A Navigation Deception Method and Device for UAV Countermeasures

Abstract

The present invention discloses a navigation deception method and device for UAV countermeasure. The deception method includes: S1: obtaining the position information of a target UAV at multiple moments and constructing a position prediction model; S2: estimating the navigation signal strength when the target UAV is located at a selected position to obtain a predicted navigation signal strength; S3: generating a navigation deception signal according to the predicted navigation signal strength; S4: when the target UAV reaches the selected position, transmitting the navigation deception signal to the target UAV. The present invention can improve the success rate of navigation deception.

Description

Technical Field

[0001] The present invention relates to the technical field related to the control of unmanned aerial vehicles (UAVs). More specifically, the present invention relates to a navigation deception method and device for UAV countermeasures. Background Art

[0002] UAVs have been widely used in fields such as logistics transportation, aerial photography, and reconnaissance. However, due to the lack of effective control means, the "illegal flight" behavior of UAVs poses a threat to normal production and life, such as affecting flight takeoffs and landings and stealing confidential information. There are already some UAV deception technical solutions in the prior art, but the anti-deception technology of UAVs is also evolving. Once it detects abnormal navigation signals, it may also take corresponding countermeasures. Therefore, it is necessary to design a technical solution that can overcome the above-mentioned defects to a certain extent. Summary of the Invention

[0003] An object of the present invention is to provide a navigation deception method and device for UAV countermeasures, which can improve the success rate of navigation deception.

[0004] To achieve these objects and other advantages of the present invention, according to one aspect of the present invention, there is provided a navigation deception method for UAV countermeasures, including: S1: obtaining the position information of a target UAV at multiple moments and constructing a position prediction model; S2: estimating the navigation signal strength when the target UAV is located at a selected position to obtain a predicted navigation signal strength; S3: generating a navigation deception signal according to the predicted navigation signal strength; S4: when the target UAV reaches the selected position, transmitting the navigation deception signal to the target UAV.

[0005] Further, in S2, the position information, terrain parameters, and weather parameters of the selected position are input into a pre-established signal strength prediction model to obtain the predicted navigation signal strength; wherein, the signal strength prediction model is trained by a decision tree model.

[0006] Further, the strength of the navigation deception signal is at least consistent with the predicted navigation signal strength.

[0007] Further, there are multiple selected positions, and the multiple selected positions are determined by gradually fine-tuning the position prediction model.

[0008] Further, when the target UAV reaches the first selected position, transmit the navigation deception signal to the target UAV and determine whether the deception is successful. If the deception is not successful, repeat S2 - S4.

[0009] Further, the method for determining whether the decoying is successful includes: obtaining a plurality of position information of the target UAV between the first selected position and the second selected position, and determining whether it conforms to the position prediction model. If it conforms, it is determined that the decoying is not successful.

[0010] According to another aspect of the present invention, there is also provided a navigation decoy device for UAV countermeasure, including: a construction module, configured to obtain the position information of the target UAV at multiple moments and construct a position prediction model; a prediction module, configured to estimate the navigation signal strength when the target UAV is located at the selected position to obtain a predicted navigation signal strength; a generation module, configured to generate a navigation decoy signal according to the predicted navigation signal strength; and a decoy module, configured to transmit the navigation decoy signal to the target UAV when the target UAV reaches the selected position.

[0011] Further, the prediction module inputs the position information, terrain parameters, and weather parameters of the selected position into a pre-established signal strength prediction model to obtain the predicted navigation signal strength; wherein, the signal strength prediction model is trained by a decision tree model.

[0012] Further, there are multiple selected positions, and the multiple selected positions are determined by gradually fine-tuning the position prediction model. According to yet another aspect of the present invention, there is also provided a navigation decoy device for UAV countermeasure, including: a processor; a memory for storing executable instructions; wherein, the processor is configured to execute the executable instructions to implement the navigation decoy method for UAV countermeasure as described above.

