Unmanned aerial vehicle formation collaborative planning method

Abstract

The invention relates to the technical field of unmanned aerial vehicle electronic data processing, provides an unmanned aerial vehicle formation collaborative planning method, and aims to solve the problem that an unmanned aerial vehicle formation cannot accurately fly according to a preset path due to high-altitude natural environment and electronic signal interference. A natural environment simulation model is established, unmanned aerial vehicle formation signal intensity and position are monitored in real time, a flight image is generated by using a digital twin model, and a flight path is dynamically corrected according to error information. The method comprises the steps of data acquisition, real-time communication configuration, signal detection and matching, flight image generation and formation adjustment, comparative analysis and dynamic correction and the like, through dynamic adjustment and genetic algorithm optimization, the unmanned aerial vehicle formation flies accurately, and the task execution efficiency and accuracy are improved. The method effectively solves the problem of unmanned aerial vehicle formation flight in a complex environment, and has a wide application prospect.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) electronic data processing, and in particular to a UAV formation collaborative planning method. Background Art

[0002] With the advancement of science and technology, drone technology has become increasingly mature and has shown broad application prospects in many fields. Among them, drone formation collaborative flight planning technology has become a research hotspot in recent years. Drone formation collaborative flight planning technology involves multiple drones flying in a specific queue in an autonomous or controlled manner to jointly complete complex flight missions. At present, with the integration of artificial intelligence, machine learning and wireless communication technology, the data processing method of drone formation collaborative flight has been significantly improved.

[0003] In the existing UAV formation collaborative flight planning, data processing methods mainly rely on advanced algorithms and systems. For example, through the path optimization algorithm, the flight path of the UAV can be quickly planned, effectively improving the efficiency and reliability of path planning. At the same time, using wireless communication technology and sensor networks, UAVs can exchange data in real time to achieve intelligent decision-making and highly autonomous collaborative control of UAV formation clusters. In addition, the application of cloud computing and big data analysis technology enables UAVs to monitor and adjust mission plans in real time, thereby optimizing the efficiency and accuracy of mission execution.

[0004] Although the technology of UAV formation collaborative flight planning has made significant progress, there are still the following technical pain points that need to be solved. During the collaborative flight of UAV formation, the UAVs transmit data to each other to achieve collaborative flight of UAV formation. At high altitude, the UAV formation flies according to the pre-set flight planning path and flight formation. Due to the influence of the high-altitude natural environment and various electronic signals, the UAV formation cannot accurately fly according to the pre-set flight planning path and flight formation during the high-altitude flight. Therefore, it is necessary to develop a UAV formation collaborative planning method based on the mutual data transmission between UAVs, so that the UAV formation can be dynamically corrected during the flight process. Summary of the invention

[0005] In view of the shortcomings of the existing technology, the present invention provides a UAV formation collaborative planning method to solve the problem that the UAV formation is unable to accurately fly according to the pre-set flight planning path and flight formation during high-altitude flight due to the influence of the high-altitude natural environment and various electronic signals.

[0006] In order to solve the above technical problems, the specific technical solutions of the present invention are as follows: The present invention provides a UAV formation collaborative planning method, comprising: Step S101, obtaining the UAV formation collaborative planning flight mission data and the UAV operation data in the UAV formation, obtaining the UAV formation flight area natural environment information and the UAV formation flight path information according to the UAV formation collaborative planning flight mission data, establishing the UAV formation flight segmentation area according to the UAV formation flight path information, retrieving the historical data of the UAVs in the UAV formation flight segmentation area, and establishing the UAV formation flight area natural environment simulation model according to the historical data in the UAV formation flight segmentation area and the UAV formation flight area natural environment information; Step S102, according to the drone formation collaborative planning flight mission data and the drone operation data in the drone formation, determine the number of drones in real-time flight of the drone formation, establish identity tags for the drones in real-time flight of the drone formation, retrieve the drone formation communication connection information included in the drone formation collaborative planning flight mission data, complete the communication connection configuration of the drone formation through the drone formation real-time flight drones to establish identity tags, and obtain the drone formation real-time communication information; Step S103, detecting the real-time communication information of the drone formation, detecting and obtaining real-time drone formation signal strength information, and sorting the detected drone formation signal strength information to obtain a drone formation signal strength information set, sequentially obtaining the position information of the drones in the drone formation signal strength information set, establishing a drone formation drone position information set, matching the drone formation signal strength information set with the drone formation drone position information set, and obtaining the real-time drone signal strengths in the drone formation and the distance information between the drones; Step S104, substitute the signal strength of drones in the real-time drone formation and the distance information between drones into the preset digital twin model, generate a first real-time drone formation flight image, receive the drone formation signal base station designated command, the drone formation signal base station designated command includes the drone internal network hotspot start command and the drone flight position adjustment command, set the drones in the drone formation as drone formation signal base stations in the real-time drone formation flight image according to the drone formation signal base station designated command, adjust the drone formation formation according to the drone flight position adjustment command, obtain the adjusted drone formation formation, and collect real-time operation data of the adjusted drone formation formation to obtain the real-time operation data of the adjusted drone formation formation; Step S105, substituting the real-time UAV formation collaborative planning flight mission data and the UAV operation data in the UAV formation into the UAV formation flight area natural environment simulation model to obtain the UAV formation pre-flight area natural environment simulation data, substituting the UAV formation pre-flight area natural environment simulation data and the adjusted UAV formation formation real-time operation data into the preset digital twin model to generate a second real-time UAV formation flight image; Step S106, compare the first real-time UAV formation flight image with the second real-time UAV formation flight image to obtain expected UAV formation flight error information, dynamically correct the flight paths of the UAVs in the UAV formation according to the expected UAV formation flight error information to obtain a corrected UAV flight path, send the corrected UAV flight path to the UAVs in the UAV formation, continue to collect operating data of the UAVs in the UAV formation, and optimize the flight paths of the UAVs in the UAV formation through a genetic algorithm until the UAVs in the UAV formation complete the UAV formation collaborative planning flight mission.

[0007] Furthermore, the UAV formation collaborative planning method of the present invention includes, in step S101: The UAV formation collaborative planning flight mission data includes flight mission objectives, flight area information, flight path information, flight communication connection information, communication methods between UAVs within the UAV formation, and flight communication frequency connections; The real-time location of the drone includes the real-time location coordinates of the drone in flight, flight speed, flight attitude, sensor data, flight attitude information of the drone, drone sensor data, status information of the drone's mechanical parts and electronic equipment, and the remaining battery power of the drone; The flight attitude includes pitch angle, yaw angle and roll angle; Drone sensor data includes data collected by weather sensors, cameras, and radars.

[0008] Furthermore, the UAV formation collaborative planning method of the present invention includes, in step S102: Collecting UAV formation collaborative planning flight mission data, which includes flight mission objectives, UAV formation composition, expected flight area information, and preset flight paths; Receive the operation data of each drone in the drone formation in real time, including real-time position, flight speed, flight attitude and sensor data; The UAV formation collaborative planning flight mission data and the operation data of each UAV in the UAV formation are analyzed to extract the real-time flight characteristics of the UAV formation. The real-time flight characteristics of the UAV formation include the real-time position characteristics of the UAV, the sensor data characteristics of the UAV, the status characteristics of the UAV, the real-time communication characteristics of the UAV formation, the number of UAVs in real-time flight in the UAV formation, the signal strength information characteristics of the UAV formation, the position information characteristics of the UAVs in the UAV formation, the natural environment simulation data characteristics of the UAV formation flight area, the flight path information characteristics of the UAV formation, and the formation information characteristics of the UAV formation According to the operation data of each drone in the drone formation, send communication signals to each drone in the drone formation to check whether the communication connection between drones is normal, verify the online status and health status of each drone and whether it has joined the current flight mission, and obtain the real-time detection results of the drone formation; According to the real-time detection results of the UAV formation, the number of UAVs in real-time flight state is calculated, and the number of UAVs in real-time flight state is obtained.

[0009] According to the number of drones in real-time flight status, the real-time flight status record of the drone formation is updated. The real-time flight status record of the drone formation includes the number of flying drones, drone identification and drone status.

[0010] Furthermore, the UAV formation collaborative planning method of the present invention includes: Establish identity tags for the real-time flying drones of the drone formation, retrieve the drone formation communication connection information included in the drone formation collaborative planning flight mission data, and complete the communication connection configuration of the drone formation through the real-time flying drones of the drone formation to obtain the real-time communication information of the drone formation. Based on the real-time status information of the flying drone, an identity tag is established for each drone. The identity tag includes the drone's MAC address, serial number, and timestamp; The UAV formation communication connection information is parsed to obtain the UAV formation communication channel, UAV formation communication frequency and UAV formation communication protocol, and the parsed UAV formation communication connection information is converted into UAV formation communication configuration instructions, and the UAV formation communication configuration instructions are sent to each UAV in the UAV formation. After receiving the instructions, the UAVs in the UAV formation configure the communication equipment of the UAVs according to the UAV formation communication configuration instructions, and establish communication connections between the UAVs in the UAV formation.

