Safety separation progressive decision tree-based unmanned aerial vehicle conflict prediction method

Abstract

Disclosed in the present invention is a safety separation progressive decision tree-based unmanned aerial vehicle conflict prediction method, comprising: establishing an unmanned aerial vehicle safety separation parameter library; establishing a coordinate transformation model parameter library for transforming a WGS-84 coordinate system or a GLONASS-PZ90 coordinate system to a CGCS2000 coordinate system, and encapsulating a constructed Bursa-Wolf model into a coordinate transformation function; parsing flight dynamics data and performing standardized transformation; performing airspace-based unmanned aerial vehicle conflict prediction, and classifying prediction results by conflict risk level into a monitoring dataset, a close-monitoring dataset, and a warning-alert dataset; and calculating the time for an unmanned aerial vehicle pair in the close-monitoring dataset to potentially reach a warning-alert level, and calculating the estimated time to collision for a conflicting unmanned aerial vehicle pair in the warning-alert dataset. The present invention can maximize space resource utilization in an airspace, thereby effectively increasing the air traffic flow within the airspace.

Description

A UAV Conflict Prediction Method Based on Safety Interval Asymptotic Decision Tree Technical Field

[0001] This invention belongs to the field of low-altitude aircraft flight management technology, specifically relating to a method for predicting UAV conflicts based on a progressive decision tree for safety intervals. Background Technology

[0002] Currently, the basic airspace classification method meticulously divides airspace into seven categories based on factors such as aircraft flight rules and performance requirements, airspace environment, and air traffic control services. Among them, Category W airspace (below 120 meters true altitude) is designated as suitable airspace for micro, light, and small unmanned aerial vehicles (UAVs). Against this backdrop, various cities have actively responded and formulated their own UAV flight management implementation measures, clearly stipulating that below 120 meters, except in prohibited airspace, no further flight plan application is required.

[0003] Currently, most low-altitude drone flight zones lack designated public airways, resulting in a lack of clear route planning and guidance for drones. This is especially true for non-commercial drone flights used by ordinary consumers for personal entertainment, photography, and video recording, often leading to uncontrolled flight patterns. This not only increases the risk of collisions with other aircraft but also poses challenges to airspace management. As drone flights continue to increase, these situations will become more frequent. Therefore, there is an urgent need for a method to effectively identify drone flight risks within airspace based on safe flight intervals. This method can identify potential conflicts in advance and proactively report these risks to government management departments, drone operators, or individual drone users, enabling relevant personnel to take early measures for risk management and handling, thereby effectively ensuring the safety of drone operations in low-altitude airspace. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention aims to provide a UAV conflict prediction method based on a progressive decision tree for safe flight distances, solving the problems of conflict identification and early warning during disorderly UAV flight in airspace. This invention establishes a UAV safe flight distance model and conflict risk levels based on the requirement that UAVs maintain appropriate safe distances. Through unified processing of UAV flight dynamic data, it determines the UAVs' position, speed, and altitude, and judges whether the distance between UAVs reaches the safe flight distance threshold for different conflict risk levels. This invention employs a progressive decision tree method to categorize potentially risky UAV pairs into three datasets: those to be observed, those requiring close monitoring, and those requiring alerts. It also predicts the collision time of UAV pairs in the alert dataset, enabling users to resolve critical conflicts in an orderly and timely manner according to different risk levels, effectively preventing UAV collisions.

[0005] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0006] The present invention provides a UAV conflict prediction method based on a safety interval progressive decision tree, comprising the following steps:

[0007] 1) Calculate the safe interval distance of the UAV based on its performance parameters and establish a safe interval parameter library for the UAV;

[0008] 2) Establish a coordinate transformation model parameter library for converting WGS-84 and GLONASS-PZ90 coordinate systems to CGCS2000 coordinate systems, and encapsulate the constructed Bursa model into coordinate transformation functions, defining the function calling method;

[0009] 3) Receive flight dynamic data sent by the UAV, parse the data and perform standardized transformation, and store the transformation results in the UAV flight dynamic database;

[0010] 4) An incremental decision tree classification method is used to predict airspace UAV conflicts, and the prediction results are divided into the observation dataset, the key attention dataset, and the alarm prompt dataset according to the conflict risk level.

[0011] 5) Calculate the time when drone pairs in the key focus dataset may reach the alarm level to prompt users to plan conflict resolution strategies in advance; calculate the expected collision time of conflicting drone pairs in the alarm alert dataset to prompt users to resolve the conflict.

[0012] Further, step 1) specifically includes:

[0013] 11) Establish a UAV performance parameter table, including the following parameters: UAV model, total thrust, angle of forward tilt in the vertical direction, UAV mass, maximum speed in the horizontal direction, and maximum speed in the vertical direction.

[0014] 12) Calculate the safe interval distance for the drone, including the following steps:

[0015] 121) Obtain the total thrust F of the UAV motor / rotor and the forward tilt angle Φ of the UAV motor / rotor with respect to the vertical direction from the UAV performance parameter table, and calculate the maximum horizontal thrust F of the UAV. h and the maximum thrust F in the vertical direction v The calculation formula is as follows; F v =F cosΦ; F h =F sinΦ;

[0016] 122) Obtain the mass M of the UAV from the UAV performance parameter table, and calculate the horizontal acceleration α of the UAV. h and the acceleration in the vertical direction α v The calculation formula is as follows: ɑ h =F h / M; ɑ v =MAX((F v -Mg) / M,g);

[0017] Where g is the acceleration due to gravity;

[0018] 123) Obtain the maximum horizontal speed of the UAV from the UAV performance parameter table. and maximum speed in the vertical direction Calculate the horizontal safety distance DI of the drone h and vertical safety interval DI v The calculation formula is as follows:

[0019] Among them, T eh and T ev These represent the redundancy times in the horizontal and vertical directions, respectively; N h and N v These are the safety interval configuration parameters for the horizontal and vertical directions, respectively.

[0020] 13) Establish a UAV safety interval parameter library, including: UAV model, UAV mass, horizontal safety interval and vertical safety interval; save the calculation results in step 12) in the UAV safety interval parameter library.

[0021] Further, step 2) specifically includes:

[0022] 21) Establish a coordinate transformation model parameter library, including the following parameters: original coordinate system type, new coordinate system type, applicable geographical area, translation parameters, rotation parameters, and scale parameters;

[0023] 22) Establish a coordinate transformation function and define the function call method;

[0024] 221) Construct the Bursa model, as follows:

[0025] Where ΔX, ΔY, and ΔZ are translation parameters, and m is a scale parameter. X1, Y1, Z1 are the original coordinates of the UAV's position in the WGS-84 or GLONASS-PZ90 coordinate system; X2, Y2, Z2 are the new coordinates of the UAV's position in the CGCS2000 coordinate system.