[0013] The present invention has at least the following beneficial effects:

[0014] The present invention obtains the position information of the target UAV at multiple moments, constructs a position prediction model, and estimates the predicted navigation signal strength when the target UAV is located at the selected position. According to the predicted navigation signal strength, a navigation decoy signal is generated to transmit the navigation decoy signal to the target UAV when the target UAV reaches the selected position; by predicting the current position of the target UAV and its navigation signal strength, the generated navigation decoy signal has a small difference from the real navigation signal, reducing the possibility of being recognized and improving the decoy success rate.

[0015] Other advantages, objectives, and features of the present invention will be partially reflected by the following description, and partially will also be understood by those skilled in the art through the research and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flowchart of an embodiment of the present application;

[0017] Figure 2Frame diagram of an embodiment of the present application. Detailed implementation manners

[0018] The present invention will be further described in detail below with reference to the accompanying drawings, so that those skilled in the art can implement it according to the description in the specification.

[0019] It should be understood that terms such as "having", "including", and "comprising" used in the embodiments of the present application do not exclude the presence or addition of one or more other elements or combinations thereof. All directional indications (such as up, down, left, right, front, back...) in the embodiments of the present application are only used to explain the relative positional relationship and movement conditions between components in a specific posture. If the specific posture changes, the directional indications will also change accordingly. When an element is referred to as being "fixed to" or "disposed on" another element, it can be directly on the other element or there may be an intermediate element at the same time. When an element is referred to as being "connected" to another element, it can be directly connected to the other element or indirectly connected to the other element through an intermediate element. The descriptions in the embodiments of the present application involving "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one such feature.

[0020] It should be noted that the technical solutions between the various embodiments of the present application can be combined with each other, but it must be based on the fact that those of ordinary skill in the art can implement them. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present application.

[0021] As Figure 1-2 shown, the embodiment of the present application provides a navigation deception method for UAV countermeasure, including:

[0022] S1: Obtain the position information of the target UAV at multiple moments and construct a position prediction model;

[0023] For example, a variety of monitoring technologies and equipment are used to obtain the location information of the target UAV at multiple different times, and the location information includes latitude information, longitude information and altitude information; these monitoring technologies may include but are not limited to radar monitoring systems, optical tracking equipment, acoustic tracking equipment and technical means based on wireless signal positioning, etc.; the radar monitoring system can transmit electromagnetic waves and receive the echo signal reflected by the target UAV, and accurately calculate the position parameters such as the distance, azimuth and pitch angle of the target UAV relative to the radar station at different times according to the time delay, Doppler frequency shift and other information of the echo; the optical tracking equipment uses high-resolution cameras and image recognition The identification algorithm is used to capture and analyze the image of the target drone in the air in real time, and its spatial position at different times is determined by processing the coordinates, size, and relative position relationship of the drone with known reference objects in the image. Based on the technology of wireless signal positioning, the communication signal and navigation signal transmitted by the target drone are received, and the approximate position of the drone at each time is calculated by using a variety of positioning methods such as signal strength, arrival time difference, and arrival angle. The sound signal of the target drone is obtained by using three or more microphones, and the position of the target drone can be estimated according to the time when the sound signal reaches each microphone and the position of the microphone itself.

[0024] For example, the position prediction model is constructed by using an exponential smoothing model, which can quickly establish a position prediction model with high accuracy after the target drone is detected. The specific formula is as follows:

[0025]

[0026]

[0027]

[0028] L xi , L yi and L zi Respectively refers to t i The smoothed values ​​of latitude, longitude, and altitude at the moment, L xi-1 , L yi-1 and L zi-1 Respectively refers to t i-1 The smoothed values ​​of latitude, longitude, and altitude at the time, x i ,y i and z i They refer to the actual values ​​of latitude, longitude, and altitude at time ti, respectively. x , α y and α zSmoothing factors for latitude, longitude, and altitude respectively, with values ranging from 0 to 1, obtained by training using the position information at several moments collected; specifically in the calculation, initialize the smoothing values L x0 、L y0 and L z0 , which can be estimated using the position information at several moments collected, taking the first position information or the average of the first few position information, and then performing iteration using the above formula.