[0011] Furthermore, the UAV formation collaborative planning method of the present invention includes, in step S103: The communication signal strength in the drone formation signal strength information set is screened to select drone formation signal strength information with a signal lower than the standard communication signal strength, and the drone identity information corresponding to the drone formation signal strength information with a signal lower than the standard communication signal strength is determined; According to the drone identity information corresponding to the drone formation signal strength information below the standard communication signal strength, determine the drone real-time flight position information corresponding to the drone formation signal strength information below the standard communication signal strength, use the drone real-time flight position information corresponding to the drone formation signal strength information below the standard communication signal strength as the reference point, perform a drone signal strength search within a 50-meter radius of the reference point, and obtain the reference point real-time drone signal strength search result; The filtered drone signal strength search results are sorted by signal strength to obtain the benchmark point real-time drone signal strength sorting results. The benchmark point real-time drone signal strength sorting results include the benchmark point real-time drone signal strength sorting results for the first period, the second benchmark point real-time drone signal strength sorting results, and the third benchmark point real-time drone signal strength sorting results.

[0012] Furthermore, the UAV formation collaborative planning method of the present invention includes, in step S103: Perform cluster analysis on the ranking results of the real-time UAV signal strength of the benchmark points in the first period, the ranking results of the real-time UAV signal strength of the second benchmark points, and the ranking results of the real-time UAV signal strength of the third benchmark points to obtain the cluster analysis results of the real-time UAV signal strength of the benchmark points; The real-time UAV signal strength clustering analysis results of the benchmark points are matched with the distance information between the UAVs to obtain the distance data of each UAV in the real-time UAV signal strength clustering analysis results of the benchmark points; The distance data of each drone in the cluster analysis results of the real-time drone signal strength of the benchmark point is selected within 50m, and the drone signal with the best ranking result of the real-time drone signal strength of the benchmark point is selected to obtain the dynamic base station screening result, and the corresponding drone is matched according to the dynamic base station screening result, and the drone that matches the dynamic base station screening result is used as the dynamic mobile base station drone; When the real-time drone signal strength at the reference point is lower than the preset value, the dynamic mobile base station drone is activated as a communication base station. The dynamic mobile base station drone sends out a wireless network hotspot to establish a communication connection with each drone in the drone formation.

[0013] Furthermore, the UAV formation collaborative planning method of the present invention includes, in step S104: Receive the designated command of the UAV formation signal base station, which includes the network hotspot start command within the UAV and the UAV flight position adjustment command; Parse the command specified by the base station of the received UAV formation signal to determine the parameters to be adjusted within the UAV formation, including the target coordinates of the position adjustment and the change of the formation shape; According to the parameters adjusted within the drone formation, the flight position of the drone formation is adjusted in the preset digital twin model, and a first real-time drone formation flight image is generated and updated; In the digital twin model, the drones in the drone formation are set as new drone formation signal base stations. The positional relationship between each drone in the drone formation and the new drone formation signal base station is calculated through the digital twin model. The positional relationship between each drone in the drone formation and the new drone formation signal base station includes the distance and angle between each drone in the drone formation and the new drone formation signal base station. According to the distance and angle between each drone in the drone formation and the new drone formation signal base station, the distance and direction between each drone and the target position are calculated, and a drone formation adjustment command is generated; The drone formation adjustment command is sent to the drones in the drone formation through the communication network, and the drone formation receives the drone formation adjustment command in real time, and the drones in the drone formation adjust their flight attitude and position; Real-time operation data of the adjusted UAV formation is collected to obtain real-time operation data of the adjusted UAV formation.

[0014] Furthermore, the UAV formation collaborative planning method of the present invention includes, in step S104: The real-time operation data of the adjusted UAV formation includes: position information of UAVs within the adjusted UAV formation, attitude of UAVs within the adjusted UAV formation, direction of UAVs within the adjusted UAV formation, flight status of UAVs within the adjusted UAV formation, communication status of UAVs within the adjusted UAV formation, sensor data of UAVs within the adjusted UAV formation, environmental data of UAVs within the adjusted UAV formation, fault information of UAVs within the adjusted UAV formation, and mission data of UAVs within the adjusted UAV formation.

[0015] Furthermore, the UAV formation collaborative planning method of the present invention includes, in step S106: Matching the first real-time UAV formation flight image and the second real-time UAV formation flight image in terms of UAV positions and UAV formation shapes, to obtain a matching result of the first real-time UAV formation flight image and the second real-time UAV formation flight image in terms of UAV positions and UAV formation shapes; Perform feature extraction on the matching results of the first real-time UAV formation flight image and the second real-time UAV formation flight image in terms of the UAV positions and the UAV formation shape, and obtain the position coordinate features, flight attitude features, speed features, formation shape features, and relative distance features of the UAVs in the first real-time UAV formation flight image and the second real-time UAV formation flight image; Compare the corresponding features in the first real-time UAV formation flight image and the second real-time UAV formation flight image one by one, the comparison content includes the difference between the actual position and the simulated position of the UAV, the deviation of the flight attitude, and the deformation degree of the formation shape, and obtain the result of comparative analysis of the first real-time UAV formation flight image and the second real-time UAV formation flight image; Based on the results of comparative analysis of the first real-time UAV formation flight image and the second real-time UAV formation flight image, the expected error information during the UAV formation flight is calculated. The expected error information during the UAV formation flight includes the number of meters of position deviation and the angle of attitude deviation. The cumulative error of the flight path of the UAVs in the UAV formation is calculated.

[0016] Furthermore, the UAV formation collaborative planning method of the present invention includes, in step S106: According to the accumulated errors of the flight paths of the drones in the drone formation, the flight paths of the drones in the drone formation are dynamically corrected. The dynamic correction includes adjusting the flight speed, direction and attitude of the drones. During the dynamic correction process of the UAV formation flight, the operation data of the UAVs in the UAV formation is collected in real time through the built-in sensors and communication systems of the UAVs, the collected operation data of the UAVs in the UAV formation is preprocessed, and the preprocessed data is subjected to feature extraction to obtain the real-time position features of the UAVs after dynamic correction, the real-time speed features of the UAVs after dynamic correction, and the real-time attitude features of the UAVs after dynamic correction; Generate an initial population, where each individual in the population represents a dynamically revised flight path plan. The flight path plan is generated based on the actual status of the current UAV formation and the flight mission requirements. Evaluate the dynamically corrected flight path plan in the population, and calculate the fitness of the dynamically corrected flight path plan in the population through a preset fitness function; According to the fitness value of the dynamically corrected flight path plan, excellent individuals are selected as parents to generate the next generation population. The selected parent individuals are crossover operated to generate new offspring individuals, and the offspring individuals are mutated to increase the number of the population. Repeat the fitness evaluation, selection, crossover and mutation operations until the maximum number of iterations is met, select the individual with the highest fitness as the optimal flight path plan, and send the optimal flight path plan to the drones in the drone formation. The drones in the drone formation adjust their flight trajectories according to the new path plan. When the drones execute the new flight path, they continue to collect the operating data of the drones adjusting the flight trajectory under the new path plan, and optimize the operating data of the flight trajectory adjusted according to the new path plan. If the optimal solution for adjusting the flight trajectory under the new path plan is found, the path plan is updated again to adjust the flight trajectory.

[0017] Beneficial effects of the present invention: The present invention significantly improves the flight accuracy and stability of the drone formation in a high-altitude complex environment by dynamically correcting the flight path of the drone formation. The drone can fly more accurately according to the preset path and formation, reducing flight deviations caused by environmental or signal interference. By detecting and matching the real-time communication information of the drone formation, the present invention can promptly discover and solve the problem of weak or interrupted communication signals. When the signal strength is insufficient, the dynamic mobile base station drone is started as a communication relay to ensure the continuity and stability of the internal communication of the drone formation. Using the digital twin model and genetic algorithm, the present invention can continuously optimize the flight path and formation of the drone formation. By real-time monitoring and adjusting the flight plan, the drone formation can adapt to environmental changes and mission requirements more quickly, and improve the efficiency and accuracy of task execution. Through efficient communication connection configuration and real-time data exchange, the present invention enhances the collaborative control capability of the drone formation, and the drones can share status information and mission instructions in real time to achieve cluster intelligent decision-making and highly autonomous collaborative control.

[0018] The present invention considers a variety of potential problems and interference factors in the collaborative planning process of drone formations and provides corresponding solutions, so that drone formations have stronger adaptability and robustness when facing emergencies or unknown environments. Due to improved flight accuracy and stability, and enhanced communication and collaborative control capabilities, the present invention enables drone formations to more reliably perform complex and changeable flight missions, such as search and rescue, environmental monitoring, target tracking, etc.

[0019] In summary, the beneficial effects of the present invention are not only to improve the accuracy and stability of the UAV formation flight process, but also to comprehensively enhance the mission execution efficiency and collaborative control capabilities of the UAV formation, providing strong support for the application of UAVs in a wider range of fields. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0021] Figure 1 A schematic diagram of a method flow chart provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. The technical solutions provided by the embodiments of the present invention are described in detail below in conjunction with the drawings.

