A UAV multi-machine simulation training control system and control method

Through environmental building blocks and prediction optimization models, the problem of low environmental update and trajectory prediction accuracy in the drone simulation training system is solved, and a more realistic and safe drone training environment and trajectory optimization is achieved.

CN118625696BActive Publication Date: 2024-11-01SHENGHANG (TAIZHOU) TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411098284.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-12
Publication Date
2024-11-01
Estimated Expiration
2044-08-12

AI Technical Summary

Technical Problem

The existing drone simulation training system lacks the ability to update dynamic environments, and has low trajectory prediction accuracy, so it is impossible to accurately predict the future trajectory of the drone in complex environments, limiting the reality and safety of the training effect.

Method used

The environment building block is used to obtain high-precision terrain data and meteorological data, combine long and short-term memory networks and genetic algorithms to build trajectory prediction and optimization models, dynamically update the training environment and trajectory to ensure prediction accuracy and security.

Benefits of technology

It enhances the authenticity of the training environment and the accuracy of trajectory optimization, ensuring safe flight and efficient mission execution of drones in complex environments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118625696B_ABST
    Figure CN118625696B_ABST
Patent Text Reader

Abstract

The present invention discloses a simulation control system and control method for multi-machine simulation training of unmanned aerial vehicles, which relates to the technical field of unmanned aerial vehicle simulation training, and includes an environment construction module, which is used to configure training scenes and obtain meteorological data in the future to construct a simulation environment for unmanned aerial vehicle simulation training; a data collection module, which is used to collect historical flight trajectory data of unmanned aerial vehicles and meteorological data in the future to integrate them into a data set; a trajectory prediction module, which is used to construct a trajectory prediction model to obtain predicted flight trajectory data; and a trajectory optimization module, which is used to optimize the trajectory according to the predicted flight trajectory data. The terrain data of the training area is obtained and a three-dimensional terrain model is generated, and environmental features are added in combination with meteorological data to enhance the authenticity of the training environment, and historical flight trajectory data of unmanned aerial vehicles in different environments are collected to provide comprehensive basic data for trajectory prediction and optimization, optimize the flight trajectory of the unmanned aerial vehicle, and ensure that the unmanned aerial vehicle flies safely and can perform tasks efficiently.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle simulation training, in particular to a simulation control system and a control method for unmanned aerial vehicle multi-machine simulation training. Background Art

[0002] The rapid development and wide application of UAV technology have enabled UAVs to play an important role in military, agriculture, logistics and other fields. However, in order to improve the skills of UAV operators and ensure the smooth execution of tasks, simulation training systems have gradually become an indispensable part. Traditional UAV simulation training systems mainly rely on preset training scenarios and manual control, which limits the realism and effectiveness of training effects. In recent years, with the advancement of computer simulation technology and virtual reality technology, UAV simulation training systems based on simulation environments have gradually emerged. These systems provide operators with a more immersive and practical training platform by generating realistic three-dimensional environments and simulating the actual flight conditions of UAVs.

[0003] Although the existing UAV simulation training system has improved the training effect to a certain extent, it still has many shortcomings. The existing technology needs to be improved in real-time acquisition and updating of training area data, resulting in a lack of realism in the dynamic changes of the training scene. The existing technology is relatively rough in trajectory prediction and planning, and cannot accurately predict the future flight trajectory of the UAV, which limits the effectiveness and safety of trajectory optimization. Summary of the invention

[0004] In view of the problems existing in the above-mentioned existing unmanned aerial vehicle multi-machine simulation training simulation control system and control method, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is that the environmental simulation module in the prior art often lacks dynamic updating capability and mainly relies on a preset static environmental model. The existing trajectory prediction technology mostly adopts a simple physical model or linear extrapolation of historical data, which has low accuracy and cannot accurately predict the future trajectory of the UAV in a complex environment.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a multi-machine simulation training control system for unmanned aerial vehicles, comprising:

[0007] The environment construction module is used to configure the training scenario and obtain weather data in the future to build a simulation environment for drone simulation training;

[0008] The data collection module is used to collect the historical flight trajectory data of the UAV and the meteorological data of the future time and integrate them into a data set;

[0009] The trajectory prediction module is used to build a trajectory prediction model and obtain the predicted flight trajectory data;

[0010] A trajectory optimization module, used to optimize the trajectory based on the predicted flight trajectory data;

[0011] The data storage module is used to store all data in the training process into the database to generate a training evaluation report.