[0026] 222) Encapsulate the Bursa model from step 221) into a coordinate transformation function, and define the function call method for use during coordinate transformation calculation; the input parameters of the function are: original coordinate system type, new coordinate system type, and the specific position of the UAV in the original coordinate system X1, Y1, Z1; the output parameters of the function are: the specific position of the UAV in the new coordinate system X2, Y2, Z2.

[0027] 223) Use coordinate transformation functions to convert the WGS-84 or GLONASS-PZ90 coordinate system to the CGCS2000 coordinate system. The specific steps are as follows:

[0028] The function's input parameters, including the original coordinate system type, new coordinate system type, and the UAV's specific position (X1, Y1, Z1) in the original coordinate system, are compared with the three parameters (original coordinate system type, new coordinate system type, and applicable geographical area) in the coordinate transformation model parameter library to obtain the translation, rotation, and scale parameters. If the data record obtained from the coordinate transformation model parameter library is not unique, the coordinate transformation calculation is terminated, and an error is displayed to the user; otherwise, the coordinate transformation calculation continues.

[0029] Substitute the original coordinate system's UAV positions X1, Y1, Z1, translation parameters, rotation parameters, and scale parameters into the coordinate transformation function to obtain the new coordinate system's UAV positions X2, Y2, Z2, and return the new coordinate system's UAV positions X2, Y2, Z2.

[0030] Furthermore, step 3) specifically includes:

[0031] 31) Establish a UAV flight dynamics database, including the following data items: flight record number, UAV serial number, takeoff time, flight status, flight dynamics data reception time, UAV model, new coordinate system type, UAV position on the X-axis, UAV position on the Y-axis, UAV position on the Z-axis, flight speed on the X-axis, flight speed on the Y-axis, flight speed on the Z-axis, track angle, horizontal safety interval, and vertical safety interval.

[0032] 32) Receive flight dynamic data sent by the UAV, parse the received UAV flight dynamic data, and obtain the flight record number, flight status, current time, UAV model, coordinate system type, position longitude, position latitude, flight altitude, vertical flight speed, horizontal flight speed and track angle;

[0033] 33) Decompose the flight record number according to the order and number of digits of the string to obtain the UAV serial number, takeoff time and random code respectively; the flight record number is composed of UAV serial number, takeoff time and random code, and the specific format is: 20-digit UAV serial number + 8-digit takeoff time + 8-digit random code;

[0034] 34) Convert the WGS-84 or GLONASS-PZ90 coordinate system to the CGCS2000 coordinate system; specifically including:

[0035] 341) Represent the WGS-84 coordinate system, CGCS2000 coordinate system, and GLONASS-PZ90 coordinate system using the geocentric rectangular coordinate system;

[0036] 3411) Define the UAV position represented by latitude, longitude, and altitude coordinates as P. L , as follows: P L = (B, L, H);

[0037] In the formula, B is the position dimension, L is the position longitude, and H is the flight altitude;

[0038] 3412) Calculate the radius of curvature N of the zonal loop, using the following formula:

[0039] Where a is the semi-major axis of the reference ellipsoid and e is the first eccentricity;

[0040] 3413) Define the UAV position in geocentric and geofixed rectangular coordinates as P. Z = (X1, Y1, Z1);

[0041] The location P of the UAV represented by latitude, longitude, and altitude coordinates. L The UAV position P converted to Earth-centered, Earth-fixed rectangular coordinates Z The calculation formulas are as follows: X1=(N+H)cos(B)cos(L); Y1=(N+H)cos(B)sin(L); Z1=(N(1-e 2 )+H)sin(B);

[0042] 342) Determine the coordinate system type. If it is the WGS-84 or GLONASS-PZ90 coordinate system, perform coordinate transformation calculations. The specific steps are: convert the obtained geocentric rectangular coordinates of the UAV position P... Z Substituting (X1, Y1, Z1), coordinate system type, and new coordinate system type into the coordinate transformation function, we obtain the specific UAV position X2, Y2, Z2 in the CGCS2000 coordinate system, and set the UAV position P in the CGCS2000 coordinate system. C = (X2, Y2, Z2); If it is the CGCS2000 coordinate system, P c =P z = (X1, Y1, Z1);

[0043] 35) Calculate the velocities v of the UAV on the X, Y, and Z axes respectively. x ,v y ,v z ; v x =v t ; v y =v l sinθ; v z =v l cosθ;

[0044] Among them, v t For vertical flight speed, v l θ is the horizontal flight speed, and θ is the track angle;

[0045] The track angle θ is the angle between the projection of the actual UAV trajectory onto the horizontal plane and the geographic north direction, measured in a clockwise direction, and ranges from 0 to 360 degrees.

[0046] 36) Using the drone model obtained in step 32), match the drone model parameter item in the drone safety interval parameter library to obtain the horizontal and vertical safety intervals; if the data record obtained from the drone safety interval parameter library is not unique, prompt an error and end the method; otherwise, proceed to step 37).

[0047] 37) The standardized data is saved into the UAV flight dynamics database. The specific data mapping is as follows:

[0048] The flight record number in the UAV flight dynamics database is equal to the flight record number obtained in step 32).

[0049] The UAV serial number in the UAV flight dynamics database is the UAV serial number obtained in step 32).

[0050] The takeoff time in the UAV flight dynamics database is equal to the takeoff time obtained in step 33).

[0051] The flight status of the UAV flight dynamics database is equal to the flight status obtained in step 32).

[0052] The flight dynamic data reception time of the UAV flight dynamic database = the current time obtained in step 32);

[0053] The drone model in the drone flight dynamics database is the drone model obtained in step 32).

[0054] The new coordinate system type for the UAV flight dynamics database is CGCS2000.

[0055] The drone position on the X-axis in the drone flight dynamics database is equal to X2 obtained in step 342).

[0056] The drone position on the Y-axis of the drone flight dynamics database is equal to Y2 obtained in step 342);

[0057] The UAV position on the Z-axis in the UAV flight dynamics database is equal to Z2 obtained in step 342).

[0058] The flight speed on the X-axis of the UAV flight dynamics database is equal to the v obtained in step 35). x ;

[0059] The flight speed on the Y-axis of the UAV flight dynamics database is equal to the v obtained in step 35). y ;

[0060] The flight speed on the Z-axis of the UAV flight dynamics database is equal to the v obtained in step 35). z ;

[0061] The track angle of the UAV flight dynamics database is equal to the track angle obtained in step 32).

