Unmanned aerial vehicle track credible management method combined with Beidou positioning

Abstract

The invention discloses an unmanned aerial vehicle track credible management method combined with Beidou positioning, and relates to the technical field of flight safety control and track analysis. The method comprises the following steps: calculating indexes such as a flight speed change rate, a course change rate and an attitude deviation angle based on collected Beidou track point data, identifying a flight behavior type, further extracting a track continuity score and a flight behavior grade score, calculating a track credibility score by adopting a weighted fusion mode, and calculating a track credibility score according to a preset score interval. A corresponding flight control feedback instruction is generated and executed through the response strategy mapping table, the method improves the quantitative evaluation capability of the flight trajectory stability and credibility, and solves the technical problems of rough flight behavior recognition, single trajectory credibility evaluation dimension and untimely flight control response in the prior art.

Description

Technical Field

[0001] The present application relates to the technical field of flight safety control and trajectory analysis, and in particular to a method for trustworthy management of UAV trajectories combined with Beidou positioning. Background Art

[0002] Currently, drones generally rely on inertial navigation and GNSS systems (such as Beidou) for flight control and trajectory planning. However, in practice, these systems are subject to issues such as abnormal flight trajectories, yaw instability, and sudden acceleration, often due to factors such as signal obstruction, environmental interference, and sensor errors. These issues can easily lead to flight control failure and path deviation. Existing flight control systems rely on simple thresholds or isolated parameter judgments to identify abnormal flight behavior. These systems lack multi-dimensional, multi-time series joint analysis and dynamic assessment mechanisms, making it difficult to promptly and accurately identify potential credible risks during flight. Furthermore, feedback strategies are sluggish in response, and there is a lack of a coordinated control mechanism based on trajectory credibility levels. This results in delayed anomaly handling and limited flight safety assurance capabilities. Therefore, a trajectory credibility management method that integrates Beidou positioning information, can model flight behavior using multiple features, and drives flight control responses is urgently needed to improve the safety, stability, and intelligence of drone operations. Summary of the Invention

[0003] The purpose of this application is to provide a reliable UAV trajectory management method combined with Beidou positioning to solve the technical problems in the existing technology, such as insufficient accuracy in flight behavior state recognition, insufficient granularity in trajectory reliability assessment, and untimely feedback on flight control response strategies.

[0004] In view of the above technical problems, this application provides a reliable management method for drone trajectories combined with Beidou positioning.

[0005] A first aspect of an embodiment of the present application provides a method for trustworthy management of drone trajectories in combination with Beidou positioning, the method comprising: The Beidou positioning module and inertial navigation unit installed on the drone collect trajectory point data, acceleration data, and angular velocity data during flight. The trajectory point data is an ordered data sequence containing a timestamp, a three-dimensional spatial position, a heading angle measurement, and a three-dimensional velocity vector. The three-dimensional velocity vector is the set of velocity components in the X-axis, Y-axis, and Z-axis directions in the airborne coordinate system at each moment. Performing inertial calculation based on the acceleration data and angular velocity data to obtain a heading angle calculation value, and extracting the flight speed change rate, heading change rate time series, and attitude offset angle based on the trajectory point data, and obtaining the heading change rate standard deviation based on the heading change rate time series; Based on the flight speed change rate, the heading change rate time series and the attitude deviation angle, matching behavior classification rules to obtain the flight behavior type of each trajectory point, the flight behavior type including stable flight, rapid acceleration, sharp turn and abnormal yaw; Calculating a standard deviation of the three-dimensional distances during the entire flight process based on the three-dimensional spatial position distances between adjacent trajectory points in the trajectory point data to obtain a trajectory continuity score for indicating the smoothness of the flight trajectory; Matching the flight behavior type to a preset risk level score table to obtain a behavior level score corresponding to the flight behavior type; A trajectory credibility score is obtained using a weighted calculation formula based on the trajectory continuity score, the heading change rate standard deviation, and the behavior level score; The trajectory credibility score is input into a preset response strategy mapping table, and the corresponding flight control feedback instructions are matched and executed according to the score interval. The flight control feedback instructions include maintaining flight, issuing reminders, triggering evaluation, and interrupting return operations.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages: The trajectory point data, acceleration data and angular velocity data during the flight are collected by the Beidou positioning module and inertial navigation device installed on the UAV. The trajectory point data is an ordered data sequence including timestamp, three-dimensional spatial position, heading angle measurement value and three-dimensional velocity vector. The three-dimensional velocity vector is a set of velocity components in the three directions of X-axis, Y-axis and Z-axis in the airborne coordinate system at each moment; inertial solution is performed based on the acceleration data and angular velocity data to obtain the heading angle estimation value, and the flight speed change rate, heading change rate time series and attitude deviation angle are extracted in combination with the trajectory point data. Based on the heading change rate time series, the heading change rate standard deviation is obtained; based on the flight speed change rate, the heading change rate time series and the attitude deviation angle, the behavior classification rules are matched to obtain each trajectory point The flight behavior type includes stable flight, rapid acceleration, sharp turn, and abnormal yaw. Based on the three-dimensional spatial position distance between adjacent trajectory points in the trajectory point data, the standard deviation of the three-dimensional spatial distance during the entire flight process is calculated to obtain a trajectory continuity score used to represent the smoothness of the flight trajectory. According to the flight behavior type, a preset risk level score table is matched to obtain the behavior level score corresponding to the flight behavior type. Based on the trajectory continuity score, the standard deviation of the heading change rate, and the behavior level score, a weighted calculation formula is used to obtain the trajectory credibility score. The trajectory credibility score is input into a preset response strategy mapping table, and the corresponding flight control feedback instructions are matched and executed according to the score interval. The flight control feedback instructions include maintaining flight, issuing reminders, triggering evaluation, and interrupting return operations. The technical problems of insufficient flight behavior state recognition accuracy, insufficient trajectory credibility evaluation granularity, and untimely flight control response strategy feedback in the existing technology are solved.

