Data processing method and system based on unmanned aerial vehicle airspace monitoring

Abstract

The application discloses a data processing method and system based on unmanned aerial vehicle airspace monitoring, and the method comprises the following steps: acquiring real-time motion parameter data and a time stamp of each unmanned aerial vehicle and an aircraft in a group of unmanned aerial vehicles; performing data point equidistant sampling operation according to the motion parameter data and the time stamp to obtain a time series data set; performing data cleaning operation according to the time series data set to obtain screening data; performing normalization operation according to the screening data to obtain normalized data; performing relative collision risk calculation according to the normalized data to obtain relative collision risk data; performing path planning matrix construction operation according to the relative collision risk data and the time series data set to obtain risk target point set data; and performing conflict-free screening operation according to the risk target point set data to obtain a target point. The method can reduce the collision risk of unmanned aerial vehicles.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) control technology, and in particular to a data processing method and system based on UAV airspace monitoring. Background Technology

[0002] Currently, drones refer to unmanned aerial vehicles controlled by radio remote control equipment or their own program control devices. They are a type of aircraft, but differ from spacecraft in that spacecraft typically fly at high altitudes outside the atmosphere, while drones fly near the ground and are commonly used in military, entertainment, surveying, and other fields. The flight airspace of a drone refers to the spatial range within which the drone operates according to its flight plan and mission. Existing drone flights still face significant collision risks, especially with the continuous expansion of civilian drone applications. Unsafe incidents involving drones and other aircraft, such as manned aircraft, are gradually increasing, and the collision risk between them is becoming increasingly significant. To improve the safety of drone flights, airspace monitoring and data processing and analysis are particularly important.

[0003] In one existing technology, historical collision data is divided into training and validation data, trained using a neural network model to obtain a predictive classification model, which then predicts the flight collision risk of civilian drones based on data characteristics. Current application scenarios have high requirements for real-time collision risk detection for drones; however, existing technologies do not address the detection and analysis of real-time drone data, thus failing to effectively reduce collision risks during real-time drone flight. Summary of the Invention

[0004] This invention provides a data processing method and system based on UAV airspace monitoring to reduce the risk of collisions during UAV flight.

[0005] Firstly, in order to solve the above-mentioned technical problems, the present invention provides a data processing method based on UAV airspace monitoring, comprising:

[0006] Acquire real-time motion parameter data and timestamps for each drone and aircraft in the drone swarm;

[0007] Based on the motion parameter data and the timestamp, perform equidistant sampling of data points to obtain a time series dataset;

[0008] Based on the time series dataset, data cleaning operations are performed to obtain filtered data;

[0009] Based on the filtered data, a normalization operation is performed to obtain normalized data;

[0010] Based on the normalized data, relative collision risk is calculated to obtain relative collision risk data;

[0011] Based on the relative collision risk data and the time series dataset, a path planning matrix construction operation is performed to obtain a set of risk target points.

[0012] Based on the set of risk target points, a conflict-free screening operation is performed to obtain the target points.

[0013] In one optional implementation, based on the motion parameter data and the timestamp, a data point sampling operation with equal intervals is performed to obtain a time series dataset, including:

[0014] The motion parameter data includes position, velocity, and acceleration;

[0015] The time series dataset is constructed as follows:

[0016] X = {X0, X1, X2, ..., X} t ,…,X T}

[0017] Among them, X t It is a multidimensional dataset at time t; T represents the number of time series samples collected.

[0018] Each X t This can be further expressed as:

[0019] X t =[u1(t) u2(t) … u M (t) a1(t) a2(t) … a N (t)] T

[0020] Among them, u i (t) represents the motion parameter data of the i-th UAV at time t, a j (t) represents the motion parameter data of the j-th aircraft at time t, M is the total number of UAVs in the swarm, and N is the total number of aircraft.

[0021] In one optional implementation, data cleaning is performed on the time series dataset to obtain filtered data, including:

[0022] Based on the time series dataset, a data segment selection operation is performed to obtain time segment data;

[0023] Based on the time segment data, a clustering operation is performed to obtain time clustered data;

[0024] Based on the time clustering data, a Laida detection operation is performed to obtain filtered data.

[0025] In one optional implementation, a Laida detection operation is performed based on the time clustering data to obtain filtered data, including:

[0026] Based on the time clustering data, the residual error is calculated to obtain the residual error;

[0027] Based on the time clustering data, the standard deviation is calculated to obtain the standard deviation.

[0028] Based on the remaining error and the standard deviation, when the absolute value of the remaining error is greater than three times the standard deviation, a deletion operation is performed to obtain filtered data;

[0029] The formula for calculating the residual error is as follows:

[0030]

[0031] Among them, v i x represents the residual error of the i-th data point; i This represents the value of the i-th data point; Represents the arithmetic mean;

[0032] The formula for calculating the standard deviation is as follows:

[0033]

[0034] Where σ represents the standard deviation; x i This represents the value of the i-th data point; represents the arithmetic mean; n represents the total number of data points.

