A sensor-based real-time monitoring and control system for drones

Abstract

The invention discloses a sensor-based unmanned aerial vehicle (UAV) real-time monitoring and control system, which relates to the field of UAVs. The invention effectively copes with the influence of multipath effects on GPS positioning in complex environments by integrating four modules: signal reception, positioning stability evaluation, positioning accuracy classification and abnormality control. The signal reception module separates direct path signals by using a multipath delay locking loop algorithm to improve positioning accuracy. The positioning stability evaluation module evaluates the positioning stability of the UAV by analyzing residual fluctuations of GPS position data. The positioning accuracy classification module determines the positioning accuracy of the UAV in real time and classifies it according to positioning data. The abnormality control module determines the action strategy of the UAV according to the positioning accuracy. By performing positioning abnormality analysis under low accuracy and judging whether it is necessary to return in advance, the navigation stability of the UAV in complex environments is not only improved, but also the loss of control caused by positioning errors is effectively prevented.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicles, and in particular to a sensor-based real-time monitoring and control system for unmanned aerial vehicles. Background Art

[0002] Sensor-based real-time monitoring and control of drones refers to the use of various sensors (such as GPS, cameras, lidar, barometers, etc.) to obtain data about the drone's surrounding environment and its own status, and by processing this data, it can achieve real-time monitoring and automatic control of the drone's flight. However, in complex urban environments or mountainous areas, GPS signals may produce multipath effects due to reflection and refraction. This may cause errors in the received GPS signals, resulting in inaccurate positioning. At the same time, serious positioning errors may cause the drone's automatic control system to lose accurate judgment of its current position, and the drone may enter an out-of-control state and be unable to respond correctly to control commands to automatically return, which may cause it to lose its way, fly out of the operator's line of sight, or even lose contact with the ground control station. Summary of the invention

[0003] The purpose of the present invention is to provide a sensor-based unmanned aerial vehicle real-time monitoring and control system to address the deficiencies in the background technology.

[0004] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a sensor-based UAV real-time monitoring and control system, comprising a signal receiving module, a positioning stability evaluation module, a positioning accuracy division module and an abnormality control module;

[0005] Signal receiving module: uses GPS receiver to receive multiple satellite signals from different paths in real time, estimates the time delay of each signal through multipath delay locking loop algorithm, and separates direct path signal from multipath signal;

[0006] Positioning stability evaluation module: For multipath signals, by comparing the GPS position data at consecutive time points within the S time period, the position residual fluctuation of the UAV positioning is analyzed to evaluate the stability of the UAV positioning;

[0007] Positioning accuracy classification module: According to the time delay state of multipath signals and the stability of UAV positioning, the accuracy of UAV positioning is evaluated and divided into high-accuracy positioning and low-accuracy positioning;

[0008] Abnormal control module: When the UAV is in a high-accuracy positioning, the UAV continues to perform the mission according to the predetermined flight path; when the UAV is in a low-accuracy positioning, the accuracy of the UAV positioning within a fixed time period is analyzed to determine whether to return early.

[0009] Preferably, in the signal receiving module, the GPS receiver receives a signal from the same satellite, generates a local pseudo-random code that matches the received satellite signal, correlates the received signal with the locally generated pseudo-random code, and generates a correlation output. A traditional delay locked loop estimates the arrival time of the signal by finding peaks in the correlation output, and uses a multipath delay locked loop algorithm to accurately analyze these peaks, and separates the direct path signal from the multipath signal based on the time delay estimated by the multipath delay locked loop algorithm.

[0010] Preferably, according to the cumulative delay of the multipath signal, the situation where the pseudorange error increases rapidly in a short period of time is analyzed to determine the positioning accuracy in the current environment, wherein the pseudorange error growth rate abnormality index is generated according to the time delay data of the multipath signal, and the method for obtaining the pseudorange error growth rate abnormality index is:

