetic field on the drone is calculated by combining the electric field strength vector (E) and the magnetic field strength vector (B) through vector superposition. Furthermore, drone attitude data (estimated by magnetometers, accelerometers, and gyroscopes using gradient descent or Kalman filtering) can be fused to correct the direction of the resultant force in the drone's coordinate system.

[0147] Specifically, Figure 5 (a)-5(b) are schematic diagrams of resultant force and resultant velocity provided in an embodiment of this application. If there is a dynamic obstacle, its velocity vector will affect the calculation of the repulsive force (such as the parallel repulsive force component), thereby indirectly adjusting the movement direction of the UAV. Figure 5 As shown, based on the attractive or repulsive force of the electromagnetic field and the target power of the UAV, the overall direction of the force is obtained through vector composition of the forces. Since the total resultant force determines the direction of the UAV's acceleration, the velocity direction gradually approaches the direction of the resultant force. Based on the velocity of the electromagnetic field and the velocity of the UAV, the overall velocity direction is obtained through vector composition of the velocities.

[0148] Example 2

[0149] like Figure 6 As shown, this application provides a UAV route planning system based on electromagnetic environment data and 3D maps, which is applied to the UAV route planning method based on electromagnetic environment data and 3D maps as described in Embodiment 1. The system includes: a 3D real-scene model construction module 11, an electromagnetic radiation source positioning module 12, a model file matching module 13, a comprehensive model construction module 14, and a target route optimization module 15.

[0150] It is understood that in this embodiment, the 3D real scene model construction module 11 acquires 3D real scene images of the target area and constructs a 3D real scene model.

[0151] It is understood that in this embodiment, the electromagnetic radiation source positioning module 12 locates the electromagnetic radiation source based on the scattered signal of the UAV.

[0152] It is understood that in this embodiment, the model file matching module 13: obtains electromagnetic radiation signals based on the location of the electromagnetic radiation source, analyzes the characteristics of the electromagnetic radiation signals, and matches the corresponding target electromagnetic radiation source model file.

[0153] It is understood that in this embodiment, the integrated model construction module 14 imports the target electromagnetic radiation source model file into the three-dimensional real scene model to construct an integrated model.

[0154] It is understood that in this embodiment, the target route optimization module 15 obtains the UAV route planning parameters and performs route planning in the comprehensive model according to the route planning parameters to obtain the target route.

[0155] This application provides a method and system for UAV flight path planning based on electromagnetic environment data and 3D maps. The method involves acquiring 3D real-world images of a target area and constructing a 3D real-world model; locating electromagnetic radiation sources; obtaining electromagnetic radiation signals based on the located sources, analyzing the characteristics of the signals, and matching them with corresponding target electromagnetic radiation source model files; importing the target electromagnetic radiation source model files into the 3D real-world model to construct a comprehensive model; obtaining UAV flight path planning parameters; and performing flight path planning within the comprehensive model based on these parameters to obtain the target flight path. By accurately locating electromagnetic radiation sources and constructing a 3D comprehensive model containing their locations, the invisible electromagnetic field is visualized in real time, providing a clear and intuitive way to obtain the desired electromagnetic information. This method can use BP neural networks to plan detour paths and optimize flight paths based on the electromagnetic radiation source field strength, thereby improving the safety and effectiveness of UAV patrols.

[0156] Figure 7 This is an electronic device provided in one embodiment of this application. For example... Figure 7 As shown, the electronic device includes at least the following components: processor 101 and memory 100, communication interface 103, and bus 102.

[0157] In this embodiment, the memory 100 is used to store executable instructions of the processor 101, which, when configured to execute instructions, implements... Figure 6 The device module shown is for UAV route planning based on electromagnetic environment data and 3D maps.

[0158] In embodiments of this application, a computer-readable storage medium includes instructions that instruct a device to perform the method as described in the first aspect. For example, the instructions instruct the device to perform... Figure 1 The method is shown in the process steps.

[0159] In one embodiment of this application, the program operating in the electronic device may be a program that controls a central processing unit (CPU) or similar device to achieve the functions of the above-described embodiments of the present invention (a program that enables the computer to function). The information processed by these devices is then temporarily stored in random access memory (RAM) during processing, and subsequently stored in various ROMs such as read-only memory (FlashROM) or hard disk drives (HDDs), and read, corrected, and written by the CPU as needed.

[0160] It should be noted that a portion of the electronic device described above can also be implemented using a computer. In this case, the program for implementing the control function can be recorded on a computer-readable recording medium, and the program recorded on the recording medium can be read into the computer and executed.

[0161] It should be noted that the term "computer" as used here refers to a computer built into an electronic device, employing hardware including an operating system and peripheral devices. Furthermore, "computer-readable recording media" refers to removable media such as floppy disks, magneto-optical disks, ROMs, and CD-ROMs, as well as storage devices such as hard drives built into a computer.