[0035] In one optional implementation, a normalization operation is performed on the filtered data to obtain normalized data, including:

[0036] Based on the filtered data, feature selection is performed to obtain similar feature data;

[0037] Based on the aforementioned similar feature data, feature normalization is performed to obtain normalized data;

[0038] The calculation formula for the feature normalization operation is as follows:

[0039] X nnnn,k =norm(X) k )

[0040] Among them, X k This is the characteristic data of the drone swarm at time k, where norm(·) is the normalization function, and X... nnnn,k This represents the normalized data of the drone swarm at time k.

[0041] In one optional implementation, relative collision risk calculation is performed based on the normalized data to obtain relative collision risk data, including:

[0042] Based on the normalized data, the distance between the UAV and the aircraft is calculated to obtain distance data;

[0043] Based on the normalized data and the distance data, the relative collision risk is calculated to obtain the relative collision risk data;

[0044] The formula for calculating relative collision risk is as follows:

[0045]

[0046] Among them, R ik d represents the relative collision risk value between the i-th drone and the k-th aircraft; ik Represents the distance between the i-th drone and the k-th aircraft; |u i | represents the magnitude of the acceleration vector of the i-th UAV; |a k | represents the magnitude of the acceleration vector of the k-th aircraft.

[0047] In one optional implementation, a path planning matrix construction operation is performed based on the relative collision risk data and the time series dataset to obtain a set of risk target points, including:

[0048] Based on the time series dataset, the drone's location information is extracted to obtain the drone's real-time location data;

[0049] Based on the real-time location data of the UAV, path planning is performed to obtain the target point set data;

[0050] Based on the target point set data and the relative collision risk data, a risk information embedding operation is performed to obtain the risk target point set data;

[0051] The set of risk target points is as follows:

[0052] P i ={p1,p2,…p j ,…,p m}

[0053] Among them, P i p represents the set of risk target points for the i-th drone; j This represents the location data of the risk information embedded in the j-th target point; m represents the number of elements in the risk target point set.

[0054] In one optional implementation, a conflict-free screening operation is performed based on the risk target point set data to obtain target points, including:

[0055] Based on the set of risk target points data, a comprehensive information assessment is performed to obtain a comprehensive information assessment value;

[0056] Based on all the comprehensive information evaluation values, the risk target point set data is sorted from smallest to largest to obtain an ordered target point set data.

[0057] Based on the ordered target point set data, the ordered target points are selected sequentially as the initial target points;

[0058] If a radius threshold is set, and other drones are found within the radius of the initial target point, the initial target point is determined as a drone collision point and discarded; if no other drones are found within the radius of the initial target point, the initial target point is determined as the target point.

[0059] The comprehensive information assessment calculation formula is as follows:

[0060]

[0061] Among them, V i Represents the comprehensive information evaluation value of the i-th UAV; N represents the total number of aircraft; R ik d represents the relative collision risk value between the i-th drone and the k-th aircraft; ik This represents the distance between the i-th drone and the k-th aircraft.

[0062] Secondly, the present invention provides a data processing system based on UAV airspace monitoring, comprising:

[0063] The input module is used to obtain real-time motion parameter data and timestamps for each drone and aircraft in the drone swarm.

[0064] The sampling module is used to perform equidistant sampling of data points based on the motion parameter data and the timestamp to obtain a time series dataset;

[0065] The filtering module is used to perform data cleaning operations based on the time series dataset to obtain filtered data;

[0066] The normalization module is used to perform a normalization operation on the filtered data to obtain normalized data;

[0067] The risk assessment module is used to calculate the relative collision risk based on the normalized data to obtain the relative collision risk data.

[0068] The target point construction module is used to perform a path planning matrix construction operation based on the relative collision risk data and the time series dataset to obtain a set of risk target points.

[0069] The output module is used to perform a conflict-free filtering operation based on the risk target point set data to obtain the target points.

[0070] Thirdly, the present invention also provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor executes the computer program to implement the data processing method based on UAV airspace monitoring as described in any one of the above.