[0007] The above description is only an overview of the technical solution of the present application. In order to more clearly illustrate the technical means of the present application and to implement it in accordance with the contents of the specification, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the accompanying drawings of the embodiments of the present disclosure are briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the systems according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in precise order. Instead, various steps may be processed in reverse order or simultaneously as needed. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0009] Figure 1 A flowchart of a method for trustworthy management of drone trajectories using Beidou positioning provided in an embodiment of the present application; DETAILED DESCRIPTION This application solves the technical problems in the existing technology of insufficient accuracy in flight behavior state recognition, insufficient granularity in trajectory credibility assessment, and untimely feedback on flight control response strategies by providing a drone trajectory credibility management method and system combined with Beidou positioning.

[0010] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only some of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0011] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0012] Example 1, as Figure 1 As shown, this application provides a reliable management method for drone trajectories combined with Beidou positioning, wherein the method includes: The Beidou positioning module and inertial navigation unit installed on the drone collect trajectory point data, acceleration data, and angular velocity data during flight. The trajectory point data is an ordered data sequence containing a timestamp, a three-dimensional spatial position, a heading angle measurement, and a three-dimensional velocity vector. The three-dimensional velocity vector is the set of velocity components in the X-axis, Y-axis, and Z-axis directions in the airborne coordinate system at each moment. Specifically, a Beidou positioning module and an inertial navigation unit installed on the drone collect multi-source motion data in real time during flight. The Beidou positioning module is used to obtain the drone's absolute geographic location at different time points and, in conjunction with the high-precision timing module, outputs three-dimensional spatial coordinate data with a unified timestamp. The inertial navigation unit includes a three-axis accelerometer and a three-axis gyroscope, respectively, which collect acceleration and angular velocity data in the drone's airborne coordinate system, providing high-frequency dynamic response capabilities. The trajectory point data constitutes an ordered data sequence with a time-series structure. Each trajectory point includes: a timestamp, three-dimensional spatial position coordinates (x, y, z), a heading angle measurement, and a three-dimensional velocity vector representing the velocity components in the X, Y, and Z axes in the airborne coordinate system at that moment. This data structure forms the basis for subsequent flight behavior recognition, trajectory stability assessment, and confidence level determination. By integrating Beidou's high-precision positioning with the short-term dynamic compensation capabilities of the inertial navigation system, the system not only achieves continuous and stable tracking of the flight trajectory but also offers the advantages of high sampling rate and low latency for real-time response.

[0013] Inertial solution is performed based on the acceleration data and angular velocity data to obtain a heading angle estimation value, and the flight speed change rate, heading change rate time series and attitude offset angle are extracted in combination with the trajectory point data. Based on the heading change rate time series, the heading change rate standard deviation is obtained.

[0014] Further, including: Performing inertial calculation based on the angular velocity data, initializing a unit quaternion using a quaternion attitude calculation method, integrating the angular velocity data hour by hour in a time series, obtaining an attitude quaternion corresponding to each moment, and converting the attitude quaternion into Euler angles to extract a heading angle component as a dead reckoning value of the heading angle; constructing a heading change rate time series based on the heading angle dead reckoning values, wherein the heading change rate is obtained by dividing the difference between adjacent heading angle dead reckoning values by a sampling time interval; Based on the three-dimensional velocity vectors in the trajectory point data, calculating the velocity modulus value sequence at each moment, and performing time differentiation on the modulus value sequence to obtain a flight velocity change rate sequence; According to the heading angle measurement values of the trajectory point data, the heading angle measurement values are compared with the heading angle estimated values at each moment, and the absolute value of the difference between the two is calculated to obtain an attitude deviation angle sequence representing the degree of deviation between the attitude solution and the actual measurement; Based on the heading change rate time series, the standard deviation of the heading angle change rate between adjacent time points is calculated. The standard deviation formula of the heading change rate is: ; in, is the standard deviation of the heading change rate, Indicates thei The rate of change of heading within a time interval, is the mean heading change rate, N is the number of sampling points.

[0015] Specifically, in this embodiment, the inertial navigation solution is performed based on the acceleration data and angular velocity data to achieve accurate estimation of the dynamic changes of flight attitude and heading angle. First, the quaternion attitude solution is performed using the angular velocity data collected by the inertial navigation device to initialize the unit quaternion. , and integrate the angular velocity data in time series, and use the quaternion differential formula and numerical integration method to calculate the attitude quaternion at each time point hour by hour The quaternion is then converted to Euler angles and the heading angle component is extracted. , as the heading angle estimated value. Then, a heading change rate time series is constructed based on the heading angle estimated value. Defined as the difference between adjacent heading angle calculations divided by the sampling time interval ,Right now: At the same time, the three-dimensional velocity vector in the trajectory point data is used , calculate its modulus sequence , and obtain the flight speed change rate series by time difference: ,Furthermore, in order to evaluate the deviation between the attitude estimation and the actual measurement, the heading angle measurement value contained in the trajectory point data is used , and the heading angle calculated value Compare moment by moment and calculate the absolute difference to get the attitude deviation angle sequence: Finally, based on the constructed heading change rate time series, the standard deviation of the heading angle change rate in each time interval is calculated, and the standard deviation of the heading change rate is calculated using the following formula: ; in, is the standard deviation of the heading change rate, represents the heading change rate in the i-th time interval, is the mean heading change rate, is the number of sampling points. Through the above process, we achieve multi-dimensional extraction of continuous dynamic characteristics of the flight state, enhance the ability to quantify changes in trajectory stability and heading consistency, and provide accurate and reliable input variables for subsequent behavior recognition and trajectory credibility assessment.

