A method and system for intelligently identifying interference signals in unmanned aerial vehicle (UAV) navigation.

Abstract

The present application provides a method and system for intelligently identifying interference signals in a drone navigation. The method involves a drone body and a sensor arranged on the drone body. The method includes: obtaining detection information within the flight range of the drone through the sensor; determining the signal type according to the interference signal information and the real-time environment information, the signal type including radio signals and electromagnetic signals; generating suppression processing information according to the signal type and the real-time navigation information of the drone; generating optimized navigation information according to the suppression processing information and the real-time navigation information of the drone; generating several planned paths according to the optimized navigation information and preset sharing rules; and determining the target navigation path according to the real-time parameter information of the drone body and several of the planned paths. The path can be generated according to the real-time situation; the path selection has better flexibility, stronger security and better stability.

Description

Technical Field

[0001] The present application relates to the field of unmanned aerial vehicle navigation technology, and in particular to a method and system for unmanned aerial vehicle navigation for intelligently identifying interference signals. Background Art

[0002] The UAV navigation system is an important part of modern UAV technology. It can help UAVs to navigate autonomously in complex flight environments and complete predetermined tasks. The path planning algorithm is one of the core technologies in the UAV navigation system. Its function is to plan an optimal path from the starting point to the end point based on the UAV's mission requirements and environmental information.

[0003] Existing UAV navigation systems usually use path planning algorithms based on graph search, such as the Dijkstra algorithm and the A* algorithm. Existing algorithms build a graph to connect the nodes that the UAV needs to pass through, and then determine the optimal path by searching for the shortest path in the graph. In addition, there are some path planning methods based on intelligent optimization algorithms, such as genetic algorithms and particle swarm optimization algorithms. Existing algorithms simulate the evolutionary process in nature to find the global optimal solution.

[0004] Although existing path planning algorithms have been able to meet the navigation needs of drones to a certain extent, they still have some problems and limitations. First, when dealing with large-scale complex environments, existing algorithms have large computational complexity and low efficiency, and are unable to generate paths in real time, which poses a challenge to the real-time navigation of drones. Second, the paths generated by existing algorithms are usually single and lack flexibility. When encountering obstacles or other abnormal situations, drones cannot quickly switch to alternative paths, resulting in flight interruption or failure. Finally, while considering the feasibility and optimality of the path, existing algorithms often ignore the safety and stability of the path, which may cause collisions or other accidents during the flight of drones. Summary of the invention

[0005] In view of the above problems, the present application is proposed to provide a method and system for intelligently identifying interference signals of unmanned aerial vehicle navigation, which overcomes the above problems or at least partially solves the above problems, including:

[0006] A drone navigation method for intelligently identifying interference signals, the method involving a drone body and a sensor arranged on the drone body, the method comprising:

[0007] Acquiring detection information within the flight range of the UAV through the sensor, wherein the detection information includes real-time environmental information and interference signal information;

[0008] Determining a signal type according to the interference signal information and the real-time environment information, the signal type including a radio signal and an electromagnetic signal;

[0009] Generate suppression processing information based on signal type and real-time navigation information of the UAV;

[0010] generating optimized navigation information based on the suppression processing information and the real-time navigation information of the UAV;

[0011] Generating a plurality of planned paths according to the optimized navigation information and preset sharing rules;

[0012] The target navigation path is determined according to the real-time parameter information of the drone body and a plurality of the planned paths.

[0013] Furthermore, the step of acquiring detection information within the flight range of the drone through the sensor, wherein the detection information includes real-time environmental information and interference signal information, comprises:

[0014] Determine the current state type of the drone body, where the current state type is an execution state or a non-execution state;

[0015] When the current state type is the execution state, the sensor collects electromagnetic information and real-time environmental information of the drone body within a preset flight range;

[0016] Performing fast Fourier transform processing on the electromagnetic information to generate a processing signal;

[0017] generating the interference signal information according to the electromagnetic information and the processed signal;

[0018] The detection information is generated according to the interference signal information and the real-time environment information.

[0019] Furthermore, the step of determining the signal type according to the interference signal information and the real-time environment information includes:

[0020] Performing a first deep learning process on the interference signal information to determine feature information, where the feature information includes frequency, intensity, and signal direction;

[0021] Performing a second deep learning process according to the frequency, the strength, the signal direction and the real-time environmental information to generate an initial interference signal recognition model;

[0022] Performing filtering processing on the initial interference signal recognition model to generate an optimization model;

[0023] Performing lightweight processing on the optimization model to generate a target interference signal recognition model;

[0024] The signal type is determined according to the interference signal information and the target interference signal identification model, wherein the signal type includes the radio signal and the electromagnetic signal.

[0025] Furthermore, the step of generating suppression processing information according to the signal type and the real-time navigation information of the UAV includes:

[0026] Analyzing and processing the target signal corresponding to the signal type to generate a feature type, wherein the feature type includes one of a frequency feature, a time domain feature, and a space feature;

[0027] When the feature type is the frequency feature, a frequency shielding range is generated according to the frequency feature and the real-time navigation information of the drone; or,

[0028] When the feature type is the spatial feature, performing minimum mean square error processing based on the spatial feature and the real-time navigation information of the UAV to determine a useful signal within the target signal; or,

[0029] When the feature type is the time domain feature, performing time domain window processing according to the time domain feature and the real-time navigation information of the UAV to generate a time domain resolution for improving the quality of the target signal;

[0030] The suppression processing information is generated according to one of the frequency masking range, the useful signal or the time domain resolution.

[0031] Furthermore, the step of generating optimized navigation information based on the suppression processing information and the real-time navigation information of the UAV includes:

[0032] Acquire navigation data in the real-time navigation information of the drone, wherein the navigation data includes position, speed and navigation direction;

[0033] Determining interference intensity of a current environment according to the position, the speed and the navigation direction;

[0034] The optimized navigation information is generated according to the interference intensity, a preset adjustment rule and a preset detection threshold, wherein the preset adjustment rule includes an adjustment period and an adjustment range.