[0162] Furthermore, a "computer-readable recording medium" can include: a medium that dynamically stores a program for a short period of time, such as a communication line used when transmitting a program via a network such as the Internet or a communication line such as a telephone line; or a medium that stores a program for a fixed period of time, such as volatile memory inside a computer that serves as a server or client in this case. In addition, the aforementioned program can be a program used to implement the above-mentioned functions, or it can be a program that can implement the above-mentioned functions by combining with programs already recorded in the computer.

[0163] Furthermore, the electronic device in the above embodiments can also be implemented as an assembly (device group) composed of multiple devices. Each device constituting the device group can possess some or all of the functions or functional blocks of the electronic device in the above embodiments. As a device group, it is sufficient to have all the functions or functional blocks of the electronic device.

[0164] Those skilled in the art should recognize that the above embodiments are only used to illustrate this application and are not intended to limit this application. Any appropriate changes and variations made to the above embodiments within the essential spirit and scope of this application fall within the scope of protection claimed in this application.

Claims

1. A method for UAV flight path planning based on electromagnetic environment data and 3D maps, characterized in that, The method includes: S1, acquire 3D real-world images of the target area and construct a 3D real-world model; S2, Locating electromagnetic radiation sources based on drone scattering signals; S3. Obtain electromagnetic radiation signals based on the location of the electromagnetic radiation source, analyze the characteristics of the electromagnetic radiation signals, and match the corresponding target electromagnetic radiation source model file. S4. Import the target electromagnetic radiation source model file into the three-dimensional reality model to construct a comprehensive model; S5, Obtain UAV route planning parameters, and perform route planning in the integrated model according to the route planning parameters to obtain the target route; The S2 method, which locates the electromagnetic radiation source based on the scattered signals from the UAV, includes: By capturing the weak signal scattered by the UAV, the Doppler translation curve is obtained based on the Doppler frequency shift function; Based on the Doppler translation curve, the Doppler frequency shift information generated by the UAV during its movement is extracted from the scattered signal; By combining the real-time flight status of the UAV, a multi-source data fusion method is used to reverse analyze and determine the location of the ground electromagnetic radiation source. Determining the location of the ground electromagnetic radiation source includes: Establish a three-dimensional spatial coordinate system, with the electromagnetic radiation source relative to time. The carrier frequency reaching the drone is: ； The carrier frequency that the drone's scattering reaches the ground receiver is: ； The Doppler frequency shift function of the electromagnetic radiation source obtained by the ground receiver is: ， in, The frequency of the electromagnetic radiation source, This indicates the speed at which electromagnetic waves propagate through the air. Indicates the drone's time The velocity vector, This represents the unit vector pointing from the electromagnetic radiation source to the location of the UAV. The unit vector representing the position of the ground receiver pointing to the position of the UAV; To facilitate determining the location of the electromagnetic radiation source, the coordinate system is simplified as follows: Establish a three-dimensional coordinate system with the ground as the reference plane, point O as the center, and the UAV's flight path as the X-axis. Let the UAV's altitude be a fixed value h and its speed be a fixed value v. Then, the UAV's time... The position is represented as The location of the ground receiver is indicated as The location of the electromagnetic radiation source is represented as Then the first The simplified Doppler frequency shift function of the electromagnetic radiation source at time t is: ； The location of the electromagnetic radiation source was calculated by substituting multiple sets of data into the simplified Doppler frequency shift function. , Indicates that drones are in The X-axis coordinate at time [time].

2. The method for UAV flight path planning based on electromagnetic environment data and 3D maps according to claim 1, characterized in that, S1 involves acquiring a 3D real-world image of the target area and constructing a 3D real-world model, including: S1.1, High-resolution depth images captured by drones: By using a drone equipped with a high-resolution camera or oblique photography equipment, multi-view, high-overlap image data of the target area is acquired. The image data must include position and attitude information and positioning data. At the same time, lidar point cloud data is collected to assist in the acquisition of depth information. S1.2, Image screening and preprocessing: The high-resolution depth image is screened to remove unqualified images, and qualified images are corrected, denoised, color-balanced, and enhanced. S1.3, Image Matching and Adjustment Calculation: Image feature points are extracted using the SIFT algorithm, and corresponding relationships of corresponding points are established through multi-view matching. Combined with ground control point data, exterior orientation elements of each image are calculated through bundle adjustment iterative optimization, and the relative coordinates are transformed to the geodetic coordinate system. S1.4, Sparse Point Cloud Denseening: An initial 3D point cloud is generated based on matching corresponding points; a multi-view stereo algorithm is used for pixel-by-pixel matching to generate a high-density point cloud; S1.5, TIN Model Construction and Optimization: Dense point clouds are converted into irregular triangular meshes. An initial model is constructed using the Delaunay triangulation algorithm. The density of the triangular mesh is adjusted according to the curvature of the surface. Triangular patches are simplified in flat areas, while details are preserved in complex areas. Abnormal triangles are repaired to ensure the continuity of the triangular mesh structure. S1.6, Texture Mapping and Model Generation: Based on the normal direction and spatial position of the TIN patch, the best texture is automatically selected from multi-view images; overlapping textures are uniformly colored and the seams are processed to ensure color consistency; the texture is associated with the geometric model to generate a 3D real-world model with real geographic coordinates and attribute information.