[0062] The horizontal safety interval of the UAV flight dynamics database is obtained in step 36).

[0063] The vertical safety interval of the UAV flight dynamics database is obtained in step 36).

[0064] Furthermore, step 4) specifically includes:

[0065] 41) Define the drone conflict risk level according to the safety interval, and classify the conflict risk level into: pending observation, key attention, and alarm prompt according to the judgment criteria configured by the user;

[0066] Under observation: The risk level is low, indicating that some key indicators show the potential for risk escalation, but it is uncertain whether it will further develop into a higher risk state. We will continue to observe its changing trend.

[0067] Key focus: The risk level is medium, indicating that most key indicators show a potential for escalation of risk, requiring users to closely monitor its dynamic changes;

[0068] Warning: High risk level indicates that the risk is significant and has a major impact on the target, requiring users to take immediate measures for risk management and handling;

[0069] 42) Receive the time range provided by the user, match the flight dynamic data reception time data items in the UAV flight dynamic database according to the time range, and form the UAV test dataset D. c ; D c ={W1,W2,W3,W4,W5,W6…W n ,|n=1,2,3…N}; W n =(XH n ,SX n ,SY n SZ n VX n VY n VZ n ,IX n IY n IZ n ,AN n |n=1,2,3…N);

[0070] Among them, D c and W n In this context, N represents the total number of matched data records; W... n This is a column for UAV flight dynamics data. Each data item in this column comes from a specific data item in the UAV flight dynamics database, as follows:

[0071] XH n For flight record numbering, SX n SY represents the drone's position on the X-axis. n SZ represents the drone's position on the Y-axis. n VX represents the drone's position on the Z-axis. n VY represents the flight speed along the X-axis. n VZ represents the flight speed on the Y-axis. n IX is the flight speed on the Z-axis. n For the horizontal safety interval, IY n For horizontal safety intervals, IZ n For the vertical safety interval, AN n The track angle;

[0072] 43) The drone test dataset D cAs the sample set for decision trees, a decision tree set D is constructed based on the characteristic that the distance between two UAVs in the sample set on the X, Y, and Z axes is less than or equal to the sum of the safe intervals between the two UAVs on the X, Y, and Z axes. y The specific steps are as follows:

[0073] For the drone test dataset D c Any two points W i and W j For i ≠ j, i ∈ n, j ∈ n, the distances on the X, Y, and Z axes are DX, respectively. ij =|SX i -SX j |,DY ij =|SY i -SY j |,DZ ij =|SZ i -SZ j |;The sum of the safety intervals on the X, Y, and Z axes are IX ij =IX i +IX j IY ij =IY i +IY j IZ ij =IZ i +IZ j ;

[0074] Calculate the decision tree set D y As follows: D y ={(W i W j )|(DX ij ≤IX ij )and(DY ij ≤IY ij )and(DZ ij ≤IZ ij )};

[0075] 44) Set the decision tree set D y As a new sample set, each is represented by a drone pair (W) i W j The decision tree set is asymptotically calculated based on the characteristic that the distance between two drones on the X, Y, and Z axes is less than or equal to the safe interval between the two drones on the X, Y, and Z axes. The specific steps are as follows:

[0076] 45) Establish observation datasets, key focus datasets, and alarm notification datasets according to conflict risk levels;

[0077] 451) Establish an alarm notification dataset. When a drone meets the set of decision trees... When all three items are in the set, the drone belongs to the alarm notification dataset D. gj Set up decision trees As a sample dataset, the alarm notification dataset D was calculated. gj ,as follows:

[0078] 452) Establish a focus dataset, where the drone only needs to satisfy the decision tree set. When any two terms are in the set, the drone belongs to the dataset of key interest D. gz Set up decision trees As a sample dataset, the dataset D of particular interest was calculated. gz ,as follows:

[0079] 453) Establish the dataset to be observed, when the drone only needs to satisfy the decision tree set When any item in the set is given, the drone belongs to the dataset D to be observed. gc Set up decision trees As a sample dataset, the dataset D to be observed is calculated. gc ,as follows:

[0080] Furthermore, step 5) specifically includes:

[0081] 51) The computational focus is on dataset D. gz The specific steps for determining when a drone may reach an alarm alert level are as follows:

[0082] The focus will be on dataset D. gz As a sample dataset;

[0083] When focusing on dataset D gz Chinese unmanned aerial vehicles (UAVs) i W j ), satisfying |SX i -SX j |>MAX(IX i ,IX j Flight record number XH i and XH j The time T that may reach the alarm notification level gz1 =|SX i -SX j | / |VX i -VX j |;

[0084] When focusing on dataset Dgz Chinese unmanned aerial vehicles (UAVs) i W j ), satisfying |SY i -SY j |>MAX(IY i IY j Flight record number XH i and XH j The time T that may reach the alarm notification level gz2 =|SY i -SY j | / |VY i -VY j |;

[0085] When focusing on dataset D gz Chinese unmanned aerial vehicles (UAVs) i W j ), satisfying |SZ i -SZ j |>MAX(IZ i IZ j Flight record number XH i and XH j The time T that may reach the alarm notification level gz3 =|SZ i -SZ j | / |VZ i -VZ j |;

[0086] Focus on dataset D gz All drones in the set T of time expected to reach the alarm alert level gz As follows: T gz ={XH i ,XH j ,(T gz1 ,T gz2 ,T gz3 )|(W i W j )∈D gz};

[0087] 52) Calculate the alarm notification dataset D gj The specific steps for determining the estimated time of collision between the two drones involved in the conflict are as follows:

[0088] The alarm notification dataset D gj As a sample dataset, the drone pairs (W) were calculated. i W j The estimated time T of the collision gj ",as follows:

[0089] Alarm prompts dataset D gj All drones in the time set T of the expected collision gj As follows: T gj ={XH i ,XH j ,T gj "|(W i W j )∈D gj}

[0090] The beneficial effects of this invention are:

[0091] 1. This invention fully considers the significant differences in performance and characteristics among different UAVs; on the one hand, it can ensure sufficient time and space to implement emergency measures in emergency situations, thereby minimizing potential risks; on the other hand, the established safety interval can maximize the utilization of airspace resources, thereby effectively increasing the flow of flights in the airspace.

[0092] 2. This invention classifies conflict risk levels into three categories from low to high: to be observed, to be closely monitored, and to be alerted. Different safety interval thresholds are set according to the risk level. On the one hand, risks can be identified early in their initial stages, allowing users to intervene as soon as possible. On the other hand, users can handle risks in a timely and orderly manner according to the determined risk levels, in descending order.