[0071] Compared with the prior art, the present invention has the following beneficial effects:

[0072] This invention provides a data processing method based on UAV airspace monitoring, characterized by comprising: acquiring real-time motion parameter data and timestamps of each UAV and aircraft in a UAV swarm; performing equidistant sampling of data points based on the motion parameter data and the timestamps to obtain a time-series dataset; performing data cleaning based on the time-series dataset to obtain filtered data; performing normalization based on the filtered data to obtain normalized data; calculating relative collision risk based on the normalized data to obtain relative collision risk data; constructing a path planning matrix based on the relative collision risk data and the time-series dataset to obtain a set of risk target points; and performing a conflict-free filtering operation based on the set of risk target points to obtain target points. This invention, by conducting real-time risk assessment during UAV flight and embedding risk information into path points, and finally performing a conflict-free filtering operation to obtain target points, can reduce the risk of UAV flight collisions. Attached Figure Description

[0073] Figure 1 This is a schematic flowchart of a data processing method based on UAV airspace monitoring provided in an embodiment of the present invention;

[0074] Figure 2 This is a schematic diagram of the system structure for data processing based on UAV airspace monitoring provided in an embodiment of the present invention. Detailed Implementation

[0075] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0076] Reference Figure 1This invention provides a data processing method based on UAV airspace monitoring, comprising the following steps:

[0077] S11, acquire real-time motion parameter data and timestamps for each drone and aircraft in the drone swarm;

[0078] S12, based on the motion parameter data and the timestamp, perform an equal-interval sampling operation on data points to obtain a time series dataset;

[0079] S13, Perform data cleaning operations based on the time series dataset to obtain filtered data;

[0080] S14, Perform a normalization operation on the filtered data to obtain normalized data;

[0081] S15, perform relative collision risk calculation based on the normalized data to obtain relative collision risk data;

[0082] S16, Based on the relative collision risk data and the time series dataset, perform a path planning matrix construction operation to obtain a set of risk target points;

[0083] S17. Based on the risk target point set data, perform a conflict-free screening operation to obtain the target points.

[0084] In step S11, it should be noted that real-time motion parameter data refers to information such as the position, velocity, and acceleration of the UAV and aircraft at a specific moment. These parameters are crucial for understanding and predicting the motion state of these aircraft. A timestamp, on the other hand, refers to the specific point in time corresponding to these motion parameter data, expressed in date and time format, used to identify the precise moment the data was recorded. The process of acquiring these features involves sensor data acquisition and time synchronization technology. Sensors equipped on UAVs and aircraft, including GPS, accelerometers, and gyroscopes, can monitor and record parameters such as the aircraft's position and velocity in real time. This sensor data is processed by the aircraft's internal system and stored or transmitted along with the current timestamp. The acquisition of the timestamp relies on the aircraft's internal clock or an external time synchronization signal, such as GPS time, to ensure accuracy and consistency. The operation of these real-time motion parameter data and timestamps involves real-time data acquisition, processing, and storage. The aircraft's control system continuously reads data from the sensors and, combined with the timestamp information, packages this data into data frames or data packets, which are then transmitted to the ground control station or data processing center via a wireless communication link. At the data processing center, this data is further analyzed and processed to monitor the aircraft's status, predict potential conflicts, and optimize flight paths. In subsequent applications, this timestamped real-time motion parameter data can be used for various operations, including path planning and conflict avoidance in drone swarms. This data can be used to predict future positions and speeds, thereby calculating potential conflict points and planning conflict-avoiding paths in advance. Furthermore, this data can be used for flight performance analysis, flight safety monitoring, and flight log recording and review. In-depth analysis of this data can improve the operational efficiency and safety of drone swarms.

[0085] In step S12, based on the motion parameter data and the timestamp, a data point sampling operation with equal intervals is performed to obtain a time series dataset, including:

[0086] The motion parameter data includes position, velocity, and acceleration;

[0087] The time series dataset is constructed as follows:

[0088] X = {X0, X1, X2, ..., X} t ,…,X T}

[0089] Among them, X t It is a multidimensional dataset at time t; T represents the number of time series samples collected.

[0090] Each X t This can be further expressed as:

[0091] X t =[u1(t) u2(t) …u i (t) … u M (t) a1(t) a2(t) …a j (t) … a N (t)] T

[0092] Among them, u i (t) represents the motion parameter data of the i-th UAV at time t, a j (t) represents the motion parameter data of the j-th aircraft at time t, M is the total number of UAVs in the swarm, and N is the total number of aircraft.