[0011] Obtain time-dependent pseudorange error data And the corresponding timestamp ; Calculate the pseudorange error growth rate for each time interval. The expression is: ; Forming a growth rate series ; Establish a Gaussian process model and determine the kernel function of the Gaussian process model , ;in, is the variance of the signal, is the length scale, and the pseudorange error growth rate is substituted into the Gaussian process model , ; where m(t) is the mean function; using the time series and pseudorange error growth rate data Train the Gaussian process model according to the kernel function Calculate the covariance matrix K and obtain the prior distribution of the Gaussian process, ;in, is the noise variance, is the identity matrix, given a new time point , calculate the corresponding growth rate forecast distribution , the expression is: ;in, is the predicted mean growth rate, indicating the The expected growth rate at is calculated as: ; is the forecast variance of the growth rate, indicating the uncertainty of the forecast growth rate, and the calculation expression is: ; is the matrix transpose; the predicted pseudorange error growth rate is Compared with the mean and variance of the predicted distribution, the pseudorange error growth rate anomaly index is calculated, and the expression is: ; In the formula, is the anomaly index of pseudorange error growth rate.

[0012] Preferably, in the positioning stability evaluation module, the residual fluctuation of the position of the UAV is analyzed to generate a residual fluctuation index, and the stability of the UAV positioning is evaluated according to the residual fluctuation index, wherein the residual fluctuation index is obtained by:

[0013] Obtain the GPS positioning data of the drone in the time period S, including the latitude and longitude of consecutive time points, compare the actual measured position with the expected position, and obtain the positioning residual at each time point. The expression is: ;in, For time point The measurement position, is the expected position, Represents the Euclidean distance of the position error; calculates the residual fluctuation amplitude of all residuals in the time period S , the expression is: ;in, is the average value of the residual, n is the number of time points in the time period S, and the average change rate AD of the residual in the time period S is calculated. The expression is: ; Calculate the residual volatility index, the expression is: ; In the formula, is the residual volatility index.

[0014] Preferably, in the positioning accuracy division module, the pseudorange error growth rate anomaly index and the residual fluctuation index are converted into a first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses each group of first eigenvectors to predict the accuracy value label of the UAV positioning as the prediction target, and minimizes the sum of the prediction errors of the accuracy value labels of all UAV positioning as the training target. The machine learning model is trained until the sum of the prediction errors converges, and the model training is stopped. The accuracy value of the UAV positioning is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0015] Preferably, the acquired accuracy value of the UAV positioning is compared with a preset reference threshold value of the UAV positioning accuracy value. If the accuracy value of the UAV positioning is greater than or equal to the preset reference threshold value of the UAV positioning accuracy value, it means that the accuracy of the UAV positioning is high, and an accurate positioning signal is generated at this time; when the accurate positioning signal is generated, the system continues normal flight operation; if the accuracy value of the UAV positioning is less than the preset reference threshold value of the UAV positioning accuracy value, it means that the accuracy of the UAV positioning is low, and an inaccurate positioning signal is generated at this time; inaccurate positioning signal: when an inaccurate positioning signal is generated, the system takes preventive measures.

[0016] Preferably, in the abnormal control module, when the UAV is in a low-accuracy positioning state, that is, the accuracy value of the UAV positioning generated within a fixed time period is less than a preset reference threshold value of the UAV positioning accuracy value, the degree of abnormality in the accuracy of the UAV positioning in a subsequent fixed time period is analyzed, the accuracy values ​​of the UAV positioning generated within the subsequent fixed time period that are less than the reference threshold value of the accuracy value are collected, and a data set is established, the mean and standard deviation of the data set are calculated, and after analysis, the degree of abnormality in the accuracy of the UAV positioning is determined, and it is determined whether to return early.

[0017] Preferably, if the mean of the accuracy values ​​in the data set is greater than or equal to the reference threshold of the mean of the accuracy values, and the standard deviation of the accuracy values ​​is less than the reference threshold of the standard deviation of the accuracy values, the accuracy level is high and the fluctuation is small, and there is no need to return. At this time, no warning signal is generated, and the mission continues to be performed, while the positioning situation is continuously monitored;

[0018] If the mean accuracy value is greater than or equal to the reference threshold of the mean accuracy value, and the standard deviation of the accuracy value is greater than or equal to the reference threshold of the standard deviation of the accuracy value, although the accuracy level is high, the positioning fluctuation is large. At this time, a level 3 warning signal is generated, the flight is decelerated, and the positioning status is closely monitored;

[0019] If the mean accuracy value is less than the reference threshold of the mean accuracy value, and the standard deviation of the accuracy value is greater than or equal to the reference threshold of the standard deviation of the accuracy value, the accuracy level is low and fluctuates greatly, and the positioning system is seriously disturbed. At this time, a first-level warning signal is generated, and preparations are made to return in advance to ensure the safety of the drone;

[0020] If the mean accuracy value is less than the reference threshold of the mean accuracy value, and the standard deviation of the accuracy value is less than the reference threshold of the standard deviation of the accuracy value, the accuracy level is low but the fluctuation is small, and there is a continuous deviation in positioning. At this time, a level 2 warning signal is generated, and it is recommended to return home in advance to prevent the accumulation of positioning errors from causing loss of flight control.

