A system and deception method to prevent drones from flying autonomously

Abstract

This invention relates to the field of drone deception technology, and discloses a system and method for preventing autonomous drone flight. The method continuously monitors the drone's flight status data stream to identify the current flight mode type; based on the identified flight mode type, it dynamically extracts a set of control parameters from the drone's navigation system; it constructs an interference activation signal sequence using the control parameter set, performs time-series analysis on the interference activation signal sequence to locate parameter change event points; it divides the parameter change event points into intra-mode event points and inter-mode event points, thereby synthesizing flight path deviation parameters; it generates deception control parameters based on the flight path deviation parameters, and executes the deception control parameters to complete the deception action. This invention, by accurately identifying the drone's flight mode and generating targeted deception control parameters, achieves effective interference and path deviation control of the drone's autonomous flight, providing a new technical means for drone management.

Description

Technical Field

[0001] This invention relates to the field of drone deception technology, specifically to a system and method for preventing drones from flying autonomously. Background Technology

[0002] The widespread adoption and expansion of drone technology, while bringing convenience, has also raised issues such as unauthorized incursions into no-fly zones, privacy violations, and even potential security threats. Effectively countering non-cooperative drones, especially those in autonomous flight mode, has become a challenge in the current security field. Traditional drone countermeasures mainly include physical destruction, radio signal jamming, and GPS signal interference. Physical destruction may generate debris that causes secondary damage and has limited applicability. Broadband radio jamming, through high-powered interference signal transmission, disrupts the communication link between the drone and its operator, forcing it to land or return. While direct, this method's non-selective interference may affect the normal operation of other legitimate electronic devices in the vicinity, and its effectiveness may be poor or even ineffective against drones with strong anti-jamming capabilities or pre-programmed autonomous emergency procedures.

[0003] GPS signal jamming works by transmitting signals in a specific frequency band to block a drone's GPS positioning reception, forcing the drone to lose its accurate positioning signal. However, this simple jamming method only cuts off the positioning source and cannot stop the drone from continuing to fly. Most drones are equipped with backup navigation modules such as inertial navigation and visual navigation. Even after losing GPS, they can still maintain autonomous flight by relying on backup systems, and even complete tasks according to preset routes or emergency procedures, greatly reducing the effectiveness of countermeasures. In addition, the above methods are mostly passive responses or "hard kill" attacks, lacking a deep understanding of the drone's current behavioral intentions and targeted utilization of its flight control logic.

[0004] When flying autonomously, unmanned aerial vehicles (UAVs) follow control laws and patterns to maintain stability and complete their missions. Their navigation systems continuously adjust control parameters based on sensor feedback and internal / external commands. By deeply understanding the current flight mode and the patterns of change in control parameters, it may be possible to identify specific "timings" or "nodes" in their control logic. This can be achieved by applying carefully calculated, subtle misleading signals, rather than brute-force full-band interference, to induce flight decision deviations and prevent the UAV from continuing its intended flight. This method requires real-time analysis of UAV flight status data, accurate identification of flight modes, dynamic extraction of control parameters, and precise timing of interference.

[0005] Existing technologies often lack exploration of such sophisticated "soft" deception strategies based on flight mode understanding and control parameter analysis, making it difficult to achieve efficient, low-collateral-effect, and highly targeted new countermeasures. Summary of the Invention

[0006] The purpose of this invention is to provide a system and method for preventing drones from flying autonomously, in order to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides a deception method for preventing autonomous flight of unmanned aerial vehicles (UAVs), the method comprising:

[0008] Continuously monitor the drone's flight status data stream to identify the current flight mode type;

[0009] Based on the identified flight mode type, control parameter sets are dynamically extracted from the UAV navigation system;

[0010] An interference activation signal sequence is constructed using the control parameter set, and time-series analysis is performed on the interference activation signal sequence to locate parameter change event points;

[0011] The parameter change event points are divided into intra-mode event points and inter-mode event points to synthesize flight path deviation parameters.

[0012] Based on the flight path deviation parameters, decoy control parameters are generated, and the decoy control parameters are executed to complete the decoy action.

[0013] Preferably, the step of dynamically extracting control parameter sets from the UAV navigation system based on the identified flight mode type includes: capturing a control reference parameter set and its duration window based on the state change curve of the flight mode type; capturing a control update parameter set and its effective time interval based on the transition trigger point of the flight mode type; processing the control update parameter set using a parameter standardization program to produce a standardized update parameter set; and fusing the control reference parameter set and the standardized update parameter set to form a control parameter set.

[0014] Preferably, the application parameter standardization procedure processes the control update parameter set to produce a standardized update parameter set, including: calculating the parameter difference measure for each state stage using a deviation evaluation algorithm, wherein the deviation evaluation algorithm uses the state influence factor, time decay coefficient, time offset between the state transition trigger point and the parameter update time, and the reference parameter setting time; and adjusting the parameter values ​​based on the proportion of the parameter difference measure in the total difference using a parameter normalization algorithm to obtain the standardized update parameter set.

[0015] Preferably, the step of constructing the interference activation signal sequence using the control parameter set includes: selecting an updated parameter subset from the control parameter set to generate an interference activation signal based on the updated parameter subset; extracting a normalized updated parameter set from the control parameter set to generate an interference activation signal based on the normalized updated parameter set; comparing the interference activation signal based on the updated parameter subset with the interference activation signal based on the normalized updated parameter set to obtain the activation signal patterns of the same flight mode type and different flight mode types in the state phase; and optimizing the generation time point of the interference activation signal sequence based on the activation signal patterns.