[0023] In order to better understand the purpose of the present invention, the present invention is described in further detail below.

[0024] See also Figure 1 The present invention provides a UAV formation collaborative planning method, comprising: Step S101, obtaining the UAV formation collaborative planning flight mission data and the UAV operation data in the UAV formation, obtaining the UAV formation flight area natural environment information and the UAV formation flight path information according to the UAV formation collaborative planning flight mission data, establishing the UAV formation flight segmentation area according to the UAV formation flight path information, retrieving the historical data of the UAVs in the UAV formation flight segmentation area, and establishing the UAV formation flight area natural environment simulation model according to the historical data in the UAV formation flight segmentation area and the UAV formation flight area natural environment information; The UAV formation collaboratively plans flight mission data and obtains mission-related data including flight mission objectives, flight area information, flight path information, flight communication connection information, communication methods between UAVs within the UAV formation, and flight communication frequency connections.

[0025] The drone operation data within the drone formation collects the real-time position coordinates, flight speed, flight attitude (including pitch angle, yaw angle and roll angle) of the drone in flight, sensor data (such as data collected by meteorological sensors, cameras and radars), status information of the drone's mechanical parts and electronic equipment, and the remaining power of the drone.

[0026] Natural environment information extraction: Based on the UAV formation collaborative planning flight mission data, the natural environment information of the UAV formation flight area, such as meteorological conditions, is extracted.

[0027] Flight path information confirmation: determine the flight path information of the drone formation, including the starting point, end point, key path points, etc.

[0028] Establish a flight segment area and divide the flight area into several segments according to the flight path information. Each segment contains a specific flight path. Retrieve the historical flight data of the drone in each flight segment area to analyze the flight characteristics of the area.

[0029] The natural environment simulation model is constructed by combining the historical data of the UAV formation flight segment area and the natural environment information of the flight area, and using mathematical modeling or simulation technology to establish a natural environment simulation model of the UAV formation flight area. The natural environment simulation model can simulate the flight conditions of UAVs under different natural environment conditions and provide basic data support for subsequent flight planning. It provides detailed data support and environmental simulation basis for the flight planning of UAV formations, which is conducive to the dynamic correction and optimization of flight paths in subsequent steps.

[0030] Step S102, according to the drone formation collaborative planning flight mission data and the drone operation data in the drone formation, determine the number of drones in real-time flight of the drone formation, establish identity tags for the drones in real-time flight of the drone formation, retrieve the drone formation communication connection information included in the drone formation collaborative planning flight mission data, complete the communication connection configuration of the drone formation through the drone formation real-time flight drones to establish identity tags, and obtain the drone formation real-time communication information; According to the UAV formation collaborative planning flight mission data and the real-time operation data of each UAV in the UAV formation, check whether the UAV has been started and participated in the current flight mission, and determine the number of UAVs currently flying in real time.

[0031] A unique identity tag is created for each drone in real-time flight. The identity tag usually contains information such as the drone's MAC address, serial number, and timestamp to facilitate identification and distinction between different drones.

[0032] The communication connection information of the UAV formation is retrieved from the UAV formation collaborative planning flight mission data. The communication connection information of the UAV formation includes the communication channel, communication frequency, communication protocol, etc. between the UAVs, which establishes the basis for the communication connection between the UAVs.

[0033] Using the identity tags of the real-time flying drones in the drone formation, combined with the communication connection information of the drone formation, the communication connection configuration of the drones in the drone formation is performed, including assigning communication parameters such as channels and frequencies to each drone.

[0034] The specific operation includes sending communication configuration instructions to each drone. After receiving the instructions, the drone configures its own communication equipment according to the content of the instructions, thereby establishing a real-time communication link within the drone formation.

[0035] Through the above steps, each drone in the drone formation will be able to exchange flight data, status information and mission instructions in real time, forming real-time communication information of the drone formation for subsequent flight path planning and dynamic correction. The drones in the drone formation are not only accurately counted and identified, but also through efficient communication connection configuration, real-time communication within the formation is realized, providing a data basis for subsequent dynamic correction of flight paths and formation adjustments.

[0036] Step S103, detecting the real-time communication information of the drone formation, detecting and obtaining real-time drone formation signal strength information, and sorting the detected drone formation signal strength information to obtain a drone formation signal strength information set, sequentially obtaining the position information of the drones in the drone formation signal strength information set, establishing a drone formation drone position information set, matching the drone formation signal strength information set with the drone formation drone position information set, and obtaining the real-time drone signal strengths in the drone formation and the distance information between the drones; Comprehensive detection of real-time communication information within the UAV formation includes receiving and parsing the communication data packets sent by each UAV to obtain information about key communication parameters such as signal strength, data integrity, and transmission delay.

[0037] The real-time signal strength value of each drone is obtained, and the detected signal strength information is sorted to form a drone formation signal strength information set. The drone formation signal strength information set is arranged from strong to weak (or from weak to strong) according to the signal strength, which is convenient for subsequent analysis and processing.

[0038] Visit each drone in the drone formation signal strength information set in turn, obtain its current location information (including latitude, longitude, altitude, etc.) through its built-in GPS or other positioning device, and organize this location information into a set, namely the drone formation drone location information set. This set corresponds to the signal strength information set, so that the signal strength and location information of each drone can be matched.

[0039] The signal strength information set of the drone formation is matched with the position information set of the drones in the drone formation, and the signal strength of each drone is matched with its specific position in three-dimensional space. Through this matching, it is possible to intuitively understand which areas in the drone formation have strong signals and which areas have weak signals, thus providing a basis for subsequent communication adjustments and flight planning.

[0040] On the basis of matching the signal strength and position information, the mutual distance between each drone in the drone formation is further calculated. The calculation can use the distance calculation formula in three-dimensional space (such as Euclidean distance). Through the calculated distance information, the spatial distribution map of the drone formation is constructed to clarify the relative position relationship between each drone.

[0041] Through the above steps, step S103 not only obtains the real-time signal strength and location information of the drone formation, but also obtains the mutual distance between the drones through matching and calculation. This is crucial for evaluating the communication quality of the drone formation, identifying potential communication blind spots, and planning subsequent flight paths. In subsequent steps, the real-time signal strength and location information of the drone formation will be used to generate a digital twin model, adjust the formation, and perform dynamic corrections to the flight path.

[0042] Step S104, substitute the signal strength of drones in the real-time drone formation and the distance information between drones into the preset digital twin model, generate a first real-time drone formation flight image, receive the drone formation signal base station designated command, the drone formation signal base station designated command includes the drone internal network hotspot start command and the drone flight position adjustment command, set the drones in the drone formation as drone formation signal base stations in the real-time drone formation flight image according to the drone formation signal base station designated command, adjust the drone formation formation according to the drone flight position adjustment command, obtain the adjusted drone formation formation, and collect real-time operation data of the adjusted drone formation formation to obtain the real-time operation data of the adjusted drone formation formation; First, the signal strength of each drone in the real-time drone formation and the distance between them are substituted into the preset digital twin model, which is a virtual environment that can simulate the actual flight conditions of drones, including their position, speed, attitude, etc. By inputting these data, the model can generate the first real-time drone formation flight image, reflecting the real-time flight status of the current drone formation.

[0043] Receive designated commands issued by the drone formation signal base station. The designated commands issued by the drone formation signal base station include the network hotspot startup command within the drone and the drone flight position adjustment command. The drone formation signal base station refers to the core drone in the formation responsible for communication and data exchange, and it is responsible for coordinating the actions of the entire formation.

[0044] According to the command to start the network hotspot within the drone issued by the drone formation signal base station, the network hotspot within the drone is started by simulating in the digital twin model, so that the drones in the drone formation can connect to each other and exchange data.

[0045] At the same time, according to the UAV flight position adjustment command, the flight position of the UAV formation is adjusted in the digital twin model. This adjustment is based on the preset flight position and real-time flight data. The purpose is to optimize the flight formation of the formation to improve flight efficiency and mission completion quality. Through the simulation of the digital twin model, the best flight position and formation can be found, and the corresponding adjustment plan can be generated.

[0046] After adjusting the flight position of the drone formation in the digital twin model, the first real-time drone formation flight image is generated and updated to reflect the adjusted formation status. This image will serve as the basis for subsequent analysis and decision-making.

[0047] Finally, real-time operation data of the adjusted UAV formation is collected, including the adjusted UAV position information, attitude, speed, sensor data, etc., to evaluate the adjustment effect and provide a basis for subsequent optimization. The real-time operation data will be further processed and analyzed so that the UAV formation can efficiently complete the flight mission according to the predetermined goals and paths.

[0048] Step S105, substituting the real-time UAV formation collaborative planning flight mission data and the UAV operation data in the UAV formation into the UAV formation flight area natural environment simulation model to obtain the UAV formation pre-flight area natural environment simulation data, substituting the UAV formation pre-flight area natural environment simulation data and the adjusted UAV formation formation real-time operation data into the preset digital twin model to generate a second real-time UAV formation flight image; The real-time acquired UAV formation collaborative planning flight mission data and the real-time operation data of each UAV in the UAV formation are substituted into the natural environment simulation model of the UAV formation flight area. The natural environment simulation model of the UAV formation flight area is used to simulate the natural environmental conditions in the area where the UAV formation is to fly, such as wind direction, wind speed, temperature, humidity, air pressure, etc. By inputting these data, the natural environment simulation model of the UAV formation flight area can generate natural environment simulation data of the UAV formation pre-flight area. The natural environment simulation data of the UAV formation pre-flight area reflects the impact of the flight environment on the UAV formation flight.