[0021] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0022] 1. The present invention can effectively separate direct path signals from multipath signals through the multipath delay locked loop algorithm of the signal receiving module, significantly improving positioning accuracy. The positioning stability evaluation module and the positioning accuracy division module further comprehensively evaluate the positioning stability and accuracy of the UAV by analyzing residual fluctuations and pseudorange errors, and use machine learning models to accurately divide the positioning accuracy, so that the UAV can adjust the flight strategy according to the real-time positioning status.

[0023] 2. The abnormal control module of the present invention continuously monitors the accuracy and stability of the UAV positioning, generates a warning signal in time when the positioning is abnormal, and takes corresponding measures, such as slowing down the flight, closely monitoring or returning in advance, to ensure flight safety. It not only improves the autonomous navigation capability of the UAV in complex environments, but also enhances the reliability and safety of the system, reduces the risk of flight accidents caused by inaccurate positioning, and ensures that the UAV can complete its mission efficiently and safely. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0025] Figure 1 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] For examples, see Figure 1 As shown, the sensor-based drone real-time monitoring and control system described in this embodiment includes a signal receiving module, a positioning stability evaluation module, a positioning accuracy classification module and an abnormality control module;

[0028] Signal receiving module: uses GPS receiver to receive multiple satellite signals from different paths in real time, estimates the time delay of each signal through multipath delay locking loop algorithm, and separates direct path signal from multipath signal;

[0029] Positioning stability evaluation module: For multipath signals, by comparing the GPS position data at consecutive time points within the S time period, the position residual fluctuation of the UAV positioning is analyzed to evaluate the stability of the UAV positioning;

[0030] Positioning accuracy classification module: According to the time delay state of multipath signals and the stability of UAV positioning, the accuracy of UAV positioning is evaluated and divided into high-accuracy positioning and low-accuracy positioning;

[0031] Abnormal control module: When the UAV is in a high-accuracy positioning, the UAV continues to perform the mission according to the predetermined flight path; when the UAV is in a low-accuracy positioning, the accuracy of the UAV positioning within a fixed time period is analyzed to determine whether to return early.

[0032] The signal receiving module receives and processes the same satellite signal from different paths in real time through the GPS receiver, estimates the time delay of each signal using the multipath delay locked loop (MEDLL) algorithm, and separates the direct path signal from the multipath signal after reflection or refraction. In this way, the module can identify and filter out the error signal caused by the multipath effect, ensuring that the drone can obtain more accurate positioning information, improve the accuracy of navigation and control, and effectively reduce the positioning error caused by the multipath effect, especially in complex environments.

[0033] The GPS receiver receives signals from the same satellite. These signals include direct path signals (LOS, Line of Sight) and signals propagated through multipath effects such as reflection and refraction. The receiver samples the received signals at high frequency, records information such as signal strength, phase, and arrival time, and provides raw data for subsequent processing.

[0034] The GPS receiver generates a local pseudo-random number (PRN code) that matches the received satellite signal. The received signal is correlated with the locally generated pseudo-random code to generate a correlation output. Traditional delay-locked loops (DLLs) estimate the arrival time of the signal by finding peaks in the correlation output. The multipath delay-locked loop (MEDLL) algorithm is used to accurately analyze these peaks. MEDLL fits the peaks in the correlation function through mathematical fitting and optimization algorithms to estimate the specific time delay of each signal. Based on the time delay estimated by the MEDLL, it is identified which peak corresponds to the direct path signal and the rest are multipath signals. The direct path signal is separated from the multipath signal. The direct path signal is used for further positioning calculations, while the multipath signal is weakened or excluded to reduce its impact on positioning accuracy.