[0016] Preferably, the step of performing time-series analysis on the interference activation signal sequence to locate parameter change event points includes: calculating a matching degree index between the interference activation signal sequence and the reference time series corresponding to historical parameter change event points; if the matching degree index exceeds a preset matching threshold, it is identified as a consistent parameter change event point and used as an intra-mode parameter change event point; calculating a matching degree index between the interference activation signal sequence and the reference time series corresponding to historical parameter reset event points; if the matching degree index is lower than a preset matching threshold, it is identified as a conflicting parameter change event point and used as an inter-mode parameter reset event point.

[0017] Preferably, the method for calculating the matching degree index between the interference activation signal sequence and the reference time series corresponding to the historical parameter reset event point includes: calculating the covariance value between the time data of the interference activation signal sequence and the reference time series, and calculating the standard deviation between the time data of the interference activation signal sequence and the standard deviation of the reference time series, and dividing the covariance value by the product of the standard deviations to obtain the matching degree index.

[0018] Preferably, optimizing the generation time of the interference activation signal sequence based on the activation signal mode includes: if the activation signal mode is greater than a preset mode threshold, then the generation of the interference activation signal sequence is triggered in advance; if the activation signal mode is less than the preset mode threshold, then the generation of the interference activation signal sequence is delayed.

[0019] Preferably, the step of dividing the parameter change event points into intra-mode event points and inter-mode event points to synthesize flight path deviation parameters includes: extracting parameter change event points caused by environmental disturbances within the same flight mode type and labeling them as intra-mode parameter change event points; extracting parameter reset event points triggered when switching between different flight mode types and labeling them as inter-mode parameter change event points; calculating the parameter change magnitude within the same flight mode type based on the intra-mode parameter change event points as internal path deviation parameters; calculating the parameter change magnitude when switching flight mode types based on the inter-mode parameter change event points as switching path deviation parameters; and using the combination result of the internal path deviation parameters and the switching path deviation parameters as the flight path deviation parameters.

[0020] Preferably, the step of generating decoy control parameters based on the flight path deviation parameters includes: using the flight state phase as a time reference, analyzing common patterns in the flight path deviation parameters, extracting parameter groups common across flight mode types, and marking them as shared parameters; analyzing specific patterns in the flight path deviation parameters, extracting parameter groups that correspond only to specific flight mode types, and marking them as exclusive parameters; applying the shared parameters as a global decoy reference to the decoy process for all flight mode types; and adaptively adjusting the decoy parameters for specific flight mode types according to the exclusive parameters.

[0021] The execution of the deception control parameters to complete the deception action includes: establishing a basic deception framework using shared parameters, and integrating exclusive parameters to adjust the specific values ​​of the deception parameters to achieve dynamic deception control.

[0022] Preferably, the present invention also includes a system for preventing autonomous flight of a drone, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor, when executing the computer program, implements the steps of the aforementioned deception method for preventing autonomous flight of a drone.

[0023] Compared with the prior art, the beneficial effects of the present invention are:

[0024] This method continuously monitors the UAV's flight status data stream, enabling real-time understanding of the UAV's flight characteristics and behavioral patterns. This continuous monitoring mechanism ensures the system's comprehensive perception of the UAV's flight status, providing ample data support for subsequent flight pattern recognition. The continuous acquisition of the flight status data stream allows the system to capture the dynamic changes in the UAV's flight, thereby more accurately understanding its flight intentions and behavioral patterns.

[0025] Flight mode type identification based on flight status data streams can effectively distinguish the flight characteristics of drones in different scenarios. This identification capability allows the system to take targeted countermeasures based on specific flight modes, improving the accuracy and effectiveness of deception operations. By accurately identifying multiple flight modes, the system can adapt to the flight characteristics of different types of drones, enhancing the universality and practicality of the method.

[0026] The process of dynamically extracting control parameter sets from the UAV navigation system enables the acquisition of the UAV's core control parameters. This dynamic extraction mechanism can adapt to the differences in navigation systems of different UAV models, ensuring the completeness and accuracy of parameter acquisition. The acquisition of control parameter sets provides a crucial data foundation for the subsequent construction of interference signals, enabling deception operations to directly affect the UAV's control system.

[0027] The method of constructing interference activation signal sequences using control parameter sets can generate interference signals that match the UAV control system. This signal construction method based on actual control parameters ensures the effectiveness and targeting of the interference signals. Through time-series analysis of the interference activation signal sequences, the system can accurately grasp the timing and patterns of parameter changes, creating conditions for subsequent parameter change event point localization.

[0028] Accurate location of parameter change event points provides crucial information for synthesizing flight path deviation parameters. Classifying parameter change event points into intra-mode and inter-mode event points allows for better differentiation of event characteristics across different types. This detailed classification enables the system to adopt differentiated processing strategies based on the event point type, improving the precision of decoy operations.

[0029] The process of generating decoy control parameters based on flight path deviation parameters achieves precise interference with the UAV's flight path. These decoy control parameters, generated from actual flight parameters, can effectively guide the UAV away from its predetermined flight path. The execution of these decoy control parameters achieves flight interference without damaging the UAV's hardware, demonstrating the non-destructive nature of the method. Attached Figure Description

[0030] Figure 1 This is a schematic diagram illustrating the working principle of the deception method for preventing autonomous flight of drones as described in this invention.