[0016] Based on the flight speed change rate, the heading change rate time series and the attitude deviation angle, matching behavior classification rules to obtain the flight behavior type of each trajectory point, the flight behavior type including stable flight, rapid acceleration, sharp turn and abnormal yaw; Further, including: Setting a plurality of continuity preset thresholds includes a first preset threshold, a second preset threshold, a third preset threshold, a fourth preset threshold, and a fifth preset threshold; The first preset threshold is the upper limit of the flight speed change rate. The first preset threshold is set by selecting trajectory segments marked as stable flight in historical flight data, calculating the mean and standard deviation of the flight speed change rate sequence, and adding twice the standard deviation to the mean. The second preset threshold is the upper limit of the standard deviation of the heading change rate. The second preset threshold is set by selecting stable flight segments in the historical flight data, calculating the mean and standard deviation of the standard deviation of the heading angle change rate between adjacent time points in the heading change rate time series, and adding one standard deviation to the mean. The third preset threshold is the upper limit of the heading change rate. The third preset threshold is set by selecting trajectory segments marked as normal turns in historical flight data, calculating the mean and standard deviation of their heading change rates, and adding twice the standard deviation to the mean. The fourth preset threshold is the upper limit of the attitude deviation angle. The fourth preset threshold is set by extracting the normal attitude control segments in the historical flight data, calculating the sequence of absolute differences between the heading angle measurement values and the heading angle estimation values, and adding one standard deviation to the mean of the sequence. The fifth preset threshold is a time window threshold representing the duration of the abnormal attitude deviation, which is set by counting the shortest duration of the attitude deviation angle exceeding the fourth preset threshold in historical abnormal flight behaviors and combining it with the response time of the flight control system; When the flight speed change rate at multiple consecutive time points is greater than a first preset threshold, and the standard deviation of the heading change rate is less than a second preset threshold, it is determined to be a sudden acceleration behavior; When the standard deviation of the heading change rate at multiple consecutive time points is greater than a third preset threshold, and the flight speed change rate is less than a fourth preset threshold, it is determined to be a sharp turn behavior; If the attitude deviation angle is greater than a fifth preset threshold value at multiple consecutive time points and the duration of the deviation exceeds a preset time window threshold value, it is determined to be an abnormal yaw behavior; If the flight speed change rate, heading change rate, and attitude deviation angle are all lower than their corresponding stable state tolerance ranges at multiple consecutive time points, it is determined to be stable flight behavior.

[0017] Specifically, after extracting the time series of flight speed rate, heading rate, and attitude deviation angle, the system further performs trajectory behavior recognition based on preset behavior classification rules to determine the flight behavior type of each trajectory point. Specifically, the system defines four flight behavior types: stable flight, rapid acceleration, sharp turn, and abnormal yaw, each corresponding to a different flight dynamic characteristic pattern. During the classification process, the system first determines whether there are multiple consecutive time points where the flight speed rate exceeds a first preset threshold and the standard deviation of the heading rate is below a second preset threshold. If so, the time period is classified as rapid acceleration behavior. If the standard deviation of the heading rate at multiple consecutive time points exceeds a third preset threshold and the flight speed rate is below a fourth preset threshold, the time period is classified as rapid turn behavior. If the attitude deviation angle remains above a fifth preset threshold for a continuous period of time and the duration exceeds a preset time window threshold, the time period is classified as abnormal yaw behavior. If the speed rate, heading rate, and attitude deviation angle are all within their respective preset stability tolerances within a sliding time window, the time period is classified as stable flight behavior. To achieve this behavior recognition, the system uses statistical modeling with multiple thresholds based on historical flight data. Specifically, it includes: the first preset threshold is used to determine the significance of the flight speed change rate, and its calculation method is to select the trajectory segment historically marked as stable flight, count the mean and standard deviation of its speed change rate time series, and set the threshold as the mean plus twice the standard deviation, thereby reflecting the upper limit tolerance under the stable state; the second preset threshold is the upper limit of the heading change rate standard deviation, and by extracting the historical stable flight segment data, constructing its heading angle change rate sequence (that is, the heading angle change per unit time), calculating the mean and standard deviation of the standard deviations of all samples in the sequence, and using the mean plus twice the standard deviation to set the threshold, so as to quantify the tolerance range under normal heading stability; the third preset threshold is used to determine the upper limit of the drastic change in heading during sharp turns, and its statistical source is the heading in the normal turning flight segment. The rate of change data is modeled based on the mean plus two standard deviations so as to clearly distinguish it from the stable flight state; the fourth preset threshold is used to measure the allowable deviation between the attitude estimation and the measured heading angle. The statistical method is to extract the historical segments with normal attitude control, calculate the absolute difference sequence between the measured heading angle and the estimated heading angle at each moment, take the mean and standard deviation of the sequence, and set the mean plus one standard deviation as the threshold to define the reasonable boundary of the attitude estimation accuracy; the fifth preset threshold is used to determine the judgment standard for the duration of attitude anomaly. The setting method is to calculate the shortest duration of the attitude deviation angle exceeding the fourth threshold in the trajectory segment marked as abnormal flight behavior in the statistical history, and combine it with the flight control system response time setting to ensure that abnormal modes with flight control deviation risks can be captured in time.