[0049] The natural environment simulation data of the pre-flight area of ​​the UAV formation is combined with the real-time operation data of the adjusted UAV formation. The adjusted UAV formation is the result of optimization based on the previous steps (such as step S104), and its real-time operation data includes the position, speed, attitude, sensor data, etc. of the UAV. The position, speed, attitude, sensor data, etc. of the UAV, together with the natural environment simulation data, provide the comprehensive environmental conditions encountered by the UAV formation during the actual flight.

[0050] These comprehensive data are substituted into the preset digital twin model, and the digital twin model uses these data to generate a second real-time UAV formation flight image. The second real-time UAV formation flight image not only reflects the real-time flight status and formation of the UAV formation, but also takes into account the influence of the flight environment. Therefore, it is closer to the actual flight situation.

[0051] The generation of the second real-time UAV formation flight image provides an important reference for subsequent flight path correction and optimization. By comparing with the first real-time UAV formation flight image (generated in step S104), the deviations and errors encountered by the UAV formation in the actual flight environment can be evaluated, and then targeted corrections and optimizations can be made.

[0052] In general, step S105 comprehensively considers flight mission data, UAV operation data and natural environmental conditions, and uses the digital twin model to generate a second real-time UAV formation flight image that is closer to the actual flight situation, providing strong support for subsequent flight path correction and optimization.

[0053] Step S106, compare the first real-time UAV formation flight image with the second real-time UAV formation flight image to obtain expected UAV formation flight error information, dynamically correct the flight paths of the UAVs in the UAV formation according to the expected UAV formation flight error information to obtain a corrected UAV flight path, send the corrected UAV flight path to the UAVs in the UAV formation, continue to collect operating data of the UAVs in the UAV formation, and optimize the flight paths of the UAVs in the UAV formation through a genetic algorithm until the UAVs in the UAV formation complete the UAV formation collaborative planning flight mission.

[0054] The first real-time UAV formation flight image generated in step S104 (reflecting the flight status of the UAV formation without considering the actual flight environment) is compared with the second real-time UAV formation flight image generated in step S105 (reflecting the comprehensive status of the UAV formation in the actual flight environment). The difference between the two is identified through comparison. The difference mainly comes from the impact of the actual flight environment on the flight status of the UAV formation.

[0055] Based on the comparison results of the flight images, the expected UAV formation flight error information is calculated. The expected UAV formation flight error information includes position deviation, attitude deviation, speed deviation, etc., which together reflect the deviation from the predetermined flight path encountered by the UAV formation during the actual flight.

[0056] Based on the predicted flight error information, the flight path of each UAV in the UAV formation is dynamically corrected. The purpose of the correction is to make the actual flight path of the UAV as close to the predetermined flight path as possible to ensure the accurate completion of the flight mission.

[0057] Correction operations include adjusting the drone's flight speed, flight direction, flight altitude and other parameters to compensate for deviations caused by the actual flight environment.

[0058] The corrected UAV flight path will be sent to each UAV in the UAV formation in a timely manner. After receiving the new flight path, the UAV will fly according to the new instructions.

[0059] While the drone formation is flying along the corrected flight path, the system continuously collects the operating data of each drone in the drone formation. The operating data of each drone in the drone formation includes the real-time position, speed, attitude, sensor data, etc. of the drone.

[0060] The collected operation data is analyzed and processed through optimization algorithms such as genetic algorithms to further optimize the flight path of the drone formation. The optimization process involves multiple iterations and adjustments to ensure that the drone formation can complete the flight mission in the best way. The flight status and progress of the drone formation are monitored in real time. When the drone formation completes the scheduled flight mission and meets the mission end conditions (such as reaching the designated target point, completing the designated action, etc.), the flight mission is determined to be over.

[0061] Specifically, the UAV formation collaborative planning method of the present invention includes, in step S101: The UAV formation collaborative planning flight mission data includes flight mission objectives, flight area information, flight path information, flight communication connection information, communication methods between UAVs within the UAV formation, and flight communication frequency connections; The real-time location of the drone includes the real-time location coordinates of the drone in flight, flight speed, flight attitude, sensor data, flight attitude information of the drone, drone sensor data, status information of the drone's mechanical parts and electronic equipment, and the remaining battery power of the drone; The flight attitude includes pitch angle, yaw angle and roll angle; Drone sensor data includes data collected by weather sensors, cameras, and radars.

[0062] Specifically, the UAV formation collaborative planning method of the present invention includes, in step S102: Collecting UAV formation collaborative planning flight mission data, which includes flight mission objectives, UAV formation composition, expected flight area information, and preset flight paths; Receive the operation data of each drone in the drone formation in real time, including real-time position, flight speed, flight attitude and sensor data; The UAV formation collaborative planning flight mission data and the operation data of each UAV in the UAV formation are analyzed to extract the real-time flight characteristics of the UAV formation. The real-time flight characteristics of the UAV formation include the real-time position characteristics of the UAV, the sensor data characteristics of the UAV, the status characteristics of the UAV, the real-time communication characteristics of the UAV formation, the number of UAVs in real-time flight in the UAV formation, the signal strength information characteristics of the UAV formation, the position information characteristics of the UAVs in the UAV formation, the natural environment simulation data characteristics of the UAV formation flight area, the flight path information characteristics of the UAV formation, and the formation information characteristics of the UAV formation; According to the operation data of each drone in the drone formation, send communication signals to each drone in the drone formation to check whether the communication connection between drones is normal, verify the online status and health status of each drone and whether it has joined the current flight mission, and obtain the real-time detection results of the drone formation; According to the real-time detection results of the UAV formation, the number of UAVs in real-time flight state is calculated, and the number of UAVs in real-time flight state is obtained.

[0063] According to the number of drones in real-time flight status, the real-time flight status record of the drone formation is updated. The real-time flight status record of the drone formation includes the number of flying drones, drone identification and drone status.

[0064] Collecting UAV formation collaborative planning flight mission data: Flight mission objective: Determine the overall mission that the drone formation needs to complete.

[0065] UAV formation composition: Understand the number, models and performance parameters of UAVs in the formation.

[0066] Estimated flight area information: including geographical, climatic and other characteristics of the flight area.

[0067] Preset flight path: Preset UAV formation flight path and key nodes.

[0068] Receive real-time operation data of each drone in the drone formation: Real-time location: The precise location of the drone in flight.

[0069] Flight speed: The current flight speed of the drone.

[0070] Flight attitude: the flight status of the drone, such as direction and tilt.

[0071] Sensor data: including but not limited to data collected by sensors such as meteorology, images, and radar.

[0072] Data analysis and feature extraction: Detailed analysis of the collected flight mission data and real-time operation data, and extraction of key features including: Drone real-time location features: the specific location information of the drone.

[0073] Drone sensor data characteristics: characteristics of the environment, images, and other data collected by the sensors.

[0074] Drone status characteristics: drone health status, battery level, etc.

[0075] Real-time communication characteristics of UAV formation: communication quality and mode between UAVs.

[0076] Real-time flying drone quantity characteristics of drone formation: the number of drones currently in flight.

[0077] UAV formation signal strength information characteristics: signal strength between UAVs.

[0078] UAV formation UAV position information characteristics: the relative position of the UAVs in the formation.

[0079] Characteristics of natural environment simulation data in the UAV formation flight area: Environmental data obtained through simulation.

[0080] UAV formation flight path information characteristics: comparison between actual flight path and preset path.

[0081] UAV formation information characteristics: the arrangement and changes of UAV formations.

[0082] Communication connection check: Send communication signals to each drone in the drone formation to verify whether the communication connection between drones is normal. Check the online status, health status and whether each drone has joined the current flight mission. Based on the communication and status check results, calculate the number of drones in real time. Update the real-time flight status record of the drone formation, including the number of drones in flight, the identity of each drone and its current status.

[0083] Specifically, the UAV formation collaborative planning method of the present invention includes, in step S102: Establish identity tags for the real-time flying drones of the drone formation, retrieve the drone formation communication connection information included in the drone formation collaborative planning flight mission data, and complete the communication connection configuration of the drone formation through the real-time flying drones of the drone formation to obtain the real-time communication information of the drone formation. Based on the real-time status information of the flying drone, an identity tag is established for each drone. The identity tag includes the drone's MAC address, serial number, and timestamp; The UAV formation communication connection information is parsed to obtain the UAV formation communication channel, UAV formation communication frequency and UAV formation communication protocol, and the parsed UAV formation communication connection information is converted into UAV formation communication configuration instructions, and the UAV formation communication configuration instructions are sent to each UAV in the UAV formation. After receiving the instructions, the UAVs in the UAV formation configure the communication equipment of the UAVs according to the UAV formation communication configuration instructions, and establish communication connections between the UAVs in the UAV formation.