[0093] It should be noted that the motion parameter data in step S12 encompasses the position, velocity, and acceleration of the UAV and aircraft. These parameters are key information describing the dynamic characteristics of the aircraft, collected in real time by sensors on the aircraft, and recorded and stored along with corresponding timestamps through the aircraft's data processing system. A timestamp is a specific point in time corresponding to the motion parameter data, used to identify the collection time of each data point, ensuring the timeliness and traceability of the data. The construction of the time-series dataset is achieved through an equally spaced sampling operation of data points. This operation involves arranging the collected discrete motion parameter data in chronological order to form a continuous time series. The time-series dataset X is represented as X = X0, X1, X2, ..., X... t ,…,X T , where X t This is a multidimensional dataset at time t, where T represents the number of time series samples collected. This representation allows the dataset to reflect its dynamic characteristics over time, providing a foundation for subsequent data analysis and processing. Each X_t can be further represented as a vector containing the motion parameters of the UAV and aircraft, specifically X... i =[u1(t),u2(t),…,u M (t), a1(t), a2(t), ..., a N (t)] T , where u i (t) represents the motion parameter data of the i-th UAV at time t, a j (t) represents the motion parameter data of the j-th aircraft at time t, M is the total number of UAVs in the swarm, and N is the total number of aircraft. This representation makes the dataset X at each time point t... tThese systems can provide complete motion status information for UAV swarms and aircraft. The acquisition and construction of these features are achieved through the collaborative work of the aircraft's sensor system, data acquisition system, and data processing system. The sensor system is responsible for collecting the aircraft's position, velocity, and acceleration data in real time; the data acquisition system is responsible for recording and storing this data along with corresponding timestamps; and the data processing system is responsible for organizing and analyzing this data in chronological order to form a time-series dataset. In subsequent applications, these features and the constructed time-series dataset can be used for various operations, including aircraft trajectory analysis, motion status prediction, flight safety monitoring, flight path planning, and conflict avoidance. In-depth analysis of the time-series dataset can improve aircraft operational efficiency and safety, optimize flight plans, reduce flight risks, and provide data support for aircraft maintenance and upgrades.

[0094] In step S13, data cleaning is performed on the time series dataset to obtain filtered data, including:

[0095] Based on the time series dataset, a data segment selection operation is performed to obtain time segment data;

[0096] Based on the time segment data, a clustering operation is performed to obtain time clustered data;

[0097] Based on the time clustering data, a Laida detection operation is performed to obtain filtered data.

[0098] The Laida detection operation is performed based on the time clustering data to obtain filtered data, including:

[0099] Based on the time clustering data, the residual error is calculated to obtain the residual error;

[0100] Based on the time clustering data, the standard deviation is calculated to obtain the standard deviation.

[0101] Based on the remaining error and the standard deviation, when the absolute value of the remaining error is greater than three times the standard deviation, a deletion operation is performed to obtain filtered data;

[0102] The formula for calculating the residual error is as follows:

[0103]

[0104] Among them, v i x represents the residual error of the u-th data point; i This represents the value of the i-th data point; Represents the arithmetic mean;

[0105] The formula for calculating the standard deviation is as follows:

[0106]

[0107] Where σ represents the standard deviation; x i This represents the value of the i-th data point; represents the arithmetic mean; n represents the total number of data points.

[0108] It should be noted that in step S13, the time series dataset is a collection of timestamps and corresponding motion parameter data, obtained from the original data through equal-interval sampling, and contains the position, velocity, and acceleration information of the UAV and aircraft at consecutive time points. Time segment data is a subset obtained by selecting data from the time series dataset for a specific time period; it represents the aircraft's motion state within a specific time window. For example, the time segment selected in this invention consists of five adjacent time points. Of course, depending on different user needs or application scenarios, time segments of other lengths can be selected, and this invention does not limit this. Clustering is the process of grouping time segment data. Using the k-means clustering algorithm, similar data points are grouped into one category, forming time clustered data. The Laida detection operation is a statistical method used to identify and handle outliers. In this process, the residual error is first calculated, which represents the deviation of each data point from the arithmetic mean of the dataset. The calculation formula is... Where v i Let x represent the residual error of the i-th data point. i This represents the value of the i-th data point. This represents the arithmetic mean. Next, we calculate the standard deviation, a statistic that measures the dispersion of the data. The formula is: Where σ represents the standard deviation, x i This represents the value of the i-th data point. The table shows the arithmetic mean, where n represents the total number of data points. The standard deviation quantifies the degree of deviation of a data point from the mean. After obtaining the residual error and standard deviation, by comparing the absolute value of the residual error for each data point with three times the standard deviation, it can be determined whether a data point is an outlier. If the absolute value of the residual error for a data point is greater than three times the standard deviation, the data point is considered outlier and is deleted, resulting in filtered data. Filtered data is a clean dataset obtained after data cleaning, eliminating outliers and improving data quality and reliability. This filtered data can be used for subsequent data analysis, model training, and decision support, ensuring the accuracy and effectiveness of the analysis results. This method effectively identifies and removes outliers from time-series datasets, providing more accurate and reliable data processing results for UAV airspace monitoring.

[0109] In step S14, a normalization operation is performed on the filtered data to obtain normalized data, including:

[0110] Based on the filtered data, feature selection is performed to obtain similar feature data;

[0111] Based on the aforementioned similar feature data, feature normalization is performed to obtain normalized data;

[0112] The calculation formula for the feature normalization operation is as follows:

[0113] X nnnn,k =norm(X) k )

[0114] Among them, X k This is the characteristic data of the drone swarm at time k, norm(X) k ) is the normalization function, X nnnn,k This represents the normalized data of the drone swarm at time k.