[0012] As a preferred solution of the UAV multi-machine simulation training and simulation control system described in the present invention, the configuration of the training scene refers to obtaining high-precision terrain data of the training area from a public data source, using a terrain generation algorithm to convert the high-precision terrain data into a three-dimensional terrain model, determining the number of UAVs participating in the training, and setting the initial position and target point of each UAV, and configuring virtual sensors, including GPS, IMU and cameras.

[0013] As a preferred solution of the multi-machine simulation training control system of the UAV described in the present invention, wherein: the acquisition of future meteorological data to build a UAV simulation training environment refers to acquiring future meteorological data from a meteorological data API, the meteorological data including wind speed, temperature and rainfall, adding environmental features to a three-dimensional terrain model according to the meteorological data, and building a UAV simulation training environment:

[0014] Using the wind speed field formula, we can get the wind speed W at the current coordinates at the future time t. x,y,z,t :

[0015]

[0016] Among them, x 0 ,y 0 、z 0 is the center coordinate of the training area, x, y, z are the current coordinates of the drone, W max is the maximum wind speed in the training area in the future time T, T is the time period of the simulation training, is the wind field diffusion coefficient of the training area in the future time T;

[0017] Using the temperature field formula, we can get the temperature E at the current coordinate at the future time t. x,y,z,t :

[0018]

[0019] Among them, E b is the average temperature of the training area in the future time T, is the difference between the highest and lowest temperatures in the training area in the future time T, is the temperature variation coefficient of the training area in the height direction in the future time T;

[0020] Using the rainfall field formula, we can get the rainfall V at the current coordinate in the future time t. x,y,t :

[0021]

[0022] Among them, V max is the maximum rainfall in the training area in the future time T, is the diffusion coefficient of the rainfall field in the training area in the future time T.

[0023] As a preferred solution of the multi-machine simulation training and control system of the UAV described in the present invention, wherein: the collecting of historical flight trajectory data of the UAV and the meteorological data of the future time and integrating them into a data set refers to collecting historical flight trajectory data of the UAV under different meteorological conditions, including speed, position, wind speed, temperature, and rainfall at different times, and integrating them with the obtained meteorological data of the future time into a data set;

[0024] The data set is preprocessed, including data cleaning and normalization.

[0025] As a preferred solution of the multi-machine simulation training and emulation control system of the unmanned aerial vehicle described in the present invention, wherein: the construction of the trajectory prediction model to obtain the predicted flight trajectory data refers to dividing the pre-processed data set into a training set and a verification set;

[0026] Use long short-term memory network to build trajectory prediction model for trajectory prediction;

[0027] Use the training set to train the trajectory prediction model and optimize the model parameters;

[0028] Use the validation set to verify the trajectory prediction model and evaluate its prediction accuracy and robustness.

[0029] Input future weather data and the real-time flight data of the UAV to obtain the predicted flight trajectory data of the UAV in the future;

[0030] The predicted flight trajectory data is the flight trajectory data of the UAV predicted under different future meteorological conditions, including the speed, position, wind speed, temperature, and rainfall at different time points t in the future time T.

[0031] As a preferred solution of the multi-machine simulation training and emulation control system of the UAV described in the present invention, the trajectory optimization according to the predicted flight trajectory data refers to dividing the predicted flight trajectory data into trajectory nodes of the UAV at different times in the future T according to the positions at different times in the future in the predicted flight trajectory data, and using a genetic algorithm to optimize the trajectory, including:

[0032] Set the number of individuals in the population. Each individual is the predicted flight trajectory data of the i-th drone, consisting of T+1 trajectory nodes composition;

[0033] Calculate the fitness value of each individual, including total trajectory length and total power consumption;