[0031] Figure 2 Flowchart of the method for dynamically extracting control parameter sets;

[0032] Figure 3 Flowchart of the method for constructing the interference activation signal sequence;

[0033] Figure 4 A graph showing the matching analysis between the interference activation signal sequence and the reference time series;

[0034] Figure 5 This is a graph showing the analysis of flight path deviation parameters. Detailed Implementation

[0035] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0036] Please see Figure 1This invention provides a system and method for preventing autonomous flight of a drone. The method includes: continuously monitoring the drone's flight status data stream; identifying the current flight mode type, such as hovering, cruising, or evasion mode, by analyzing pattern characteristics in the data stream, such as the rate of change of heading angle, speed fluctuations, or altitude deviations; dynamically extracting a set of control parameters from the drone's navigation system based on the identified flight mode type. This process involves real-time reading of internal parameters of the navigation system, such as PID controller setpoints or path planning points, and filtering relevant parameters based on mode characteristics; and constructing an interference activation signal sequence using the control parameter set, which consists of a series of timestamps corresponding to... The system consists of pulses representing parameter changes, and time-series analysis is performed on the sequence to locate parameter change event points. The time-series analysis uses a sliding window algorithm to compare signal differences between adjacent time periods. Parameter change event points are divided into intra-mode event points and inter-mode event points. Intra-mode event points refer to parameter adjustments caused by environmental disturbances within the same flight mode, while inter-mode event points involve parameter resets during mode switching. Based on these event points, the magnitude of parameter changes is calculated, and flight path deviation parameters are synthesized. Finally, decoy control parameters are generated based on the flight path deviation parameters. For example, navigation commands are adjusted through interpolation or extrapolation, and these parameters are executed to inject misleading signals, causing the UAV to deviate from the predetermined path.

[0037] Example 1: See Figure 2 In specific implementation, the process of dynamically extracting the control parameter set begins by capturing the control reference parameter set and its duration window based on the state change curves of the flight mode type. The state change curves of the flight mode type are constructed by continuously monitoring the UAV's flight state data stream, such as real-time sampling of accelerometer output or gyroscope data to generate curve trajectories, thereby identifying mode characteristics such as linear segments in the uniform flight phase or nonlinear fluctuations in the maneuvering flight phase. Based on these curves, the control reference parameter set is extracted, and the parameters include target waypoint coordinates, speed setpoints, or attitude stability thresholds. Simultaneously, the duration window of each parameter is recorded, i.e., the time interval from parameter activation to deactivation, and the window boundaries are marked with timestamps to ensure timing accuracy. In some embodiments, the generation of the state change curves uses a moving average filter to smooth the raw data to reduce noise interference, and derivative analysis is used to detect curve inflection points, thereby accurately dividing the state stages. When capturing the control reference parameter set, parameter selection is based on the inherent characteristics of the mode type; for example, hovering mode focuses on vertical velocity parameters, while cruise mode emphasizes horizontal heading parameters, ensuring that the parameter set is highly correlated with the mode. It is understandable that the determination of the duration window depends on the continuous verification of flight status data. The window length is confirmed by comparing the consistency of parameters at adjacent time points to avoid misjudgment due to instantaneous fluctuations.

[0038] The system captures the control update parameter set and its effective time interval based on the flight mode transition trigger point. The transition trigger point is detected by analyzing abrupt events in the flight status data stream; for example, when the UAV transitions from hovering mode to cruise mode, a step change in speed reading or a heading angular rate exceeding a threshold is identified as a transition trigger point. The control update parameter set includes controller gain coefficients, path planning update intervals, or sensor calibration parameters. These parameters are dynamically adjusted during mode switching. The effective time interval is calculated from the transition trigger point until the next stable state is established. In practice, the detection of the transition trigger point employs a multi-condition fusion strategy, combining time series analysis and pattern recognition algorithms, such as Hidden Markov Models or decision trees, to improve detection robustness. When capturing the control update parameter set, parameter values ​​are read from the UAV navigation system's real-time data bus and associated with the effective time interval. The interval length is derived statistically from historical mode transition data or dynamically adjusted through real-time feedback. Optionally, the setting of the effective time interval can consider environmental factor compensation, such as extending the interval under strong wind conditions to accommodate a longer adjustment cycle, but the core remains based on the transition trigger point.

[0039] The application parameter standardization procedure processes the control update parameter set to produce a normalized update parameter set. The core of the parameter standardization procedure is the deviation assessment algorithm, which calculates the parameter difference metric for each state stage. The deviation assessment algorithm uses multiple input elements: a state influence factor weighting the contribution of parameter changes to flight stability (the state influence factor is weighted according to the parameter's role in the control loop, e.g., navigation parameters have a higher weight than auxiliary parameters); a time decay coefficient adjusting the contribution of historical parameter data (the time decay coefficient exponentially reduces the influence of old data, emphasizing recent changes); the time offset between the state transition trigger point and the parameter update time measuring the synchronicity of parameter adjustments (a small time offset indicates timely response, while a large time offset indicates lag); and the reference parameter setting time as a baseline time used to calculate relative differences. In practice, the parameter difference metric is calculated through weighted summation, formally expressed as: difference metric equals state influence factor multiplied by parameter change, plus offset compensation adjusted by the time decay coefficient, divided by the time offset normalization factor. However, the specific numerical processing avoids using mathematical formulas and is instead described as scalar operations. The output of the deviation assessment algorithm is a scalar value representing the degree of abnormality of the parameter in the current state. It is understandable that the parameter difference measure serves the subsequent normalization, and its calculation needs to ensure numerical stability, for example, by using amplitude limiting to prevent overflow.

[0040] A normalized parameter set is obtained by adjusting parameter values ​​based on the proportion of parameter difference measures in the total difference using a parameter normalization algorithm. The algorithm first aggregates parameter difference measures from all state stages, calculating the total difference as the normalization benchmark. The total difference is the sum or vector magnitude of the difference measures from each stage. Then, based on the proportion of each parameter difference measure in the total difference, the original parameter values ​​are adjusted. For example, parameter values ​​are linearly mapped to the 0-1 interval, or non-linear scaling is performed using the sigmoid function to ensure consistent parameter scale. In some embodiments, the parameter normalization algorithm introduces an adaptive adjustment mechanism: when the total difference is too small, a minimum threshold is used to avoid division by zero errors; when the total difference is too large, truncation is used to prevent distortion. The output of the normalized parameter set makes parameter values ​​comparable, eliminating the influence of dimensional differences and inter-pattern fluctuations. Optionally, the parameter normalization algorithm can be combined with machine learning methods, such as cluster analysis, to identify parameter distribution patterns, but the basic implementation still focuses on proportional adjustment.