[0035] Furthermore, the step of generating a plurality of planned paths according to the optimized navigation information and the preset sharing rules includes:

[0036] Sharing the optimized navigation information with a preset sharing platform to generate avoidance information for avoiding the same adjustment situation;

[0037] A plurality of the planned paths are generated according to the avoidance information and the optimized navigation information.

[0038] Furthermore, the step of determining the target navigation path based on the real-time parameter information of the drone body and the plurality of planned paths includes:

[0039] Performing deep learning processing on the plurality of planned paths and the real-time parameter information to determine the priority of the plurality of planned paths;

[0040] Selecting a planned path with a priority greater than or equal to 90% from the plurality of planned paths and determining it as a priority path set;

[0041] Generating the stability of each priority path according to the preset evaluation index and the priority path set;

[0042] Determine a first target path by comparing the stability of each of the paths with a preset stability threshold;

[0043] Determining whether there is a preset abnormal situation in the execution process of the first target path;

[0044] When the execution process of the first target path does not contain the preset abnormal situation, determining the target navigation path to be the first target path to continue to execute; or,

[0045] When the preset abnormal situation exists in the execution process of the first target path, a second target path is determined according to the first target path and a first stability corresponding to the first target path, and the second target path is marked as the target navigation path.

[0046] An embodiment of the present application further discloses a drone navigation system based on intelligent identification of interference signals, the system involving a drone body and a sensor disposed on the drone body, the system comprising:

[0047] An acquisition module, used to acquire detection information within the flight range of the UAV through the sensor, wherein the detection information includes real-time environment information and interference signal information;

[0048] A first determination module, configured to determine a signal type according to the interference signal information and the real-time environment information, wherein the signal type includes a radio signal and an electromagnetic signal;

[0049] The first generation module is used to generate suppression processing information according to the signal type and the real-time navigation information of the UAV;

[0050] A second generating module is used to generate optimized navigation information according to the suppression processing information and the real-time navigation information of the UAV;

[0051] A third generation module is used to generate a plurality of planned paths according to the optimized navigation information and preset sharing rules;

[0052] The second determination module is used to determine the target navigation path according to the real-time parameter information of the drone body and a plurality of the planned paths.

[0053] An embodiment of the present application also discloses a computer device, including a processor, a memory, and a computer program stored in the memory and capable of running on the processor. When the computer program is executed by the processor, the steps of the above-mentioned drone navigation method based on intelligent identification of interference signals are implemented.

[0054] An embodiment of the present application further discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned method for unmanned aerial vehicle navigation based on intelligent identification of interference signals are implemented.

[0055] This application has the following advantages:

[0056] In the embodiments of the present application, compared with the existing algorithms in the prior art, when dealing with large-scale complex environments, the existing algorithms have large computational complexity, low efficiency, and cannot generate paths in real time, which poses a challenge to the real-time navigation of drones; the paths generated by existing algorithms are usually single and lack flexibility. When encountering obstacles or other abnormal situations, the drone cannot quickly switch to an alternative path, resulting in flight interruption or failure; while considering the feasibility and optimality of the path, the existing algorithms often ignore the safety and stability of the path, which may cause the drone to collide or other accidents during flight. The present application provides a solution with better flexibility, stronger safety and better stability in path selection for drone navigation, specifically: a method based on intelligent identification of interference signals A drone navigation method, the method involves a drone body and a sensor arranged on the drone body, the method comprising: obtaining detection information within the flight range of the drone through the sensor, wherein the detection information includes real-time environmental information and interference signal information; determining a signal type according to the interference signal information and the real-time environmental information, the signal type including a radio signal and an electromagnetic signal; generating suppression processing information according to the signal type and the drone real-time navigation information; generating optimized navigation information according to the suppression processing information and the drone real-time navigation information; generating a plurality of planned paths according to the optimized navigation information and preset sharing rules; and determining a target navigation path according to the real-time parameter information of the drone body and the plurality of planned paths. By generating suppression processing information according to the signal type and the real-time navigation information of the UAV; generating optimized navigation information according to the suppression processing information and the real-time navigation information of the UAV; generating several planned paths according to the optimized navigation information and preset sharing rules; and determining the target navigation path according to the real-time parameter information of the UAV body and several of the planned paths, the problem that the existing algorithms have large computational complexity, low efficiency and cannot generate paths in real time when dealing with large-scale complex environments, which poses a challenge to the real-time navigation of the UAV; the paths generated by the existing algorithms are usually single and lack flexibility. When encountering obstacles or other abnormal situations, the UAV cannot quickly switch to an alternative path, resulting in flight interruption or failure; while considering the feasibility and optimality of the path, the existing algorithms often ignore the safety and stability of the path, which may cause the UAV to collide or other accidents during flight, thereby achieving the ability to generate paths according to real-time conditions; and having better flexibility, stronger safety and better stability in path selection. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the description of the present application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0058] Figure 1 It is a flowchart of a method for unmanned aerial vehicle navigation based on intelligent identification of interference signals provided by an embodiment of the present application;

[0059] Figure 2 It is a structural block diagram of a UAV navigation system based on intelligent identification of interference signals provided by an embodiment of the present application;

[0060] Figure 3 It is a structural schematic diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the objects, features and advantages of the present application more obvious and understandable, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0062] Reference Figure 1 , showing a flowchart of a method for UAV navigation based on intelligent identification of interference signals provided by an embodiment of the present application;

[0063] A drone navigation method for intelligently identifying interference signals, the method involving a drone body and a sensor arranged on the drone body, the method comprising:

[0064] S110, acquiring detection information within the flight range of the UAV through the sensor, wherein the detection information includes real-time environment information and interference signal information;

[0065] S120, determining a signal type according to the interference signal information and the real-time environment information, where the signal type includes a radio signal and an electromagnetic signal;

[0066] S130, generating suppression processing information according to the signal type and the real-time navigation information of the UAV;

[0067] S140, generating optimized navigation information according to the suppression processing information and the real-time navigation information of the UAV;

[0068] S150, generating a plurality of planned paths according to the optimized navigation information and preset sharing rules;

[0069] S160: determining a target navigation path according to the real-time parameter information of the drone body and the plurality of planned paths.