[0018] Calculating a standard deviation of the three-dimensional distances during the entire flight process based on the three-dimensional spatial position distances between adjacent trajectory points in the trajectory point data to obtain a trajectory continuity score for indicating the smoothness of the flight trajectory; Further, including: Extract the three-dimensional coordinates of two adjacent trajectory points from the trajectory point data ( , , ), the trajectory point data is collected based on Beidou positioning results; Calculate the three-dimensional distance between each pair of adjacent trajectory points , the formula is ; in, is the track distance correction factor used to adjust the overall scale of the track distance, , , is the three-dimensional coordinate of the i-th trajectory point data, , For the i+1 The three-dimensional coordinates of the trajectory point data; According to the three-dimensional space distance , calculate the standard deviation of the three-dimensional space distance to measure the degree of fluctuation of the spatial position change. The calculation formula of the standard deviation of the three-dimensional space distance is: ; in, is the standard deviation adjustment coefficient, which is used to dynamically amplify or reduce the weight of the volatility measurement results. is the three-dimensional space distance, For all three-dimensional distances The average value of is the total number of trajectory points, is the standard deviation of the three-dimensional distance; The three-dimensional distance Average value The calculation formula is: ; The three-dimensional distance standard deviation Compared with the preset normalized reference value Compare and calculate the trajectory continuity score. The trajectory continuity score calculation formula is: ; in is the trajectory score adjustment coefficient, the preset normalized reference value It is obtained based on the average value of the standard deviation of the three-dimensional space distance calculated from multiple historical stable flight trajectory samples. Score trajectory continuity.

[0019] Specifically, based on the three-dimensional spatial position distance between adjacent trajectory points in the trajectory point data, the standard deviation of the three-dimensional spatial distance in the entire flight process is calculated to obtain a trajectory continuity score for characterizing the smoothness of the flight trajectory. The trajectory point data is collected based on the Beidou positioning results, and the three-dimensional coordinates of each pair of adjacent trajectory points are extracted. and , the following formula is used to calculate the three-dimensional space distance between each pair of adjacent trajectory points ;in, This is a preset positive coefficient used to adjust the overall impact of trajectory distance on subsequent scoring indicators. This parameter can be set based on the typical fluctuation amplitude of stable trajectory segments in historical flight missions and dynamically configured according to the sensitivity requirements of the flight platform. By introducing this coefficient, the influence of trajectory fluctuations can be finely controlled without changing the spatial structure calculation logic, which is conducive to improving the discrimination and stability of trajectory continuity scoring and further enhancing the accuracy of trajectory credibility assessment. ， ， For the i The three-dimensional coordinates of the trajectory point data, , , For the i+1 The three-dimensional coordinates of the trajectory point data; Represents the index of the trajectory point in the time series. Calculate the standard deviation of , to measure the degree of fluctuation of spatial position changes. The calculation formula for the standard deviation of the three-dimensional space distance is: ;in, is the standard deviation adjustment coefficient, which is used to dynamically amplify or reduce the weight of the volatility measurement results. is the three-dimensional space distance, is all three-dimensional space distances Average value Represents the average value of all three-dimensional space distances, and the calculation formula is: ; and N is the number of all valid three-dimensional space distances. To quantify the continuity of the trajectory, the three-dimensional space distance standard deviation is further The trajectory continuity score is calculated by comparing it with the average value of the standard deviation of the three-dimensional space distance calculated based on the historical stable flight sample trajectory. ;in The trajectory score adjustment coefficient is recommended to be in the range of 0.5 to 2.0. The preset normalized reference value It is obtained based on the average value of the standard deviation of the three-dimensional space distance calculated from multiple historical stable flight trajectory samples. is the trajectory continuity score, where Smaller values indicate a smoother flight trajectory. η<1: Slows down the score drop rate, making it more tolerant to minor fluctuations. η>1: Increases the sensitivity to score drops, making it easier to identify unstable trajectories.

[0020] The flight behavior type is matched with a preset risk level score table to obtain a behavior level score corresponding to the flight behavior type.

[0021] Further, including: Obtaining the flight behavior type corresponding to each trajectory point, matching the flight behavior type with a preset flight behavior risk level score table to obtain a basic behavior level score corresponding to the flight behavior type. The flight behavior risk level score table is used to assess the flight safety risk level of different flight behaviors and set a basic score value for each behavior; If the flight behavior risk level score table is provided with a weighted correction rule based on behavior sub-features, the basic behavior level score is further weightedly corrected based on the sub-features; The sub-features include the duration of abnormal attitude deviation angle, the trajectory continuity score, the standard deviation of the heading change rate, and the flight speed change rate; The duration of abnormal posture deviation angle is the length of time that the posture deviation angle continuously exceeds the preset abnormal threshold value; According to the basic behavior level score and the sub-feature value, a preset weighted correction coefficient is used to calculate a corrected behavior level score.