[0041] The control reference parameter set and the normalized updated parameter set are merged to form a control parameter group. The fusion process employs a weighted averaging strategy. The weights of the control reference parameter set are allocated based on the length of the duration window; a longer window results in a higher weight, indicating stronger parameter stability. The weights of the normalized updated parameter set are allocated based on the reciprocal of the parameter difference metric; smaller differences result in higher weights, emphasizing reliability. The fused parameter group contains the integrated parameter values ​​and their time attributes, ensuring a comprehensive reflection of the control requirements of the current flight mode type. In implementation, the fusion operation is achieved by merging parameters one by one. For overlapping parameters, the values ​​from the normalized updated parameter set are preferentially used to reflect real-time performance while retaining the background information of the control reference parameter set. The formation of the control parameter group is a dynamic process, updated along with the flight status data stream to maintain the adaptability of the decoy method. It is understandable that the design of the fusion strategy needs to balance historical reference and real-time updates to avoid excessive bias towards either side, which could lead to control deviations.

[0042] Example 2: See Figure 3In specific implementation, the initial step in constructing the interference activation signal sequence is to screen an updated parameter subset from the control parameter set. This updated parameter subset includes parameter members with high dynamic change frequencies, such as real-time updated heading angle setpoints, thrust output percentages, or position feedback increments. The screening process is based on a historical rate of change threshold for the parameters. The rate of change is obtained by calculating the absolute difference between parameter values ​​within adjacent sampling periods. When the rate of change consistently exceeds a preset threshold, the parameter is included in the updated parameter subset. When generating the interference activation signal based on the updated parameter subset, the value of each member of the updated parameter subset is converted into a discrete time-series pulse. The pulse amplitude is proportional to the degree to which the parameter deviates from its reference value, and the pulse width is related to the parameter update time interval, thus forming a set of signal segments reflecting real-time parameter fluctuations. In some embodiments, the screening of the updated parameter subset uses a sliding window mechanism to monitor the parameter rate of change. The window size is adjusted according to the dynamic characteristics of the flight mode type; for example, a smaller window is used in agile maneuver mode to capture rapid changes. When generating the interference activation signal based on the updated parameter subset, the pulse generation time is synchronized with the control cycle of the UAV navigation system to ensure time alignment between the signal and the underlying control logic. It is understandable that the interference activation signal based on the updated parameter subset is essentially a time-encoded parameter change event, and its integrity depends on the accurate analysis of the control parameter set update mechanism.

[0043] A normalized updated parameter set is extracted from the control parameter set. This set, processed by a parameter normalization procedure, possesses a unified numerical scale and temporal characteristics. When generating the interference activation signal based on this normalized updated parameter set, each parameter value is mapped to a normalized pulse. The amplitude of the normalized pulse is directly determined by the normalized value of the parameter, and the pulse's temporal position corresponds to the parameter's effective moment within its effective time interval. In practice, extracting the normalized updated parameter set is a direct read operation, as it is already stored in a specific buffer after being generated by the parameter normalization procedure. Generating the interference activation signal based on this set emphasizes the relative changes between parameters; the pulse sequence's morphology reveals the overall pattern of parameter changes rather than individual fluctuations. Optionally, a smoothing filter can be introduced during the interference activation signal generation process to suppress high-frequency noise that may be introduced during normalization, but the core principle is to maintain the coordination between parameters.

[0044] Comparing the interference activation signal based on the updated parameter subset with that based on the normalized updated parameter set is a crucial step in obtaining the activation signal pattern. The comparison is performed over time, aligning and comparing the two signal sequences within the same state phase time window. Comparison methods include calculating the cross-correlation coefficient between signal segments to quantify waveform similarity, or calculating the integral of the absolute difference in pulse amplitude at corresponding time points to quantify the degree of difference. Through systematic comparison, the activation signal patterns of the same and different flight mode types at different state phases can be obtained. Under the same flight mode type, the interference activation signal based on the updated parameter subset and that based on the normalized updated parameter set usually show high similarity, with the envelope shape and main peak positions of the pulse sequences tending to be consistent. However, during the state phase of switching between different flight mode types, the two signals may show significant differences. For example, the interference activation signal based on the updated parameter subset may exhibit violently jittering pulses, while the interference activation signal based on the normalized updated parameter set may be relatively smooth. This difference constitutes the identification feature of inter-mode transition signals. In some embodiments, the extraction of activation signal patterns employs a pattern recognition algorithm to perform cluster analysis on the comparison results. Signals with similarity above a threshold are classified as stable patterns, while those below the threshold are classified as abrupt change patterns. It can be understood that activation signal patterns are a quantitative description of the consistency of UAV control behavior and an important basis for determining the nature of parameter changes.