[0070] In the embodiments of the present application, compared with the existing algorithms in the prior art, when dealing with large-scale complex environments, the existing algorithms have large computational complexity, low efficiency, and cannot generate paths in real time, which poses a challenge to the real-time navigation of drones; the paths generated by existing algorithms are usually single and lack flexibility. When encountering obstacles or other abnormal situations, the drone cannot quickly switch to an alternative path, resulting in flight interruption or failure; while considering the feasibility and optimality of the path, the existing algorithms often ignore the safety and stability of the path, which may cause the drone to collide or other accidents during flight. The present application provides a solution with better flexibility, stronger safety and better stability in path selection for drone navigation, specifically: a method based on intelligent identification of interference signals A drone navigation method, the method involves a drone body and a sensor arranged on the drone body, the method comprising: obtaining detection information within the flight range of the drone through the sensor, wherein the detection information includes real-time environmental information and interference signal information; determining a signal type according to the interference signal information and the real-time environmental information, the signal type including a radio signal and an electromagnetic signal; generating suppression processing information according to the signal type and the drone real-time navigation information; generating optimized navigation information according to the suppression processing information and the drone real-time navigation information; generating a plurality of planned paths according to the optimized navigation information and preset sharing rules; and determining a target navigation path according to the real-time parameter information of the drone body and the plurality of planned paths. By generating suppression processing information according to the signal type and the real-time navigation information of the UAV; generating optimized navigation information according to the suppression processing information and the real-time navigation information of the UAV; generating several planned paths according to the optimized navigation information and preset sharing rules; and determining the target navigation path according to the real-time parameter information of the UAV body and several of the planned paths, the problem that the existing algorithms have large computational complexity, low efficiency and cannot generate paths in real time when dealing with large-scale complex environments, which poses a challenge to the real-time navigation of the UAV; the paths generated by the existing algorithms are usually single and lack flexibility. When encountering obstacles or other abnormal situations, the UAV cannot quickly switch to an alternative path, resulting in flight interruption or failure; while considering the feasibility and optimality of the path, the existing algorithms often ignore the safety and stability of the path, which may cause the UAV to collide or other accidents during flight, thereby achieving the ability to generate paths according to real-time conditions; and having better flexibility, stronger safety and better stability in path selection.

[0071] Next, a drone navigation method for intelligently identifying interference signals in this exemplary embodiment will be further described.

[0072] As described in step S110, detection information within the flight range of the drone is acquired through the sensor, wherein the detection information includes real-time environment information and interference signal information.

[0073] In one embodiment of the present invention, the specific process of "obtaining detection information within the flight range of the drone through the sensor, wherein the detection information includes real-time environmental information and interference signal information" in step S110 can be further explained in combination with the following description.

[0074] As described in the following steps,

[0075] S210, determining a current state type of the drone body, wherein the current state type is an execution state or a non-execution state;

[0076] S220, when the current state type is the execution state, the sensor collects electromagnetic information and real-time environmental information of the drone body within a preset flight range;

[0077] S230, performing fast Fourier transform processing on the electromagnetic information to generate a processing signal;

[0078] S240, generating the interference signal information according to the electromagnetic information and the processed signal;

[0079] S250: Generate the detection information according to the interference signal information and the real-time environment information.

[0080] It should be noted that whether to collect data through sensors is determined by the current state type of the drone body. The sensors can be radio interference detectors and electromagnetic interference detectors. The radio interference detector is used to detect interference signals from various radio devices, and the electromagnetic interference detector is used to detect interference signals from various electromagnetic devices.

[0081] As an example, by combining sensors and signal processing technology, the electromagnetic information of the drone is collected and analyzed in real time. The sensor model is SDR-3000, the signal processing algorithm adopts FFT (Fast Fourier Transform) algorithm, the time window length is set to 10ms, and the frequency resolution is set to 1kHz; the SDR-3000 sensor is used to collect electromagnetic information; the sensor is set on the drone, and through its high sensitivity and low noise characteristics, it effectively reduces the impact of external noise and interference on signal quality, thereby improving the signal-to-noise ratio of the sensor; the FFT algorithm is used to process the collected electromagnetic information; the time window length is set to 10ms, and the frequency resolution is set to 1kHz, which improves the precision and accuracy of signal processing, avoids problems such as signal distortion and insufficient frequency resolution, realizes real-time collection and analysis of the electromagnetic environment information of the drone, improves calculation efficiency, and meets real-time requirements. In this embodiment, the implementation environment of the FFT algorithm is MATLAB software; the temperature during data acquisition and analysis is controlled between 20℃ and 25℃, the time is controlled within 10ms, and the pressure is controlled at about 1 atmosphere.

[0082] In a specific implementation, it also includes multi-sensor fusion; using multiple sensors on the drone, including lidar, camera, ultrasonic sensor, etc., to comprehensively process and analyze the environment; the specific working parameters include the scanning frequency of the lidar, the resolution of the camera, the detection distance of the ultrasonic sensor, etc.; through multi-sensor fusion technology, the environmental perception ability of the drone is improved.

[0083] As described in step S120, the signal type is determined according to the interference signal information and the real-time environment information, and the signal type includes a radio signal and an electromagnetic signal.

[0084] In an embodiment of the present invention, the specific process of "determining the signal type according to the interference signal information and the real-time environment information, wherein the signal type includes a radio signal and an electromagnetic signal" in step S120 can be further explained in combination with the following description.