[0084] Specifically, the UAV formation collaborative planning method of the present invention includes, in step S103: The communication signal strength in the drone formation signal strength information set is screened to select drone formation signal strength information with a signal lower than the standard communication signal strength, and the drone identity information corresponding to the drone formation signal strength information with a signal lower than the standard communication signal strength is determined; According to the drone identity information corresponding to the drone formation signal strength information lower than the standard communication signal strength, determine the drone real-time flight position information corresponding to the drone formation signal strength information lower than the standard communication signal strength, use the drone real-time flight position information corresponding to the drone formation signal strength information lower than the standard communication signal strength as the reference point, perform a drone signal strength search within a 50-meter radius of the reference point, and obtain the reference point real-time drone signal strength search result; The filtered drone signal strength search results are sorted by signal strength to obtain the benchmark point real-time drone signal strength sorting results. The benchmark point real-time drone signal strength sorting results include the benchmark point real-time drone signal strength sorting results for the first period, the second benchmark point real-time drone signal strength sorting results, and the third benchmark point real-time drone signal strength sorting results.

[0085] In the UAV formation collaborative planning method, in order to ensure effective communication and collaboration within the UAV formation, the present invention takes a series of detailed steps to establish real-time communication connections between UAVs. Specifically, this process includes the following aspects: Creation of identity tags Generation of drone identity tags: Create unique ID tags for each drone in real-time flight. These ID tags contain key information for quick identification and differentiation during communication.

[0086] The main contents of the identity tag include the drone's MAC address, serial number and timestamp. The MAC address provides a unique physical identification of the device, the serial number is used to distinguish drones of the same model, and the timestamp records the time when the tag was generated, which helps with tracking and recording.

[0087] Configuration of communication connection information Calling and parsing of drone formation communication connection information: The communication connection information of the UAV formation is retrieved from the UAV formation collaborative planning flight mission data. This information describes in detail how the UAVs can communicate effectively, including the communication channels, frequencies and protocols used.

[0088] The communication connection information is parsed in detail to extract the channel number, communication frequency and specific communication protocol specifications required for UAV formation communication.

[0089] Generation and sending of communication configuration instructions: The parsed communication connection information is converted into UAV formation communication configuration instructions. These instructions contain the specific parameters and settings required for each UAV to communicate.

[0090] The communication configuration command is sent to each drone in the drone formation. After receiving the command, the drone automatically configures its communication equipment according to the command content to ensure that all drones can communicate according to the predetermined parameters.

[0091] Establishing a communication connection Configuration and connection of drone communication equipment: Each drone automatically configures its internal communication equipment according to the received communication configuration instructions. This includes setting the correct communication channel, frequency and complying with specific communication protocols.

[0092] After the configuration is completed, effective real-time communication connections are established between the drones in the drone formation. These connections support high-speed and stable data transmission, ensuring that the drones can exchange flight data, status information and mission instructions in real time.

[0093] Through the above steps, the present invention establishes a clear identity tag for each drone in the drone formation and realizes efficient communication connection within the formation. This not only improves the coordination efficiency of the drone formation, but also enhances the adaptability and stability of the formation in complex environments.

[0094] Specifically, the UAV formation collaborative planning method of the present invention includes, in step S103: Perform cluster analysis on the ranking results of the real-time UAV signal strength of the benchmark points in the first period, the ranking results of the real-time UAV signal strength of the second benchmark points, and the ranking results of the real-time UAV signal strength of the third benchmark points to obtain the cluster analysis results of the real-time UAV signal strength of the benchmark points; The real-time UAV signal strength clustering analysis results of the benchmark points are matched with the distance information between the UAVs to obtain the distance data of each UAV in the real-time UAV signal strength clustering analysis results of the benchmark points; The distance data of each drone in the cluster analysis results of the real-time drone signal strength of the benchmark point is selected within 50m, and the drone signal with the best ranking result of the real-time drone signal strength of the benchmark point is selected to obtain the dynamic base station screening result, and the corresponding drone is matched according to the dynamic base station screening result, and the drone that matches the dynamic base station screening result is used as the dynamic mobile base station drone; When the real-time drone signal strength at the reference point is lower than the preset value, the dynamic mobile base station drone is activated as a communication base station. The dynamic mobile base station drone sends out a wireless network hotspot to establish a communication connection with each drone in the drone formation.

[0095] Signal strength screening and benchmark determination,First, all communication signal strengths within the UAV formation are monitored and collected in real time to form a signal strength information set. According to the preset standard communication signal strength threshold, the signal strength in the signal strength information set is screened to identify signal strength information below the standard value.

[0096] For the filtered low signal strength information, the corresponding drone identity information is further determined, that is, which drones have weaker communication signals.

[0097] For each drone with a signal below the standard, its real-time flight position information is used as a reference point. With this reference point as the center, the system conducts a detailed signal strength search within a radius of 50 meters. This range is set based on the effective communication distance and signal attenuation characteristics of the communication equipment. Through this search process, the real-time signal strength data of all drones in the area can be obtained, providing a basis for subsequent signal enhancement and formation adjustment.

[0098] The searched drone signal strength data is sorted to generate the real-time drone signal strength sorting results of the benchmark points. In order to more comprehensively understand the changes in signal strength, the sorting results may be divided into different time periods, such as the first period, the second period, and the third period, and each period corresponds to the signal strength record within a period of time.

[0099] By analyzing the signal strength ranking results at different time periods, we can more accurately grasp the changing trends and patterns of communication signals within the UAV formation. Time period analysis helps to identify possible interference factors (such as terrain, weather, etc.) to the communication signal, and provide data support for subsequent communication optimization and formation adjustment.

[0100] Through the above steps, the present invention effectively monitors the communication signal strength within the UAV formation and promptly identifies and resolves potential communication problems. This not only improves the coordination efficiency and stability of the UAV formation, but also improves the reliability and safety of the formation when performing complex tasks.

[0101] Specifically, the UAV formation collaborative planning method of the present invention includes, in step S104: Receive the designated command of the UAV formation signal base station, which includes the network hotspot start command within the UAV and the UAV flight position adjustment command; Parse the command specified by the base station of the received UAV formation signal to determine the parameters to be adjusted within the UAV formation, including the target coordinates of the position adjustment and the change of the formation shape; According to the parameters adjusted within the drone formation, the flight position of the drone formation is adjusted in the preset digital twin model, and a first real-time drone formation flight image is generated and updated; In the digital twin model, the drones in the drone formation are set as new drone formation signal base stations. The positional relationship between each drone in the drone formation and the new drone formation signal base station is calculated through the digital twin model. The positional relationship between each drone in the drone formation and the new drone formation signal base station includes the distance and angle between each drone in the drone formation and the new drone formation signal base station. According to the distance and angle between each drone in the drone formation and the new drone formation signal base station, the distance and direction between each drone and the target position are calculated, and a drone formation adjustment command is generated; The drone formation adjustment command is sent to the drones in the drone formation through the communication network, and the drone formation receives the drone formation adjustment command in real time, and the drones in the drone formation adjust their flight attitude and position; Real-time operation data of the adjusted UAV formation is collected to obtain real-time operation data of the adjusted UAV formation.

[0102] The signal base station in the drone formation is responsible for sending commands to the entire formation, including the start-up command of the network hotspot within the drone and the adjustment command of the drone's flight position. The command is transmitted to each drone in the formation in real time through the communication network, so that all drones can receive the adjustment instructions in time.

[0103] After receiving the designated commands, each drone first interprets these commands to identify the specific parameters that need to be adjusted in the formation. These parameters usually include the target coordinates of the position adjustment (i.e. the new position the drone should fly to) and the requirements for changing the formation shape (such as the formation spacing, angle, etc.).

[0104] Adjust the flight position in the digital twin model. Using the preset digital twin model, the system first simulates the adjustment of the flight position of the drone formation in the virtual environment according to the analyzed adjustment parameters. Through digital twin technology, the flight trajectory of the drone can be predicted and adjusted intuitively and accurately, reducing errors and uncertainties in actual flight.

[0105] Based on the adjusted flight positions, the digital twin model generates the first real-time drone formation flight image. This image reflects the flight status and formation layout of the formation in real time. As the formation is adjusted, the flight image is constantly updated to ensure a high degree of consistency between the model and the actual situation.

[0106] In the digital twin model, a certain drone in the formation is set as a new signal base station as needed. This change helps optimize the communication link and improve signal transmission efficiency. By calculating the position relationship (including distance and angle) between each drone and the new signal base station, the system can accurately plan the communication path and signal coverage between drones.

[0107] Based on the positional relationship between the drones and the new signal base station, the precise distance and direction between each drone and the target position (i.e. the adjusted flight position) are further calculated. The calculation results provide key data support for generating the formation adjustment command of the drone formation.

[0108] According to the calculation results, a detailed UAV formation adjustment command is generated. The UAV formation adjustment command includes the flight attitude and position adjustment measures that each UAV needs to take.