[0035] According to the cumulative delay of the multipath signal, the situation where the pseudorange error increases rapidly in a short period of time is analyzed to determine the positioning accuracy in the current environment. The pseudorange error growth rate anomaly index is generated according to the time delay data of the multipath signal. The method for obtaining the pseudorange error growth rate anomaly index is:

[0036] Obtain time-dependent pseudorange error data And the corresponding timestamp ; Calculate the pseudorange error growth rate for each time interval. The expression is: ; Forming a growth rate series ; Establish a Gaussian process model and determine the kernel function of the Gaussian process model , ;in, is the variance of the signal, is the length scale, controlling the correlation between time points, and substituting the pseudorange error growth rate into the Gaussian process model , ; where m(t) is the mean function (usually set to 0); using the time series and pseudorange error growth rate data Train the Gaussian process model according to the kernel function Calculate the covariance matrix K and obtain the prior distribution of the Gaussian process, ;in, is the noise variance, is the identity matrix, given a new time point , calculate the corresponding growth rate forecast distribution , the expression is: ;in, is the predicted mean growth rate, indicating the The expected growth rate at is calculated as: ; is the forecast variance of the growth rate, indicating the uncertainty of the forecast growth rate, and the calculation expression is: ; is the matrix transpose; the predicted pseudorange error growth rate is Compared with the mean and variance of the predicted distribution, the pseudorange error growth rate anomaly index is calculated, and the expression is: ; In the formula, is the anomaly index of pseudorange error growth rate.

[0037] The pseudorange error growth rate anomaly index reflects the degree of deviation between the observed value and the Gaussian process model prediction. The larger the pseudorange error growth rate anomaly index is, the more significant anomalies there are in the pseudorange error growth rate, and the positioning accuracy may be seriously affected by the multipath effect.

[0038] Positioning stability evaluation module: For multipath signals, by comparing the GPS position data at consecutive time points within the S time period, the position residual fluctuation of the UAV positioning is analyzed to evaluate the stability of the UAV positioning.

[0039] By comparing the GPS position data at consecutive time points within the S time period, the position residual fluctuation caused by multipath signals to the UAV positioning can be analyzed. This analysis can reveal the stability and accuracy of the position data in a short period of time and help identify abnormal deviations or error accumulation caused by multipath effects. In this way, the positioning accuracy can be effectively evaluated and positioning errors that may affect flight safety can be detected in a timely manner, thereby optimizing the navigation system and ensuring that the UAV maintains a high-precision flight path in complex environments.

[0040] After analyzing the residual fluctuation of the UAV positioning, a residual fluctuation index is generated. The stability of the UAV positioning is evaluated according to the residual fluctuation index. The residual fluctuation index is obtained as follows:

[0041] Obtain the GPS positioning data of the drone in the time period S, including the latitude and longitude of consecutive time points, compare the actual measured position with the expected position, and obtain the positioning residual at each time point. The expression is: ;in, For time point The measurement position, is the expected position, Represents the Euclidean distance of the position error; calculates the residual fluctuation amplitude of all residuals in the time period S , the expression is: ;in, is the average value of the residual, n is the number of time points in the time period S, and the average change rate AD of the residual in the time period S is calculated. The expression is: ; Calculate the residual volatility index, the expression is: ; In the formula, is the residual volatility index.

[0042] The residual fluctuation index can comprehensively evaluate the positioning stability of the drone over a period of time. A higher residual fluctuation index indicates unstable positioning data, while a lower value indicates relatively stable positioning. By calculating and monitoring the residual fluctuation index, abnormal fluctuations in the positioning system can be detected in a timely manner to ensure the safety and reliability of drone flight.

[0043] Positioning accuracy classification module: According to the time delay state of the multipath signal and the stability of the UAV positioning, the accuracy of the UAV positioning is evaluated and divided into high-accuracy positioning and low-accuracy positioning.

[0044] The pseudorange error growth rate anomaly index and the residual fluctuation index are converted into the first eigenvector, and the first eigenvector is used as the input of the machine learning model. The machine learning model uses each group of first eigenvectors to predict the accuracy value label of the UAV positioning as the prediction target, and takes minimizing the sum of the prediction errors of the accuracy value labels of all UAV positioning as the training target. The machine learning model is trained until the sum of the prediction errors converges, and the model training is stopped. The accuracy value of the UAV positioning is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0045] The method for obtaining the accuracy value of drone positioning is to obtain the corresponding function expression from the first eigenvector training data of the trained machine learning model: ; In the formula, is the output function of the model, is the pseudorange error growth rate anomaly index, is the residual volatility index, The accuracy value of the drone positioning.