[0085] As described in the following steps,

[0086] S310, performing a first deep learning process on the interference signal information to determine feature information, where the feature information includes frequency, intensity, and signal direction;

[0087] S320, performing a second deep learning process according to the frequency, the strength, the signal direction and the real-time environment information to generate an initial interference signal recognition model;

[0088] S330, filtering the initial interference signal recognition model to generate an optimization model;

[0089] S340, performing lightweight processing on the optimization model to generate a target interference signal recognition model;

[0090] S350. Determine a signal type according to the interference signal information and the target interference signal identification model, wherein the signal type includes the radio signal and the electromagnetic signal.

[0091] It should be noted that the first deep learning processing is used to analyze features within the interference signal information to obtain feature information; the second deep learning processing is used to generate an initial interference signal recognition model based on the features and real-time environmental information.

[0092] As an example, the first deep learning process uses a deep learning artificial intelligence algorithm to intelligently identify the characteristics of interference signals. The deep learning model uses a convolutional neural network (CNN). The model training data set includes 10,000 normal signal samples and 5,000 interference signal samples. The cross-validation method is used in the model training process, and the validation set accounts for 20%. The loss function in the model training process uses the mean square error (MSE). The optimizer uses the Adam algorithm, and the learning rate is set to 0.001; the characteristics of the interference signal include frequency, intensity, and direction. In the second deep learning process, one of the convolutional neural network (CNN), recurrent neural network (RNN), or long short-term memory network (LSTM) is used to obtain the initial interference recognition model; then, by optimizing the existing signal processing algorithm and artificial intelligence model, the efficiency and real-time performance of interference signal recognition are improved. The optimized signal processing algorithm uses an adaptive filtering algorithm, and the artificial intelligence model uses a lightweight neural network model, which reduces model parameters by 30% and computing time by 50%.

[0093] In a specific implementation, the interference signals emitted by the electronic device are divided into radio signals of various radio devices and electromagnetic signals of various electromagnetic devices.

[0094] As described in step S130, suppression processing information is generated according to the signal type and the real-time navigation information of the UAV.

[0095] In one embodiment of the present invention, the specific process of "generating suppression processing information according to the signal type and the real-time navigation information of the drone" in step S130 can be further explained in combination with the following description.

[0096] As described in the following steps,

[0097] S410, analyzing and processing the target signal corresponding to the signal type to generate a feature type, where the feature type includes one of a frequency feature, a time domain feature, and a space feature;

[0098] S420, when the feature type is the frequency feature, generating a frequency shielding range according to the frequency feature and the real-time navigation information of the drone; or,

[0099] S430, when the feature type is the spatial feature, performing minimum mean square error processing according to the spatial feature and the real-time navigation information of the UAV to determine a useful signal in the target signal; or,

[0100] S440, when the feature type is the time domain feature, performing time domain window processing according to the time domain feature and the real-time navigation information of the UAV to generate a time domain resolution for improving the quality of the target signal;

[0101] S450: Generate the suppression processing information according to one of the frequency masking range, the useful signal, or the time domain resolution.

[0102] It should be noted that the interference signal characteristics and type identification. The received signal is analyzed by the signal processing system to identify the characteristics and type of the interference signal. This includes the analysis of the frequency, time domain and spatial characteristics of the signal, so as to take corresponding interference suppression measures.

[0103] As an example, the signal is analyzed in the frequency domain using power spectral density to determine the frequency characteristics of the interference signal; the signal is analyzed in the time domain using the autocorrelation function to determine the time domain characteristics of the interference signal; and the signal is analyzed in the space domain using a multi-antenna array to determine the spatial characteristics of the interference signal.

[0104] In a specific implementation, frequency shielding: according to the frequency characteristics of the identified interference signal, the frequency shielding range is set to ±5kHz of the interference signal frequency, and the frequency of the interference signal is shielded to reduce its impact on the useful signal; specifically, a bandpass filter can be used to filter out the frequency components of the interference signal, thereby retaining the frequency components of the useful signal.

[0105] Spatial filtering: Use multiple antenna arrays and spatial diversity technology to suppress interference. Multiple antenna arrays can receive signals from different directions. Through signal processing algorithms, useful signals can be separated from interference signals, thereby suppressing interference; specifically, the minimum mean square error (MMSE) criterion can be used to estimate the weights of the multiple antenna arrays, thereby maximizing the separation effect of useful signals and interference signals.

[0106] Time domain window: Window the signal in the time domain, and set the time window length to 50ms. Windowing can reduce the frequency domain leakage of the signal and improve the time domain resolution of the signal, thereby improving the quality of the signal. Specifically, the Hamming window can be used to window the signal, because the Hamming window has good time domain resolution and frequency domain resolution, which can effectively suppress the frequency domain leakage of the signal.

[0107] According to the characteristics and types of interference signals monitored in real time, the parameters of interference suppression measures are dynamically adjusted to adapt to dynamically changing interference signals. This includes dynamically adjusting parameters such as frequency shielding range, spatial filtering algorithm and time domain window length; in addition, adaptive algorithms can be used in combination to monitor and adjust parameters in real time to ensure the effectiveness and adaptability of interference suppression measures; in actual applications, the above steps can be adjusted and optimized according to specific environments and needs. For example, parameters such as frequency shielding range, spatial filtering algorithm and time domain window length can be adjusted according to the actual characteristics and types of interference signals; appropriate spatial filtering algorithms and time domain window functions can be selected according to the computing resources and algorithm complexity of the equipment; appropriate interference signal characteristics and type identification methods can be selected according to the actual environment and needs.

[0108] As described in step S140, optimized navigation information is generated based on the suppression processing information and the real-time navigation information of the drone.

[0109] In one embodiment of the present invention, the specific process of "generating optimized navigation information based on the suppression processing information and the real-time navigation information of the drone" in step S140 can be further explained in combination with the following description.