[0109] The formation adjustment command of the drone formation is sent to each drone in the formation in real time through the communication network. After receiving the command, the drone immediately performs the corresponding flight attitude and position adjustment operations. During the formation adjustment process of the drone formation, the system continuously collects the real-time operation data of each drone. The real-time operation data of the drone includes key indicators such as position information, flight speed, and attitude parameters. Through real-time data collection, the system can fully grasp the operation status of the formation and provide data support for subsequent optimization and adjustment.

[0110] Specifically, the UAV formation collaborative planning method of the present invention includes, in step S104: The real-time operation data of the adjusted UAV formation includes: position information of UAVs within the adjusted UAV formation, attitude of UAVs within the adjusted UAV formation, direction of UAVs within the adjusted UAV formation, flight status of UAVs within the adjusted UAV formation, communication status of UAVs within the adjusted UAV formation, sensor data of UAVs within the adjusted UAV formation, environmental data of UAVs within the adjusted UAV formation, fault information of UAVs within the adjusted UAV formation, and mission data of UAVs within the adjusted UAV formation.

[0111] In step S104 of the UAV formation collaborative planning method, after the UAV formation is adjusted and flying stably, the operation data is collected and processed in real time to comprehensively monitor and timely adjust the formation status.

[0112] The precise position coordinates of each drone in three-dimensional space, including longitude, latitude and altitude information, are obtained in real time through GPS or other positioning technologies. The position data is an important basis for evaluating whether the formation meets the predetermined requirements.

[0113] The attitude information of a drone reflects its flight direction and angle, including pitch, yaw, and roll. These data are acquired in real time through attitude sensors (such as gyroscopes and accelerometers) to monitor the flight stability and attitude adjustment effect of the drone.

[0114] In addition to attitude information, the flight direction of the drone is also an important monitoring indicator. It reflects the direction of the drone's nose, which is crucial for the formation to maintain a consistent flight direction. The flight status of the drones in the adjusted drone formation includes the flight speed, acceleration and other dynamic parameters of the drones. Dynamic parameters such as acceleration directly reflect the flight performance and response speed of the drone, which is of great significance for evaluating the overall flight effectiveness of the formation.

[0115] After the adjustment, the communication status data of drones in the drone formation includes key indicators such as signal strength, packet loss rate, and delay. By monitoring the communication status in real time, potential problems in the communication link can be discovered and solved in a timely manner.

[0116] Various sensors carried by drones (such as meteorological sensors, cameras, radars, etc.) collect a large amount of environmental information and target data, which play a vital role in the environmental perception, target tracking and decision-making of drone formations.

[0117] The adjusted drone environmental data in the drone formation includes meteorological conditions such as wind speed, wind direction, air pressure, temperature, and natural environment data such as topography. By acquiring and analyzing this data in real time, the drone formation can better adapt to the complex and changing external environment and improve flight safety and mission execution efficiency.

[0118] After adjusting the drone fault information in the drone formation, the operating status and health of the drones are monitored in real time. When a fault or abnormal situation (such as damage to mechanical parts, failure of electronic equipment, etc.) is found, the fault information is immediately recorded and reported.

[0119] The mission data of the drones in the adjusted drone formation includes key indicators such as mission progress and target completion. By collecting and analyzing mission data in real time, the mission execution efficiency of the drone formation can be evaluated, providing a basis for subsequent mission planning and adjustments.

[0120] In summary, the real-time operation data of the adjusted UAV formation collected in step S104 comprehensively covers multiple aspects such as the position, attitude, flight status, communication status, sensor data, environmental data, fault information and mission data of the UAVs.

[0121] Specifically, the UAV formation collaborative planning method of the present invention includes, in step S106: Matching the first real-time UAV formation flight image and the second real-time UAV formation flight image in terms of UAV positions and UAV formation shapes, to obtain a matching result of the first real-time UAV formation flight image and the second real-time UAV formation flight image in terms of UAV positions and UAV formation shapes; Perform feature extraction on the matching results of the first real-time UAV formation flight image and the second real-time UAV formation flight image in terms of the UAV positions and the UAV formation shape, and obtain the position coordinate features, flight attitude features, speed features, formation shape features, and relative distance features of the UAVs in the first real-time UAV formation flight image and the second real-time UAV formation flight image; Compare the corresponding features in the first real-time UAV formation flight image and the second real-time UAV formation flight image one by one, the comparison content includes the difference between the actual position and the simulated position of the UAV, the deviation of the flight attitude, and the deformation degree of the formation shape, and obtain the result of comparative analysis of the first real-time UAV formation flight image and the second real-time UAV formation flight image; Based on the results of comparative analysis of the first real-time UAV formation flight image and the second real-time UAV formation flight image, the expected error information during the UAV formation flight is calculated. The expected error information during the UAV formation flight includes the number of meters of position deviation and the angle of attitude deviation. The cumulative error of the flight path of the UAVs in the UAV formation is calculated.

[0122] In step S106 of the UAV formation collaborative planning method, in order to ensure that the UAV formation can accurately fly according to the predetermined path and formation, the present invention adopts a method of comparing and analyzing the first real-time UAV formation flight image and the second real-time UAV formation flight image to evaluate the deviation between the actual performance during the flight and the theoretical expectation, and perform dynamic correction accordingly. The specific steps are as follows: The first real-time UAV formation flight image (generated based on the digital twin model, an ideal flight state without considering the impact of the actual environment) is matched with the second real-time UAV formation flight image (real-time flight state considering the impact of the actual flight environment) in terms of UAV position and formation shape. The difference between the two can be intuitively compared through matching.

[0123] Next, feature extraction is performed on the two matched flight images, focusing on the following key features: Position coordinate feature: Extract the precise position coordinates of each drone in the image.

[0124] Flight attitude characteristics: including pitch angle, yaw angle and roll angle, etc., reflecting the flight direction and angle of the drone.

[0125] Speed ​​characteristics: real-time flight speed information of the drone.

[0126] Formation shape characteristics: the overall layout and shape of the drone formation.

[0127] Relative distance feature: the relative distance relationship between drones in a formation.

[0128] The extracted features are compared one by one. The main comparison contents include: Difference between actual and simulated positions: Calculates the deviation between the actual flight position and the ideal flight position for each drone.

[0129] Flight attitude deviation: compare the angle difference between the actual flight attitude and the theoretical attitude.

[0130] Degree of deformation of formation shape: Evaluate the degree of similarity or difference between the actual formation shape and the predetermined formation shape.

[0131] Based on the results of the above comparative analysis, the expected error information during the UAV formation flight is calculated, including: Position Deviation in Meters: Quantifies the straight-line distance deviation between the actual position of the drone and the ideal position.

[0132] Angle of attitude deviation: quantifies the angle deviation between the actual flight attitude of the drone and the ideal attitude in degrees.

[0133] Cumulative error: Taking into account the position deviation and attitude deviation of all drones in the entire formation, the cumulative error of the flight path of the drone formation is calculated to evaluate the overall flight accuracy.

[0134] Through this series of comparative analysis steps, the present invention can identify the deviation between the UAV formation and the predetermined path and formation during the actual flight process, and provide reliable data support for subsequent dynamic correction. At the same time, based on the calculation results of the cumulative error, the flight path and formation control strategy can be further optimized to improve the flight accuracy and mission execution efficiency of the UAV formation.

[0135] Specifically, the UAV formation collaborative planning method of the present invention includes, in step S106: According to the accumulated errors of the flight paths of the drones in the drone formation, the flight paths of the drones in the drone formation are dynamically corrected. The dynamic correction includes adjusting the flight speed, direction and attitude of the drones. During the dynamic correction process of the UAV formation flight, the operation data of the UAVs in the UAV formation is collected in real time through the built-in sensors and communication systems of the UAVs, the collected operation data of the UAVs in the UAV formation is preprocessed, and the preprocessed data is subjected to feature extraction to obtain the real-time position features of the UAVs after dynamic correction, the real-time speed features of the UAVs after dynamic correction, and the real-time attitude features of the UAVs after dynamic correction; Generate an initial population, where each individual in the population represents a dynamically revised flight path plan. The flight path plan is generated based on the actual status of the current UAV formation and the flight mission requirements. Evaluate the dynamically corrected flight path plan in the population, and calculate the fitness of the dynamically corrected flight path plan in the population through a preset fitness function; According to the fitness value of the dynamically corrected flight path plan, excellent individuals are selected as parents to generate the next generation population. The selected parent individuals are crossover operated to generate new offspring individuals, and the offspring individuals are mutated to increase the number of the population. Repeat the fitness evaluation, selection, crossover and mutation operations until the maximum number of iterations is met, select the individual with the highest fitness as the optimal flight path plan, and send the optimal flight path plan to the drones in the drone formation. The drones in the drone formation adjust their flight trajectories according to the new path plan. When the drones execute the new flight path, they continue to collect the operating data of the drones adjusting the flight trajectory under the new path plan, and optimize the operating data of the flight trajectory adjusted according to the new path plan. If the optimal solution for adjusting the flight trajectory under the new path plan is found, the path plan is updated again to adjust the flight trajectory.