[0034] According to the trajectory nodes of the i-th UAV at different times in the future By calculating the straight-line distance between two adjacent trajectory nodes of the i-th UAV, the total trajectory length of the i-th UAV in the future time T is obtained :

[0035]

[0036] Among them, T is the time period of simulation training, are the x, y, and z coordinates of the i-th UAV at time point t;

[0037] According to the average temperature E of the training area in the future time T b and the temperature of the training area at the current coordinates at the future time t, the current temperature E x,y,z,t , define the coefficient k of the effect of temperature on wind speed E , calculate the wind speed W in the training area under the influence of temperature change at future time t E (x,y,z,t):

[0038]

[0039] Among them, k E is the coefficient of the influence of temperature on wind speed, the temperature E at the current coordinate x,y,z,t , E b is the average temperature of the training area in the future time T;

[0040] According to the rainfall V at the current coordinate in the future time t x,y,t and the maximum rainfall V in the training area in the future time T max , define the coefficient k of the effect of temperature on wind speed V , calculate the wind speed W in the training area affected by rainfall changes at future time t V (x,y,t):

[0041]

[0042] Among them, k V is the coefficient of rainfall effect on wind speed;

[0043] According to the formula for the influence of temperature change on wind speed and the formula for the influence of rainfall change on wind speed, a comprehensive wind speed formula is constructed to obtain the comprehensive wind speed W at the current coordinates of the training area in the future time t. E,V,t :

[0044]

[0045] Set the basic power consumption of the drone when there is no wind speed influence to F b According to the air resistance principle in hydrodynamics, air resistance is proportional to the square of speed. The power required for the i-th UAV to overcome the air resistance caused by wind speed in the future time t is obtained. :

[0046] ;

[0047]

[0048] Among them, k W is the influence coefficient of comprehensive wind speed on energy consumption, is the total power consumption of the i-th UAV at the future time t, is the power required by the i-th UAV to overcome the air resistance caused by wind speed at the future time t;

[0049] Normalize the total trajectory length and total power consumption to [0,1], define the fitness value formula, and obtain the fitness value A of the predicted flight trajectory data of the i-th UAV i , the formula is:

[0050]

[0051] Among them, A i is the fitness value of the predicted flight trajectory data of the i-th UAV, and f are weight parameters;

[0052] The tournament selection method is used to randomly select several individuals from the population and compare their fitness values. The individual with the highest fitness value is selected for crossover and mutation to generate new individuals.

[0053] Update the population to form a new generation of population, set the threshold for fitness value change, and repeat the steps until the change in fitness value is less than the fitness threshold, completing trajectory optimization.

[0054] As a preferred solution of the UAV multi-machine simulation training and simulation control system described in the present invention, the storing of all data in the training process into a database to generate a training evaluation report refers to real-time recording of all data in the training process and storing them in a database, analyzing the flight trajectory of the UAV, evaluating the UAV mission completion and performance, generating a detailed training evaluation report, and feeding back the evaluation report to the operator and technical team.

[0055] Another object of the present invention is to provide a method for controlling a multi-machine simulation training of unmanned aerial vehicles, which comprises:

[0056] Configure training scenarios and obtain future weather data to build a UAV simulation training environment;

[0057] Collect historical flight trajectory data of drones and weather data for future time periods and integrate them into a data set;

[0058] Construct a trajectory prediction model to obtain predicted flight trajectory data;

[0059] Optimize the trajectory based on the predicted flight trajectory data;

[0060] Store all data during the training process into the database to generate a training evaluation report.

[0061] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of a multi-machine simulation training and emulation control system of unmanned aerial vehicles when executing the computer program.

[0062] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a multi-machine simulation training and emulation control system for unmanned aerial vehicles.

[0063] The beneficial effects of the present invention are: obtaining terrain data of the training area and generating a three-dimensional terrain model, adding environmental features in combination with meteorological data, enhancing the authenticity of the training environment, collecting historical flight trajectory data of drones in different environments, providing comprehensive basic data for trajectory prediction and optimization, optimizing the flight trajectory of drones, ensuring that drones fly safely and can perform tasks efficiently. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0065] Figure 1This is a structural schematic diagram of a UAV multi-machine simulation training control system.