[0110] As described in the following steps,

[0111] S510, obtaining navigation data in the real-time navigation information of the drone, wherein the navigation data includes position, speed and navigation direction;

[0112] S520, determining the interference intensity of the current environment according to the position, the speed and the navigation direction;

[0113] S530: Generate the optimized navigation information according to the interference intensity, a preset adjustment rule and a preset detection threshold, wherein the preset adjustment rule includes an adjustment period and an adjustment range.

[0114] It should be noted that the initial interference detection and suppression strategy includes parameters such as the detection threshold and suppression strength of the interference signal.

[0115] As an example, during the flight, the drone collects navigation data in real time through built-in sensors and receiving devices. The navigation data includes information such as position, speed, and direction; the drone dynamically adjusts the interference detection and suppression strategy through an adaptive algorithm. The adjustment cycle is 10 seconds, and the dynamic adjustment range is ±10dB; specifically, when the electromagnetic environment changes, the drone calculates the interference intensity of the current environment in real time and compares it with the set detection threshold. If the current interference intensity exceeds the set detection threshold, the interference detection and suppression strategy is automatically adjusted to increase the detection threshold and suppression intensity to suppress the impact of the interference signal.

[0116] In a specific implementation, the drone can also use a high-precision navigation algorithm, combined with real-time navigation data and electromagnetic environment changes, to perform high-precision navigation calculations to improve navigation accuracy. At the same time, the drone uses an adaptive filtering algorithm to further improve navigation accuracy and stability; the drone uses multi-antenna reception technology to improve the multipath diversity effect of signal reception and enhance anti-interference capabilities. At the same time, the drone uses advanced interference signal suppression algorithms to further suppress the impact of interference signals.

[0117] As described in step S150, a plurality of planned paths are generated according to the optimized navigation information and the preset sharing rules.

[0118] In an embodiment of the present invention, the specific process of "generating a plurality of planned paths according to the optimized navigation information and the preset sharing rules" in step S150 can be further explained in combination with the following description.

[0119] As described in the following steps,

[0120] S610, sharing the optimized navigation information with a preset sharing platform to generate avoidance information for avoiding the same adjustment situation;

[0121] S620: Generate a plurality of planned paths according to the avoidance information and the optimized navigation information.

[0122] It should be noted that before the drone takes off, the initial interference detection and suppression strategy, as well as the collaborative cooperation mechanism, are set through the ground station; the collaborative cooperation mechanism includes the communication method with other drones or ground stations, the data sharing scope, etc.

[0123] In a specific implementation, the drone establishes a collaborative mechanism with other drones or ground stations through a wireless communication network to share interference signal information and navigation data; specifically, the drone sends the collected navigation data and environmental data to other drones or ground stations through the wireless communication network, and at the same time receives data sent by other drones or ground stations.

[0124] As described in step S160, the target navigation path is determined based on the real-time parameter information of the drone body and the plurality of planned paths.

[0125] In one embodiment of the present invention, the specific process of "determining the target navigation path based on the real-time parameter information of the drone body and the plurality of planned paths" in step S160 can be further explained in combination with the following description.

[0126] As described in the following steps,

[0127] S710, performing deep learning processing on the plurality of planned paths and the real-time parameter information to determine the priority of the plurality of planned paths;

[0128] S720, selecting a planned path with a priority greater than or equal to 90% from the plurality of planned paths and determining it as a priority path set;

[0129] S730, generating the stability of each priority path according to the preset evaluation index and the priority path set;

[0130] S740, determining a first target path by comparing the stability of each path with a preset stability threshold;

[0131] S750: Determine whether there is a preset abnormal situation in the execution process of the first target path;

[0132] S760: When the execution process of the first target path does not contain the preset abnormal situation, determine the target navigation path as the first target path to continue to be executed; or

[0133] S770: When the preset abnormal situation exists in the execution process of the first target path, a second target path is determined according to the first target path and a first stability corresponding to the first target path, and the second target path is marked as the target navigation path.

[0134] It should be noted that the second target path is switched only when a preset abnormal situation occurs during the execution of the first target path; the preset abnormal situation includes path blocking, signal loss, low battery power, etc.

[0135] As an example, the deep Q network (DQN) algorithm is used. The network structure includes an input layer, a hidden layer, and an output layer. The input layer includes the position, speed, direction and other state information of the drone. The hidden layer uses a convolutional neural network (CNN) to extract path features. The output layer outputs the cost value of the path. When training the network, the Q learning algorithm is used to update the network weights so that the network can generate the optimal path in real time according to the state information of the drone. In the path planning process, multiple possible planning paths are generated, and at least two target planning paths are selected from them. These planning paths have different routes and strategies on the premise of meeting the flight requirements of the drone, so that when encountering obstacles or other abnormal situations, the drone can automatically switch to the backup navigation path to ensure flight stability and navigation accuracy; safety and stability evaluation. In the process of generating path planning, safety and stability evaluation indicators such as the curvature of the path, the rate of change of altitude, the distance to obstacles, etc. are introduced to evaluate the generated path to ensure the safety and stability of the drone during flight; automatic switching mechanism. During the flight of the drone, the status of the current path is monitored in real time. When obstacles or other abnormal conditions occur, the drone automatically switches to the backup navigation path. In specific implementation, when path obstruction, signal loss, low battery, etc. are detected, the drone automatically switches to the backup navigation path. Collaborative control and optimization. After the drone switches to the backup navigation path, the flight parameters and control instructions of the drone are adjusted in real time to ensure that the drone can fly stably along the new path. In specific implementation, the multi-agent system (MAS) algorithm is used to achieve collaborative control and optimization of drones.