[0115] It should be noted that in step S14, the filtered data refers to the dataset after data cleaning, in which outliers have been removed. This data forms the basis for subsequent analysis and processing. Similar feature data refers to data with the same attributes or types in the filtered data, such as the location data of all drones or the speed data of all aircraft. Feature selection is the process of extracting similar feature data from the filtered data. This step aims to simplify the data structure and facilitate subsequent processing. Feature normalization scales the similar feature data to make it fall within the range of [-1, 1], eliminating the influence of different dimensions between features and improving the convergence speed and accuracy of the algorithm. The normalization calculation formula is X. nnnk =norm(X) k ), where X k This is the characteristic data of the drone swarm at time k, where norm(·) is the normalization function, and X... nnnk This represents the normalized data of the drone swarm at time k. Different algorithms can be used for the normalization function; in this invention, the min-max normalization method is chosen. However, depending on user needs or application scenarios, other normalization methods, such as Z-score normalization, can be selected, and this invention does not limit this choice. The normalization operation involves applying a normalization function to each similar feature data point, transforming the original data into data of a uniform scale. This process can be implemented programmatically. The normalized data can be used for subsequent statistical analysis because all features have the same scale; normalized data can improve the performance and accuracy of these methods. Furthermore, normalized data also helps to more intuitively compare the relationships between different features during data visualization.

[0116] In step S15, relative collision risk is calculated based on the normalized data to obtain relative collision risk data, including:

[0117] Based on the normalized data, the distance between the UAV and the aircraft is calculated to obtain distance data;

[0118] Based on the normalized data and the distance data, the relative collision risk is calculated to obtain the relative collision risk data;

[0119] The formula for calculating relative collision risk is as follows:

[0120]

[0121] Among them, R ik d represents the relative collision risk value between the i-th drone and the k-th aircraft; ik Represents the distance between the i-th drone and the k-th aircraft; |u i | represents the magnitude of the acceleration vector of the i-th UAV; |a k | represents the magnitude of the acceleration vector of the k-th aircraft.

[0122] It should be noted that in step S15, the normalized data is a dataset that has undergone normalization, containing the position, velocity, and acceleration information of the drone and aircraft at various times. This data has been scaled to a uniform scale. Distance data is obtained by calculating the distance between the drone and aircraft, a calculation based on the position information in the normalized data. Specifically, the Euclidean distance formula can be used to calculate the straight-line distance between the two objects, i.e. Where x i ,y i ,z i The coordinates of the i-th drone are (x) k ,y k ,z k () represents the position coordinates of the k-th aircraft. Relative collision risk data is calculated based on normalized and distance data, quantifying the probability of a collision between the UAV and an aircraft. The formula for calculating relative collision risk is: Where R k d represents the relative collision risk value between the i-th drone and the k-th aircraft. k It is the numerical distance between the two, |u i | is the magnitude of the acceleration vector of the i-th UAV, |a k | is the magnitude of the acceleration vector of the k-th aircraft. The magnitude of the acceleration vector can be obtained by calculating the Euclidean norm of the acceleration vector, i.e. and Where u i ,u i ,u i a is the acceleration component of the i-th drone. i ,a i ,a i This represents the acceleration component of the k-th aircraft. These calculations are implemented through programming; corresponding functions can be defined in data processing software or programming languages ​​and applied to the normalized dataset. Relative collision risk data can be used as a basis for flight safety monitoring and path planning, helping to identify potential collision risks and take preventative measures. In practical applications, this data can be used to adjust the flight paths of drones and aircraft to avoid high-risk approach situations and ensure flight safety.

[0123] In step S16, based on the relative collision risk data and the time series dataset, a path planning matrix construction operation is performed to obtain a set of risk target points, including:

[0124] Based on the time series dataset, the drone's location information is extracted to obtain the drone's real-time location data;

[0125] Based on the real-time location data of the UAV, path planning is performed to obtain the target point set data;

[0126] Based on the target point set data and the relative collision risk data, a risk information embedding operation is performed to obtain the risk target point set data;

[0127] The set of risk target points is as follows:

[0128] P i ={p1,p2,…p j ,…,p m}

[0129] Among them, P i p represents the set of risk target points for the i-th drone; j This represents the location data of the risk information embedded in the j-th target point; m represents the number of elements in the risk target point set.

[0130] It should be noted that in step S16, the relative collision risk data is calculated based on the distance and acceleration vector magnitude between the UAV and the aircraft, quantifying the potential collision risk. The time-series dataset contains the position, velocity, and acceleration information of the UAV and aircraft at continuous time points. This information is obtained through real-time acquisition by sensors and sampling at equal intervals. The UAV's real-time position data is extracted from the time-series dataset, reflecting the UAV's spatial position at a specific time point. Path planning is performed based on the UAV's real-time position data, aiming to plan a path from the UAV's current position to the target position, obtaining a set of target points, which includes key location points that the UAV needs to pass through during flight. The risk information embedding operation is the process of combining the relative collision risk data with the target point set data, aiming to label the collision risk level associated with each target point, forming a risk target point set data. Risk target point set data P i ={p1,p2,…,p j ,…,p m} represents the set of risk target points for the i-th drone, where p j Let represent the location data of the j-th target point with embedded risk information, and m represent the number of elements in the risk target point set. This risk target point set data can be used as a basis for UAV flight path planning and decision support, helping UAV operators and automatic control systems identify high-risk areas and take corresponding avoidance measures. In practical applications, this data can be used to dynamically adjust flight paths, avoid high-risk areas, and ensure flight safety.