3. The method for UAV route planning based on electromagnetic environment data and three-dimensional maps according to claim 2, characterized in that, Step S3 involves acquiring electromagnetic radiation signals based on the located electromagnetic radiation source, analyzing the characteristics of the electromagnetic radiation signals, and matching them with the corresponding target electromagnetic radiation source model file, including: Construct different electromagnetic radiation source model files; Electromagnetic radiation signals are obtained based on the location of the electromagnetic radiation source; The electromagnetic radiation signal is subjected to feature extraction to obtain electromagnetic fingerprint features; Electromagnetic fingerprint features are input into the electromagnetic radiation source identification model to obtain the electromagnetic radiation source type; Based on the identified electromagnetic radiation source type, obtain the target electromagnetic radiation source model file.

4. The method for UAV flight path planning based on electromagnetic environment data and 3D maps according to claim 3, characterized in that, Step S4 involves importing the target electromagnetic radiation source model file into the 3D reality model to construct a comprehensive model, including: Import the 3D reality model and extract its geometric topology and texture coordinates; Obtain the electric field strength, potential field function, and radiation power density from the target electromagnetic radiation source model file; The electric field strength, potential field function, and radiated power density are normalized to texture pixel values ​​and matched with the model vertex coordinates to generate a lookup table for electromagnetic parameters. Electromagnetic parameters can be converted into texture colors or transparency through shader programming or software plugins and mapped onto the model surface to obtain a comprehensive model with electromagnetic radiation. The mapping methods include dynamic texture overlay and multiphysics coupling; If it is necessary to display the dynamic changes of the electromagnetic field, the time variable is incorporated into the texture parameters to generate a dynamic texture sequence; if the mapping method is multi-physics coupling, the electromagnetic simulation field distribution results are directly output as texture maps in the COMSOL modeling software, and the ModelFun tool is used for automated mapping. Verify the consistency of the mapping, verify the physical rationality of the electromagnetic texture through electromagnetic field observation data, and ensure that the radiation field distribution meets theoretical expectations; Combine and save the geometric topology and texture coordinates with the lookup table.

5. The method for UAV flight path planning based on electromagnetic environment data and three-dimensional maps according to claim 4, characterized in that, Step S5 involves acquiring UAV route planning parameters and performing route planning in the integrated model based on these parameters to obtain the target route, including: By using multi-sensor fusion and integrated model calculation, it is determined whether the distance between the drone and the electromagnetic field source is within the threshold of a safe range; When the drone is in an electromagnetic field environment, the electromagnetic field strength vector is combined with the drone's position and attitude data to calculate the direction of the resultant force of the electromagnetic field on the drone body, and the flight speed is optimized based on the real-time field strength distribution. When the drone is outside the electromagnetic field environment, a backpropagation neural network is used to plan a detour path.

6. A UAV flight path planning system based on electromagnetic environment data and a 3D map, applied to the UAV flight path planning method based on electromagnetic environment data and a 3D map as described in any one of claims 1 to 5, characterized in that, include: 3D Reality Model Construction Module: Acquires 3D reality images of the target area and constructs a 3D reality model; Electromagnetic radiation source location module: locates electromagnetic radiation sources based on the scattered signals from UAVs; Model file matching module: Obtains electromagnetic radiation signals based on the located electromagnetic radiation source, analyzes the characteristics of the electromagnetic radiation signals, and matches the corresponding target electromagnetic radiation source model file; Integrated Model Construction Module: Imports the target electromagnetic radiation source model file into the 3D reality model to construct an integrated model; The target route optimization module obtains the UAV route planning parameters and performs route planning in the integrated model based on the route planning parameters to obtain the target route. The S2 method, which locates the electromagnetic radiation source based on the scattered signals from the UAV, includes: By capturing the weak signal scattered by the UAV, the Doppler translation curve is obtained based on the Doppler frequency shift function; Based on the Doppler translation curve, the Doppler frequency shift information generated by the UAV during its movement is extracted from the scattered signal; By combining the real-time flight status of the UAV, a multi-source data fusion method is used to reverse analyze and determine the location of the ground electromagnetic radiation source.

7. An electronic device, characterized in that, include: processor; Memory used to store processor-executable instructions; The processor is configured to implement the UAV route planning method based on electromagnetic environment data and three-dimensional map as described in any one of claims 1 to 5 when executing the instructions.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that instructs the device to perform the UAV route planning method based on electromagnetic environment data and a three-dimensional map as described in any one of claims 1 to 5.

Images