[0136] In a specific implementation, the parameters of the deep Q network (DQN) algorithm used by the drone are as follows: the input layer includes the drone's position, speed, direction and other state information, the hidden layer uses a convolutional neural network (CNN) to extract path features, and the output layer outputs the cost value of the path. During network training, the Q learning algorithm is used to update the network weights, the learning rate is set to 0.001, the discount factor is set to 0.99, and the number of training rounds is set to 10000; the strategy of multi-path screening is as follows: according to the safety and stability evaluation indicators such as the curvature of the path, the height change rate, and the obstacle distance, the generated paths are scored, and at least two paths with the highest scores are selected as the target planning path; the preset conditions of the automatic switching mechanism are as follows: when the path is blocked, the drone automatically switches to the backup navigation path; when the signal is lost, the drone automatically switches to the backup navigation path; when the battery is low, the drone automatically switches to the backup navigation path; the parameters of the multi-agent system (MAS) algorithm for collaborative control and optimization are as follows: the number of agents is set to 3, each agent is responsible for adjusting a certain flight parameter of the drone, such as position, speed, direction, etc., and the agents use a cooperative game algorithm to coordinate to maximize the overall flight performance of the drone.

[0137] The beneficial effects of this technical solution are as follows: 1. Intelligent identification of interference signals: This technical solution can effectively deal with various interference signals in complex electromagnetic environments, including pseudo-signals, dynamically changing signals, etc., by intelligently identifying the characteristics and types of interference signals. Compared with the prior art, this technical solution can more accurately identify and classify interference signals, thereby improving the navigation accuracy of the UAV. 2. Real-time performance: This technical solution adopts efficient signal processing and artificial intelligence algorithms, which can complete the identification and suppression of interference signals in a shorter time, meeting the real-time requirements of UAV navigation. Compared with the prior art, this technical solution requires less computing resources and time when processing interference signals in complex electromagnetic environments, thereby improving the efficiency of the system. 3. Adaptability: This technical solution can automatically analyze and identify the characteristics and types of interference signals through machine learning, deep learning and other methods, so as to take corresponding interference suppression measures. Compared with the prior art, this technical solution has stronger adaptability, can adapt to complex and changing environments, and reduce missed reports and false reports. 4. Safety: This technical solution can reduce the impact of interference signals on the navigation route or path of the UAV by taking corresponding interference suppression measures, thereby improving the flight safety of the UAV. Compared with the existing technology, this technical solution can more effectively ensure the navigation safety and stability of drones in complex electromagnetic environments. 5. Broad application prospects: This technical solution is not only suitable for drone navigation, but can also be promoted and applied to other fields that require navigation and path planning, such as self-driving cars, robots, etc.

[0138] As for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0139] Reference Figure 2 , showing a structural block diagram of a UAV navigation system based on intelligent identification of interference signals provided by an embodiment of the present application;

[0140] A drone navigation system based on intelligent identification of interference signals, the system involves a drone body and a sensor arranged on the drone body, the system comprising:

[0141] An acquisition module 210 is used to acquire detection information within the flight range of the UAV through the sensor, wherein the detection information includes real-time environment information and interference signal information;

[0142] A first determination module 220, configured to determine a signal type according to the interference signal information and the real-time environment information, wherein the signal type includes a radio signal and an electromagnetic signal;

[0143] A first generating module 230, for generating suppression processing information according to the signal type and the real-time navigation information of the UAV;

[0144] A second generating module 240 is used to generate optimized navigation information according to the suppression processing information and the real-time navigation information of the UAV;

[0145] A third generating module 250 is used to generate a plurality of planned paths according to the optimized navigation information and preset sharing rules;

[0146] The second determination module 260 is used to determine the target navigation path according to the real-time parameter information of the drone body and the plurality of planned paths.

[0147] In one embodiment of the present invention, the acquisition module 210 includes:

[0148] A first determination submodule is used to determine the current state type of the drone body, where the current state type is an execution state or a non-execution state;

[0149] A first collection submodule, configured to, when the current state type is the execution state, cause the sensor to collect electromagnetic information and real-time environmental information of the drone body within a preset flight range;

[0150] A first generating submodule, used for performing fast Fourier transform processing on the electromagnetic information to generate a processing signal;

[0151] A second generating submodule, configured to generate the interference signal information according to the electromagnetic information and the processed signal;

[0152] The third generating submodule is used to generate the detection information according to the interference signal information and the real-time environment information.

[0153] In one embodiment of the present invention, the first determining module 220 includes:

[0154] A second determination submodule is used to perform a first deep learning process on the interference signal information to determine characteristic information, where the characteristic information includes frequency, intensity and signal direction;

[0155] A fourth generating submodule, configured to perform a second deep learning process according to the frequency, the strength, the signal direction and the real-time environmental information to generate an initial interference signal recognition model;

[0156] A fifth generating submodule, used for filtering the initial interference signal recognition model to generate an optimized model;

[0157] A sixth generation submodule, used for performing lightweight processing on the optimization model to generate a target interference signal recognition model;

[0158] The third determination submodule is used to determine the signal type according to the interference signal information and the target interference signal identification model, wherein the signal type includes the radio signal and the electromagnetic signal.

[0159] In one embodiment of the present invention, the first generating module 230 includes:

[0160] A seventh generating submodule, configured to analyze and process the target signal corresponding to the signal type to generate a feature type, wherein the feature type includes one of a frequency feature, a time domain feature, and a space feature;

[0161] an eighth generating submodule, for generating a frequency shielding range according to the frequency feature and the real-time navigation information of the drone when the feature type is the frequency feature; or,

[0162] A fourth determination submodule is configured to, when the feature type is the spatial feature, perform minimum mean square error processing based on the spatial feature and the real-time navigation information of the UAV to determine a useful signal within the target signal; or

[0163] a ninth generating submodule, for, when the feature type is the time domain feature, performing time domain window processing according to the time domain feature and the real-time navigation information of the UAV to generate a time domain resolution for improving the quality of the target signal;

[0164] The tenth generating submodule is used to generate the suppression processing information according to one of the frequency masking range, the useful signal or the time domain resolution.