[0131] In step S17, a conflict-free screening operation is performed based on the risk target point set data to obtain target points, including:

[0132] Based on the set of risk target points data, a comprehensive information assessment is performed to obtain a comprehensive information assessment value;

[0133] Based on all the comprehensive information evaluation values, the risk target point set data is sorted from smallest to largest to obtain an ordered target point set data.

[0134] Based on the ordered target point set data, the ordered target points are selected sequentially as the initial target points;

[0135] If a radius threshold is set, and other drones are found within the radius of the initial target point, the initial target point is determined as a drone collision point and discarded; if no other drones are found within the radius of the initial target point, the initial target point is determined as the target point.

[0136] The comprehensive information assessment calculation formula is as follows:

[0137]

[0138] Among them, V i Represents the comprehensive information evaluation value of the i-th UAV; N represents the total number of aircraft; R ik d represents the relative collision risk value between the i-th drone and the k-th aircraft; ik This represents the distance between the i-th drone and the k-th aircraft.

[0139] It should be noted that in step S17, the risk target point set data is constructed based on the positions of the UAV and aircraft, their relative collision risk values, and the distance values ​​between them, with each target point embedding corresponding risk information. The comprehensive information assessment value V i It is achieved by calculating the relative collision risk R between the i-th drone and all aircraft. k and distance value d k The formula is obtained by weighted summation and averaging. Where N is the total number of aircraft. This assessment value comprehensively considers the relative collision risk and distance between UAVs and aircraft, providing a quantitative risk metric for each UAV. The ordered target point set data is obtained by sorting the risk target point set based on the comprehensive information assessment value. The sorting can be based on the magnitude of the comprehensive information assessment value, resulting in a target point set sorted by risk level. This ordered target point set data helps to prioritize the processing of target points with higher risks. UAV collision detection is performed based on the ordered target point set data, aiming to identify and eliminate target points that may lead to conflict. The UAV collision detection method used in this invention sets a radius threshold. When other UAVs are determined to be within the radius of a target point, the target point is identified as a UAV collision point and discarded. In this invention, a threshold radius of 50m is selected. Of course, other radius thresholds can be selected according to different user needs or application scenarios; this invention does not limit this. These operations are implemented through algorithms, and corresponding functions can be defined in a programming language and applied to the risk target point set data. The result of the conflict-free screening operation, i.e., the target points, can be used as the final output of UAV flight path planning, guiding the UAV to choose a safe flight path, avoid high-risk areas, and ensure flight safety.

[0140] To facilitate understanding of the present invention, some preferred embodiments of the present invention will be described in further detail below.

[0141] The method flow of this invention provides a comprehensive solution for a typical UAV airspace monitoring and path planning application scenario, from real-time data acquisition to final flight path decision. In this scenario, UAV swarms are used to perform a series of tasks, and ensuring their flight safety and avoiding conflicts with other aircraft is crucial.

[0142] Step 1: The input module collects real-time motion parameter data from the drone and aircraft, including position, velocity, and acceleration, as well as timestamps for recording this data. This data is acquired by sensors on the drone and aircraft and transmitted to a ground control station or data processing center. These sensors may include GPS modules, accelerometers, and gyroscopes, ensuring the accuracy and real-time nature of the data.

[0143] Step 2: The sampling module converts the acquired data into a time-series dataset. Through equally spaced sampling, a multidimensional dataset containing motion parameters at continuous time points is formed. This dataset provides the foundation for subsequent data analysis and processing. The construction of the time-series dataset enables us to comprehensively analyze the dynamic behavior of drones and aircraft, thereby better predicting their trajectories and potential conflict risks.

[0144] Step 3: Perform data cleaning operations, including data segment selection, clustering, and Laida detection to identify and remove outliers. Laida detection calculates the residual error and standard deviation of the data, removing data points with a residual error exceeding three times the standard deviation, thus obtaining filtered data. Data cleaning is a crucial step because it ensures that the data on which the analysis is based is of high quality and reliable, avoiding the impact of outliers on the analysis results.

[0145] Step 4: The filtering module normalizes the filtered data to eliminate the influence of different dimensions and improve data processing efficiency. Normalization uses a specific normalization function to scale the data to a uniform scale.