[0093] 3. This invention employs an incremental decision tree method, which is relatively simple to construct and can handle various types of data. On the one hand, when faced with large-scale datasets, decision trees can be trained and predicted quickly; on the other hand, the incremental approach allows for relatively independent computation at each stage, thereby improving the parallel efficiency of the operation and the flexibility of the functional implementation. Attached Figure Description

[0094] Figure 1 is a flowchart of the method of the present invention;

[0095] Figure 2 is a schematic diagram of a drone conducting safe-spaced flight at low altitudes in an urban area. Detailed Implementation

[0096] To facilitate understanding by those skilled in the art, the present invention will be further described below with reference to embodiments and accompanying drawings. The content mentioned in the embodiments is not intended to limit the present invention.

[0097] Referring to Figures 1 and 2, the UAV conflict prediction method based on a safety interval progressive decision tree according to the present invention comprises the following steps:

[0098] 1) Calculate the safe interval distance of the UAV based on its performance parameters and establish a safe interval parameter library for the UAV;

[0099] Safety separation refers to the certain distance and time interval that two drones need to maintain in order to ensure the safety of drone flight; in the air, safety separation includes longitudinal separation (front-to-back distance), lateral separation (left-to-right distance), and vertical separation (vertical height difference).

[0100] 11) Establish a UAV performance parameter table, including UAV model, total thrust, vertical tilt angle, UAV mass, maximum horizontal speed, and maximum vertical speed.

[0101] 12) Calculate the safe interval distance for the drone, including the following steps:

[0102] 121) Obtain the total thrust F of the UAV motor / rotor and the forward tilt angle Φ of the UAV motor / rotor with respect to the vertical direction from the UAV performance parameter table, and calculate the maximum horizontal thrust F of the UAV. h and the maximum thrust F in the vertical direction v The calculation formula is as follows; F v =F cosΦ; F h =F sinΦ;

[0103] 122) Obtain the mass M of the UAV from the UAV performance parameter table, and calculate the horizontal acceleration α of the UAV. h and the acceleration in the vertical direction α v The calculation formula is as follows: ɑ h =F h / M; ɑ v =MAX((F v -Mg) / M,g);

[0104] Where g is the acceleration due to gravity;

[0105] 123) Obtain the maximum horizontal speed of the UAV from the UAV performance parameter table. and maximum speed in the vertical direction Calculate the horizontal safety distance DI of the drone h and vertical safety interval DI v The calculation formula is as follows:

[0106] Among them, T eh and T ev These represent the redundancy times (including reaction time, etc.) in the horizontal and vertical directions, respectively; N h and N v These are the safety interval configuration parameters for the horizontal and vertical directions, which can be configured by the user according to their own actual situation.

[0107] 13) Establish a UAV safety interval parameter library, including UAV model, UAV mass, horizontal safety interval, and vertical safety interval; save the calculation results in step 12) in the UAV safety interval parameter library.

[0108] 2) Establish a coordinate transformation model parameter library for converting WGS-84 and GLONASS-PZ90 coordinate systems to CGCS2000 coordinate systems, and encapsulate the constructed Bursa model into coordinate transformation functions, defining the function calling method for use during coordinate transformation calculations;

[0109] 21) Establish a coordinate transformation model parameter library, including the original coordinate system type, new coordinate system type, applicable geographical area, translation parameters, rotation parameters, and scale parameters;

[0110] 22) Establish a coordinate transformation function and define the function call method for use during coordinate transformation calculations;

[0111] 221) Construct the Bursa model, as follows:

[0112] Where ΔX, ΔY, and ΔZ are translation parameters, and m is a scale parameter. X1, Y1, Z1 are the original coordinates of the UAV's position in the WGS-84 or GLONASS-PZ90 coordinate system; X2, Y2, Z2 are the new coordinates of the UAV's position in the CGCS2000 coordinate system.

[0113] Among them, WGS-84 is used in GPS navigation systems;

[0114] CGCS2000 is used in the BeiDou Navigation Satellite System;

[0115] GLONASS-PZ90 is used in Russia's GLONASS satellite navigation system;

[0116] 222) Encapsulate the Bursa model from step 221) into a coordinate transformation function, and define the function call method for use during coordinate transformation calculation; the input parameters of the function are: original coordinate system type, new coordinate system type, and the specific position of the UAV in the original coordinate system X1, Y1, Z1; the output parameters of the function are: the specific position of the UAV in the new coordinate system X2, Y2, Z2.

[0117] 223) Use coordinate transformation functions to convert the WGS-84 or GLONASS-PZ90 coordinate system to the CGCS2000 coordinate system. The specific steps are as follows:

[0118] The function's input parameters, including the original coordinate system type, new coordinate system type, and the UAV's specific position (X1, Y1, Z1) in the original coordinate system, are compared with the three parameters (original coordinate system type, new coordinate system type, and applicable geographical area) in the coordinate transformation model parameter library to obtain the translation, rotation, and scale parameters. If the data record obtained from the coordinate transformation model parameter library is not unique, the coordinate transformation calculation is terminated, and an error is displayed to the user; otherwise, the coordinate transformation calculation continues.

[0119] Substitute the original coordinate system's UAV positions X1, Y1, Z1, translation parameters, rotation parameters, and scale parameters into the coordinate transformation function to obtain the new coordinate system's UAV positions X2, Y2, Z2, and return the new coordinate system's UAV positions X2, Y2, Z2.

[0120] 3) Receive flight dynamic data sent by the UAV, parse the data and perform standardized transformation, and store the transformation results in the UAV flight dynamic database;

[0121] 31) Establish a UAV flight dynamics database. Data items include flight record number, UAV serial number, takeoff time, flight status, flight dynamics data reception time, UAV model, new coordinate system type, UAV position on X-axis, UAV position on Y-axis, UAV position on Z-axis, flight speed on X-axis, flight speed on Y-axis, flight speed on Z-axis, track angle, horizontal safety interval, and vertical safety interval.