[0029] S2: Estimate the navigation signal strength when the target UAV is at the selected position to obtain the predicted navigation signal strength; the selected position is predicted according to the position prediction model and also needs to be specifically determined in combination with the set UAV countermeasure range and the position of the navigation deception device;

[0030] Exemplarily, collect the navigation signal strengths at multiple positions, establish a regression model, a machine learning model, or a neural network model to predict the navigation signal strength at the selected position;

[0031] S3: Generate a navigation deception signal according to the predicted navigation signal strength;

[0032] Specifically, according to the navigation information coding rule followed by the target UAV navigation system, generate the signal coding content including false navigation-related information such as position, speed, and time, and embed it into the deception signal waveform, so that after the UAV receives the deception signal, it parses out these false navigation information and mistakenly believes it is the valid information from the real navigation satellite, thereby changing its own navigation state;

[0033] Exemplarily, the strength of the navigation deception signal should be the same as or slightly higher than the predicted navigation signal strength (specifically determined considering the distance between the navigation deception device and the UAV, ignoring the distance factor when the position is relatively close), to avoid being considered abnormal by the target UAV due to too high signal strength or not being adopted by the target UAV due to too low signal strength;

[0034] S4: When the target UAV reaches the selected position, transmit the navigation deception signal to the target UAV;

[0035] In this step, continuously track the target UAV and collect its position information. When it reaches the selected position, the navigation deception signal is sent;

[0036] It can be seen that in this embodiment, the position prediction model is used to accurately predict the position of the target UAV, and then the predicted navigation signal strength is accurately estimated, so that the generated navigation deception signal is less different from the real navigation signal, reducing the possibility of being recognized and improving the deception success rate.

[0037] In another embodiment, in S2, the position information, terrain parameters, and weather parameters of the selected location are input into a pre-established signal strength prediction model to obtain the predicted navigation signal strength; wherein, the signal strength prediction model is obtained by training a decision tree model;

[0038] In this embodiment, compared with some complex deep learning models, the decision tree model does not require large-scale iterative optimization, complex gradient calculations, etc. during the training process. It is relatively simple and easy to understand. When dealing with tasks such as predicting navigation signal strength where the data scale is usually not extremely large, the training process can be completed relatively quickly to obtain a usable prediction model; once the decision tree model is trained, when predicting the navigation signal strength, only need to judge which child node to go to along the branch structure of the tree according to the feature values of the input samples, and finally reach the leaf node to obtain the corresponding predicted value; this process has a relatively small amount of calculation and can quickly give the prediction result. For navigation spoofing scenarios with high real-time requirements, it can provide the required signal strength information in a timely manner;

[0039] Specifically, the position information is the latitude information, longitude information, and altitude information mentioned above. The terrain parameter data can be obtained through a high-precision Geographic Information System (GIS) including information such as the degree of terrain undulation, surface roughness, terrain slope, and landform type. It can also obtain the position, height, density, etc. of artificial buildings such as buildings, large bridges, and towers, as well as natural tall trees in space through an electronic map. The weather parameter data includes various weather-related parameters such as atmospheric temperature, humidity, air pressure, wind speed, wind direction, and precipitation conditions (different precipitation types such as rain, snow, fog, etc. and their intensities). Considering that weather conditions have a significant impact on the propagation of electromagnetic signals, for example, rainfall will absorb and scatter signals, resulting in signal strength attenuation; it is also necessary to obtain actual navigation signal strength measurement data. Under the above various different positions, terrains, and weather conditions, use professional signal strength detection equipment to measure the navigation signal strength on-site and use it as the label for model training;

[0040] Perform a comprehensive data cleaning operation on the collected various data to remove the existing outliers (such as obviously unreasonable signal strength values due to measurement equipment failures, or incorrect data points with coordinate positions outside the reasonable range, etc.) and duplicate data records to ensure the accuracy and consistency of the data and avoid interference from these abnormal data on subsequent model training;