[0022] Specifically, the Beidou positioning module and the flight control sensor module jointly collect flight data from each trajectory point during flight, including time-series information such as three-dimensional position, velocity, heading angle, and attitude angle, as the raw data source. Based on these flight parameters, the system extracts the flight behavior type corresponding to each trajectory point and matches it with a preset flight behavior risk level score table to obtain the corresponding basic behavior level score. The flight behavior risk level score table is a predefined two-dimensional mapping table that lists common flight behaviors and their basic safety level scores. The scores are typically set based on historical flight risk event statistics and are used to provide a basic risk assessment. If the score table includes sub-feature-based weighted correction rules, multiple key behavior characteristic indicators are further extracted, including: the duration of the attitude deviation angle abnormality, i.e., the length of time during which the attitude deviation angle continuously exceeds a preset abnormality threshold; the trajectory continuity score, calculated by calculating the standard deviation of the three-dimensional spatial distances between adjacent trajectory points within a sliding window, reflecting the stability of the trajectory; the heading change rate standard deviation, which quantifies the stability of the flight heading angle per unit time; and the flight speed change rate, obtained by differencing the speed series and used to characterize the degree of speed fluctuation. The system multiplies each of these sub-feature values by the corresponding weighted correction coefficient and combines it with the base score to ultimately calculate a corrected behavioral grade score. This weighting strategy flexibly adapts to the degree of behavioral anomaly in different flight scenarios, enabling fine-grained correction of the base score and improving the accuracy of flight behavior risk identification.

[0023] A trajectory credibility score is obtained using a weighted calculation formula based on the trajectory continuity score, the heading change rate standard deviation, and the behavior level score.

[0024] Further, including: Different weight factors are set for the trajectory continuity score, the heading change rate standard deviation, and the behavior level score. The trajectory credibility score of the entire trajectory is obtained by weighted fusion of the three. The weighted fusion calculation formula is: ; Wherein, K is the behavior grade score, is the standard deviation of the heading change rate, C is the trajectory continuity score, 、 、 is the preset weighting coefficient, satisfying α + β + γ = 1, and T is the trajectory credibility score; The credibility level of the current flight process is determined according to the numerical value of the trajectory credibility score T and the preset trajectory credibility level threshold range.

[0025] Furthermore, the preset trajectory credibility level threshold range includes: Obtain the trajectory credibility score obtained by weighted calculation of trajectory continuity score, heading change rate standard deviation and behavior level score in historical flight missions, and construct a trajectory credibility score sample set; Based on the distribution characteristics of the trajectory credibility score sample set, setting multiple independent trajectory credibility level threshold intervals; The confidence level threshold intervals of each trajectory are set to high confidence level, medium confidence level, low confidence level and abnormal level, and each level corresponds to a flight control feedback instruction; During the flight, the trajectory credibility level threshold interval is located according to the trajectory credibility score of the current flight segment, and the credibility level corresponding to the flight process is determined according to the trajectory credibility level threshold interval.

[0026] Specifically, in order to realize the credibility assessment of the UAV flight trajectory, the system is based on the flight trajectory point data collected by the Beidou positioning system, combined with the flight state recognition results, and comprehensively considers the flight trajectory continuity score C, the heading change rate standard deviation, and the flight state recognition result. The trajectory credibility score T is calculated by weighted fusion with the behavior level score K. Among them, the trajectory continuity score C is calculated by extracting the three-dimensional coordinates of adjacent trajectory points in the trajectory point data and calculating the three-dimensional spatial distance between each pair of adjacent trajectory points. , and further get the standard deviation of all three-dimensional space distances, where is the average three-dimensional space distance, and finally Compared with the preset normalized reference value Compare and calculate trajectory continuity score ;in The trajectory score adjustment coefficient is recommended to be in the range of 0.5 to 2.0. The preset normalized reference value It is obtained based on the average value of the standard deviation of the three-dimensional space distance calculated from multiple historical stable flight trajectory samples. is the trajectory continuity score, where The smaller the value, the steadier the flight trajectory. η<1: Slows down the score drop rate and is more tolerant to slight fluctuations. η>1: Increases the sensitivity of score drop and makes it easier to identify unstable trajectories. It is used to measure the volatility of heading changes during flight. The behavior grade score K is based on the flight behavior type and its sub-characteristics (including the duration of abnormal attitude deviation angle, trajectory continuity score C, standard deviation of heading change rate, etc.). , flight speed change rate) is calculated. If the correction rules are defined in the preset flight behavior risk level score table, the weighted correction method is used for adjustment. The trajectory credibility score calculation formula is , 、 、 is a preset weighting coefficient satisfying α + β + γ = 1, and T is the trajectory credibility score. After obtaining the trajectory credibility score T, the system constructs a sample set of trajectory credibility scores based on historical flight mission data, calculates its distribution characteristics, and sets multiple non-overlapping credibility level intervals, corresponding to high credibility, medium credibility, low credibility, and abnormality levels. Each level interval is bound to a corresponding flight control feedback strategy. During flight, the T value of the current flight segment is used to locate the level interval to which it belongs in real time, thereby determining the credibility level of the flight process and triggering corresponding flight control response instructions, such as maintaining autonomous flight, path correction, control intervention, or emergency avoidance. Through this implementation, real-time credibility quantitative assessment of the UAV flight process can be achieved, effectively improving the intelligent decision-making capabilities of the flight control system in trajectory safety management.

[0027] The trajectory credibility score is input into a preset response strategy mapping table, and the corresponding flight control feedback instructions are matched and executed according to the score interval. The flight control feedback instructions include maintaining flight, issuing reminders, triggering evaluation, and interrupting return operations.