[0045] Based on the activation signal pattern, optimizing the generation time of the interference activation signal sequence is a feedback adjustment process. The optimization decision is based on the comparison between the activation signal pattern value and the preset pattern threshold. The preset pattern threshold is an empirical value determined through historical data analysis or simulation verification, used to distinguish between high-consistency and low-consistency patterns. If the activation signal pattern is greater than the preset pattern threshold, it indicates that the parameter changes in the current flight state are highly predictable and repeatable. For example, parameter adjustments follow a fixed pattern during stable cruise. In this case, the generation of the interference activation signal sequence is triggered in advance. The amount of advance triggering is dynamically calculated based on the magnitude of the pattern exceeding the threshold. For example, if the pattern value exceeds the threshold by 10%, it is triggered one control cycle in advance. The purpose is to inject interference signals before the expected parameter changes occur in the UAV navigation system, thus seizing control timing. If the activation signal pattern is less than the preset pattern threshold, it indicates that the parameter change behavior is irregular or in a transitional state. For example, there is uncertainty in parameter adjustments at the beginning of mode transition. In this case, the generation of the interference activation signal sequence is delayed. The delay time is determined based on the degree to which the pattern is below the threshold and the average duration of historical mode switching. The purpose is to wait until the flight mode is stable and the parameter change pattern is clear before applying interference, avoiding decoy failure or abnormal UAV behavior due to inappropriate timing. In practice, the optimization process is implemented through a programmable timing trigger. This trigger receives the activation signal pattern as input and outputs an adjusted signal generation command. Optionally, the optimization strategy can employ a proportional-integral regulator to smooth the adjustment range of the generation time point, preventing excessive advancement or delay that could cause the signal and control events to lose synchronization. It can be understood that optimizing the generation time point of the interference activation signal sequence essentially aims to synchronize the decoy actions with the autonomous flight control rhythm of the UAV, or at least slightly advance them, thereby enhancing the stealth and effectiveness of the decoy.

[0046] Example 3: In specific implementation, the process of performing time-series analysis on the interference activation signal sequence to locate parameter change event points begins with calculating the matching degree index between the interference activation signal sequence and the reference time series corresponding to historical parameter change event points. The interference activation signal sequence is a time-domain discrete signal constructed from a set of control parameters. The reference time series corresponding to historical parameter change event points is a standard signal waveform recorded when a known type of parameter change event occurs, extracted from past successful deception cases or typical UAV flight logs. The calculation of the matching degree index aims to quantify the morphological similarity between the interference activation signal sequence and the reference time series. In some embodiments, the reference time series is constructed by aligning and averaging a large number of historical event signals to eliminate random noise and retain common features. Before matching, the interference activation signal sequence needs to undergo preprocessing with time windows of the same length and amplitude normalization to eliminate the influence of scale differences on the matching results. The calculated matching degree index is a value within a specific range; the higher the value, the stronger the similarity. If the matching index exceeds the preset matching threshold, which is a threshold value determined through statistical learning, the time corresponding to the current interference activation signal sequence is marked as a consistent parameter change event point. A consistent parameter change event point means that the currently detected event is highly consistent with the parameter fine-tuning event characteristics that occurred in the same flight mode in the historical record. Therefore, it is classified as an intra-mode parameter change event point. Intra-mode parameter change event points usually correspond to the routine parameter adjustments made by the flight control system to cope with minor environmental disturbances (such as gusts).

[0047] The matching degree index is calculated using an algorithm based on covariance and standard deviation. This algorithm first calculates the covariance between the time data of the interference activation signal sequence and the reference time sequence. The covariance reflects the degree of consistency in the fluctuations of the two sequences around their respective means. Its calculation involves multiplying the values ​​at corresponding time points of the two sequences by their deviations from their respective means, and then taking the average of these products. Let the interference activation signal sequence be... Its mean is The base time series is Its mean is Then the covariance value The calculation can be expressed as:

[0048]

[0049] in: The representative interference activation signal sequence is in the first... Values ​​at each point in time. Represents the reference time series at the 1st Values ​​at each point in time. This represents the total number of time points involved in the calculation. It is the arithmetic mean of all values ​​in the interference activation signal sequence. It is the arithmetic mean of all values ​​in the base time series. It can be understood that the sign and magnitude of the covariance value indicate whether the changes in the two series are in the same or opposite direction, and the strength of the linear association.

[0050] The algorithm needs to calculate the standard deviation of the time data of the interference activation signal sequence and the standard deviation of the reference time series. Standard deviation is a statistic that measures how much data points within a sequence deviate from their mean. The standard deviation of the interference activation signal sequence... The calculation formula is:

[0051]

[0052] Standard deviation of the benchmark time series The calculation formula is:

[0053]

[0054] The calculation of standard deviation completes the assessment of the dispersion of each sequence. Finally, the covariance value is... Divide by the standard deviation of the interference activation signal sequence Standard deviation from the baseline time series The product of these factors yields the matching index. :

[0055]

[0056] This matching index Mathematically equivalent to the Pearson correlation coefficient, its value ranges between -1 and +1. The closer the value is to +1, the stronger the positive linear correlation and the more similar the shapes of the two sequences. In some embodiments, to simplify subsequent judgment logic, the matching index may be linearly transformed to map it to the interval of zero to one hundred, but the core comparison logic remains unchanged. It can be understood that this calculation method can effectively capture the shape similarity between sequences, while being insensitive to the absolute numerical amplitude, and is suitable for comparing signals that may have different baselines or gains.

[0057] The matching degree index is calculated between the interference activation signal sequence and the reference time series corresponding to the historical parameter reset event point. The reference time series corresponding to the historical parameter reset event point represents the standard parameter reset signal waveform recorded when the flight mode changes. The calculation method for the matching degree index is exactly the same as above, that is, the covariance value between the interference activation signal sequence and the reference time series corresponding to the historical parameter reset event point is calculated and divided by the product of their respective standard deviations. If the matching degree index calculated this time is lower than the preset matching threshold, it indicates that the shape of the current interference activation signal sequence is very different from the parameter reset event characteristics during typical mode switching and has no similarity. Therefore, the current moment is marked as a conflict-type parameter change event point. A conflict-type parameter change event point means that the detected event does not conform to the known intra-mode adjustment pattern. Instead, it is identified as possibly caused by flight mode type conversion due to its low correlation with mode switching events, and is therefore classified as an inter-mode parameter reset event point. In some embodiments, there may be a situation where the matching degree index is both higher than the intra-mode event threshold and lower than the inter-mode event threshold. In this case, a more complex classifier or multi-feature fusion decision can be introduced. However, in basic implementations, a clear division is usually made based on a preset priority or nearest neighbor principle. Optionally, the preset matching threshold can be the same value for judging intra-mode events and inter-mode events, or it can be different values ​​set according to the false alarm rate and false negative rate requirements. The core of the entire time series analysis process lies in interpreting the continuous interference activation signal sequence into discrete, type-labeled parameter change event points through signal matching technology.