[0041] Encode the collected data to make it suitable as the input of the decision tree model. For example, there are five different categories of landform types. After one-hot encoding, five binary feature columns will be generated, and each column corresponds to a landform type, so as to clearly represent which landform this position belongs to and facilitate the model to be processed and analyzed during the training process;

[0042] Given that the coordinate values in the location information, various quantization metrics in the terrain parameters, and the numerical ranges in the weather parameters vary greatly, in order to enable the decision tree model to treat each feature fairly during the training process and avoid the dominant influence of certain feature values being too large or too small on the model, these numerical variables are normalized or standardized;

[0043] The CART (Classification and Regression Tree) algorithm is selected to construct the decision tree model. This algorithm can be used for both classification tasks and regression tasks and is very suitable for predicting continuous numerical target variables such as navigation signal strength. In the model initialization stage, some key hyperparameters need to be set, such as the maximum depth of the tree (initially set to a moderate value, such as 10, which limits the growth of the decision tree and avoids overfitting due to an overly complex tree, but the specific appropriate value needs to be further optimized and determined through methods such as cross-validation later), the minimum number of samples for splitting (set to a small value, such as 2, meaning that at least 2 sample quantities need to be included in the node to allow the node to continue splitting, preventing the generation of overly fragmented leaf nodes. Similarly, this parameter will be adjusted according to the training situation later), the minimum number of samples in the leaf (set to 1 to ensure that the leaf node contains at least 1 sample quantity and makes it representative), and the splitting criterion for feature selection (here, the mean squared error is selected as the indicator to measure the quality of node division. Since it is a regression task, the mean squared error can well reflect the difference degree between the predicted value and the actual value), etc.;

[0044] The feature data after preprocessing, selection, and engineering, as well as the corresponding actual navigation signal strength data, are divided into a training set and a test set according to a certain ratio. The division ratio is 8:2, that is, 80% of the data is used for model training to enable the model to learn the relationship law between features and signal strength; 20% of the data is used as the test set to evaluate the prediction performance of the model on unseen data after the model training is completed, so as to verify the generalization ability of the model and ensure that the model does not overfit and can accurately predict the navigation signal strength in new scenarios in actual applications;

[0045] The training set data is input into the selected CART algorithm for training. The decision tree algorithm will continuously construct the branch structure of the tree based on the relationship between features and the target variable. At each node, by calculating the mean squared error corresponding to different features, the feature that minimizes the mean squared error is selected as the basis for dividing the node, and the node is continuously split so that the data within each leaf node is as similar as possible in terms of navigation signal strength. This process is to learn the patterns in the data for subsequent prediction. During the training process, it will iterate multiple times, and each iteration will adjust the structure and parameters of the tree according to the current training data, gradually optimizing the model until the preset stop condition is reached (such as reaching the maximum number of iterations, or the performance on the validation set no longer improves, etc.).

[0046] When the construction, evaluation, and optimization of the model are completed, the position information, terrain parameters, and weather parameters of the selected location of the target UAV (these parameters go through the same preprocessing, feature selection, and engineering steps to keep the data format consistent with that during the training of the model) can be input into the trained decision tree model. The model will output the corresponding predicted navigation signal strength according to the complex decision rules it has learned and the mapping relationship between features and signal strength. This is the predicted navigation signal strength mentioned above.

[0047] In another embodiment, there are multiple selected locations, and the multiple selected locations are determined by gradually fine-tuning the position prediction model;

[0048] Specifically, the smoothing factors α x 、α y and α z of latitude, longitude, and altitude in the above text can be gradually fine-tuned. For example, except for the first selected location, the subsequent selected locations are all obtained from the fine-tuned position prediction model, such as multiplying by an adjustment coefficient, and each is gradually increased or decreased in proportion, so that the adjusted selected location changes slowly compared to the original trajectory, avoiding large changes that may cause the target UAV to be recognized and resulting in the failure of deception. It should be noted that the navigation signal strength prediction and the generation of navigation deception signals are re-performed for each selected location.