[0046] The obtained drone positioning accuracy value is compared with the preset drone positioning accuracy value reference threshold. If the drone positioning accuracy value is greater than or equal to the preset drone positioning accuracy value reference threshold, it means that the drone positioning accuracy is high, and a positioning accuracy signal is generated at this time. When the positioning accuracy signal is generated, the system can continue normal flight operations, perform tasks or maintain the current path. This signal may trigger a series of normal operations, such as continuing data collection, task execution, etc.

[0047] If the accuracy value of the drone positioning is less than the pre-set reference threshold of the drone positioning accuracy value, it means that the accuracy of the drone positioning is low, and an inaccurate positioning signal is generated at this time; inaccurate positioning signal: when an inaccurate positioning signal is generated, the system may take some preventive measures, such as slowing down, hovering, trying to reposition, switching to an alternative navigation mode, or triggering an alarm to notify the operator, indicating that manual intervention may be required.

[0048] Abnormal control module: When the UAV is in a high-accuracy positioning, the UAV continues to perform the mission according to the predetermined flight path; when the UAV is in a low-accuracy positioning, the accuracy of the UAV positioning within a fixed time period is analyzed to determine whether to return early.

[0049] When the drone is in a high-accuracy positioning state, it means that the location information provided by its navigation system meets the mission requirements, and the drone can continue to perform the mission according to the predetermined flight path. Thanks to high-precision positioning, the drone can accurately track the flight path, avoid obstacles, and maintain a stable flight state in complex environments. In this case, the system can run various tasks at full speed, such as inspection, mapping, or logistics distribution, to ensure the efficiency and accuracy of the tasks and maximize the performance advantages of the drone.

[0050] When the UAV is in a state of low accuracy positioning, that is, the accuracy value of the UAV positioning generated within a fixed time period is less than the reference threshold of the accuracy value of the UAV positioning set in advance, the degree of abnormality of the accuracy of the UAV positioning in the subsequent fixed time period is analyzed, and the accuracy values ​​of the UAV positioning generated within the subsequent fixed time period that are less than the reference threshold of the accuracy value are collected, and a data set is established, and the mean and standard deviation of the data set are calculated. After analysis, the degree of abnormality of the accuracy of the UAV positioning is determined, and it is determined whether to return early.

[0051] If the mean accuracy value in the data set is greater than or equal to the reference threshold of the mean accuracy value, and the standard deviation of the accuracy value is less than the reference threshold of the standard deviation of the accuracy value, the accuracy level is high and the fluctuation is small. Although there was a problem with positioning, the stability has improved in the subsequent time period and there is no need to return. At this time, no warning signal is generated, and the mission continues to be performed, while the positioning situation is continuously monitored;

[0052] If the mean accuracy value is greater than or equal to the reference threshold of the mean accuracy value, and the standard deviation of the accuracy value is greater than or equal to the reference threshold of the standard deviation of the accuracy value, although the accuracy level is high, the positioning fluctuation is large, and there may be intermittent or unstable interference. You need to be vigilant. At this time, a level 3 warning signal is generated. Consider slowing down the flight and closely monitoring the positioning status. If the fluctuation intensifies, you may need to return;

[0053] If the mean accuracy value is less than the reference threshold of the mean accuracy value, and the standard deviation of the accuracy value is greater than or equal to the reference threshold of the standard deviation of the accuracy value, the accuracy level is low and fluctuates greatly, the positioning system may be seriously disturbed, and the stability is insufficient. At this time, a first-level warning signal is generated, and preparations are made to return in advance to ensure the safety of the drone;

[0054] If the mean accuracy value is less than the reference threshold of the mean accuracy value, and the standard deviation of the accuracy value is less than the reference threshold of the standard deviation of the accuracy value, the accuracy level is low but the fluctuation is small, and there may be continuous deviations in positioning, which may be difficult to correct. At this time, a second-level warning signal is generated, and it is recommended to return home in advance to prevent the accumulation of positioning errors from causing loss of flight control.

