A virtual-reality interaction method and system for unmanned aerial vehicle simulation training flight

Abstract

A virtual-reality interaction method and system for simulated training flight of unmanned aerial vehicles (UAVs) relates to the general field of control or regulation systems. In this method, airflow channels are divided in a preset geographical area; real-time meteorological data is nonlinearly interpolated according to the position of preset detection points in each airflow channel to obtain meteorological data for each preset detection point; an airflow disturbance characteristic map is generated; based on the airflow disturbance characteristic map, a regional conversion buffer zone is set between the stable airflow zone, the weak disturbance zone, and the strong disturbance zone; when the virtual UAV is determined to enter the regional conversion buffer zone based on the real-time position coordinates of the virtual UAV in the virtual training environment, the pitch angle, roll angle, and yaw angle of the virtual UAV are adjusted at preset time intervals with a preset incremental coefficient to obtain an angle change; the angle change is converted into a force feedback signal and fed back to the operator through a force feedback device. This application improves the authenticity and effectiveness of virtual UAV training flights.

Description

Technical Field

[0001] The present application belongs to the general field of control or regulation systems, and in particular relates to a virtual-reality interaction method and system for simulated training flight of unmanned aerial vehicles. Background Art

[0002] With the rapid development of drone technology, drones have been widely used in various fields. Traditional drone flight training methods are not only costly but also pose safety risks. This is especially true during emergency rescue flight training in adverse weather conditions such as heavy rain and strong winds. Beginners can easily damage their drones or cause accidents due to improper operation. Furthermore, weather conditions make it difficult to ensure the continuity and effectiveness of training.

[0003] Among related technologies, virtual simulation technology driven by meteorological data can be used for UAV flight training in harsh environments. By acquiring real-time environmental parameters such as wind speed and precipitation from a weather station and combining them with fluid dynamics models to simulate the UAV's flight state, trainees can use control devices similar to actual UAV remote controls to practice flight operations in a virtual environment. This training method is unaffected by the external environment and allows for repeated practice, reducing training costs and safety risks.

[0004] However, in complex terrain environments such as mountain rescue, when strong winds and heavy rain interact with each other, there will be airflow disturbance characteristics under the superposition of multiple severe weather conditions, resulting in reduced accuracy of trainees' prediction of flight status under complex weather conditions during training. For example, when conducting rescue in a valley, the virtual training system finds it difficult to simulate the combined effects of rising air currents and heavy rain in the valley, making it difficult for trainees to gain corresponding training experience in simulated training flights. As a result, trainees need longer time to adapt to such complex weather conditions when actually performing tasks, reducing the effectiveness of drone simulation training flights. Summary of the Invention

[0005] The present application provides a virtual-reality interaction method and system for simulated training flight of unmanned aerial vehicles. By establishing an airflow channel model based on terrain data and fluid mechanics, and combining it with real-time meteorological data for nonlinear interpolation calculation, an accurate airflow disturbance characteristic map is generated. Through regional division and buffer zone design, when the virtual unmanned aerial vehicle crosses different airflow areas, the angle change is transmitted to the operator in real time through a force feedback device, so that the trainees can truly feel the airflow changes under complex terrain and multiple severe weather conditions, thereby improving the authenticity and effectiveness of virtual training.

[0006] In a first aspect, the present application provides a virtual-reality interaction method for simulated training flight of a UAV, which divides airflow channels in a preset geographical area based on terrain elevation data of the preset geographical area and the principles of fluid mechanics;

[0007] Perform nonlinear interpolation calculation on the real-time meteorological data according to the position of the preset detection point in each airflow channel to obtain the meteorological data of each preset detection point;

[0008] Generate an airflow disturbance characteristic map based on the meteorological data of each preset detection point;

[0009] Based on the airflow disturbance characteristic map, the preset geographical area is divided into stable airflow area, weak disturbance area and strong disturbance area, and regional transition buffer zones are set between the stable airflow area, weak disturbance area and strong disturbance area respectively;

[0010] When determining that the virtual drone enters the regional conversion buffer zone according to the real-time position coordinates of the virtual drone in the virtual training environment, adjusting the pitch angle, roll angle, and yaw angle of the virtual drone by a preset incremental coefficient at a preset time interval to obtain an angle change amount;

[0011] The angle change is converted into a force feedback signal and fed back to the operator through the force feedback device.