[0028] Further, including: Inputting the trajectory credibility score into a preset response strategy mapping table for table lookup and matching, wherein the response strategy mapping table predefines multiple trajectory credibility level threshold intervals, each trajectory credibility level uniquely corresponds to a trajectory credibility level threshold interval and is associated with a set of flight control feedback instructions; Determining a corresponding trajectory credibility level according to the trajectory credibility level threshold interval to which the trajectory credibility score belongs; Based on the trajectory credibility level, selecting and executing a corresponding flight control feedback instruction from the flight control feedback instruction set; The flight control feedback instruction selection rule is to execute a continuous control instruction for maintaining the flight state when the trajectory credibility score is in a high credibility level interval; When the trajectory credibility score is in the medium credibility level interval, executing a reminder instruction for generating a flight warning and sending it to the flight control management terminal; When the trajectory credibility score is in a low credibility level interval, executing a control instruction for triggering a flight behavior reassessment process; When the trajectory credibility score is within the abnormal level range, executing a flight control safety instruction for interrupting the flight mission and initiating return control; The flight control feedback instruction is sent to the flight control module through the data interface of the flight control system, and is used to drive the UAV to perform flight control operations that are compatible with the trajectory credibility level.

[0029] Specifically, after calculating the trajectory credibility score T, the system inputs this score into a preset response strategy mapping table for a lookup match to trigger the corresponding flight control feedback command, in order to implement intelligent feedback control of the flight status. The response strategy mapping table predefines multiple, non-overlapping trajectory credibility threshold intervals. Each score interval corresponds to a unique trajectory credibility level label, such as high credibility, medium credibility, low credibility, and abnormal. Each level label is associated with a set of preset flight control feedback commands, forming a ternary correspondence: score interval, credibility level, and feedback command. When the trajectory credibility score T falls within the high confidence level, the system invokes continuous control commands to maintain flight status, ensuring stable mission execution. When T falls within the medium confidence level, the system generates a flight warning and sends a reminder to the flight control management terminal, alerting operators to the current flight status. When T falls within the low confidence level, the system automatically triggers a flight behavior reassessment process, invoking the control logic module to recalibrate the trajectory and behavioral characteristics. If T falls within the abnormal level, the system immediately invokes flight control safety commands to abort the mission and initiate return-to-home control, thereby ensuring flight safety for both equipment and the environment. These flight control feedback commands are transmitted via a data interface with the flight control system and connected to the UAV's flight control module. Execution of these commands enables dynamic intervention and management of the UAV's flight behavior. This mechanism implements an adaptive flight control response strategy based on dynamic trajectory credibility perception, significantly improving the UAV's operational safety and autonomous decision-making capabilities in complex environments.

[0030] In summary, the embodiments of the present application have at least the following technical effects: The trajectory point data, acceleration data and angular velocity data during the flight are collected by the Beidou positioning module and inertial navigation device installed on the UAV. The trajectory point data is an ordered data sequence including timestamp, three-dimensional spatial position, heading angle measurement value and three-dimensional velocity vector. The three-dimensional velocity vector is a set of velocity components in the three directions of X-axis, Y-axis and Z-axis in the airborne coordinate system at each moment; inertial solution is performed based on the acceleration data and angular velocity data to obtain the heading angle estimation value, and the flight speed change rate, heading change rate time series and attitude deviation angle are extracted in combination with the trajectory point data. Based on the heading change rate time series, the heading change rate standard deviation is obtained; based on the flight speed change rate, the heading change rate time series and the attitude deviation angle, the behavior classification rules are matched to obtain each trajectory point The flight behavior type includes stable flight, sudden acceleration, sharp turn, and abnormal yaw; based on the three-dimensional spatial position distance between adjacent trajectory points in the trajectory point data, the standard deviation of the three-dimensional spatial distance in the entire flight process is calculated to obtain a trajectory continuity score for representing the smoothness of the flight trajectory; according to the flight behavior type, a preset risk level score table is matched to obtain the behavior level score corresponding to the flight behavior type; based on the trajectory continuity score, the standard deviation of the heading change rate and the behavior level score, a weighted calculation formula is used to obtain the trajectory credibility score; the trajectory credibility score is input into a preset response strategy mapping table, and the corresponding flight control feedback instructions are matched and executed according to the score interval, and the flight control feedback instructions include maintaining flight, issuing reminders, triggering evaluation, and interrupting return operations.

[0031] It should be noted that the above-mentioned order of the embodiments of the present application is for descriptive purposes only and does not represent the superiority or inferiority of the embodiments. The above description is of specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0032] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

[0033] This specification and drawings are merely illustrative of the present application and are intended to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, this application is intended to include such modifications and variations as fall within the scope of this application and its equivalents.