[0165] In one embodiment of the present invention, the second generating module 240 includes:

[0166] A first acquisition submodule is used to acquire navigation data in the real-time navigation information of the drone, wherein the navigation data includes position, speed and navigation direction;

[0167] a fifth determination submodule, configured to determine the interference intensity of the current environment according to the position, the speed and the navigation direction;

[0168] The eleventh generating submodule is used to generate the optimized navigation information according to the interference intensity, a preset adjustment rule and a preset detection threshold, wherein the preset adjustment rule includes an adjustment period and an adjustment range.

[0169] In one embodiment of the present invention, the third generating module 250 includes:

[0170] A twelfth generating submodule, used for sharing the optimized navigation information with a preset sharing platform to generate avoidance information for avoiding the same adjustment situation;

[0171] The thirteenth generation submodule is used to generate a plurality of the planned paths according to the avoidance information and the optimized navigation information.

[0172] In one embodiment of the present invention, the second determining module 260 includes:

[0173] A sixth determination submodule, configured to determine the priority of the plurality of planned paths by performing deep learning processing on the plurality of planned paths and the real-time parameter information;

[0174] A seventh determination submodule is used to select a planned path with a priority greater than or equal to 90% from the plurality of planned paths and determine it as a priority path set;

[0175] A fourteenth generating submodule, used for generating the stability of each priority path according to a preset evaluation index and the priority path set;

[0176] An eighth determination submodule, configured to determine a first target path by comparing the stability of each of the paths with a preset stability threshold;

[0177] a ninth determination submodule, configured to determine whether there is a preset abnormality in the execution process of the first target path;

[0178] a tenth determining submodule, configured to determine that the target navigation path is the first target path to be continued to be executed when the execution process of the first target path does not contain the preset abnormal situation; or

[0179] An eleventh determination submodule is used to determine a second target path according to the first target path and a first stability corresponding to the first target path and mark the second target path as the target navigation path when the preset abnormal situation exists in the execution process of the first target path.

[0180] Reference Figure 3 , shows a computer device of a drone navigation method based on intelligent identification of interference signals of the present invention, which may specifically include the following:

[0181] The computer device 12 is in the form of a general-purpose computing device, and the components of the computer device 12 may include but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0182] The bus 18 represents one or more of several types of bus 18 structures, including a memory bus 18 or memory controller, a peripheral bus 18, an accelerated graphics port, a processor, or a local bus 18 using any of a variety of bus 18 architectures. These architectures include, by way of example, but are not limited to, an Industry Standard Architecture (ISA) bus 18, a Micro Channel Architecture (MAC) bus 18, an Enhanced ISA bus 18, an Audio Video Electronics Standards Association (VESA) local bus 18, and a Peripheral Component Interconnect (PCI) bus 18.

[0183] The computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computer device 12, including volatile and non-volatile media, removable and non-removable media.

[0184] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Computer device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (commonly referred to as a "hard drive"). Although Figure 3 Not shown, a disk drive for reading and writing to a removable non-volatile disk (such as a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM or other optical medium) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The memory may include at least one program product having a set (e.g., at least one) of program modules 42, which are configured to perform the functions of various embodiments of the present invention.

[0185] A program / utility 40 having a set (at least one) of program modules 42 may be stored in, for example, a memory, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules 42, and program data, each of which or some combination may include an implementation of a network environment. The program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0186] The computer device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, cameras, etc.), one or more devices that enable a user to interact with the computer device 12, and / or any device that enables the computer device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the computer device 12 may also communicate with one or more networks (e.g., local area networks (LANs)), wide area networks (WANs), and / or public networks (e.g., the Internet) via a network adapter 20. As shown, the network adapter 20 communicates with other modules of the computer device 12 via a bus 18. It should be understood that although Figure 3 Not shown, other hardware and / or software modules may be used in conjunction with the computer device 12, including but not limited to: microcode, device drivers, redundant processing units 16, external disk drive arrays, RAID systems, tape drives, and data backup storage systems 34, etc.

[0187] The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28, such as implementing a UAV navigation method based on intelligent identification of interference signals provided in an embodiment of the present invention.

[0188] That is, when the processing unit 16 executes the program, it realizes: acquiring detection information within the flight range of the UAV through the sensor, wherein the detection information includes real-time environmental information and interference signal information; determining the signal type based on the interference signal information and the real-time environmental information, wherein the signal type includes radio signals and electromagnetic signals; generating suppression processing information based on the signal type and the real-time navigation information of the UAV; generating optimized navigation information based on the suppression processing information and the real-time navigation information of the UAV; generating a number of planned paths based on the optimized navigation information and preset sharing rules; and determining the target navigation path based on the real-time parameter information of the UAV body and a number of the planned paths.

[0189] In an embodiment of the present invention, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a drone navigation method based on intelligent identification of interference signals as provided in all embodiments of the present application:

[0190] That is, when the program is executed by the processor, it is implemented as follows: acquiring detection information within the flight range of the drone through the sensor, wherein the detection information includes real-time environmental information and interference signal information; determining the signal type based on the interference signal information and the real-time environmental information, the signal type includes radio signals and electromagnetic signals; generating suppression processing information based on the signal type and the real-time navigation information of the drone; generating optimized navigation information based on the suppression processing information and the real-time navigation information of the drone; generating a number of planned paths based on the optimized navigation information and preset sharing rules; and determining the target navigation path based on the real-time parameter information of the drone body and a number of the planned paths.

[0191] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, device or device.

[0192] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0193] The computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet). The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the various embodiments can be referred to each other.