[0012] By implementing the above technical solution and establishing a network of airflow channels and detection points, accurate modeling of airflow conditions within a pre-defined geographic area is achieved. Nonlinear interpolation calculations based on real-time meteorological data can obtain accurate meteorological data at the detection points, thereby generating a disturbance characteristic map reflecting the regional airflow distribution characteristics. By dividing the area into different airflow disturbance levels and setting buffer zones, the system can smoothly adjust the flight attitude of the virtual drone according to preset time intervals and incremental coefficients as it crosses different airflow zones, avoiding the sudden increase in control difficulty caused by sudden attitude changes. The calculated angle change is converted into a force feedback signal and transmitted to the operator, allowing them to truly feel the control resistance in different airflow environments, enhancing the realism of the training process. This virtual-real interaction method based on real-time meteorological data and physical models enables the drone simulation training system to more accurately simulate the effects of airflow in actual flight environments, helping operators master flying skills in complex weather conditions.

[0013] In conjunction with some embodiments of the first aspect, in some embodiments, dividing the airflow channel in the preset geographical area according to terrain elevation data of the preset geographical area and fluid mechanics principles specifically includes:

[0014] Convert terrain elevation data of a preset geographical area into three-dimensional grid data;

[0015] Extract ridge lines and valley lines based on 3D grid data;

[0016] The preset geographical area is divided into multiple sub-areas based on the ridgeline;

[0017] In each sub-area, the direction of airflow movement is calculated based on the principles of fluid mechanics;

[0018] According to the direction of airflow movement, adjacent grid units with the same airflow movement trend are combined to form multiple airflow channels.

[0019] By adopting the above technical solution, by converting terrain elevation data into a three-dimensional grid and extracting terrain features, an accurate description of the patterns of airflow movement in complex terrain is achieved. Regional division based on ridge lines and the calculation of airflow movement directions within each sub-region in combination with fluid mechanics principles enable the system to accurately identify and simulate the impact of terrain on airflow movement. By combining adjacent grid cells with the same airflow movement trends to form airflow channels, a complete regional airflow network model is established. This airflow channel division method based on terrain features and fluid mechanics enables the system to accurately reflect the guiding effect of terrain undulations on airflow movement, improving the accuracy of airflow simulation in virtual training environments.

[0020] In conjunction with some embodiments of the first aspect, in some embodiments, adjusting the pitch angle, roll angle, and yaw angle of the virtual drone by a preset incremental coefficient at a preset time interval to obtain an angle change specifically includes:

[0021] Determine the difference in airflow disturbance characteristics between the two sides of the regional transition buffer zone;

[0022] Calculate the target attitude angle according to the difference of airflow disturbance characteristics, and the target attitude angle includes the target pitch angle, target roll angle and target yaw angle;

[0023] Obtain the preset increment coefficient at the current moment according to the preset time interval, where the value range of the preset increment coefficient is 0 to 1;

[0024] The difference between the target attitude angle and the current attitude angle is multiplied by a preset incremental coefficient to obtain the angle change, which includes the pitch angle change, roll angle change, and yaw angle change.

[0025] By adopting the above technical solution, the target attitude angle is determined by calculating the difference in airflow disturbance characteristics between the areas on both sides of the buffer zone, and a preset incremental coefficient is used to achieve a smooth transition of the attitude angle, avoiding the sudden attitude changes that may occur when switching between different airflow areas. The system calculates the required attitude adjustment amount based on the actual differences in airflow disturbance characteristics and accurately controls the adjustment process through an incremental coefficient that varies between 0 and 1, ensuring that the attitude changes of the virtual drone are continuous and natural when crossing different airflow areas. This progressive attitude adjustment method based on the actual differences in airflow characteristics not only ensures the drone's timely response to airflow changes, but also avoids the abruptness caused by drastic attitude changes to the operator, thereby enhancing the realism and controllability of the virtual training process.

[0026] In conjunction with some embodiments of the first aspect, in some embodiments, after converting the angle variation into a force feedback signal and feeding it back to the operator through the force feedback device, the method further includes:

[0027] The virtual drone is used as the airflow disturbance source to generate a moving disturbance field centered on the virtual drone.

[0028] Based on the interaction between the moving disturbance field and the airflow channels in the preset geographical area, a dynamic airflow environment is formed;

[0029] Calculate the feedback disturbance acting on the virtual drone based on the dynamic airflow environment;

[0030] Fusing the feedback disturbance with the angle variation to obtain the fused angle variation;

[0031] Update the force feedback signal based on the fused angle change.

[0032] By adopting the above technical solution, a dynamic simulation of the airflow changes caused by the drone's flight is achieved by using a virtual drone as an airflow disturbance source and generating a moving disturbance field. Based on the interaction between the moving disturbance field and the existing airflow channel, the system calculates and updates the dynamic airflow environment, thereby obtaining a feedback disturbance acting on the virtual drone. This feedback disturbance is then integrated with the original angle change to update the force feedback signal, allowing the system to simultaneously reflect the combined impact of the ambient airflow and the drone's own motion on the flight state. This dynamic feedback mechanism, which takes into account the interaction between the drone and the airflow environment, achieves a force feedback effect that is closer to the actual flight state, improving the accuracy and authenticity of the simulation of aerodynamic effects during training.