Claims

1. The reliable management method of drone trajectory combined with Beidou positioning is characterized by: include: The Beidou positioning module and inertial navigation unit installed on the drone collect trajectory point data, acceleration data, and angular velocity data during flight. The trajectory point data is an ordered data sequence containing a timestamp, a three-dimensional spatial position, a heading angle measurement, and a three-dimensional velocity vector. The three-dimensional velocity vector is the set of velocity components in the X-axis, Y-axis, and Z-axis directions in the airborne coordinate system at each moment. Performing inertial calculation based on the acceleration data and angular velocity data to obtain a heading angle calculation value, and extracting the flight speed change rate, heading change rate time series, and attitude offset angle based on the trajectory point data, and obtaining the heading change rate standard deviation based on the heading change rate time series; Based on the flight speed change rate, the heading change rate time series and the attitude deviation angle, matching behavior classification rules to obtain the flight behavior type of each trajectory point, the flight behavior type including stable flight, rapid acceleration, sharp turn and abnormal yaw; Calculating a standard deviation of the three-dimensional distances during the entire flight process based on the three-dimensional spatial position distances between adjacent trajectory points in the trajectory point data to obtain a trajectory continuity score for indicating the smoothness of the flight trajectory; Matching the flight behavior type to a preset risk level score table to obtain a behavior level score corresponding to the flight behavior type; A trajectory credibility score is obtained using a weighted calculation formula based on the trajectory continuity score, the heading change rate standard deviation, and the behavior level score; The trajectory credibility score is input into a preset response strategy mapping table, and the corresponding flight control feedback instructions are matched and executed according to the score interval. The flight control feedback instructions include maintaining flight, issuing reminders, triggering evaluation, and interrupting return operations.

2. The method for reliable management of drone trajectories in combination with Beidou positioning according to claim 1 is characterized in that: The inertial solution is performed based on the acceleration data and the angular velocity data to obtain a heading angle calculation value, and the flight speed change rate, the heading change rate time series and the attitude deviation angle are extracted in combination with the trajectory point data. The heading change rate standard deviation is obtained based on the heading change rate time series, including: Performing inertial calculation based on the angular velocity data, initializing a unit quaternion using a quaternion attitude calculation method, integrating the angular velocity data hour by hour in a time series, obtaining an attitude quaternion corresponding to each moment, and converting the attitude quaternion into Euler angles to extract a heading angle component as a dead reckoning value of the heading angle; constructing a heading change rate time series based on the heading angle dead reckoning values, wherein the heading change rate is obtained by dividing the difference between adjacent heading angle dead reckoning values by a sampling time interval; Based on the three-dimensional velocity vectors in the trajectory point data, calculating the velocity modulus value sequence at each moment, and performing time differentiation on the modulus value sequence to obtain a flight velocity change rate sequence; According to the heading angle measurement values of the trajectory point data, the heading angle measurement values are compared with the heading angle estimated values at each moment, and the absolute value of the difference between the two is calculated to obtain an attitude deviation angle sequence representing the degree of deviation between the attitude solution and the actual measurement; Based on the heading change rate time series, the standard deviation of the heading angle change rate between adjacent time points is calculated. The standard deviation formula of the heading change rate is: ； in, is the standard deviation of the heading change rate, Indicates the i The rate of change of heading within a time interval, is the mean heading change rate, N is the number of sampling points.

3. The method for reliable management of drone trajectories in combination with Beidou positioning according to claim 1 is characterized in that: The flight behavior type of each trajectory point is obtained by matching the behavior classification rules based on the flight speed change rate, the heading change rate time series and the attitude deviation angle. The flight behavior types include stable flight, rapid acceleration, sharp turn and abnormal yaw, including: Setting a plurality of continuity preset thresholds includes a first preset threshold, a second preset threshold, a third preset threshold, a fourth preset threshold, and a fifth preset threshold; The first preset threshold is the upper limit of the flight speed change rate. The first preset threshold is set by selecting trajectory segments marked as stable flight in historical flight data, calculating the mean and standard deviation of the flight speed change rate sequence, and adding twice the standard deviation to the mean. The second preset threshold is the upper limit of the standard deviation of the heading change rate. The second preset threshold is set by selecting stable flight segments in the historical flight data, calculating the mean and standard deviation of the standard deviation of the heading angle change rate between adjacent time points in the heading change rate time series, and adding one standard deviation to the mean. The third preset threshold is the upper limit of the heading change rate. The third preset threshold is set by selecting trajectory segments marked as normal turns in historical flight data, calculating the mean and standard deviation of their heading change rates, and adding twice the standard deviation to the mean. The fourth preset threshold is the upper limit of the attitude deviation angle. The fourth preset threshold is set by extracting the normal attitude control segments in the historical flight data, calculating the sequence of absolute differences between the heading angle measurement values and the heading angle estimation values, and adding one standard deviation to the mean of the sequence. The fifth preset threshold is a time window threshold representing the duration of the abnormal attitude deviation, which is set by counting the shortest duration of the attitude deviation angle exceeding the fourth preset threshold in historical abnormal flight behaviors and combining it with the response time of the flight control system; When the flight speed change rate at multiple consecutive time points is greater than a first preset threshold, and the standard deviation of the heading change rate is less than a second preset threshold, it is determined to be a sudden acceleration behavior; When the standard deviation of the heading change rate at multiple consecutive time points is greater than a third preset threshold, and the flight speed change rate is less than a fourth preset threshold, it is determined to be a sharp turn behavior; If the attitude deviation angle is greater than a fifth preset threshold value at multiple consecutive time points and the duration of the deviation exceeds a preset time window threshold value, it is determined to be an abnormal yaw behavior; If the flight speed change rate, heading change rate, and attitude deviation angle are all lower than their corresponding stable state tolerance ranges at multiple consecutive time points, it is determined to be stable flight behavior.