[0136] First, based on the cumulative error of the flight paths of the drones in the drone formation (including the number of meters of position deviation and the angle of attitude deviation), the flight paths of the drones are dynamically adjusted. The adjustment measures include: Adjust the drone's flight speed to speed up or slow down the flight process and compensate for position deviation.

[0137] Adjust the flight direction of the drone so that it can point to the target point more accurately and reduce directional deviation.

[0138] Adjust the flight attitude of the drone (pitch angle, yaw angle and roll angle) to ensure that the drone maintains a stable flight attitude and avoid the influence of attitude deviation on the flight path.

[0139] Real-time data collection and processing: During the dynamic correction process, the drone's operating data is collected in real time through the drone's built-in sensors and communication systems. The drone's built-in sensors and communication systems collect the drone's operating data in real time, including but not limited to the drone's position, speed, attitude, sensor readings, etc.

[0140] The collected raw data is preprocessed, including filtering, denoising and other steps, to improve the quality and accuracy of the data.

[0141] Feature extraction is performed on the preprocessed data to extract the real-time position features, real-time speed features, and real-time attitude features of the dynamically corrected drone, providing a basis for subsequent analysis and optimization.

[0142] Optimization based on genetic algorithm: Generate an initial population, each individual in the population represents a possible dynamically revised flight path plan. The flight path plan is generated based on the actual status of the current UAV formation and the flight mission requirements, aiming to reduce the cumulative error by optimizing the path.

[0143] Each flight path plan in the population is evaluated and its fitness is calculated through a preset fitness function. The fitness function usually takes into account multiple factors such as path length, flight time, energy consumption, safety, etc. to ensure that the generated path is both efficient and safe.

[0144] According to the fitness value, excellent individuals are selected as parents to generate the next generation of population. New offspring individuals are generated through crossover operations (such as single-point crossover, multi-point crossover, etc.), and the diversity of the population is increased through mutation operations (such as random mutation, Gaussian mutation, etc.).

[0145] Repeat the fitness evaluation, selection, crossover and mutation operations until the preset maximum number of iterations is met or the optimal solution that meets the conditions is found.

[0146] The individual with the highest fitness is selected as the optimal flight path plan and sent to each drone in the drone formation. The drone adjusts its flight trajectory according to the new path plan and continues to perform the flight mission.

[0147] When the drone executes a new flight path, it continuously collects its operating data and optimizes the flight trajectory. If it finds that the new path plan can further reduce the cumulative error or improve flight efficiency, the system will update the path plan again and notify the drone to make adjustments. Through this continuous optimization and feedback mechanism, the drone formation can continuously adapt to environmental changes and mission requirements during the actual flight process to ensure the smooth completion of the flight mission.

[0148] In summary, the UAV formation collaborative planning method described in the present invention effectively improves the flight accuracy and stability of the UAV formation in a high-altitude complex environment through dynamic correction and optimization strategy based on genetic algorithm in step S106.

[0149] The technology of the present invention solves the problem that the UAV formation cannot accurately fly according to the pre-set flight planning path and flight formation during high-altitude flight due to the influence of the high-altitude natural environment and various electronic signals. The specific solution is as follows; The present invention establishes a natural environment simulation model of the drone formation flight area by acquiring drone formation collaborative planning flight mission data and drone operation data. The natural environment simulation model of the drone formation flight area can simulate the high-altitude natural environment and help predict and respond to the impact of the natural environment on flight. The present invention determines the number of drones flying in the drone formation in real time, establishes identity tags for them, and completes the communication connection configuration. The signal strength of the drone formation is monitored in real time, and the signal strength and distance information between the drones are obtained through sorting and position matching. The real-time signal strength and distance information are substituted into the preset digital twin model to generate a first real-time drone formation flight image. By comparing the simulated flight image with the second flight image generated by the actual flight data, the error in the flight process is identified.

[0150] Based on the estimated error information obtained from the comparative analysis, the flight path of the drone formation is dynamically corrected, including adjusting the flight speed, direction and attitude. The flight path is continuously optimized using genetic algorithms to ensure that the drone formation can fly more accurately according to the preset path and formation. During the flight, the real-time operation data of the drone is continuously collected, including position, attitude, speed, sensor data, etc., to continuously update the natural environment simulation model and digital twin model of the flight area to ensure that the model is consistent with the actual situation.

[0151] When the signal strength is lower than the preset value, the dynamic mobile base station drone is activated to provide a stable communication network and enhance the communication stability and reliability of the drone formation during high-altitude flight. According to the command specified by the drone formation signal base station, the formation and flight position of the drone formation are dynamically adjusted to adapt to the changes in the high-altitude flight environment and ensure the overall stability and coordination of the formation.

[0152] The technical solution of the present invention effectively solves the impact of the high-altitude natural environment and various electronic signals on the flight path and formation accuracy of the UAV formation, and improves the stability and mission execution efficiency of the UAV formation in high-altitude flight.

[0153] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations, and the above-described embodiments of the present invention do not constitute a limitation on the scope of protection of the present invention.

Claims

1. A UAV formation collaborative planning method, characterized in that: include: Step S101, obtaining the UAV formation collaborative planning flight mission data and the UAV operation data in the UAV formation, obtaining the UAV formation flight area natural environment information and the UAV formation flight path information according to the UAV formation collaborative planning flight mission data, establishing the UAV formation flight segmentation area according to the UAV formation flight path information, retrieving the historical data of the UAVs in the UAV formation flight segmentation area, and establishing the UAV formation flight area natural environment simulation model according to the historical data in the UAV formation flight segmentation area and the UAV formation flight area natural environment information; Step S102, according to the drone formation collaborative planning flight mission data and the drone operation data in the drone formation, determine the number of drones in real-time flight of the drone formation, establish identity tags for the drones in real-time flight of the drone formation, retrieve the drone formation communication connection information included in the drone formation collaborative planning flight mission data, complete the communication connection configuration of the drone formation through the drone formation real-time flight drones to establish identity tags, and obtain the drone formation real-time communication information; Step S103, detecting the real-time communication information of the drone formation, detecting and obtaining real-time drone formation signal strength information, and sorting the detected drone formation signal strength information to obtain a drone formation signal strength information set, sequentially obtaining the position information of the drones in the drone formation signal strength information set, establishing a drone formation drone position information set, matching the drone formation signal strength information set with the drone formation drone position information set, and obtaining the real-time drone signal strengths in the drone formation and the distance information between the drones; Step S104, substitute the signal strength of drones in the real-time drone formation and the distance information between drones into the preset digital twin model, generate a first real-time drone formation flight image, receive the drone formation signal base station designated command, the drone formation signal base station designated command includes the drone internal network hotspot start command and the drone flight position adjustment command, set the drones in the drone formation as drone formation signal base stations in the real-time drone formation flight image according to the drone formation signal base station designated command, adjust the drone formation formation according to the drone flight position adjustment command, obtain the adjusted drone formation formation, and collect real-time operation data of the adjusted drone formation formation to obtain the real-time operation data of the adjusted drone formation formation; Step S105, substituting the real-time UAV formation collaborative planning flight mission data and the UAV operation data in the UAV formation into the UAV formation flight area natural environment simulation model to obtain the UAV formation pre-flight area natural environment simulation data, substituting the UAV formation pre-flight area natural environment simulation data and the adjusted UAV formation formation real-time operation data into the preset digital twin model to generate a second real-time UAV formation flight image; Step S106, compare the first real-time UAV formation flight image with the second real-time UAV formation flight image to obtain expected UAV formation flight error information, dynamically correct the flight paths of the UAVs in the UAV formation according to the expected UAV formation flight error information to obtain a corrected UAV flight path, send the corrected UAV flight path to the UAVs in the UAV formation, continue to collect operating data of the UAVs in the UAV formation, and optimize the flight paths of the UAVs in the UAV formation through a genetic algorithm until the UAVs in the UAV formation complete the UAV formation collaborative planning flight mission.

2. The UAV formation collaborative planning method according to claim 1, characterized in that: In step S101, it includes: The UAV formation collaborative planning flight mission data includes flight mission objectives, flight area information, flight path information, flight communication connection information, communication methods between UAVs within the UAV formation, and flight communication frequency connections; The real-time location of the drone includes the real-time location coordinates of the drone in flight, flight speed, flight attitude, sensor data, flight attitude information of the drone, drone sensor data, status information of the drone's mechanical parts and electronic equipment, and the remaining battery power of the drone; The flight attitude includes pitch angle, yaw angle and roll angle; Drone sensor data includes data collected by weather sensors, cameras, and radars.