[0146] Step 5: The normalization module calculates the relative collision risk value between the UAV and the aircraft based on the normalized data. By calculating the distance and acceleration vector magnitudes, relative collision risk data is obtained, providing a quantitative risk assessment for flight safety. By calculating the relative distance and relative speed between the two, potential future collisions can be predicted, allowing for preventative measures to be taken.

[0147] Step 6: The target point construction module uses relative collision risk data and time-series datasets to construct a path planning matrix and extracts the UAV's real-time position data to plan the target point set data. Then, risk information is embedded into the target point set data to form a risk target point set data. The path planning matrix can employ dynamic programming or A* algorithms, combined with real-time updated collision risk data, to dynamically adjust the UAV's flight path and avoid potential collisions.

[0148] Step 7: The prediction module performs a comprehensive information assessment on the risk target point set data, calculates a comprehensive information assessment value for each UAV, and sorts the target point set based on this assessment value to obtain the comprehensive information assessment value. Through UAV conflict detection, conflict-free target points are filtered out, ensuring that the UAV's flight path avoids high-risk areas, thereby guaranteeing flight safety. The comprehensive information assessment value can be calculated based on multiple factors such as collision risk, path length, and flight time to ensure that the UAV selects the optimal path.

[0149] The entire process, through automated data processing and flight path planning, improves the operational efficiency and safety of drone swarms, reduces the need for human intervention, and adapts to constantly changing airspace conditions. This method allows drone swarms to optimize flight paths while adhering to airspace rules, reducing operating costs and increasing mission success rates. Applications of this process include, but are not limited to, urban logistics delivery, agricultural monitoring, air traffic management, and emergency response missions, providing strong technical support for the widespread application of drones.

[0150] In summary, this invention provides a data processing method based on UAV airspace monitoring, characterized by comprising: acquiring real-time motion parameter data and timestamps of each UAV and aircraft in a UAV swarm; performing equidistant sampling of data points based on the motion parameter data and the timestamps to obtain a time-series dataset; performing data cleaning based on the time-series dataset to obtain filtered data; performing normalization based on the filtered data to obtain normalized data; calculating relative collision risk based on the normalized data to obtain relative collision risk data; constructing a path planning matrix based on the relative collision risk data and the time-series dataset to obtain a set of risk target points; and performing a conflict-free filtering operation based on the set of risk target points to obtain target points. This invention reduces the risk of UAV collisions by conducting real-time risk assessment during UAV flight and embedding risk information into path points.

[0151] Reference Figure 2 This invention provides a data processing system based on UAV airspace monitoring, comprising:

[0152] The input module is used to obtain real-time motion parameter data and timestamps for each drone and aircraft in the drone swarm.

[0153] The sampling module is used to perform equidistant sampling of data points based on the motion parameter data and the timestamp to obtain a time series dataset;

[0154] The filtering module is used to perform data cleaning operations based on the time series dataset to obtain filtered data;

[0155] The normalization module is used to perform a normalization operation on the filtered data to obtain normalized data;

[0156] The risk assessment module is used to calculate the relative collision risk based on the normalized data to obtain the relative collision risk data.

[0157] The target point construction module is used to perform a path planning matrix construction operation based on the relative collision risk data and the time series dataset to obtain a set of risk target points.

[0158] The output module is used to perform a conflict-free filtering operation based on the risk target point set data to obtain the target points.

[0159] It should be noted that the data processing device based on UAV airspace monitoring provided in this embodiment of the invention is used to execute all the process steps of the data processing method based on UAV airspace monitoring in the above embodiment. The working principles and beneficial effects of the two are one-to-one, so they will not be described again.

[0160] This invention also provides an electronic device. The electronic device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps described in the above embodiments of the data processing method based on UAV airspace monitoring, for example... Figure 1 The step S11 shown. Alternatively, when the processor executes the computer program, it implements the functions of each module / unit in the above-described device embodiments.

[0161] For example, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0162] The electronic device may be a desktop computer, laptop, handheld computer, or smart tablet, etc. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above components are merely examples of electronic devices and do not constitute a limitation on the electronic device. It may include more or fewer components than described above, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0163] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the electronic device, connecting all parts of the electronic device via various interfaces and lines.