[0033] In conjunction with some embodiments of the first aspect, in some embodiments, a dynamic airflow environment is formed based on the interaction between the moving disturbance field and the airflow channel in a preset geographical area, specifically including:

[0034] Calculate the disturbance propagation direction of the moving disturbance field in each airflow channel;

[0035] Determine the disturbance intensity of the moving disturbance field on each airflow channel according to the disturbance propagation direction;

[0036] The disturbance intensity is superimposed with the original airflow characteristics of each airflow channel to obtain a superposition result, and new airflow distribution data is calculated based on the superposition result;

[0037] Generate a dynamic airflow environment based on the new airflow distribution data.

[0038] By adopting the above technical solution, the disturbance propagation direction of the moving disturbance field in each airflow channel is calculated, and the disturbance intensity of each airflow channel is determined based on the propagation direction. The disturbance intensity is then superimposed with the original airflow characteristics to generate new airflow distribution data, and finally a dynamic airflow environment is formed, so that the system can accurately simulate the actual impact of the drone on the surrounding airflow environment during flight. Because the propagation characteristics of the disturbance in different airflow channels are taken into account, the system can truly reflect the wake effect generated by the drone and the interaction process between these wakes and the surrounding airflow. This dynamic update mechanism of the airflow environment based on physical laws can enable trainees to experience airflow changes that are closer to reality, improving the realism and accuracy of simulation training.

[0039] In conjunction with some embodiments of the first aspect, in some embodiments, generating a dynamic airflow environment according to new airflow distribution data specifically includes:

[0040] Extract the airflow gradient between each airflow area and calculate the rate of change of the airflow gradient over time;

[0041] Determine transition characteristics between airflow regions based on rate of change;

[0042] The continuous airflow field generated based on the transition characteristics is used as the dynamic airflow environment.

[0043] By adopting the above technical solution, by extracting the airflow gradient between airflow areas and calculating its rate of change over time, the system establishes a transition characteristic model between airflow areas and generates a continuous dynamic airflow field, which can provide a more delicate and realistic airflow transition effect and improve the simulation level of the simulation training system.

[0044] In conjunction with some embodiments of the first aspect, in some embodiments, calculating the feedback disturbance acting on the virtual drone based on the dynamic airflow environment specifically includes:

[0045] Obtain the airflow speed and direction at the location of the virtual drone in a dynamic airflow environment;

[0046] Calculate the force exerted by airflow speed and direction on each force-bearing surface of the virtual drone;

[0047] Calculate the resultant moment based on the forces and positions of the action points on each load-bearing surface;

[0048] The attitude angle change obtained by converting the synthetic torque is used as the feedback disturbance acting on the virtual UAV.

[0049] By employing this technical solution, the system obtains the airflow velocity and direction at the virtual drone's location, calculates the force exerted by the airflow on each force-bearing surface, and converts the resultant torque into a change in attitude angle. This takes into account the different forces acting on various parts of the drone and the resulting torque effects, accurately reflecting the effects of airflow on the drone in a real flight environment. By converting airflow effects into specific changes in attitude angle, the system provides trainees with accurate force feedback signals, allowing them to intuitively experience the changes in the drone's attitude under different airflow conditions. This enhances the physical realism of the simulation training and allows trainees to accumulate practical experience in dealing with various airflow disturbances in a safe virtual environment.

[0050] In second aspect, an embodiment of the present application provides a virtual-reality interaction system for simulated training flight of a drone, the virtual-reality interaction system for simulated training flight of a drone comprising: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code comprises computer instructions, and one or more processors call the computer instructions to enable the system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0051] In a third aspect, an embodiment of the present application provides a computer-readable storage medium comprising instructions, which, when executed on a system, enables the system to execute the method described in the first aspect and any possible implementation of the first aspect.

[0052] In a fourth aspect, an embodiment of the present application provides a computer program product, which, when executed on a system, enables the system to execute the method described in any possible implementation manner in the first aspect.

[0053] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages:

[0054] 1. This application provides a virtual-reality interaction method for simulated training flights of unmanned aerial vehicles (UAVs). By establishing a network of airflow channels and detection points, it achieves accurate modeling of airflow conditions within a preset geographical area. Based on nonlinear interpolation calculations of real-time meteorological data, accurate meteorological data of the detection points can be obtained, and then a disturbance characteristic map reflecting the regional airflow distribution characteristics can be generated. By dividing the area into different airflow disturbance levels and setting buffer zones, the system can smoothly adjust the flight attitude of the virtual UAV according to preset time intervals and incremental coefficients when crossing different airflow areas, avoiding a sharp increase in control difficulty caused by sudden changes in attitude. The calculated angle change is converted into a force feedback signal and transmitted to the operator, allowing the operator to truly feel the control resistance under different airflow environments, thereby improving the authenticity of the training process. This virtual-reality interaction method based on real-time meteorological data and physical models enables the UAV simulation training system to more accurately simulate the impact of airflow in actual flight environments, helping operators master flying skills under complex weather conditions.