[0066] Figure 2 The figure is a flow chart of a method for simulating and controlling multi-machine UAV training. DETAILED DESCRIPTION

[0067] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0068] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0069] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0070] Example 1

[0071] Reference Figure 1 , which is the first embodiment of the present invention, and which provides a multi-machine simulation training control system for unmanned aerial vehicles. The multi-machine simulation training control system for unmanned aerial vehicles includes:

[0072] S1, environment construction module, used to configure training scenarios and obtain future weather data to build a UAV simulation training environment;

[0073] Specifically, configuring a training scenario means obtaining high-precision terrain data of the training area from a public data source, using a terrain generation algorithm to convert the high-precision terrain data into a three-dimensional terrain model, determining the number of drones participating in the training based on the training mission requirements, setting the initial position and final target point of each drone, and configuring virtual sensors, including GPS, IMU, and cameras.

[0074] Configuring training scenarios includes obtaining high-precision terrain data from public data sources, converting it into a three-dimensional terrain model using a terrain generation algorithm, determining the number of drones required for the training mission and their initial positions and target points, and configuring virtual sensors to ensure the authenticity and reliability of the simulation environment and the accuracy of drone training.

[0075] Furthermore, obtaining weather data in the future to build a UAV simulation training environment means obtaining weather data in the future from the weather data API. The weather data includes wind speed, temperature, and rainfall. According to the weather data, environmental features are added to the three-dimensional terrain model to build a UAV simulation training environment:

[0076] Using the wind speed field formula, we can get the wind speed W at the current coordinates at the future time t. x,y,z,t :

[0077]

[0078] Among them, x 0 ,y 0 、z 0 is the center coordinate of the training area, x, y, z are the current coordinates of the drone, W max is the maximum wind speed in the training area in the future time T, T is the time period of the simulation training, The wind field diffusion coefficient of the training area in the future time T is obtained based on field measurements and analysis of wind speeds at different locations and heights;

[0079] Using the temperature field formula, we can get the temperature E at the current coordinate at the future time t. x,y,z,t :

[0080]

[0081] Among them, E b is the average temperature of the training area in the future time T, is the difference between the highest and lowest temperatures in the training area in the future time T, To obtain the temperature variation coefficient of the training area in the height direction in the future time T, a temperature field model in the training area is established by using computational fluid dynamics software, and the temperature variation coefficient of the training area in the height direction in the future time T is obtained after running the simulation;

[0082] Using the rainfall field formula, we can get the rainfall V at the current coordinate in the future time t. x,y,t :

[0083]

[0084] Among them, V max is the maximum rainfall in the training area in the future time T, The diffusion coefficient of the rainfall field in the training area in the future time T is obtained through references and databases in related fields.

[0085] By obtaining environmental data of the drone training area from public data sources, including terrain data and meteorological data, and using terrain generation algorithms to generate three-dimensional terrain models, the realism and accuracy of the simulation system can be significantly improved. In the three-dimensional terrain model, environmental features such as wind speed, temperature and rainfall are added based on meteorological data to further optimize the realism of the training environment. Compared with the traditional linear diffusion model, the use of the Gaussian distribution model can more accurately simulate the uneven diffusion of wind speed in different directions, improve the realism of the wind speed field, and add time points, so that the impact of wind speed on the drone flight trajectory can be judged according to the time points. The sine function is used to simulate the daily cycle change of temperature. In the existing daily cycle temperature change model, On this basis, the height attenuation effect is added to make the change of temperature with height more realistic and accurate. The Gaussian distribution model is used to simulate the diffusion of rainfall in space, and combined with the time period change, the time period change is added on the basis of the existing Gaussian distribution rainfall model to make the change of rainfall over time more in line with the actual rainfall law. Through the application of these models, the environmental changes of the UAV in the training area can be dynamically and accurately simulated, and the path planning and flight control can be adjusted in real time to ensure the safe and efficient operation of the UAV in complex environments. It not only improves the training effect of the operators and their ability to cope with complex environments, but also makes the entire training system more adaptable and reliable, thereby comprehensively improving the training quality and effect.