[0122] 32) Receive flight dynamic data sent by the UAV, parse the received UAV flight dynamic data, and obtain the flight record number, flight status, current time, UAV model, coordinate system type, position longitude, position latitude, flight altitude, vertical flight speed, horizontal flight speed and track angle;

[0123] 33) Decompose the flight record number according to the order and number of digits of the string to obtain the UAV serial number, takeoff time and random code respectively; the flight record number is composed of UAV serial number, takeoff time and random code, and the specific format is: 20-digit UAV serial number + 8-digit takeoff time + 8-digit random code;

[0124] 34) Convert the WGS-84 or GLONASS-PZ90 coordinate system to the CGCS2000 coordinate system;

[0125] 341) Represent the WGS-84 coordinate system, CGCS2000 coordinate system, and GLONASS-PZ90 coordinate system using the Earth-centered Earth-fixed Rectangular Coordinate System (ECEF);

[0126] 3411) Define the UAV position represented by latitude, longitude, and altitude coordinates as P. L , as follows: PL = (B, L, H);

[0127] In the formula, B is the position dimension, L is the position longitude, and H is the flight altitude;

[0128] 3412) Calculate the radius of curvature N of the zonal loop, using the following formula:

[0129] Where a is the semi-major axis of the reference ellipsoid and e is the first eccentricity;

[0130] 3413) Define the UAV position in geocentric and geofixed rectangular coordinates as P. Z = (X1, Y1, Z1);

[0131] The location P of the UAV represented by latitude, longitude, and altitude coordinates. L The UAV position P converted to Earth-centered, Earth-fixed rectangular coordinates Z The calculation formulas are as follows: X1=(N+H)cos(B)cos(L); Y1=(N+H)cos(B)sin(L); Z1=(N(1-e 2 )+H)sin(B);

[0132] 342) Determine the coordinate system type. If it is the WGS-84 or GLONASS-PZ90 coordinate system, perform coordinate transformation calculations. The specific steps are: convert the obtained geocentric rectangular coordinates of the UAV position P... Z Substituting (X1, Y1, Z1), coordinate system type, and new coordinate system type into the coordinate transformation function, we obtain the specific UAV position X2, Y2, Z2 in the CGCS2000 coordinate system, and set the UAV position P in the CGCS2000 coordinate system. c = (X2, Y2, Z2); If it is the CGCS2000 coordinate system, P c =P z = (X1, Y1, Z1);

[0133] 35) Calculate the velocities v of the UAV on the X, Y, and Z axes respectively. x ,v y ,v z ; v x =v t ; v y =v l sinθ; v z =v l cosθ;

[0134] Among them, v t For vertical flight speed, v l θ is the horizontal flight speed, and θ is the track angle;

[0135] The track angle θ is the angle between the projection of the actual UAV trajectory onto the horizontal plane and the geographic north direction, measured in a clockwise direction, and ranges from 0 to 360 degrees.

[0136] 36) Using the drone model obtained in step 32), match the drone model parameter item in the drone safety interval parameter library to obtain the horizontal safety interval and the vertical safety interval; if the data record obtained from the drone safety interval parameter library is not unique, prompt an error and end the method; otherwise, continue to execute step 37).

[0137] 37) The standardized data is saved into the UAV flight dynamics database. The specific data mapping is as follows:

[0138] The flight record number in the UAV flight dynamics database is equal to the flight record number obtained in step 32).

[0139] The UAV serial number in the UAV flight dynamics database is the UAV serial number obtained in step 32).

[0140] The takeoff time in the UAV flight dynamics database is equal to the takeoff time obtained in step 33).

[0141] The flight status of the UAV flight dynamics database is equal to the flight status obtained in step 32).

[0142] The flight dynamic data reception time of the UAV flight dynamic database = the current time obtained in step 32);

[0143] The drone model in the drone flight dynamics database is the drone model obtained in step 32).

[0144] The new coordinate system type for the UAV flight dynamics database is CGCS2000.

[0145] The drone position on the X-axis in the drone flight dynamics database is equal to X2 obtained in step 342).

[0146] The drone position on the Y-axis of the drone flight dynamics database is equal to Y2 obtained in step 342);

[0147] The UAV position on the Z-axis in the UAV flight dynamics database is equal to Z2 obtained in step 342).

[0148] The flight speed on the X-axis of the UAV flight dynamics database is equal to the v obtained in step 35). x ;

[0149] The flight speed on the Y-axis of the UAV flight dynamics database is equal to the v obtained in step 35). y ;

[0150] The flight speed on the Z-axis of the UAV flight dynamics database is equal to the v obtained in step 35). z ;

[0151] The track angle of the UAV flight dynamics database is equal to the track angle obtained in step 32).

[0152] The horizontal safety interval of the UAV flight dynamics database is obtained in step 36).

[0153] The vertical safety interval of the UAV flight dynamics database is obtained in step 36).

[0154] 4) An incremental decision tree classification method is used to predict airspace UAV conflicts, and the prediction results are divided into three conflict risk level datasets: pending observation, key concern, and alarm prompt.

[0155] 41) Define the drone conflict risk level according to the safety interval, and classify the conflict risk level into: pending observation, key attention, and alarm prompt according to the judgment criteria configured by the user;

[0156] Under observation: The risk level is low, indicating that some key indicators show the potential for risk escalation, but it is uncertain whether it will further develop into a higher risk state. We will continue to observe its changing trend.

[0157] Key focus: The risk level is medium, indicating that most key indicators show a potential for escalation of risk. Users need to closely monitor its dynamic changes in order to take timely countermeasures.

[0158] Warning: High risk level indicates that the risk is obvious and has a significant impact on the target, requiring users to take immediate measures for risk management and handling;

[0159] 42) Receive the time range provided by the user (the time is the current time when calculating drone conflicts in real time), match the flight dynamic data received time data items in the drone flight dynamic database according to the time range, and form the drone test dataset D. c ; D c ={W1,W2,W3,W4,W5,W6…W n ,|n=1,2,3…N}; W n =(XH n ,SX n ,SY n SZ n VX n VY n VZ n ,IX n IYn IZ n ,AN n |n=1,2,3…N);

[0160] Among them, D c and W n In this context, N represents the total number of matched data records; W... n This is a column for UAV flight dynamics data. Each data item in this column comes from a specific data item in the UAV flight dynamics database, as follows:

[0161] XH n For flight record numbering, SX n SY represents the drone's position on the X-axis. n SZ represents the drone's position on the Y-axis. n VX represents the drone's position on the Z-axis. n VY represents the flight speed along the X-axis. n VZ represents the flight speed on the Y-axis. n IX is the flight speed on the Z-axis. n For the horizontal safety interval, IY n For horizontal safety intervals, IZ n For the vertical safety interval, AN n The track angle;

[0162] 43) The drone test dataset D c As the sample set for decision trees, a decision tree set D is constructed based on the characteristic that the distance between two UAVs in the sample set on the X, Y, and Z axes is less than or equal to the sum of the safe intervals between the two UAVs on the X, Y, and Z axes. y The specific steps are as follows:

[0163] For the drone test dataset D c Any two points W i and W j For i ≠ j, i ∈ n, j ∈ n, the distances on the X, Y, and Z axes are DX, respectively. ij =|SX i -SX j |,DY ij =|SY i -SY j |,DZ ij =|SZ i -SZ j |;The sum of the safety intervals on the X, Y, and Z axes are IX ij =IX i +IX j IY ij =IY i +IY j IZij =IZ i +IZ j ;

[0164] Calculate the decision tree set D y As follows: D y ={(W i W j )|(DX ij ≤IX ij )and(DY ij ≤IY ij )and(DZ ij ≤IZ ij )};

[0165] 44) Set the decision tree set D y As a new sample set, each is represented by a drone pair (W) i W j The decision tree set is asymptotically calculated based on the characteristic that the distance between two drones on the X, Y, and Z axes is less than or equal to the safe interval between the two drones on the X, Y, and Z axes (the larger of the two drones' safe intervals is used). The specific steps are as follows:

[0166] 45) Establish observation datasets, key focus datasets, and alarm notification datasets according to conflict risk levels;

[0167] 451) Establish an alarm notification dataset. When a drone meets the set of decision trees... When all three items are in the set, the drone belongs to the alarm notification dataset D. gj Set up decision trees As a sample dataset, the alarm notification dataset D was calculated. gj ,as follows:

[0168] 452) Establish a focus dataset, where the drone only needs to satisfy the decision tree set. When any two terms are in the set, the drone belongs to the dataset of key interest D. gz Set up decision trees As a sample dataset, the dataset D of particular interest was calculated. gz ,as follows:

[0169] 453) Establish the dataset to be observed, when the drone only needs to satisfy the decision tree set When any item in the set is given, the drone belongs to the dataset D to be observed. gc Set up decision trees As a sample dataset, the dataset D to be observed is calculated. gc ,as follows:

[0170] 5) The computation focuses on dataset D. gz The system tracks the time when drones may reach an alarm alert level to prompt users to plan conflict resolution strategies in advance; it also calculates the alarm alert dataset D. gj The system uses the estimated time of collision between conflicting drones to alert users and facilitate conflict resolution.

[0171] 51) The computational focus is on dataset D. gz The specific steps for determining when a drone may reach an alarm alert level are as follows:

[0172] The focus will be on dataset D. gz As a sample dataset,

[0173] When focusing on dataset D gz Chinese unmanned aerial vehicles (UAVs) i W j ), satisfying |SX i -SX j |>MAX(IX i ,IX j Flight record number XH i and XH j The time T that may reach the alarm notification level gz1 =|SX i -SX j | / |VX i -VX j |;

[0174] When focusing on dataset D gz Chinese unmanned aerial vehicles (UAVs) i W j ), satisfying |SY i -SY j |>MAX(IY i IY j Flight record number XH i and XH j The time T that may reach the alarm notification level gz2 =|SY i -SY j | / |VY i -VY j |;

[0175] When focusing on dataset D gz Chinese unmanned aerial vehicles (UAVs) i W j ), satisfying |SZi -SZ j |>MAX(IZ i IZ j Flight record number XH i and XH j The time T that may reach the alarm notification level gz3 =|SZ i -SZ j | / |VZ i -VZ j |;

[0176] Focus on dataset D gz All drones in the set T of time expected to reach the alarm alert level gz As follows: T gz ={XH i ,XH j ,(T gz1 ,T gz2 ,T gz3 )|(W i W j )∈D gz};

[0177] 52) Calculate the alarm notification dataset D gj The specific steps for determining the estimated time of collision between the two drones involved in the conflict are as follows:

[0178] The alarm notification dataset D gj As a sample dataset, the drone pairs (W) were calculated. i W j The estimated time T of the collision gj ",as follows:

[0179] Alarm prompts dataset D gj All drones in the time set T of the expected collision gj As follows: T gj ={XH i ,XH j ,T gj "|(W i W j )∈D gj}

[0180] This invention has many specific applications. The above description is only a preferred embodiment of this invention. It should be noted that for those skilled in the art, several improvements can be made without departing from the principle of this invention, and these improvements should also be considered within the scope of protection of this invention.

Claims

1. A method for predicting UAV conflicts based on a safety interval progressive decision tree, characterized in that, The steps are as follows: 1) Calculate the safe interval distance of the UAV based on its performance parameters and establish a safe interval parameter library for the UAV; 2) Establish a coordinate transformation model parameter library for converting WGS-84 and GLONASS-PZ90 coordinate systems to CGCS2000 coordinate systems, and encapsulate the constructed Bursa model into coordinate transformation functions, defining the function calling method; 3) Receive flight dynamic data sent by the UAV, parse the data and perform standardized transformation, and store the transformation results in the UAV flight dynamic database; 4) An incremental decision tree classification method is used to predict airspace UAV conflicts, and the prediction results are divided into the observation dataset, the key attention dataset, and the alarm prompt dataset according to the conflict risk level. 5) Calculate the time when drone pairs in the key dataset may reach the alarm alert level, so as to prompt users to plan conflict resolution solutions in advance; Calculate the estimated time of collision between conflicting drones in the alarm alert dataset to prompt the user to take action to resolve the conflict.

2. The UAV conflict prediction method based on a safety interval progressive decision tree according to claim 1, characterized in that, Step 1) specifically includes: 11) Establish a UAV performance parameter table, including the following parameters: UAV model, total thrust, angle of forward tilt in the vertical direction, UAV mass, maximum speed in the horizontal direction, and maximum speed in the vertical direction. 12) Calculate the safe interval distance for the drone; 13) Establish a UAV safety interval parameter library, including: UAV model, UAV mass, horizontal safety interval and vertical safety interval; save the calculation results in step 12) in the UAV safety interval parameter library.

3. The UAV conflict prediction method based on a safety interval progressive decision tree according to claim 2, characterized in that, Step 12) specifically includes: 121) Obtain the total thrust F of the UAV motor / rotor and the forward tilt angle Φ of the UAV motor / rotor with respect to the vertical direction from the UAV performance parameter table, and calculate the maximum horizontal thrust F of the UAV. h and the maximum thrust F in the vertical direction v The calculation formula is as follows; F v =F cos Φ; F h =F sin Φ; 122) Obtain the mass M of the UAV from the UAV performance parameter table, and calculate the horizontal acceleration α of the UAV. h and the acceleration in the vertical direction α v The calculation formula is as follows: ɑ h =F h / M; ɑ v =MAX((F v -Mg) / M,g); Where g is the acceleration due to gravity; 123) Obtain the maximum horizontal speed of the UAV from the UAV performance parameter table. and maximum speed in the vertical direction Calculate the horizontal safety distance DI of the drone h and vertical safety interval DI v The calculation formula is as follows: Among them, T eh and T ev These represent the redundancy times in the horizontal and vertical directions, respectively; N h and N v These are the safety interval configuration parameters for the horizontal and vertical directions, respectively.