[0055] 2. The present application provides a virtual-reality interaction method for simulated training flight of a UAV. By using a virtual UAV as an airflow disturbance source and generating a moving disturbance field, a dynamic simulation of the airflow changes caused by the UAV flight is achieved. Based on the interaction law between the moving disturbance field and the existing airflow channel, the system calculates and updates the dynamic airflow environment, and then obtains the feedback disturbance acting on the virtual UAV. This feedback disturbance is integrated with the original angle change and the force feedback signal is updated, so that the system can simultaneously reflect the combined impact of the ambient airflow and the UAV's own movement on the flight state. This dynamic feedback mechanism that takes into account the interaction between the UAV and the airflow environment achieves a force feedback effect that is closer to the real flight state, and improves the accuracy and authenticity of the simulation of aerodynamic effects during training. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a flow chart of a virtual-reality interaction method for a UAV simulation training flight in an embodiment of the present application.

[0057] Figure 2 This is a flow chart of a virtual-reality interaction method that takes into account the wake effect of a drone in an embodiment of the present application.

[0058] Figure 3 This is a schematic diagram of the physical device structure of a virtual-reality interaction system for simulated training flight of a drone provided in an embodiment of the present application. DETAILED DESCRIPTION

[0059] The terms used in the following examples of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the specification and appended claims of this application, the singular expressions "a," "an," "said," "above," "the," and "this" are intended to include plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used in this application refers to any or all possible combinations comprising one or more of the listed items.

[0060] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to imply or suggest relative importance or implicitly indicate the number of the technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of this application, unless otherwise specified, "plurality" means two or more.

[0061] The following uses an embodiment and combines Figure 1 , a virtual-reality interaction method for a UAV simulation training flight in an embodiment of the present application is described:

[0062] See also Figure 1 , which is a flow chart of a virtual-reality interaction method for a UAV simulation training flight in an embodiment of the present application.

[0063] S101, dividing airflow channels in a preset geographical area according to terrain elevation data of the preset geographical area and principles of fluid mechanics;

[0064] The system divides airflow channels in a preset geographical area based on the terrain elevation data of the preset geographical area and the principles of fluid mechanics. Specifically, the system includes: converting the terrain elevation data of the preset geographical area into three-dimensional grid data; extracting ridge lines and valley lines based on the three-dimensional grid data; dividing the preset geographical area into multiple sub-areas with the ridge lines as the boundaries; within each sub-area, calculating the direction of airflow movement based on the principles of fluid mechanics; and combining adjacent grid units with the same airflow movement trend according to the airflow movement direction to form multiple airflow channels.

[0065] In this step, the system uses the terrain elevation data of the preset geographic area and the principles of fluid dynamics to divide the airflow paths within the preset geographic area. Terrain elevation data describes changes in surface elevation and can be obtained through various methods such as surveying and mapping and remote sensing. Fluid dynamics principles describe the laws governing fluid motion, including the laws of conservation of mass, momentum, and energy. The system comprehensively considers terrain factors and the laws of airflow to rationally divide the airflow paths within the preset geographic area.

[0066] In specific implementation, the system can convert the terrain elevation data of a preset geographic area into three-dimensional grid data for subsequent processing and analysis. The system can then extract ridge lines and valley lines based on the three-dimensional grid data as an important reference for dividing airflow channels. Using the ridge lines as the dividing line, the system divides the preset geographic area into multiple sub-areas. Within each sub-area, the system calculates the direction of airflow movement based on the principles of fluid mechanics and combines adjacent grid cells with the same airflow movement trend according to the airflow movement direction, ultimately forming multiple airflow channels.

[0067] In actual applications, the terrain of a pre-defined geographic area can be very complex, with numerous mountain ranges, canyons, basins, and other topographical features, making it difficult to accurately determine the direction of airflow. To address this issue, the system can incorporate terrain factors such as slope, aspect, and curvature as correction parameters for airflow direction calculation. The system can also consider the impact of surface cover factors such as vegetation and buildings on airflow, further improving the accuracy of airflow channel delineation.

[0068] S102, performing nonlinear interpolation calculation on the real-time meteorological data according to the position of the preset detection point in each airflow channel to obtain meteorological data of each preset detection point;

[0069] In this step, the system maps real-time meteorological data to pre-set detection points within the airflow channel, obtaining meteorological data for each pre-set detection point. Real-time meteorological data typically comes from meteorological observation stations or meteorological sensors, and includes various meteorological factors such as wind speed, wind direction, temperature, and air pressure. Pre-set detection points are virtual observation points set by the system within the airflow channel to simulate airflow disturbances. Because the real-time meteorological data and pre-set detection points may not completely overlap in spatial location, the system requires data interpolation.