[0086] S2, data collection module, used to collect historical flight trajectory data of drones and weather data of future time and integrate them into a data set;

[0087] Specifically, collecting the historical flight trajectory data of the UAV and integrating the meteorological data of the future time into a data set means collecting the historical flight trajectory data of the UAV under different meteorological conditions, including the speed, position, wind speed, temperature, and rainfall at different times, and integrating it with the obtained meteorological data of the future time into a data set;

[0088] The data set is preprocessed, including data cleaning and normalization.

[0089] The historical flight trajectory data of UAVs under different meteorological conditions are collected and integrated with the meteorological data of future time into a data set. Through data cleaning and normalization, the data set is made neater and more consistent, thereby improving the accuracy and adaptability of the prediction model.

[0090] S3, trajectory prediction module, used to build a trajectory prediction model and obtain predicted flight trajectory data;

[0091] Specifically, constructing a trajectory prediction model and obtaining predicted flight trajectory data means dividing the preprocessed data set into a training set and a validation set;

[0092] Use long short-term memory network to build trajectory prediction model for trajectory prediction;

[0093] Use the training set to train the trajectory prediction model and optimize the model parameters;

[0094] Use the validation set to verify the trajectory prediction model and evaluate its prediction accuracy and robustness.

[0095] Input future weather data and the real-time flight data of the UAV to obtain the predicted flight trajectory data of the UAV in the future;

[0096] The predicted flight trajectory data is the flight trajectory data of the UAV predicted under different future meteorological conditions, including the speed, position, wind speed, temperature, and rainfall at different time points t in the future time T.

[0097] By dividing the preprocessed data set into a training set and a validation set, the trajectory prediction model is constructed and trained using a long short-term memory network, the model parameters are optimized, and the prediction accuracy and robustness of the model are evaluated through the validation set. Finally, future meteorological data and the real-time flight data of the UAV are input to obtain the predicted flight trajectory data of the UAV in the future, thereby improving the accuracy and reliability of trajectory prediction.

[0098] S4, trajectory optimization module, used for performing trajectory optimization according to the predicted flight trajectory data;

[0099] Specifically, performing trajectory optimization based on predicted flight trajectory data means dividing the predicted flight trajectory data into trajectory nodes of the UAV at different times in the future according to the positions at different times in the predicted flight trajectory data, and using a genetic algorithm to perform trajectory optimization, including:

[0100] Set the number of individuals in the population. Each individual is the predicted flight trajectory data of the i-th drone, consisting of T+1 trajectory nodes composition;

[0101] Calculate the fitness value of each individual, including total trajectory length and total power consumption;

[0102] According to the trajectory nodes of the i-th UAV at different times in the future By calculating the straight-line distance between two adjacent trajectory nodes of the i-th UAV, the total trajectory length of the i-th UAV in the future time T is obtained :

[0103]

[0104] Among them, T is the time period of simulation training, are the x, y, and z coordinates of the i-th UAV at time point t;

[0105] According to the average temperature E of the training area in the future time T b and the temperature of the training area at the current coordinates at the future time t, the current temperature E x,y,z,t , define the coefficient k of the effect of temperature on wind speed E , calculate the wind speed W in the training area under the influence of temperature change at future time t E (x,y,z,t):

[0106]

[0107] Among them, k E is the coefficient of the influence of temperature on wind speed, the temperature E at the current coordinate x,y,z,t , E b is the average temperature of the training area in the future time T;

[0108] According to the rainfall V at the current coordinate in the future time t x,y,t and the maximum rainfall V in the training area in the future time T max , define the coefficient k of the effect of temperature on wind speed V , calculate the wind speed W in the training area affected by rainfall changes at future time t V (x,y,t):

[0109]

[0110] Among them, k V is the coefficient of rainfall effect on wind speed;

[0111] According to the formula for the influence of temperature change on wind speed and the formula for the influence of rainfall change on wind speed, a comprehensive wind speed formula is constructed to obtain the comprehensive wind speed W at the current coordinates of the training area in the future time t. E,V,t :