[0055] It should be noted here that the importance of the first-level warning signal is greater than that of the second-level warning signal, and the importance of the second-level warning signal is greater than that of the third-level warning signal. According to the levels of different warning signals, the system will automatically or prompt the operator to decide whether to return immediately or take other safety measures to ensure the safe flight of the drone in a low-accuracy positioning state.

[0056] In this embodiment, the precise positioning and flight control of the UAV in a complex environment are achieved through the collaborative work of multiple modules. First, the signal receiving module uses a GPS receiver to receive the same satellite signal from multiple paths in real time, and separates the direct path signal through a multipath delay locked loop algorithm. Then, the positioning stability evaluation module evaluates the positioning stability of the UAV by analyzing the position residual fluctuations within a specific time period. Next, the positioning accuracy division module evaluates the positioning accuracy of the UAV based on time delay and positioning stability, and divides it into high-accuracy positioning and low-accuracy positioning. Finally, the abnormal control module determines the operation of the UAV based on the positioning accuracy: continue the mission execution under high-accuracy positioning; under low-accuracy positioning, analyze the positioning abnormality, and determine whether to return early according to the situation to ensure flight safety.

[0057] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0058] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0059] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0060] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0061] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0062] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0063] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0064] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A sensor-based drone real-time monitoring and control system, characterized by: It includes a signal receiving module, a positioning stability evaluation module, a positioning accuracy classification module and an abnormality control module; Signal receiving module: uses GPS receiver to receive multiple satellite signals from different paths in real time, estimates the time delay of each signal through multipath delay locked loop algorithm, and separates direct path signal from multipath signal; The signal receiving module specifically includes: analyzing the rapid increase of pseudo-range error in a short time according to the cumulative delay of the multi-path signal, and judging the positioning accuracy in the current environment, wherein the pseudo-range error growth rate abnormality index is generated according to the time delay data of the multi-path signal, and the method for obtaining the pseudo-range error growth rate abnormality index is: Obtain time-dependent pseudorange error data And the corresponding timestamp ; Calculate the pseudorange error growth rate for each time interval. The expression is: ; Forming a growth rate series ; Establish a Gaussian process model and determine the kernel function of the Gaussian process model , ;in, is the variance of the signal, is the length scale, and the pseudorange error growth rate is substituted into the Gaussian process model , ; where m(t) is the mean function; using the time series and pseudorange error growth rate data Train the Gaussian process model according to the kernel function Calculate the covariance matrix K and obtain the prior distribution of the Gaussian process, ;in, is the noise variance, is the identity matrix, given a new time point , calculate the corresponding growth rate forecast distribution , the expression is: ;in, is the predicted mean growth rate, indicating the The expected growth rate at is calculated as: ; is the forecast variance of the growth rate, indicating the uncertainty of the forecast growth rate, and the calculation expression is: ; is the matrix transpose; the predicted pseudorange error growth rate is Compared with the mean and variance of the predicted distribution, the pseudorange error growth rate anomaly index is calculated, and the expression is: ; In the formula, is the pseudorange error growth rate anomaly index; Positioning stability evaluation module: For multipath signals, by comparing the GPS position data at consecutive time points within the S time period, the position residual fluctuation of the UAV positioning is analyzed to evaluate the stability of the UAV positioning; The positioning stability evaluation module specifically includes: analyzing the residual fluctuation of the position of the UAV positioning to generate a residual fluctuation index, and evaluating the stability of the UAV positioning according to the residual fluctuation index, wherein the residual fluctuation index is obtained by: Obtain the GPS positioning data of the drone in the time period S, including the latitude and longitude of consecutive time points, compare the actual measured position with the expected position, and obtain the positioning residual at each time point. The expression is: ;in, For time point The measurement position, is the expected position, Represents the Euclidean distance of the position error; calculates the residual fluctuation amplitude of all residuals in the time period S , the expression is: ;in, is the average value of the residual, n is the number of time points in the time period S, and the average change rate AD of the residual in the time period S is calculated. The expression is: ; Calculate the residual volatility index, the expression is: ; In the formula, is the residual volatility index; Positioning accuracy classification module: According to the time delay state of multipath signals and the stability of UAV positioning, the accuracy of UAV positioning is evaluated and divided into high-accuracy positioning and low-accuracy positioning; The positioning accuracy division module specifically includes: converting the pseudorange error growth rate anomaly index and the residual fluctuation index into a first eigenvector, taking the first eigenvector as the input of the machine learning model, the machine learning model uses each group of first eigenvectors to predict the accuracy value label of the UAV positioning as the prediction target, and minimizing the sum of the prediction errors of the accuracy value labels of all UAV positioning as the training target, training the machine learning model until the sum of the prediction errors reaches convergence, stopping the model training, and determining the accuracy value of the UAV positioning according to the model output result, wherein the machine learning model is a polynomial regression model; The acquired accuracy value of the drone positioning is compared with the preset reference threshold of the drone positioning accuracy value. If the accuracy value of the drone positioning is greater than or equal to the preset reference threshold of the drone positioning accuracy value, it means that the accuracy of the drone positioning is high, and an accurate positioning signal is generated at this time; when the accurate positioning signal is generated, the system continues the normal flight operation; if the accuracy value of the drone positioning is less than the preset reference threshold of the drone positioning accuracy value, it means that the accuracy of the drone positioning is low, and an inaccurate positioning signal is generated at this time; inaccurate positioning signal: when an inaccurate positioning signal is generated, the system takes preventive measures; Abnormal control module: When the UAV is in a high-accuracy positioning, the UAV continues to perform the mission according to the predetermined flight path; when the UAV is in a low-accuracy positioning, the accuracy of the UAV positioning within a fixed time period is analyzed to determine whether to return early.