[0070] In specific implementations, the system can use nonlinear interpolation algorithms, such as Kriging and spline interpolation, to interpolate real-time meteorological data to the locations of pre-set detection points. Nonlinear interpolation algorithms can account for the spatial correlation and nonlinear variation of meteorological elements, improving the accuracy of interpolation results. The system can optimize interpolation algorithm parameters, such as search radius and sample size, based on the morphological characteristics of the airflow channel and the distribution patterns of meteorological elements.

[0071] In practical applications, the temporal and spatial resolution of real-time meteorological data may be low, making it difficult to meet the requirements of refined simulations. To address this issue, the system can incorporate numerical meteorological forecast models, such as WRF and MM5, to generate high-temporal and spatial resolution meteorological data products to supplement real-time meteorological data. The system can also utilize machine learning algorithms, such as neural networks and support vector machines, to establish correlation models between meteorological elements and factors such as topography and underlying surface, enabling intelligent correction and optimization of real-time meteorological data.

[0072] S103, generating an airflow disturbance characteristic map based on the meteorological data of each preset detection point;

[0073] In this step, the system generates a characteristic map reflecting airflow disturbances based on meteorological data from each pre-set detection point. Airflow disturbances are a significant factor affecting drone flight stability and safety, manifesting as dramatic changes in airflow speed, direction, and turbulence intensity. This characteristic map provides a visual representation of the spatial distribution of airflow disturbances, providing a reference for drone flight path planning and flight control.

[0074] In specific implementations, the system can select meteorological factors such as wind speed, wind direction, and turbulence intensity to calculate airflow disturbance indicators, such as wind shear rate and turbulent energy dissipation rate, at each preset detection point. The system can then use spatial interpolation algorithms, such as inverse distance weighted interpolation and ordinary kriging interpolation, to interpolate these discrete airflow disturbance indicators across the entire preset geographic area, generating a continuous airflow disturbance feature map. Based on the application requirements of the airflow disturbance feature map, the system can adjust the interpolation algorithm parameters to control the smoothness and detail of the feature map.

[0075] S104, dividing the preset geographical area into a stable airflow area, a weak disturbance area, and a strong disturbance area based on the airflow disturbance characteristic map, and setting area transition buffer zones between the stable airflow area, the weak disturbance area, and the strong disturbance area respectively;

[0076] In this step, the system zons the pre-set geographic area for airflow stability based on the airflow disturbance signature map and establishes transition buffer zones. Airflow stability zoning divides the pre-set geographic area into different sub-regions based on the intensity of airflow disturbances, including stable airflow zones, weak disturbance zones, and strong disturbance zones. The airflow disturbance characteristics within different sub-regions vary significantly, posing different requirements for drone flight control. Transition buffer zones are transition zones between adjacent sub-regions to mitigate sudden airflow changes that drones may encounter when flying across different regions.

[0077] In specific implementations, the system can perform threshold segmentation on the airflow disturbance feature map and divide the preset geographical area into stable airflow zones, weak disturbance zones, and strong disturbance zones based on the magnitude of the airflow disturbance index. The selection of thresholds can refer to the flight performance and adaptability of the drone, or can be determined through test flights and expert experience. For the establishment of regional transition buffer zones, the system can use morphological operations such as dilation and erosion to process the boundaries of adjacent sub-regions and generate transition zones of a certain width. The system can also consider the impact of factors such as terrain and underlying surface on the airflow stability zoning and make adaptive adjustments.

[0078] In practical applications, airflow stability partitions can exhibit fragmented regions and irregular boundaries, impacting the continuity and smoothness of the UAV's flight path. To address this, the system can incorporate region merging and boundary smoothing algorithms to optimize the initially generated airflow stability partitions. The system can also dynamically adjust the airflow stability partitions based on the UAV's mission requirements and performance parameters, such as expanding the stable airflow zone and reducing the highly disturbed zone, thereby improving the flexibility and adaptability of flight path planning.

[0079] S105, when it is determined based on the real-time position coordinates of the virtual drone in the virtual training environment that the virtual drone has entered the regional conversion buffer zone, adjusting the pitch angle, roll angle, and yaw angle of the virtual drone by a preset incremental coefficient at a preset time interval to obtain an angle change;

[0080] When it is determined that the virtual drone enters the area conversion buffer zone based on the real-time position coordinates of the virtual drone in the virtual training environment, the system adjusts the pitch angle, roll angle and yaw angle of the virtual drone at a preset time interval with a preset incremental coefficient to obtain an angle change. Specifically, the airflow disturbance characteristic difference of the areas on both sides of the area conversion buffer zone is determined; the target attitude angle is calculated based on the airflow disturbance characteristic difference, and the target attitude angle includes a target pitch angle, a target roll angle and a target yaw angle; the preset incremental coefficient at the current moment is obtained at a preset time interval, and the value range of the preset incremental coefficient is 0 to 1; the difference between the target attitude angle and the current attitude angle is multiplied by the preset incremental coefficient to obtain an angle change, and the angle change includes a pitch angle change, a roll angle change and a yaw angle change.