[0112]

[0113] Set the basic power consumption of the drone when there is no wind speed influence to F b According to the air resistance principle in hydrodynamics, air resistance is proportional to the square of speed. The power required for the i-th UAV to overcome the air resistance caused by wind speed in the future time t is obtained. :

[0114]

[0115]

[0116] Among them, k W is the influence coefficient of comprehensive wind speed on energy consumption, is the total power consumption of the i-th UAV at the future time t, is the power required by the i-th UAV to overcome the air resistance caused by wind speed at the future time t;

[0117] Normalize the total trajectory length and total power consumption to [0,1], define the fitness value formula, and obtain the fitness value A of the predicted flight trajectory data of the i-th UAV i , the formula is:

[0118]

[0119] Among them, A i is the fitness value of the predicted flight trajectory data of the i-th UAV, and f are weight parameters;

[0120] The tournament selection method is used to randomly select several individuals from the population and compare their fitness values. The individual with the highest fitness value is selected for crossover and mutation to generate new individuals.

[0121] Update the population to form a new generation of population, set the threshold for fitness value change, and repeat the steps until the change in fitness value is less than the fitness threshold, completing trajectory optimization.

[0122] The trajectory is optimized by predicting the flight trajectory data. The trajectory of the drone is optimized using a genetic algorithm. The number of individuals in the population is set. Each individual represents the predicted flight trajectory data of the drone in the future. It is composed of multiple trajectory nodes, which represent the predicted positions of the drone at different time points. Each individual contains information about the entire flight path. The fitness value of each individual is calculated, including the total trajectory length and total power consumption, to evaluate the pros and cons of each trajectory. In the calculation process, the effects of temperature and rainfall on wind speed are taken into account. Temperature changes lead to changes in air density, which in turn affects wind speed. By designing the corresponding formula, it is concluded that the training area will be affected by temperature changes in the future. The wind speed under the influence of rainfall increases the moisture in the air and changes the aerodynamic characteristics. The wind speed under the influence of rainfall changes is calculated through the corresponding formula. Combining these two factors, a comprehensive wind speed formula is constructed to obtain the comprehensive wind speed at the current coordinates of the training area in the future time, ensuring comprehensive consideration of environmental factors and making trajectory optimization more accurate and realistic. Based on the reference data, according to the air resistance principle in aerodynamics, the air resistance is proportional to the square of the speed, so the power required for the drone to overcome the air resistance caused by wind speed in the future time is obtained, ensuring the scientificity and accuracy of the power consumption calculation, and normalizing the total trajectory length and total power consumption to [0,1] In this way, the indicators of different units can be weighted and summed to construct the fitness value formula. By setting the weight parameters, the relative importance of trajectory length and power consumption can be adjusted according to specific needs, so that the optimization results are more in line with the actual application needs. The tournament selection method is adopted to select the individuals with the highest fitness value for crossover and mutation. Through crossover and mutation operations, new individuals are generated, and the population is continuously updated to form a new generation of population. In each generation of population, a fitness value threshold is set, and the steps of calculating fitness, selection, crossover and mutation are repeated until the change in fitness value is less than the set threshold, thereby ensuring that the algorithm converges to the optimal solution.

[0123] S5, a data storage module, used to store all data in the training process into a database to generate a training evaluation report;

[0124] Specifically, storing all data in the training process into a database to generate a training evaluation report means recording all data in the training process in real time and storing it in a database, analyzing the flight trajectory of the UAV, evaluating the UAV mission completion and performance, generating a detailed training evaluation report, and feeding back the evaluation report to the operator and technical team.

[0125] By recording all data during the training process in real time and storing it in a database, the flight trajectory of the UAV can be comprehensively analyzed, the completion and performance of the UAV mission can be evaluated, and detailed training evaluation reports can be generated. These evaluation reports provide valuable feedback information that can help operators and technical teams identify and solve potential problems, optimize the flight strategy and control algorithm of the UAV, and improve the effectiveness of training and the skill level of operators. Systematic evaluation reports also provide reliable data support for subsequent improvements and decision-making, ensuring the efficient and safe operation of UAVs in actual missions.