4. The UAV conflict prediction method based on a safety interval progressive decision tree according to claim 3, characterized in that, Step 2) specifically includes: 21) Establish a coordinate transformation model parameter library, including the following parameters: original coordinate system type, new coordinate system type, applicable geographical area, translation parameters, rotation parameters, and scale parameters; 22) Establish a coordinate transformation function and define the function call method.

5. The UAV conflict prediction method based on a safety interval progressive decision tree according to claim 4, characterized in that, Step 22) specifically includes: 221) Construct the Bursa model, as follows: Where ΔX, ΔY, and ΔZ are translation parameters, and m is a scale parameter. X1, Y1, Z1 are the original coordinates of the UAV's position in the WGS-84 or GLONASS-PZ90 coordinate system; X2, Y2, Z2 are the new coordinates of the UAV's position in the CGCS2000 coordinate system. 222) Encapsulate the Bursa model from step 221) into a coordinate transformation function, and define the function call method for use during coordinate transformation calculation; the input parameters of the function are: original coordinate system type, new coordinate system type, and the specific position of the UAV in the original coordinate system X1, Y1, Z1; the output parameters of the function are: the specific position of the UAV in the new coordinate system X2, Y2, Z2. 223) Use coordinate transformation functions to convert the WGS-84 or GLONASS-PZ90 coordinate system to the CGCS2000 coordinate system.

6. The UAV conflict prediction method based on a safety interval progressive decision tree according to claim 5, characterized in that, Step 223) is as follows: The function's input parameters, including the original coordinate system type, new coordinate system type, and the UAV's specific position (X1, Y1, Z1) in the original coordinate system, are compared with the three parameters (original coordinate system type, new coordinate system type, and applicable geographical area) in the coordinate transformation model parameter library to obtain the translation, rotation, and scale parameters. If the data record obtained from the coordinate transformation model parameter library is not unique, the coordinate transformation calculation is terminated, and an error is displayed to the user; otherwise, the coordinate transformation calculation continues. Substitute the original coordinate system's UAV positions X1, Y1, Z1, translation parameters, rotation parameters, and scale parameters into the coordinate transformation function to obtain the new coordinate system's UAV positions X2, Y2, Z2, and return the new coordinate system's UAV positions X2, Y2, Z2.

7. The UAV conflict prediction method based on a safety interval progressive decision tree according to claim 6, characterized in that, Step 3) specifically includes: 31) Establish a UAV flight dynamics database, including the following data items: flight record number, UAV serial number, takeoff time, flight status, flight dynamics data reception time, UAV model, new coordinate system type, UAV position on the X-axis, UAV position on the Y-axis, UAV position on the Z-axis, flight speed on the X-axis, flight speed on the Y-axis, flight speed on the Z-axis, track angle, horizontal safety interval, and vertical safety interval. 32) Receive flight dynamic data sent by the UAV, parse the received UAV flight dynamic data, and obtain the flight record number, flight status, current time, UAV model, coordinate system type, position longitude, position latitude, flight altitude, vertical flight speed, horizontal flight speed and track angle; 33) Decompose the flight record number according to the order and number of digits of the string to obtain the UAV serial number, takeoff time and random code respectively; the flight record number is composed of UAV serial number, takeoff time and random code, and the specific format is: 20-digit UAV serial number + 8-digit takeoff time + 8-digit random code; 34) Convert the WGS-84 or GLONASS-PZ90 coordinate system to the CGCS2000 coordinate system; specifically including: 341) Represent the WGS-84 coordinate system, CGCS2000 coordinate system, and GLONASS-PZ90 coordinate system using the geocentric rectangular coordinate system; 3411) Define the UAV position represented by latitude, longitude, and altitude coordinates as P. L ,as follows: P L =(B,L,H); In the formula, B is the position dimension, L is the position longitude, and H is the flight altitude; 3412) Calculate the radius of curvature N of the zonal loop, using the following formula: Where a is the semi-major axis of the reference ellipsoid and e is the first eccentricity; 3413) Define the UAV position in geocentric and geofixed rectangular coordinates as P. Z = (X1, Y1, Z1); The location P of the UAV represented by latitude, longitude, and altitude coordinates. L The UAV position P converted to Earth-centered, Earth-fixed rectangular coordinates Z The calculation formula is as follows: X1 = (N+H)cos(B)cos(L); Y1 = (N+H)cos(B)sin(L); Z1=(N(1-e 2 )+H)sin(B); 342) Determine the coordinate system type. If it is the WGS-84 or GLONASS-PZ90 coordinate system, perform coordinate transformation calculations. The specific steps are: convert the obtained geocentric rectangular coordinates of the UAV position P... Z Substituting (X1, Y1, Z1), coordinate system type, and new coordinate system type into the coordinate transformation function, we obtain the specific UAV position X2, Y2, Z2 in the CGCS2000 coordinate system, and set the UAV position P in the CGCS2000 coordinate system. C = (X2, Y2, Z2); If it is the CGCS2000 coordinate system, P C =P Z = (X1, Y1, Z1); 35) Calculate the velocities v of the UAV on the X, Y, and Z axes respectively. x ,v y ,v z ; v x =v t ; v y =v l sinθ; v z =v l cosθ; Among them, v t For vertical flight speed, v l θ is the horizontal flight speed, and θ is the track angle; 36) Using the drone model obtained in step 32), match the drone model parameter item in the drone safety interval parameter library to obtain the horizontal and vertical safety intervals; if the data record obtained from the drone safety interval parameter library is not unique, prompt an error and end the method; otherwise, proceed to step 37). 37) The standardized data is saved into the UAV flight dynamics database. The specific data mapping is as follows: The flight record number in the UAV flight dynamics database is equal to the flight record number obtained in step 32). The UAV serial number in the UAV flight dynamics database is the UAV serial number obtained in step 32). The takeoff time in the UAV flight dynamics database is equal to the takeoff time obtained in step 33). The flight status of the UAV flight dynamics database is equal to the flight status obtained in step 32). The flight dynamic data reception time of the UAV flight dynamic database = the current time obtained in step 32); The drone model in the drone flight dynamics database is the drone model obtained in step 32). The new coordinate system type for the UAV flight dynamics database is CGCS2000. The drone position on the X-axis in the drone flight dynamics database is equal to X2 obtained in step 342). The drone position on the Y-axis of the drone flight dynamics database is equal to Y2 obtained in step 342); The UAV position on the Z-axis in the UAV flight dynamics database is equal to Z2 obtained in step 342). The flight speed on the X-axis of the UAV flight dynamics database is equal to the v obtained in step 35). x ; The flight speed on the Y-axis of the UAV flight dynamics database is equal to the v obtained in step 35). y ; The flight speed on the Z-axis of the UAV flight dynamics database is equal to the v obtained in step 35). z ; The track angle of the UAV flight dynamics database is equal to the track angle obtained in step 32). The horizontal safety interval of the UAV flight dynamics database is obtained in step 36). The vertical safety interval of the UAV flight dynamics database is obtained in step 36).