[0081] In this step, the system determines whether the virtual drone has entered the zone transition buffer zone based on its real-time position. Upon entering the zone transition buffer zone, the system gradually adjusts the virtual drone's attitude angle to simulate the virtual drone's attitude changes as it crosses different airflow disturbance zones. This attitude angle adjustment is achieved by setting a preset time interval and a preset increment coefficient, ultimately resulting in changes in the virtual drone's pitch, roll, and yaw angles.

[0082] In practice, the system first needs to obtain the virtual drone's position coordinates in real time and compare them with the spatial extent of the area transition buffer zone to determine whether the virtual drone has entered the area transition buffer zone. Once the virtual drone enters the area transition buffer zone, the system begins executing the attitude angle adjustment algorithm.

[0083] The algorithm first determines the difference in airflow disturbance characteristics between the two sides of the transition buffer. These characteristics can include parameters such as wind speed, direction, and turbulence intensity. The system calculates the difference in these parameters between the two sides of the buffer to quantify the degree of change in airflow disturbance.

[0084] The second step is to calculate the target attitude angle based on the airflow disturbance characteristic difference. The target attitude angles, including the target pitch, roll, and yaw angles, represent the attitude state the virtual drone should achieve when fully entering the target area. The calculation of the target attitude angles requires comprehensive consideration of factors such as the airflow disturbance characteristic difference, the drone's flight performance, and control strategy. It can be estimated using physical models, empirical formulas, or machine learning methods.

[0085] The third step is to obtain the preset increment coefficient for the current moment at a preset time interval. The preset time interval represents the time step for attitude angle adjustment, such as 0.1 seconds or 0.5 seconds, and can be set based on factors such as the drone's control frequency and computing resources. The preset increment coefficient represents the ratio of the attitude angle change within each time step to the total target attitude angle change, and ranges from 0 to 1. The preset increment coefficient can be a fixed value, such as 0.1 or 0.2, or a variable value, such as gradually decreasing over time, to achieve a smooth transition of attitude angle changes.

[0086] The fourth step multiplies the difference between the target attitude angle and the current attitude angle by a preset increment coefficient to obtain the attitude angle change within the current time step. The attitude angle change includes pitch, roll, and yaw angle changes, representing the change in the virtual drone's rotation angle in the three spatial directions. The system updates the current attitude angle by this attitude angle change, obtaining the new attitude angle of the virtual drone at the end of the current time step.

[0087] The above four steps are repeated repeatedly until the virtual drone fully enters the target area, completing the entire attitude angle adjustment process. In actual applications, the system can adaptively adjust the parameters of the attitude angle adjustment algorithm based on factors such as the virtual drone's flight status and the changing pattern of airflow disturbances to improve the accuracy and stability of attitude control.

[0088] S106: Convert the angle variation into a force feedback signal, and feed it back to the operator through a force feedback device.

[0089] In this step, the system converts the virtual drone's attitude angle changes into force feedback signals, which are transmitted to the operator via a force feedback device. Force feedback is a tactile interaction technology that simulates the tactile sensation of a real environment by applying varying forces or torques to the operator. In the virtual drone training system, force feedback technology allows operators to intuitively perceive the virtual drone's attitude changes under airflow disturbances, enhancing the immersive and realistic control experience.

[0090] In specific implementations, the system can establish a mapping relationship between the change in attitude angle and the force feedback signal, such as a linear proportional relationship or a nonlinear curve relationship. The force feedback signal can be expressed as current, voltage, PWM wave, etc., and is used to drive the actuators in the force feedback device, such as motors and hydraulic cylinders. The force feedback device can use commercial devices such as game controllers and joysticks, or it can be customized and developed for a dedicated force feedback device, such as a six-degree-of-freedom force feedback device based on a parallel mechanism. The system requires calibration and verification of the force feedback device to ensure that the force feedback signal is accurately transmitted to the operator.

[0091] In actual applications, the performance parameters of force feedback devices, such as feedback force magnitude, frequency, and accuracy, may not fully meet the requirements of virtual drone training. To address this issue, the system can incorporate sensory enhancement technology to compensate and optimize force feedback signals through multi-channel feedback, such as visual and auditory feedback. The system can also customize force feedback parameters based on the operator's physiological characteristics and control habits to improve control comfort. Furthermore, the system can set force feedback thresholds and limits to prevent physical damage to the operator due to excessive feedback force or prolonged duration.