[0126] Example 2

[0127] Reference Figure 2 , which is the second embodiment of the present invention, and which is different from the previous embodiment, provides a method for controlling a multi-machine simulation training of unmanned aerial vehicles, comprising:

[0128] Configure training scenarios and obtain future weather data to build a UAV simulation training environment;

[0129] Collect historical flight trajectory data of drones and weather data for future time periods and integrate them into a data set;

[0130] Construct a trajectory prediction model to obtain predicted flight trajectory data;

[0131] Optimize the trajectory based on the predicted flight trajectory data;

[0132] Store all data during the training process into the database to generate a training evaluation report.

[0133] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0134] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0135] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0136] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit with a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit with a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0137] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A multi-machine simulation training control system for unmanned aerial vehicles, characterized by: include, The environment construction module is used to configure the training scenario and obtain weather data in the future to build a simulation environment for drone simulation training; The data collection module is used to collect the historical flight trajectory data of the UAV and the meteorological data of the future time and integrate them into a data set; The trajectory prediction module is used to build a trajectory prediction model and obtain the predicted flight trajectory data; A trajectory optimization module, used to optimize the trajectory based on the predicted flight trajectory data; The data storage module is used to store all the data in the training process into the database to generate a training evaluation report; The acquisition of future weather data to build a UAV simulation training environment refers to acquiring future weather data from a weather data API, where the weather data includes wind speed, temperature, and rainfall, adding environmental features to a three-dimensional terrain model based on the weather data, and building a UAV simulation training environment: Using the wind speed field formula, we can get the wind speed W at the current coordinates at the future time t. x,y,z,t : ; Among them, x0, y0, z0 are the center coordinates of the training area, x, y, z are the current coordinates of the drone, and W max is the maximum wind speed in the training area in the future time T, T is the time period of the simulation training, is the wind field diffusion coefficient of the training area in the future time T; Using the temperature field formula, we can get the temperature E at the current coordinate at the future time t. x,y,z,t : ; Among them, E b is the average temperature of the training area in the future time T, is the difference between the highest and lowest temperatures in the training area in the future time T, is the temperature variation coefficient of the training area in the height direction in the future time T; Using the rainfall field formula, we can get the rainfall V at the current coordinate in the future time t. x,y,t : ; Among them, Vmax is the maximum rainfall in the training area in the future time T, is the diffusion coefficient of the rainfall field in the training area in the future time T; The trajectory optimization according to the predicted flight trajectory data refers to dividing the predicted flight trajectory data into trajectory nodes of the UAV at different times in the future time T according to the positions at different times in the future in the predicted flight trajectory data, and using a genetic algorithm to optimize the trajectory, including: Set the number of individuals in the population. Each individual is the predicted flight trajectory data of the i-th drone, consisting of T+1 trajectory nodes composition; Calculate the fitness value of each individual, including the total trajectory length and total power consumption; According to the trajectory nodes of the i-th UAV at different times in the future By calculating the straight-line distance between two adjacent trajectory nodes of the i-th UAV, the total trajectory length of the i-th UAV in the future time T is obtained : ; Among them, T is the time period of simulation training, are the x, y, and z coordinates of the i-th UAV at time point t; According to the average temperature E of the training area in the future time T b and the temperature of the training area at the current coordinates at the future time t, the current temperature E x,y,z,t , define the coefficient k of the effect of temperature on wind speed E , calculate the wind speed W in the training area under the influence of temperature change at future time t E (x,y,z,t): ; Among them, k E is the coefficient of the influence of temperature on wind speed, the temperature E at the current coordinate x,y,z,t , E b is the average temperature of the training area in the future time T; According to the rainfall V at the current coordinate in the future time t x,y,t and the maximum rainfall V in the training area in the future time T max , define the coefficient k of the effect of temperature on wind speed V , calculate the wind speed W in the training area affected by rainfall changes at future time t V (x,y,t): ; Among them, k V is the coefficient of rainfall effect on wind speed; According to the formula for the influence of temperature change on wind speed and the formula for the influence of rainfall change on wind speed, a comprehensive wind speed formula is constructed to obtain the comprehensive wind speed W at the current coordinates of the training area in the future time t. E,V,t : ; Set the basic power consumption of the drone when there is no wind speed influence to F b According to the air resistance principle in hydrodynamics, air resistance is proportional to the square of speed. The power required for the i-th UAV to overcome the air resistance caused by wind speed in the future time t is obtained. : ; ; Among them, k W is the influence coefficient of comprehensive wind speed on energy consumption, is the total power consumption of the i-th UAV at the future time t, is the power required by the i-th UAV to overcome the air resistance caused by wind speed at the future time t; Normalize the total trajectory length and total power consumption to [0,1], define the fitness value formula, and obtain the fitness value A of the predicted flight trajectory data of the i-th UAV i , the formula is: ; Among them, A i is the fitness value of the predicted flight trajectory data of the i-th UAV, and f are weight parameters; The tournament selection method is used to randomly select several individuals from the population and compare their fitness values. The individual with the highest fitness value is selected for crossover and mutation to generate new individuals. Update the population to form a new generation of population, set the threshold for fitness value change, and repeat the steps until the change in fitness value is less than the fitness threshold, completing trajectory optimization.