[0058] See Figure 4 This chart presents the matching analysis results between the interference activation signal sequence and the baseline time series. The chart includes the baseline time series and multiple interference activation signal sequences. The Pearson correlation coefficient is used as the matching degree index to identify parameter change event points. The blue solid line in the chart represents the baseline time series of parameter changes within the mode, reflecting the routine parameter adjustments made by the UAV in stable flight mode to cope with environmental disturbances. Other colored lines represent different interference activation signal sequences; solid lines represent signals identified as consistent parameter change event points, and dashed lines represent signals identified as conflicting parameter change event points. The marked dotted areas in the chart indicate moments when the matching degree exceeds a preset threshold; these moments are identified as parameter change event points. Through this time series analysis method, the system can accurately distinguish between routine parameter adjustments within a mode and parameter reset events between modes, providing basic data for subsequent flight path deviation parameter synthesis. The chart clearly shows the morphological similarity differences between signal sequences, demonstrating the crucial role of matching degree calculation in event classification.

[0059] Example 4: In specific implementation, the process of dividing parameter change event points into intra-mode event points and inter-mode event points begins with extracting parameter change event points caused by environmental disturbances within the same flight mode type. These parameter change event points are time points located after time-series analysis of the interference activation signal sequence. The extraction operation is based on the attribute labels of the event points. When a parameter change event point is labeled as a consistent parameter change event point, it indicates that the event originates from a state adjustment within the flight mode, and is thus labeled as an intra-mode parameter change event point. Intra-mode parameter change event points are typically associated with control parameter updates triggered by the UAV to compensate for wind disturbances, maintain heading, or make minor path corrections. In specific implementation, the extraction process is completed by querying the event point database. Each event point record in the database contains a timestamp, an event type identifier, and associated flight mode context information. The filtering logic selects records where the event type identifier corresponds to "consistent" and the flight mode context remains unchanged before and after the event. It can be understood that accurately labeling intra-mode parameter change event points depends on the accuracy of the matching degree index calculation in the previous time-series analysis and the rationality of the preset matching threshold setting.

[0060] Simultaneously, the process involves extracting parameter reset event points triggered during different flight mode type transitions. These parameter reset event points are a subset of the conflict-type parameter change event points identified in the time-series analysis. The extraction operation focuses on event points near the flight mode type transition trigger point. When the time difference between the occurrence of a parameter change event point and a known flight mode type transition trigger point is within a preset tolerance, and its label is a conflict-type parameter change event point, it is marked as an inter-mode parameter change event point. Inter-mode parameter change event points represent a fundamental reset of control law or path planning parameters by the UAV navigation system in response to higher-level commands. In practice, the labeling of inter-mode parameter change event points needs to be cross-validated with the pattern recognition results in the flight status data stream to ensure that the event points actually occur during the transition period of mode switching rather than isolated abnormal fluctuations. Optionally, a confidence score can be set for inter-mode parameter change event points, calculated based on their temporal proximity to the transition trigger point and the significance of conflict-type features.

[0061] Based on intra-mode parameter change event points, the parameter change magnitude within the same flight mode type is calculated. The parameter change magnitude aims to quantify the cumulative change of control parameters during the duration of a single flight mode. The calculation process is performed on the control parameters associated with each intra-mode parameter change event point. First, the numerical difference of the parameter before and after the event point is determined, i.e., the instantaneous change. Then, the instantaneous changes caused by all intra-mode parameter change event points within a time window are aggregated. Aggregation methods can include absolute value summation, square root of square, or taking the maximum absolute value, etc. The final output value is used as the internal path deviation parameter. The internal path deviation parameter reflects the potential trend of path deviation caused by continuous external disturbances or internal adjustment requirements in a stable flight mode. In practical implementation, the calculation of parameter change magnitude needs to distinguish between parameter types. For example, position-related parameters and attitude-related parameters may use different aggregation weights to accurately reflect their comprehensive impact on the actual flight path. Refer to Table 1, which shows a simplified calculation of the internal path deviation parameter, where the aggregation method uses absolute value summation.

[0062] Table 1: Calculation of Internal Path Deviation Parameters (for Cruise Mode)

[0063]

[0064] Based on inter-mode parameter change event points, the magnitude of parameter changes during flight mode type transitions is calculated. This calculation focuses on the jumps in parameter values ​​during the instant of mode switching or within a short transition period. For each inter-mode parameter change event point, its directly associated control parameters are identified, and the numerical difference between the parameters in the two steady states before and after the mode switch is calculated. This difference is typically much larger than the fine-tuning amount within the mode, for example, switching from a target speed of 10 m / s in cruise mode to a target speed of 0 m / s in hover mode. The calculated difference is the contribution of that event point to the switching path deviation parameter. The switching path deviation parameter can be synthesized from these jump values ​​in various ways, such as taking the maximum absolute value of the changes in all associated parameters during the mode switch event as a representative, or calculating a weighted average of these changes, with the weights determined by the importance of the parameters' impact on the flight path. The switching path deviation parameter characterizes the degree of path dispersion introduced by fundamental changes in the flight mission. In some embodiments, for complex mode switches where multiple parameters are reset simultaneously, the calculation of the switching path deviation parameter considers the vector synthesis of parameter changes to more comprehensively assess path deviation.