3. The UAV formation collaborative planning method according to claim 1, characterized in that: In step S102, it includes: Collecting UAV formation collaborative planning flight mission data, which includes flight mission objectives, UAV formation composition, expected flight area information, and preset flight paths; Receive the operation data of each drone in the drone formation in real time, including real-time position, flight speed, flight attitude and sensor data; The UAV formation collaborative planning flight mission data and the operation data of each UAV in the UAV formation are analyzed to extract the real-time flight characteristics of the UAV formation. The real-time flight characteristics of the UAV formation include the real-time position characteristics of the UAV, the sensor data characteristics of the UAV, the status characteristics of the UAV, the real-time communication characteristics of the UAV formation, the number of UAVs in real-time flight in the UAV formation, the signal strength information characteristics of the UAV formation, the position information characteristics of the UAVs in the UAV formation, the natural environment simulation data characteristics of the UAV formation flight area, the flight path information characteristics of the UAV formation, and the formation information characteristics of the UAV formation According to the operation data of each drone in the drone formation, send communication signals to each drone in the drone formation to check whether the communication connection between drones is normal, verify the online status and health status of each drone and whether it has joined the current flight mission, and obtain the real-time detection results of the drone formation; According to the real-time detection result of the UAV formation, the number of UAVs in real-time flight state is calculated to obtain the number of UAVs in real-time flight state; According to the number of drones in real-time flight status, the real-time flight status record of the drone formation is updated. The real-time flight status record of the drone formation includes the number of flying drones, drone identification and drone status.

4. The UAV formation collaborative planning method according to claim 1, characterized in that: In step S102, it includes: Establish identity tags for the real-time flying drones of the drone formation, retrieve the drone formation communication connection information included in the drone formation collaborative planning flight mission data, and complete the communication connection configuration of the drone formation through the real-time flying drones of the drone formation to obtain the real-time communication information of the drone formation. Based on the real-time status information of the flying drone, an identity tag is established for each drone. The identity tag includes the drone's MAC address, serial number, and timestamp; The UAV formation communication connection information is parsed to obtain the UAV formation communication channel, UAV formation communication frequency and UAV formation communication protocol, and the parsed UAV formation communication connection information is converted into UAV formation communication configuration instructions, and the UAV formation communication configuration instructions are sent to each UAV in the UAV formation. After receiving the instructions, the UAVs in the UAV formation configure the communication equipment of the UAVs according to the UAV formation communication configuration instructions, and establish communication connections between the UAVs in the UAV formation.

5. The UAV formation collaborative planning method according to claim 1, characterized in that: In step S103, it includes: The communication signal strength in the drone formation signal strength information set is screened to select drone formation signal strength information with a signal lower than the standard communication signal strength, and the drone identity information corresponding to the drone formation signal strength information with a signal lower than the standard communication signal strength is determined; According to the drone identity information corresponding to the drone formation signal strength information below the standard communication signal strength, determine the drone real-time flight position information corresponding to the drone formation signal strength information below the standard communication signal strength, use the drone real-time flight position information corresponding to the drone formation signal strength information below the standard communication signal strength as the reference point, perform a drone signal strength search within a 50-meter radius of the reference point, and obtain the reference point real-time drone signal strength search result; The filtered drone signal strength search results are sorted by signal strength to obtain the benchmark point real-time drone signal strength sorting results. The benchmark point real-time drone signal strength sorting results include the benchmark point real-time drone signal strength sorting results for the first period, the second benchmark point real-time drone signal strength sorting results, and the third benchmark point real-time drone signal strength sorting results.

6. The UAV formation collaborative planning method according to claim 5, characterized in that: In step S103, it includes: Perform cluster analysis on the ranking results of the real-time UAV signal strength of the benchmark points in the first period, the ranking results of the real-time UAV signal strength of the second benchmark points, and the ranking results of the real-time UAV signal strength of the third benchmark points to obtain the cluster analysis results of the real-time UAV signal strength of the benchmark points; The real-time UAV signal strength clustering analysis results of the benchmark points are matched with the distance information between the UAVs to obtain the distance data of each UAV in the real-time UAV signal strength clustering analysis results of the benchmark points; The distance data of each drone in the cluster analysis results of the real-time drone signal strength of the benchmark point is selected within 50m, and the drone signal with the best ranking result of the real-time drone signal strength of the benchmark point is selected to obtain the dynamic base station screening result, and the corresponding drone is matched according to the dynamic base station screening result, and the drone that matches the dynamic base station screening result is used as the dynamic mobile base station drone; When the real-time drone signal strength at the reference point is lower than the preset value, the dynamic mobile base station drone is activated as a communication base station. The dynamic mobile base station drone sends out a wireless network hotspot to establish a communication connection with each drone in the drone formation.

7. The UAV formation collaborative planning method according to claim 1, characterized in that: In step S104, it includes: Receive the designated command of the UAV formation signal base station, which includes the network hotspot start command within the UAV and the UAV flight position adjustment command; Parse the command specified by the base station of the received UAV formation signal to determine the parameters to be adjusted within the UAV formation, including the target coordinates of the position adjustment and the change of the formation shape; According to the parameters adjusted within the drone formation, the flight position of the drone formation is adjusted in the preset digital twin model, and a first real-time drone formation flight image is generated and updated; In the digital twin model, the drones in the drone formation are set as new drone formation signal base stations. The positional relationship between each drone in the drone formation and the new drone formation signal base station is calculated through the digital twin model. The positional relationship between each drone in the drone formation and the new drone formation signal base station includes the distance and angle between each drone in the drone formation and the new drone formation signal base station. According to the distance and angle between each drone in the drone formation and the new drone formation signal base station, the distance and direction between each drone and the target position are calculated, and a drone formation adjustment command is generated; The drone formation adjustment command is sent to the drones in the drone formation through the communication network, and the drone formation receives the drone formation adjustment command in real time, and the drones in the drone formation adjust their flight attitude and position; Real-time operation data of the adjusted UAV formation is collected to obtain real-time operation data of the adjusted UAV formation.

8. The UAV formation collaborative planning method according to claim 1, characterized in that: In step S104, it includes: The real-time operation data of the adjusted UAV formation includes: position information of UAVs within the adjusted UAV formation, attitude of UAVs within the adjusted UAV formation, direction of UAVs within the adjusted UAV formation, flight status of UAVs within the adjusted UAV formation, communication status of UAVs within the adjusted UAV formation, sensor data of UAVs within the adjusted UAV formation, environmental data of UAVs within the adjusted UAV formation, fault information of UAVs within the adjusted UAV formation, and mission data of UAVs within the adjusted UAV formation.

9. The UAV formation collaborative planning method according to claim 1, characterized in that: In step S106, it includes: Matching the first real-time UAV formation flight image and the second real-time UAV formation flight image in terms of UAV positions and UAV formation shapes, to obtain a matching result of the first real-time UAV formation flight image and the second real-time UAV formation flight image in terms of UAV positions and UAV formation shapes; Perform feature extraction on the matching results of the first real-time UAV formation flight image and the second real-time UAV formation flight image in terms of the UAV positions and the UAV formation shape, and obtain the position coordinate features, flight attitude features, speed features, formation shape features, and relative distance features of the UAVs in the first real-time UAV formation flight image and the second real-time UAV formation flight image; Compare the corresponding features in the first real-time UAV formation flight image and the second real-time UAV formation flight image one by one, the comparison content includes the difference between the actual position and the simulated position of the UAV, the deviation of the flight attitude, and the deformation degree of the formation shape, and obtain the result of comparative analysis of the first real-time UAV formation flight image and the second real-time UAV formation flight image; Based on the results of comparative analysis of the first real-time UAV formation flight image and the second real-time UAV formation flight image, the expected error information during the UAV formation flight is calculated. The expected error information during the UAV formation flight includes the number of meters of position deviation and the angle of attitude deviation. The cumulative error of the flight path of the UAVs in the UAV formation is calculated.

10. The UAV formation collaborative planning method according to claim 1, characterized in that: In step S106, it includes: According to the accumulated errors of the flight paths of the drones in the drone formation, the flight paths of the drones in the drone formation are dynamically corrected. The dynamic correction includes adjusting the flight speed, direction and attitude of the drones. During the dynamic correction process of the UAV formation flight, the operation data of the UAVs in the UAV formation is collected in real time through the built-in sensors and communication systems of the UAVs, the collected operation data of the UAVs in the UAV formation is preprocessed, and the preprocessed data is subjected to feature extraction to obtain the real-time position features of the UAVs after dynamic correction, the real-time speed features of the UAVs after dynamic correction, and the real-time attitude features of the UAVs after dynamic correction; Generate an initial population, where each individual in the population represents a dynamically revised flight path plan. The flight path plan is generated based on the actual status of the current UAV formation and the flight mission requirements. Evaluate the dynamically corrected flight path plan in the population, and calculate the fitness of the dynamically corrected flight path plan in the population through a preset fitness function; According to the fitness value of the dynamically corrected flight path plan, excellent individuals are selected as parents to generate the next generation population. The selected parent individuals are crossover operated to generate new offspring individuals, and the offspring individuals are mutated to increase the number of the population. Repeat the fitness evaluation, selection, crossover and mutation operations until the maximum number of iterations is met, select the individual with the highest fitness as the optimal flight path plan, and send the optimal flight path plan to the drones in the drone formation. The drones in the drone formation adjust their flight trajectories according to the new path plan. When the drones execute the new flight path, they continue to collect the operating data of the drones adjusting the flight trajectory under the new path plan, and optimize the operating data of the flight trajectory adjusted according to the new path plan. If the optimal solution for adjusting the flight trajectory under the new path plan is found, the path plan is updated again to adjust the flight trajectory.

Images