[0092] In the above-described embodiment, by establishing a network of airflow channels and detection points, accurate modeling of airflow conditions within a preset geographic area is achieved. Based on nonlinear interpolation calculations based on real-time meteorological data, accurate meteorological data for the detection points can be obtained, thereby generating a disturbance characteristic map reflecting the regional airflow distribution characteristics. By dividing the region into different airflow disturbance levels and setting buffer zones, the system can smoothly adjust the flight attitude of the virtual drone according to preset time intervals and incremental coefficients as it crosses different airflow areas, avoiding a sudden increase in control difficulty caused by sudden attitude changes. The calculated angle change is converted into a force feedback signal and transmitted to the operator, allowing the operator to truly experience the control resistance in different airflow environments, thereby enhancing the authenticity of the training process. This virtual-real interaction method based on real-time meteorological data and physical models enables the drone simulation training system to more accurately simulate the effects of airflow in actual flight environments, helping operators master flying skills in complex weather conditions.

[0093] In order to further improve the realism and interactivity of the virtual training environment, the system also needs to consider the impact of the drone itself on the surrounding airflow environment. During actual flight, the drone will not only be affected by the ambient airflow, but its high-speed rotating propellers will also produce significant wake effects. These wakes will interact with the surrounding airflow to form a more complex airflow environment. Therefore, based on the above embodiments, this application also proposes a virtual-reality interaction method that takes into account the wake effect of the drone. By simulating the two-way coupling between the drone and the airflow environment, a higher-fidelity flight simulation training effect is achieved. The following is combined with Figure 2, a virtual-reality interaction method considering the wake effect of a drone in an embodiment of the present application is described:

[0094] See also Figure 2 , which is a flow chart of a virtual-reality interaction method considering the wake effect of a drone in an embodiment of the present application.

[0095] S201, using a virtual drone as an airflow disturbance source to generate a moving disturbance field centered on the virtual drone;

[0096] In this step, the system treats the virtual drone as a moving source of airflow disturbance. By simulating the wake effect of the drone's propellers, it generates a moving disturbance field centered on the virtual drone within the virtual environment. This moving disturbance field is a region of airflow disturbance that changes with the drone's motion, reflecting its impact on the surrounding airflow environment. By introducing this moving disturbance field, the system achieves bidirectional coupling between the drone and the airflow environment, enhancing the realism of flight simulation.

[0097] In specific implementations, the system can employ computational fluid dynamics (CFD) methods, such as numerical simulations based on the Euler or Navier-Stokes equations, to calculate the wake velocity field generated by the drone's propellers. Based on information such as the drone's geometry, propeller speed, and blade parameters, the system must set appropriate boundary and initial conditions, and select an appropriate turbulence model and discretization scheme to ensure the accuracy and stability of the wake field simulation. After obtaining the wake velocity field, the system can superimpose it on the background airflow field surrounding the drone, forming a moving disturbance field centered on the drone.

[0098] S202: forming a dynamic airflow environment based on the interaction between the moving disturbance field and the airflow channel in the preset geographical area;

[0099] The system forms a dynamic airflow environment based on the interaction between the mobile disturbance field and the airflow channels in a preset geographical area. Specifically, it includes: calculating the disturbance propagation direction of the mobile disturbance field in each airflow channel; determining the disturbance intensity of the mobile disturbance field on each airflow channel according to the disturbance propagation direction; superimposing the disturbance intensity with the original airflow characteristics of each airflow channel to obtain the superposition result, and calculating new airflow distribution data based on the superposition result; and generating a dynamic airflow environment according to the new airflow distribution data.

[0100] Among them, a dynamic airflow environment is generated based on the new airflow distribution data, specifically including: extracting the airflow gradient between each airflow area and calculating the rate of change of the airflow gradient over time; determining the transition characteristics between the airflow areas based on the rate of change; and using the continuous airflow field generated based on the transition characteristics as the dynamic airflow environment.

[0101] In this step, the system considers the interaction between the moving disturbance field and the airflow channels within a pre-defined geographic area, creating a dynamically changing airflow environment. The moving disturbance field disrupts and alters the existing airflow channels, while the morphological characteristics of the airflow channels also affect the propagation and attenuation of the moving disturbance field. By simulating this bidirectional coupling, the system can generate a more realistic and complex airflow environment, providing higher-fidelity simulation conditions for UAV flight training.