[0065] The combined result of the internal path deviation parameter and the switching path deviation parameter is used as the flight path deviation parameter. The combination operation is not a simple numerical addition, but rather a data fusion process based on the needs of the deception strategy. A typical combination method is to assign different weight coefficients to the internal path deviation parameter and the switching path deviation parameter. These weight coefficients reflect the importance of different types of deviations in the overall path prediction. For example, if the deception strategy focuses more on cumulative drift within a mode, the internal path deviation parameter has a higher weight; if it focuses more on sudden changes in direction during mode switching, the switching path deviation parameter has a higher weight. The weighted sum is the flight path deviation parameter. The flight path deviation parameter is a comprehensive indicator used to quantify the overall degree to which the UAV may deviate from the desired path under current and recent control behavior. In practice, the weight coefficients can be determined based on historical flight data analysis or through simulation optimization. Optionally, the combination process can also introduce nonlinear functions, such as selecting different fusion rules based on the relative magnitudes of the internal path deviation parameter and the switching path deviation parameter. It can be understood that the accurate synthesis of the flight path deviation parameter is the foundation for generating effective deception control parameters, and it needs to consider both the continuity and discrete abrupt changes in flight behavior.

[0066] See Figure 5 This paper presents the analysis results of flight path deviation parameters, showcasing the characteristic differences of different types of parameter change events through a combination of bar charts and scatter plots. The bar charts display the average deviation magnitude and standard deviation of parameter change events within each flight mode, reflecting the range of parameter changes caused by environmental disturbances under stable flight conditions. Different colored bars correspond to different flight modes, with bar height representing the average level of parameter change under that mode, and error bars showing the fluctuation range of the changes. The red dots in the scatter plot represent parameter reset events between modes. These events occur during flight mode switching, and the parameter changes are typically significantly larger than regular adjustments within a mode. The distribution of these scatter points shows the correlation between parameter reset events and each flight mode, as well as the intensity of parameter jumps. By comparing the data in the bar charts and scatter plots, the essential differences in parameter change magnitude between intra-mode and inter-mode events can be clearly seen. This difference analysis provides an important basis for synthesizing flight path deviation parameters, enabling the system to more accurately predict the path deviation trend of the UAV and generate effective decoy control parameters.

[0067] Example 5: In specific implementation, the process of generating decoy control parameters based on flight path deviation parameters unfolds with the flight state phase as the time reference. The flight state phase is a time interval divided according to the flight mode type and its internal sub-states (such as acceleration, constant speed, deceleration). Analyzing common patterns in the flight path deviation parameters aims to discover those deviation characteristics that repeatedly appear under different flight mode types and have common features. For example, in various modes such as hovering, cruise, and point-flying, small periodic oscillations around the preset heading may be observed due to sensor noise or basic controller characteristics. This oscillation pattern is a common pattern. Extracting parameter sets common to flight mode types is an operation based on common patterns. Through cluster analysis or frequent pattern mining algorithms, parameter combinations with high statistical significance in a multi-mode context are identified from historical flight path deviation parameter data. For example, a set of parameters including basic heading control gain, position loop integral coefficient, and vertical speed limiter is marked as shared parameters. Shared parameters constitute the control basis that affects different flight modes. In some embodiments, the analysis of common patterns employs time series pattern matching technology to align and compare flight path deviation parameter sequences under different patterns in order to identify morphologically similar segments and their corresponding control parameters.

[0068] Simultaneously, the analysis focuses on anomalies in flight path deviation parameters. Anomalies refer to deviation characteristics that are closely related to a specific flight mode type and are insignificant or morphologically different in other modes. Examples include high-frequency fine-tuning of vertical altitude caused by rotor downwash disturbance, unique to hovering mode, or anti-crosswind roll moment compensation, unique to high-speed cruise mode, for maintaining straight flight. Extracting parameter groups specific to a particular flight mode type is an operation targeting anomalies. Through comparative analysis, parameters that are actively presented in flight path deviation parameters only within a specific flight mode type and are strongly correlated with mode characteristics are separated. Examples include altitude lock-up threshold parameters in hovering mode and forward velocity planning curve parameters in cruise mode. These parameters are labeled as specific parameters. Specific parameters reflect the unique control requirements of a specific flight mission. In practice, the analysis of anomalies needs to be combined with semantic information of the flight mode type. For example, when the mode recognizer outputs "precise hovering," the focus is on examining the deviation components and their control parameters related to position-keeping accuracy.

[0069] Applying shared parameters as a global deception baseline to the deception process across all flight mode types means that regardless of whether the drone is hovering, cruising, or in any other mode, the deception system will first load and use the basic misleading strategy defined by the shared parameters. For example, if the shared parameters include a basic heading offset, this offset will be added as a constant or slowly varying component to the deception commands in all modes. Adaptive adjustment of deception parameters for specific flight mode types based on dedicated parameters represents a fine-tuning process built upon the global baseline. When the system detects that the drone has entered a specific mode (such as transitioning from cruising to hovering), it dynamically calls the dedicated parameter set corresponding to that mode and calculates the specific deception adjustment amount for that mode based on the current values ​​of these parameters and the degree of deviation indicated by the flight path deviation parameters. For example, in hovering mode, the altitude command perturbation amplitude in the deception signal is dynamically fine-tuned based on the altitude lock threshold in the dedicated parameters. In practice, the application of shared parameters is typically implemented through a global parameter lookup table or configuration file, while the adaptive adjustment of dedicated parameters is accomplished through a callback function or rule engine bound to the flight mode state machine. Optionally, there may be overlaps or conflicts between shared parameters and dedicated parameters. The handling strategy can be to set a lower priority limit for shared parameters or to resolve conflicts by using a weighted fusion method.