[0049] In another embodiment, when the target UAV reaches the first selected location, a navigation deception signal is transmitted to the target UAV, and it is judged whether the deception is successful. If the deception is not successful, then S2 - S4 are repeated, that is, the selected location is re-determined, the navigation signal strength is predicted, the navigation deception signal is generated, and the navigation deception signal is transmitted until the deception is successful;

[0050] Exemplarily, the method for determining whether the decoying is successful includes: obtaining multiple position information of the target UAV between a first selected position and a second selected position, and determining whether it conforms to the position prediction model. If it conforms, it is determined that the decoying is not successful, that is, it is determined whether the target UAV deviates from the original trajectory according to the position prediction model. If it does not deviate, it is determined that the decoying is not successful.

[0051] In another embodiment, when it is determined that the decoying fails, decoying sensitive information is transmitted to the target UAV in a non-sensitive area to mislead the target UAV to fly towards the non-sensitive area.

[0052] Specifically, multiple high-precision radars, optical detectors, radio spectrum analyzers and other devices can be used to work together to cover the target area of interest of the target UAV and a certain range around it, ensuring that the azimuth, altitude, speed, model and other key information of the target UAV can be captured in real time and accurately. The data of these monitoring devices are summarized to the central control unit through a high-speed data link. The central control unit is built-in with an intelligent analysis algorithm, which quickly processes the collected data according to preset rules to determine whether the target UAV is approaching the sensitive area. Once it is determined that the decoying fails, the subsequent decoying process is immediately started.

[0053] Immediately afterwards, multiple decoy signal transmission base stations are set up in a non-sensitive area that is far from the sensitive area and has been pre-surveyed. These base stations are equipped with high-power transmission devices specifically for common UAV communication frequency bands, and can quickly adjust the transmission parameters according to the instructions of the central control unit. When receiving the decoying instruction, the transmission base station carefully constructs the content containing false sensitive information according to the model and communication protocol characteristics of the target UAV, such as some classified information. When the UAV captures these false sensitive information, it can make the UAV operator think that the information sending place has important reconnaissance value, thus changing the UAV flight direction.

[0054] At the same time, to ensure the decoying effect, during the process of transmitting the decoying sensitive information, continuously observe the flight attitude change of the target UAV through the monitoring system, and dynamically adjust the intensity, frequency and content details of the decoying sensitive information according to the real-time response of the UAV. If it is found that the UAV flight trajectory begins to deviate from the original sensitive direction, gradually weaken the intensity of the decoying sensitive information to guide it to land smoothly in the selected non-sensitive area; if the UAV still does not change its course as expected, further strengthen the decoying strategy to increase the credibility of the false information until it is successfully decoyed away from the sensitive area to ensure the airspace safety of the sensitive area.

[0055] An embodiment of the present application further provides a navigation spoofing device for UAV countermeasure, including: a construction module, configured to obtain the position information of a target UAV at multiple moments and construct a position prediction model; a prediction module, configured to estimate the navigation signal strength when the target UAV is located at a selected position to obtain a predicted navigation signal strength; a generation module, configured to generate a navigation spoofing signal according to the predicted navigation signal strength; a spoofing module, configured to transmit the navigation spoofing signal to the target UAV when the target UAV reaches the selected position.

[0056] In this embodiment, a construction module, a prediction module, a generation module, and a spoofing module are constructed by using a computer program. The construction module collects data to establish a position prediction model. The prediction module predicts the navigation signal strength according to the position information. The generation module calls a radio frequency signal generator to generate a navigation spoofing signal. The spoofing module calls an antenna to transmit the navigation spoofing signal. In this embodiment, the position prediction model is used to accurately predict the position of the target UAV, and then the predicted navigation signal strength is accurately estimated, so that the generated navigation spoofing signal has a small difference from the real navigation signal, reducing the possibility of being recognized and improving the spoofing success rate.