8. The UAV conflict prediction method based on a safety interval progressive decision tree according to claim 7, characterized in that, Step 4) specifically includes: 41) Define the drone conflict risk level according to the safety interval, and classify the conflict risk level into: pending observation, key attention, and alarm prompt according to the judgment criteria configured by the user; Under observation: The risk level is low, indicating that some key indicators show the potential for risk escalation, but it is uncertain whether it will further develop into a higher risk state. We will continue to observe its changing trend. Key focus: The risk level is medium, indicating that most key indicators show a potential for escalation of risk, requiring users to closely monitor its dynamic changes; Warning: High risk level indicates that the risk is significant and has a major impact on the target, requiring users to take immediate measures for risk management and handling; 42) Receive the time range provided by the user, match the flight dynamic data reception time data items in the UAV flight dynamic database according to the time range, and form the UAV test dataset D. c ; D c {W1,W2,W3,W4,W5,W6…W n ,|n=1,2,3…N}; W n (XH n ,SX n ,SY n ,SZ n ,VX n ,VY n ,VZ n , IX n ,IY n ,IZ n ,AN n |n=1,2,3...N); Among them, D c and W n In this context, N represents the total number of matched data records; W... n This is a column for UAV flight dynamics data. Each data item in this column comes from a specific data item in the UAV flight dynamics database, as follows: XH n For flight record numbering, SX n SY represents the drone's position on the X-axis. n SZ represents the drone's position on the Y-axis. n VX represents the drone's position on the Z-axis. n VY represents the flight speed along the X-axis. n VZ represents the flight speed on the Y-axis. n IX is the flight speed on the Z-axis. n For the horizontal safety interval, IY n For horizontal safety intervals, IZ n For the vertical safety interval, AN n The track angle; 43) The drone test dataset D c As the sample set for decision trees, a decision tree set D is constructed based on the characteristic that the distance between two UAVs in the sample set on the X, Y, and Z axes is less than or equal to the sum of the safe intervals between the two UAVs on the X, Y, and Z axes. y The specific steps are as follows: For the drone test dataset D c Any two points W i and W j For i ≠ j, i ∈ n, j ∈ n, the distances on the X, Y, and Z axes are DX, respectively. ij =|SX i -SX j |,DY ij =|SY i -SY j |,DZ ij =|SZ i -SZ j |;The sum of the safety intervals on the X, Y, and Z axes are IX ij =IX i +IX j IY ij =IY i +IY j IZ ij =IZ i +IZ j ; Calculate the decision tree set D y ,as follows: D y ={(W i ,W j )|(DX ij ≤IX ij )and(DY ij ≤IY ij )and(DZ ij ≤IZ ij )); 44) Set the decision tree set D y As a new sample set, each is represented by a drone pair (W) i W j The decision tree set is asymptotically calculated based on the characteristic that the distance between two drones on the X, Y, and Z axes is less than or equal to the safe interval between the two drones on the X, Y, and Z axes. The specific steps are as follows: 45) Based on the conflict risk level, establish separate datasets for observation, key focus, and alarm notification.

9. The UAV conflict prediction method based on a safety interval progressive decision tree according to claim 8, characterized in that, Step 45) specifically includes: 451) Establish an alarm notification dataset. When a drone meets the set of decision trees... When all three items are in the set, the drone belongs to the alarm notification dataset D. gj Set up decision trees As a sample dataset, the alarm notification dataset D was calculated. gj ,as follows: 452) Establish a focus dataset, where the drone only needs to satisfy the decision tree set. When any two terms are in the set, the drone belongs to the dataset of key interest D. gz Set up decision trees As a sample dataset, the dataset D of particular interest was calculated. gz ,as follows: 453) Establish the dataset to be observed, when the drone only needs to satisfy the decision tree set When any item in the set is given, the drone belongs to the dataset D to be observed. gc Set up decision trees As a sample dataset, the dataset D to be observed is calculated. gc ,as follows:

10. The UAV conflict prediction method based on a safety interval progressive decision tree according to claim 9, characterized in that, Step 5) specifically includes: 51) The computational focus is on dataset D. gz The specific steps for determining when a drone may reach an alarm alert level are as follows: The focus will be on dataset D. gz As a sample dataset; When focusing on dataset D gz Chinese unmanned aerial vehicles (UAVs) i W j ), satisfying |SX i -SX j |>MAX(IX i ,IX j Flight record number XH i and XH j The time T that may reach the alarm notification level gz1 =|SX i -SX j | / |VX i -VX j |; When focusing on dataset D gz Chinese unmanned aerial vehicles (UAVs) i W j ), satisfying |SY i -SY j |>MAX(IY i IY j Flight record number XH i and XH j The time T that may reach the alarm notification level gz2 =|SY i -SY j | / |VY i -VY j |; When focusing on dataset D gz Chinese unmanned aerial vehicles (UAVs) i W j ), satisfying |SZ i -SZ j |>MAX(IZ i IZ j Flight record number XH i and XH j The time T that may reach the alarm notification level gz3 =|SZ i -SZ j | / |VZ i -VZ j |; Focus on dataset D gz All drones in the set T of time expected to reach the alarm alert level gz ,as follows: T gz ={XH i ,XH j ,(T gz1 ,T gz2 ,T gz3 )|(W i ,W j )∈D gz }; 52) Calculate the alarm notification dataset D gj The specific steps for determining the estimated time of collision between the two drones involved in the conflict are as follows: The alarm notification dataset D gj As a sample dataset, the drone pairs (W) were calculated. i W j The estimated time T of the collision gj ",as follows: Alarm prompts dataset D gj All drones in the time set T of the expected collision gj ,as follows: T gj ={XH i ,XH j ,T gj "|(W i ,W j )∈D gj }。

Images