4. The method for reliable management of drone trajectories combined with Beidou positioning according to claim 1 is characterized in that: The step of calculating the standard deviation of the three-dimensional distances during the entire flight process based on the three-dimensional spatial position distances between adjacent trajectory points in the trajectory point data to obtain a trajectory continuity score for indicating the smoothness of the flight trajectory includes: Extract the three-dimensional coordinates of two adjacent trajectory points from the trajectory point data ( , , ), the trajectory point data is collected based on Beidou positioning results; Calculate the three-dimensional distance between each pair of adjacent trajectory points , the formula is ； in, is the track distance correction factor used to adjust the overall scale of the track distance, , , is the three-dimensional coordinate of the i-th trajectory point data, , For the i+1 The three-dimensional coordinates of the trajectory point data; According to the three-dimensional space distance , calculate the standard deviation of the three-dimensional space distance to measure the degree of fluctuation of the spatial position change. The calculation formula of the standard deviation of the three-dimensional space distance is: ； in, is the standard deviation adjustment coefficient, which is used to dynamically amplify or reduce the weight of the volatility measurement results. is the three-dimensional space distance, For all three-dimensional distances The average value of is the total number of trajectory points, is the standard deviation of the three-dimensional distance; The three-dimensional distance Average value The calculation formula is: ； The three-dimensional distance standard deviation Compared with the preset normalized reference value Compare and calculate the trajectory continuity score. The trajectory continuity score calculation formula is: ； in is the trajectory score adjustment coefficient, the preset normalized reference value It is obtained based on the average value of the standard deviation of the three-dimensional space distance calculated from multiple historical stable flight trajectory samples. Score trajectory continuity.

5. The method for reliable management of drone trajectories in combination with Beidou positioning according to claim 1 is characterized in that: According to the flight behavior type, a preset risk level score table is matched to obtain the behavior level score corresponding to the flight behavior type, including: Obtaining the flight behavior type corresponding to each trajectory point, matching the flight behavior type with a preset flight behavior risk level score table to obtain a basic behavior level score corresponding to the flight behavior type. The flight behavior risk level score table is used to assess the flight safety risk level of different flight behaviors and set a basic score value for each behavior; If the flight behavior risk level score table is provided with a weighted correction rule based on behavior sub-features, the basic behavior level score is further weightedly corrected based on the sub-features; The sub-features include the duration of abnormal attitude deviation angle, the trajectory continuity score, the standard deviation of the heading change rate, and the flight speed change rate; The duration of abnormal posture deviation angle is the length of time that the posture deviation angle continuously exceeds the preset abnormal threshold value; According to the basic behavior level score and the sub-feature value, a preset weighted correction coefficient is used to calculate a corrected behavior level score.

6. The method for reliable management of drone trajectories in combination with Beidou positioning according to claim 1 is characterized in that: Based on the trajectory continuity score, the heading change rate standard deviation, and the behavior level score, a weighted calculation formula is used to obtain a trajectory credibility score, including: Different weight factors are set for the trajectory continuity score, the heading change rate standard deviation, and the behavior level score. The trajectory credibility score of the entire trajectory is obtained by weighted fusion of the three. The weighted fusion calculation formula is: ； Wherein, K is the behavior grade score, is the standard deviation of the heading change rate, C is the trajectory continuity score, 、 、 is the preset weighting coefficient, satisfying α + β + γ = 1, and T is the trajectory credibility score; The credibility level of the current flight process is determined according to the numerical value of the trajectory credibility score T and the preset trajectory credibility level threshold range.

7. The method for reliable management of drone trajectories in combination with Beidou positioning according to claim 6 is characterized in that: The preset trajectory credibility level threshold range includes: Obtain the trajectory credibility score obtained by weighted calculation of trajectory continuity score, heading change rate standard deviation and behavior grade score in historical flight missions, and construct a trajectory credibility score sample set; Based on the distribution characteristics of the trajectory credibility score sample set, setting multiple independent trajectory credibility level threshold intervals; The confidence level threshold intervals of each trajectory are set to high confidence level, medium confidence level, low confidence level and abnormal level, and each level corresponds to a flight control feedback instruction; During the flight, the trajectory credibility level threshold interval is located according to the trajectory credibility score of the current flight segment, and the credibility level corresponding to the flight process is determined according to the trajectory credibility level threshold interval.

8. The method for reliable management of drone trajectories in combination with Beidou positioning according to claim 1, characterized in that: Inputting the trajectory credibility score into a preset response strategy mapping table, matching and executing corresponding flight control feedback instructions according to the score interval, includes: Inputting the trajectory credibility score into a preset response strategy mapping table for table lookup and matching, wherein the response strategy mapping table predefines multiple trajectory credibility level threshold intervals, each trajectory credibility level uniquely corresponds to a trajectory credibility level threshold interval and is associated with a set of flight control feedback instructions; Determining a corresponding trajectory credibility level according to the trajectory credibility level threshold interval to which the trajectory credibility score belongs; Based on the trajectory credibility level, selecting and executing a corresponding flight control feedback instruction from the flight control feedback instruction set; The flight control feedback instruction selection rule is to execute a continuous control instruction for maintaining the flight state when the trajectory credibility score is in a high credibility level interval; When the trajectory credibility score is in the medium credibility level interval, executing a reminder instruction for generating a flight warning and sending it to the flight control management terminal; When the trajectory credibility score is in a low credibility level interval, executing a control instruction for triggering a flight behavior reassessment process; When the trajectory credibility score is within the abnormal level range, executing a flight control safety instruction for interrupting the flight mission and initiating return control; The flight control feedback instruction is sent to the flight control module through the data interface of the flight control system, and is used to drive the UAV to perform flight control operations that are compatible with the trajectory credibility level.

Images