2. The UAV multi-machine simulation training control system according to claim 1, characterized in that: The configuration of the training scenario refers to obtaining high-precision terrain data of the training area from a public data source, using a terrain generation algorithm to convert the high-precision terrain data into a three-dimensional terrain model, determining the number of drones participating in the training, setting the initial position and target point of each drone, and configuring virtual sensors, including GPS, IMU and cameras.

3. A UAV multi-machine simulation training control system as claimed in claim 2, characterized in that: The collecting of historical flight trajectory data of the UAV and the meteorological data of the future time and integrating them into a data set refers to collecting historical flight trajectory data of the UAV under different meteorological conditions, including speed, position, wind speed, temperature, and rainfall at different times, and integrating them with the obtained meteorological data of the future time into a data set; The data set is preprocessed, including data cleaning and normalization.

4. A UAV multi-machine simulation training control system as claimed in claim 3, characterized in that: The constructing of the trajectory prediction model to obtain the predicted flight trajectory data refers to dividing the preprocessed data set into a training set and a validation set; Use long short-term memory network to build trajectory prediction model for trajectory prediction; Use the training set to train the trajectory prediction model and optimize the model parameters; Use the validation set to verify the trajectory prediction model and evaluate its prediction accuracy and robustness. Input future weather data and the real-time flight data of the UAV to obtain the predicted flight trajectory data of the UAV in the future; The predicted flight trajectory data is the flight trajectory data of the UAV predicted under different future meteorological conditions, including the speed, position, wind speed, temperature, and rainfall at different time points t in the future time T.

5. The UAV multi-machine simulation training control system as claimed in claim 4, characterized in that: Storing all data in the training process into a database to generate a training evaluation report refers to recording all data in the training process in real time and storing it in a database, analyzing the flight trajectory of the drone, evaluating the mission completion and performance of the drone, generating a detailed training evaluation report, and feeding the evaluation report back to the operator and the technical team.

6. A method for controlling a multi-machine simulation training of a UAV based on the multi-machine simulation training and simulation control system of any one of claims 1 to 5, characterized in that: include, Configure training scenarios and obtain future weather data to build a UAV simulation training environment; Collect historical flight trajectory data of drones and weather data for future time periods and integrate them into a data set; Construct a trajectory prediction model to obtain predicted flight trajectory data; Optimize the trajectory based on the predicted flight trajectory data; Store all data during the training process into the database to generate a training evaluation report.

7. A computer device comprising: Memory and processor; The memory stores a computer program, characterized in that when the processor executes the computer program, the steps of a multi-machine simulation training and control system for unmanned aerial vehicles described in any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of a multi-machine simulation training and control system for unmanned aerial vehicles described in any one of claims 1 to 5 are implemented.

Citation Information

Cited By

  • Unmanned aerial vehicle personal simulation training system based on actual combat task driving

    CN123142495A