[0057] In another embodiment, the prediction module inputs the position information, terrain parameters, and weather parameters of the selected position into a pre-established signal strength prediction model to obtain the predicted navigation signal strength; wherein, the signal strength prediction model is trained by a decision tree model. In this embodiment, a decision tree model is used to construct the signal strength prediction model. Its training process does not require large-scale iterative optimization, complex gradient calculation, etc., and can complete the training process relatively quickly, with a relatively small amount of calculation, and can quickly give a prediction result. For a navigation spoofing scenario with high real-time requirements, it can provide the required signal strength information in a timely manner. For the specific establishment process, please refer to the previous text.

[0058] In another embodiment, there are multiple selected positions, and the multiple selected positions are determined by gradually fine-tuning the position prediction model; in this embodiment, the smoothing factors α x , α y and α z of latitude, longitude, and altitude in the above text can be gradually fine-tuned, so that the selected positions obtained according to the adjusted position prediction model change slowly compared with the original trajectory, avoiding large changes from causing the target UAV to be recognized and resulting in spoofing failure.

[0059] Embodiments of the present application further provide a navigation deception device for UAV countermeasure, including: a processor; a memory for storing executable instructions; wherein, the processor is configured to execute the executable instructions to implement the navigation deception method for UAV countermeasure; the device of this embodiment may be a mobile phone, a laptop computer, a tablet computer, a vehicle-mounted terminal, a UAV, etc., with a memory and a processor internally provided to execute the target detection method of the above embodiment.

[0060] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the embodiments. It can be fully applied to various fields suitable for the present invention. For those skilled in the art, additional modifications can be easily made. Therefore, without departing from the general concept defined by the claims and the equivalent scope, the present invention is not limited to the specific details and the illustrated examples here.

Claims

1. A navigation deception method for countering drones, applied to a navigation deception device, characterized in that: include: S1: Obtain the location information of the target UAV at multiple times and build a location prediction model; S2: estimating the navigation signal strength when the target UAV is located at a selected position to obtain a predicted navigation signal strength; there are multiple selected positions, and the multiple selected positions are determined by gradually fine-tuning the position prediction model; Inputting the location information, terrain parameters and weather parameters of the selected location into a pre-established signal strength prediction model to obtain the predicted navigation signal strength; wherein the signal strength prediction model is obtained by training a decision tree model; S3: generating a navigation decoy signal according to the predicted navigation signal strength; the strength of the navigation decoy signal is at least consistent with the predicted navigation signal strength; S4: When the target UAV reaches the selected location, transmitting a navigation decoy signal to the target UAV; When the target UAV reaches the first selected position, a navigation decoy signal is transmitted to the target UAV, and it is determined whether the decoy is successful. If the decoy is not successful, S2-S4 are repeated.

2. The navigation deception method for countering drones according to claim 1, characterized in that: Methods for determining whether the deception was successful include: A plurality of position information of the target UAV is obtained between the first selected position and the second selected position, and it is determined whether it conforms to the position prediction model. If so, it is determined that the deception is not successful.

3. A navigation deception device for countering drones, characterized in that: include: A construction module is used to obtain the location information of the target UAV at multiple times and build a location prediction model; A prediction module, used to estimate the navigation signal strength when the target UAV is located at a selected position to obtain a predicted navigation signal strength; A generating module, used for generating a navigation decoy signal according to the predicted navigation signal strength; The strength of the navigation decoy signal is at least consistent with the predicted navigation signal strength; A decoy module, used for transmitting a navigation decoy signal to the target UAV when the target UAV reaches a selected position; The prediction module inputs the location information, terrain parameters and weather parameters of the selected location into a pre-established signal strength prediction model to obtain the predicted navigation signal strength; wherein the signal strength prediction model is obtained by training a decision tree model; There are multiple selected positions, and the multiple selected positions are determined by gradually fine-tuning the position prediction model; When the target UAV reaches the first selected position, a navigation decoy signal is transmitted to the target UAV, and it is determined whether the decoy is successful. If the decoy is not successful, the operations of the prediction module, the generation module and the decoy module are repeated.

4. A navigation deception device for countering drones, characterized in that: include: processor; A memory for storing executable instructions; Wherein, the processor is configured to execute the executable instructions to implement the navigation spoofing method for drone countermeasure as described in any one of claims 1 to 2.

Images