[0070] The system executes decoy control parameters to complete the decoy action. A basic decoy framework is established using shared parameters. This framework defines the basic structure and constraints of the decoy behavior. For example, the framework stipulates that the injection point of the decoy command is located after the navigation calculation module and before the controller execution. The framework also defines the maximum amplitude limit and rate of change limit of the decoy signal. The baseline values ​​of these limits are derived from the shared parameters. The integration of dedicated parameters to adjust the specific values ​​of the decoy parameters is a dynamic assignment process performed within the basic decoy framework. The system reads the currently effective set of dedicated parameters and, based on the real-time calculated decoy requirements, specifically determines the amplitude, frequency, duration, and other attributes of the decoy signal within the boundaries set by the shared parameters, thereby achieving dynamic decoy control. For example, shared parameters might set the maximum range of heading decoy amount to ±30 degrees, which is a safety boundary. When the drone is in cruise mode, dedicated parameters might indicate that the rate of change of the decoy amount can be faster in this mode, and the system will generate a heading misleading signal that fluctuates at a faster rate within the ±30-degree range. When the drone switches to hover mode, the corresponding dedicated parameters might indicate that the decoy should focus on slow position drift rather than rapid heading changes, and the system will generate a decoy signal that increases slowly in the position dimension and changes little in the heading dimension. In practice, the integration operation is usually completed in a real-time scheduling loop, and the decoy command is recalculated based on the latest flight status, shared parameters, and dedicated parameters in each control cycle. Optionally, a feedback mechanism can be introduced into the integration process to fine-tune the scaling factor of the dedicated parameters based on the actual response of the drone after the decoy action is executed, so as to optimize the decoy effect. It can be understood that this layered decoy strategy based on shared and dedicated parameters ensures the consistency of decoy behavior across different modes and has the ability to adapt to different flight scenarios, thereby achieving precise and covert dynamic decoy control. In some embodiments, the adjustment of specific parameters may not only depend on the current pattern, but also take into account the historical sequence of pattern transitions or environmental context information, making the deception strategy more proactive. Optionally, the basic deception framework itself may also contain some pre-set complex deception scripts that can be triggered by specific parameters, further enhancing the realism and effectiveness of the deception.

[0071] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A decoy method for preventing autonomous flight of a drone, characterized in that, The method comprises: continuously monitoring the flight state data stream of the unmanned aerial vehicle to identify the current flight mode type; dynamically extracting a control parameter group from the unmanned aerial vehicle navigation system according to the identified flight mode type; using the control parameter group to construct an interference activation signal sequence, and performing timing analysis on the interference activation signal sequence to locate a parameter change event point; dividing the parameter change event point into an intra-mode event point and an inter-mode event point, thereby synthesizing a flight path deviation parameter; generating a decoy control parameter based on the flight path deviation parameter, and executing the decoy control parameter to complete a decoy action; The method comprises:

2. The decoy method of claim 1, wherein, The method comprises:

3. The decoy method of claim 1, wherein, The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises: The method comprises 4. The decoy method of claim 3, wherein, The matching degree index of the interference activation signal sequence and the reference time sequence corresponding to the historical parameter reset event point comprises: calculating the covariance value of the time data of the interference activation signal sequence and the reference time sequence, and calculating the standard deviation of the time data of the interference activation signal sequence and the standard deviation of the reference time sequence, and obtaining the matching degree index by dividing the product of the covariance value and the standard deviation.

5. The decoy method of claim 2, wherein, The generation time point of the interference activation signal sequence is optimized according to the activation signal mode, which comprises: if the activation signal mode is greater than a preset mode threshold, triggering the generation of the interference activation signal sequence in advance; if the activation signal mode is less than the preset mode threshold, delaying the generation of the interference activation signal sequence.

6. The decoy method of deterring autonomous flight of drones of claim 1, wherein, The parameter change event points are divided into mode-in event points and mode-out event points, and a flight path deviation parameter is synthesized, which comprises: extracting parameter change event points caused by environmental disturbance in the same flight mode type, and marking them as mode-in parameter change event points; extracting parameter reset event points triggered when the flight mode type is switched, and marking them as mode-out parameter change event points; calculating the parameter change amplitude in the same flight mode type based on the mode-in parameter change event points as an internal path deviation parameter; calculating the parameter change amplitude when the flight mode type is switched based on the mode-out parameter change event points as a switching path deviation parameter; and combining the internal path deviation parameter and the switching path deviation parameter as a flight path deviation parameter.

7. The decoy method of deterring autonomous flight of drones of claim 1, wherein, The flight path deviation parameter is used to generate a decoy control parameter, which comprises: taking the flight state stage as a time reference, analyzing the common mode in the flight path deviation parameter, extracting a parameter group common to all flight mode types, and marking it as a shared parameter; analyzing the specific mode in the flight path deviation parameter, extracting a parameter group corresponding only to a specific flight mode type, and marking it as an exclusive parameter; applying the shared parameter as a global decoy reference to the decoy process of all flight mode types; and adaptively adjusting the decoy parameters of the specific flight mode type according to the exclusive parameters. The decoy control parameter is executed to complete the decoy action, which comprises: establishing a basic decoy framework using the shared parameter, and integrating the specific values of the decoy parameters adjusted by the exclusive parameters to realize dynamic decoy control.

8. A system for preventing autonomous flight of a drone, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, The processor, when executing the computer program, realizes the steps of the decoy method for preventing the unmanned aerial vehicle from autonomous flight according to any one of claims 1 to 7.

Images