[0164] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0165] Wherein, if the modules / units integrated in the electronic device are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0166] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0167] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A data processing method based on unmanned aerial space monitoring, characterized in that, The method is executed by a computer and comprises: obtaining real-time motion parameter data and time stamps of each unmanned aerial vehicle and aircraft in a group of unmanned aerial vehicles; performing equidistant sampling on data points based on the motion parameter data and the time stamps to obtain a time series data set; performing data cleaning on the time series data set to obtain filtered data; performing normalization on the filtered data to obtain normalized data; performing relative collision risk calculation on the normalized data to obtain relative collision risk data; performing path planning matrix construction on the relative collision risk data and the time series data set to obtain risk target point set data; performing conflict-free filtering on the risk target point set data to obtain target points. The data cleaning on the time series data set to obtain filtered data comprises: performing data segment selection on the time series data set to obtain time segment data; performing clustering on the time segment data to obtain time clustering data; performing RAOB detection on the time clustering data to obtain filtered data. The RAOB detection on the time clustering data to obtain filtered data comprises: performing residual error calculation on the time clustering data to obtain a residual error; performing standard deviation calculation on the time clustering data to obtain a standard deviation; when the absolute value of the residual error is greater than three times the standard deviation, performing deletion to obtain filtered data. The conflict-free filtering on the risk target point set data to obtain target points comprises: performing comprehensive information evaluation on the risk target point set data to obtain comprehensive information evaluation values; sorting the risk target point set data in descending order of the comprehensive information evaluation values to obtain ordered target point set data; selecting ordered target points in sequence as initial target points; setting a radius threshold, and when there are other unmanned aerial vehicles within the radius range of the initial target point, determining the initial target point as a collision point of unmanned aerial vehicles and discarding the initial target point; when there are no other unmanned aerial vehicles within the radius range of the initial target point, determining the initial target point as a target point. The comprehensive information evaluation calculation formula is as follows: in, Indicates the first Comprehensive information assessment values ​​for each drone; Indicates the total number of aircraft; Indicates the first The drone and the first The relative collision risk values ​​between individual aircraft; Indicates the first The drone and the first The distance values ​​between the aircraft; Indicates the first The magnitude of the acceleration vector of a drone; Indicates the first The magnitude of the aircraft's acceleration vector; wherein the risk target point set data is constructed based on the positions of unmanned aerial vehicles and aircraft, relative collision risk values, and distance values between them, wherein each target point is embedded with corresponding risk information; the ordered target point set data is obtained by sorting the risk target point set based on the comprehensive information evaluation values, and the sorting basis can be the size of the comprehensive information evaluation values, thereby obtaining a target point set sorted according to risk levels. 2.The data processing method based on UAV airspace monitoring according to claim 1, characterized in that, The equidistant sampling on data points based on the motion parameter data and the time stamps to obtain a time series data set comprises: the motion parameter data comprises position, velocity, and acceleration; the time series data set is constructed as follows: wherein, is the time of the multi-dimensional data set; denotes the number of time series acquired; each may be further expressed as: in, It is the first A drone in time Motion parameter data, It is the first The aircraft in time Motion parameter data, It is the total number of drone swarms. It represents the total number of aircraft. 3.The data processing method based on UAV airspace monitoring according to claim 1, characterized in that, According to the screening data, normalization operation is performed to obtain normalized data, including: According to the screening data, feature selection is performed to obtain homogeneous feature data; According to the homogeneous feature data, feature normalization operation is performed to obtain normalized data; The calculation formula of the feature normalization operation is as follows: wherein, is the normalized data of the UAV group at time t, is a normalization function, denotes the normalized data of the UAV group at time t. 4.The method of claim 1, wherein, According to the normalized data, relative collision risk calculation is performed to obtain relative collision risk data, including: According to the normalized data, the distance between the unmanned aerial vehicle and the aircraft is calculated to obtain distance data; According to the normalized data and the distance data, relative collision risk calculation is performed to obtain relative collision risk data. 5.The data processing method based on UAV airspace monitoring according to claim 1, characterized in that, According to the relative collision risk data and the time series data set, path planning matrix construction operation is performed to obtain risk target point set data, including: According to the time series data set, unmanned aerial vehicle position information extraction is performed to obtain unmanned aerial vehicle real-time position data; According to the unmanned aerial vehicle real-time position data, path planning is performed to obtain target point set data; According to the target point set data and the relative collision risk data, risk information embedding operation is performed to obtain risk target point set data; The risk target point set data is as follows: wherein, represents the th unmanned aerial vehicle risk target point set; represents the th target point embedding risk information position data; represents the risk target point set element quantity. 6.A data processing system based on UAV airspace monitoring, used to implement the data processing method based on UAV airspace monitoring according to any one of claims 1 to 5. Including: An input module for obtaining real-time motion parameter data and time stamps of each unmanned aerial vehicle and aircraft in the unmanned aerial vehicle group; A sampling module for performing data point equidistant sampling operation according to the motion parameter data and the time stamps to obtain a time series data set; A screening module for performing data cleaning operation according to the time series data set to obtain screening data; A normalization module for performing normalization operation according to the screening data to obtain normalized data; A risk assessment module for performing relative collision risk calculation according to the normalized data to obtain relative collision risk data; A target point construction module for performing path planning matrix construction operation according to the relative collision risk data and the time series data set to obtain risk target point set data; An output module for performing conflict-free screening operation according to the risk target point set data to obtain target points.

7. An electronic device, comprising: A processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor executes the computer program to implement the data processing method based on unmanned aerial vehicle airspace monitoring according to any one of claims 1-5.

Images