2. A sensor-based drone real-time monitoring and control system according to claim 1, characterized in that: In the signal receiving module, the GPS receiver receives the signal from the same satellite, generates a local pseudo-random code that matches the received satellite signal, correlates the received signal with the locally generated pseudo-random code, and generates a correlation output. The traditional delay-locked loop estimates the arrival time of the signal by finding the peaks in the correlation output, and uses the multipath delay-locked loop algorithm to accurately analyze these peaks, and separates the direct path signal from the multipath signal based on the time delay estimated by the multipath delay-locked loop algorithm.

3. The sensor-based real-time monitoring and control system for unmanned aerial vehicles according to claim 1, characterized in that: In the abnormal control module, when the UAV is in a low-accuracy positioning state, that is, the accuracy value of the UAV positioning generated within a fixed time period is less than the preset reference threshold of the UAV positioning accuracy value, the degree of abnormality of the accuracy of the UAV positioning in the subsequent fixed time period is analyzed, and the accuracy values ​​of the UAV positioning generated within the subsequent fixed time period that are less than the reference threshold of the accuracy value are collected, and a data set is established, and the mean and standard deviation of the data set are calculated. After analysis, the degree of abnormality of the accuracy of the UAV positioning is determined, and it is determined whether to return early.

4. A sensor-based drone real-time monitoring and control system according to claim 3, characterized in that: If the mean accuracy value in the data set is greater than or equal to the reference threshold of the mean accuracy value, and the standard deviation of the accuracy value is less than the reference threshold of the standard deviation of the accuracy value, the accuracy level is high and the fluctuation is small, and there is no need to return. At this time, no warning signal is generated, and the mission continues to be performed, while the positioning situation is continuously monitored; If the mean accuracy value is greater than or equal to the reference threshold of the mean accuracy value, and the standard deviation of the accuracy value is greater than or equal to the reference threshold of the standard deviation of the accuracy value, although the accuracy level is high, the positioning fluctuation is large. At this time, a level 3 warning signal is generated, the flight is decelerated, and the positioning status is closely monitored; If the mean accuracy value is less than the reference threshold of the mean accuracy value, and the standard deviation of the accuracy value is greater than or equal to the reference threshold of the standard deviation of the accuracy value, the accuracy level is low and fluctuates greatly, and the positioning system is seriously disturbed. At this time, a first-level warning signal is generated, and preparations are made to return in advance to ensure the safety of the drone; If the mean accuracy value is less than the reference threshold of the mean accuracy value, and the standard deviation of the accuracy value is less than the reference threshold of the standard deviation of the accuracy value, the accuracy level is low but the fluctuation is small, and there is a continuous deviation in positioning. At this time, a level 2 warning signal is generated, and it is recommended to return home in advance to prevent the accumulation of positioning errors from causing loss of flight control.

Images