[0194] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0195] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0196] The above is a detailed introduction to a drone navigation method and system for intelligently identifying interference signals provided by the present application. This article uses specific examples to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for general technical personnel in this field, according to the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A UAV navigation method based on intelligent identification of interference signals, characterized in that: The method involves a drone body and a sensor disposed on the drone body, and the method comprises: Acquiring detection information within the flight range of the UAV through the sensor, wherein the detection information includes real-time environmental information and interference signal information; Determine the signal type based on the interference signal information and the real-time environment information, the signal type includes radio signals and electromagnetic signals; perform a first deep learning process on the interference signal information to determine feature information, the feature information includes frequency, intensity and signal direction; perform a second deep learning process based on the frequency, the intensity, the signal direction and the real-time environment information to generate an initial interference signal recognition model; perform filtering processing on the initial interference signal recognition model to generate an optimization model; perform lightweight processing on the optimization model to generate a target interference signal recognition model; determine the signal type based on the interference signal information and the target interference signal recognition model; Generate suppression processing information according to the signal type and the real-time navigation information of the UAV; analyze and process the target signal corresponding to the signal type to generate a feature type, wherein the feature type includes one of a frequency feature, a time domain feature and a space feature; when the feature type is the frequency feature, generate a frequency shielding range according to the frequency feature and the real-time navigation information of the UAV; or, when the feature type is the space feature, perform minimum mean square error processing according to the space feature and the real-time navigation information of the UAV to determine a useful signal within the target signal; or, when the feature type is the time domain feature, perform time domain window processing according to the time domain feature and the real-time navigation information of the UAV to generate a time domain resolution for improving the quality of the target signal; generate the suppression processing information according to one of the frequency shielding range, the useful signal or the time domain resolution; generating optimized navigation information based on the suppression processing information and the real-time navigation information of the UAV; Generating a plurality of planned paths according to the optimized navigation information and preset sharing rules; The target navigation path is determined according to the real-time parameter information of the drone body and a plurality of the planned paths.

2. The method according to claim 1, characterized in that The step of acquiring detection information within the flight range of the drone through the sensor, wherein the detection information includes real-time environmental information and interference signal information, comprises: Determine the current state type of the drone body, where the current state type is an execution state or a non-execution state; When the current state type is the execution state, the sensor collects electromagnetic information and real-time environmental information of the drone body within a preset flight range; Performing fast Fourier transform processing on the electromagnetic information to generate a processing signal; generating the interference signal information according to the electromagnetic information and the processed signal; The detection information is generated according to the interference signal information and the real-time environment information.

3. The method according to claim 1, characterized in that The step of generating optimized navigation information based on the suppression processing information and the real-time navigation information of the UAV comprises: Acquire navigation data in the real-time navigation information of the drone, wherein the navigation data includes position, speed and navigation direction; Determining interference intensity of a current environment according to the position, the speed and the navigation direction; The optimized navigation information is generated according to the interference intensity, a preset adjustment rule and a preset detection threshold, wherein the preset adjustment rule includes an adjustment period and an adjustment range.

4. The method according to claim 1, characterized in that: The step of generating a plurality of planned paths according to the optimized navigation information and the preset sharing rules includes: Sharing the optimized navigation information with a preset sharing platform to generate avoidance information for avoiding the same adjustment situation; A plurality of the planned paths are generated according to the avoidance information and the optimized navigation information.

5. The method according to claim 1, characterized in that The step of determining the target navigation path based on the real-time parameter information of the drone body and the plurality of planned paths includes: Performing deep learning processing on the plurality of planned paths and the real-time parameter information to determine the priority of the plurality of planned paths; Selecting a planned path with a priority greater than or equal to 90% from the plurality of planned paths and determining it as a priority path set; Generating the stability of each priority path according to the preset evaluation index and the priority path set; Determine a first target path by comparing the stability of each of the paths with a preset stability threshold; Determining whether there is a preset abnormal situation in the execution process of the first target path; When the execution process of the first target path does not contain the preset abnormal situation, determining the target navigation path to be the first target path to continue to execute; or, When the preset abnormal situation exists in the execution process of the first target path, a second target path is determined according to the first target path and a first stability corresponding to the first target path, and the second target path is marked as the target navigation path.

6. A UAV navigation system based on intelligent identification of interference signals, characterized in that: The system involves a drone body and a sensor arranged on the drone body, and the system includes: An acquisition module, used to acquire detection information within the flight range of the UAV through the sensor, wherein the detection information includes real-time environment information and interference signal information; A first determination module is used to determine the signal type based on the interference signal information and the real-time environment information, the signal type including radio signals and electromagnetic signals; perform a first deep learning process on the interference signal information to determine feature information, the feature information including frequency, intensity and signal direction; perform a second deep learning process based on the frequency, intensity, signal direction and the real-time environment information to generate an initial interference signal recognition model; perform filtering processing on the initial interference signal recognition model to generate an optimization model; perform lightweight processing on the optimization model to generate a target interference signal recognition model; determine the signal type based on the interference signal information and the target interference signal recognition model; The first generating module is used to generate suppression processing information according to the signal type and the real-time navigation information of the UAV; analyze and process the target signal corresponding to the signal type to generate a feature type, and the feature type includes one of a frequency feature, a time domain feature and a space feature; when the feature type is the frequency feature, a frequency shielding range is generated according to the frequency feature and the real-time navigation information of the UAV; or, when the feature type is the space feature, a minimum mean square error processing is performed according to the space feature and the real-time navigation information of the UAV to determine a useful signal in the target signal; or, when the feature type is the time domain feature, a time domain window processing is performed according to the time domain feature and the real-time navigation information of the UAV to generate a time domain resolution for improving the quality of the target signal; the suppression processing information is generated according to one of the frequency shielding range, the useful signal or the time domain resolution; A second generating module is used to generate optimized navigation information according to the suppression processing information and the real-time navigation information of the UAV; A third generation module is used to generate a plurality of planned paths according to the optimized navigation information and preset sharing rules; The second determination module is used to determine the target navigation path according to the real-time parameter information of the drone body and a plurality of the planned paths.

7. A computer device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the method according to any one of claims 1 to 5 when executed by the processor.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images