[0102] In specific implementation, the system first calculates the propagation direction of the moving disturbance field in each airflow channel. This propagation direction depends on the velocity direction of the moving disturbance field and the morphological characteristics of the airflow channel, such as the channel curvature and cross-sectional area variation. The system can use methods such as streamline tracing and characteristic line methods to determine the propagation path of the disturbance in the airflow channel. Then, based on the disturbance propagation direction, the system calculates the disturbance intensity of the moving disturbance field on each airflow channel. The disturbance intensity is related to factors such as the velocity of the moving disturbance field, the propagation distance, and the damping characteristics of the airflow channel. The system can use methods such as energy attenuation models and turbulence dissipation models to quantitatively describe the spatial distribution of the disturbance intensity. Next, the system superimposes the calculated disturbance intensity with the original airflow characteristics of each airflow channel to obtain the new airflow distribution data for the airflow channel under the influence of the disturbance. Finally, the system generates a dynamic airflow environment based on this new airflow distribution data, which serves as the background conditions for the virtual drone flight.

[0103] When generating a dynamic airflow environment, the system needs to consider the transition characteristics between different airflow regions to ensure the continuity and realism of the airflow field. The system can extract the airflow gradient between each airflow region and calculate the rate of change of the airflow gradient over time. The airflow gradient reflects the degree of spatial variation in airflow speed and direction. The larger the gradient, the more obvious the difference between airflow regions. The rate of change of the airflow gradient reflects the speed of the transition between airflow regions. Based on the rate of change of the airflow gradient, the system can determine the transition boundaries between different airflow regions and the size of the transition region. Within the transition region, the system uses interpolation and smoothing methods to generate continuously changing airflow speed and direction data, thereby obtaining a natural and smooth dynamic airflow environment.

[0104] S203, calculating a feedback disturbance acting on the virtual UAV according to the dynamic airflow environment;

[0105] The system calculates the feedback disturbance acting on the virtual drone based on the dynamic airflow environment, specifically including: obtaining the airflow velocity and direction at the location of the virtual drone in the dynamic airflow environment; calculating the force exerted by the airflow velocity and direction on each force-bearing surface of the virtual drone; calculating the resultant torque based on the force and the position of the action point on each force-bearing surface; and using the attitude angle change obtained by converting the resultant torque as the feedback disturbance acting on the virtual drone.

[0106] In this step, the system calculates the feedback disturbance forces and torques acting on the virtual drone based on the generated dynamic airflow environment. Feedback disturbance refers to the interference and influence of the airflow environment on the drone, which changes the drone's force state and flight attitude. By calculating feedback disturbance, the system can simulate the drone's motion response under complex airflow conditions, improving the relevance and effectiveness of flight control and maneuvering training.

[0107] In specific implementation, the system first needs to obtain airflow velocity and direction data at the location of the virtual drone in a dynamic airflow environment. This can be achieved by placing virtual sensors in the airflow field or by estimating discrete airflow data around the drone using interpolation algorithms. The system then maps the airflow velocity and direction data onto various load-bearing surfaces of the virtual drone, such as the wings, tail, and fuselage. The size, shape, and spatial location of these load-bearing surfaces can be determined based on the drone's 3D model and current attitude. Next, the system calculates the normal and tangential components of the airflow velocity and direction on each load-bearing surface. Based on aerodynamic principles such as Bernoulli's equation and Kroger's theorem, the corresponding aerodynamic forces are calculated. Aerodynamic forces include lift, drag, and lateral force, and their magnitude and direction depend on factors such as the windward angle, frontal area, and local airflow conditions of the load-bearing surface. Finally, the system vectorially synthesizes the aerodynamic forces on each load-bearing surface and the locations of their application points to obtain the resultant force and torque acting on the entire drone. The resultant torque can be further converted into a change in the drone's attitude angle and output as a feedback disturbance to the flight control system.

[0108] S204, fusing the feedback disturbance with the angle variation to obtain a fused angle variation;

[0109] In this step, the system fuses the attitude angle change caused by the feedback disturbance with the UAV's active attitude adjustments within the zone transition buffer zone to generate a comprehensive attitude angle change command. This fusion process considers the dual effects of airflow disturbances and control commands, resulting in a smoother and more coordinated attitude control command, avoiding undesirable phenomena such as sudden changes or chattering.

[0110] In specific implementation, the system first needs to unify the attitude angle change caused by the feedback disturbance and the active attitude adjustment amount into the same coordinate system, such as the body coordinate system or the geographic coordinate system. This requires coordinate transformation and rotation alignment of the two changes based on the current UAV attitude and position information. Then, the system can use a weighted superposition method to linearly combine the two changes according to a certain weight coefficient to obtain the fused attitude angle change. The value of the weight coefficient can be determined based on factors such as the airflow disturbance characteristics of the area where the UAV is located, flight mission requirements, and operator habits. In general, the active attitude adjustment amount should dominate, while the change caused by the feedback disturbance plays an auxiliary and corrective role.

[0111] S205: Update the force feedback signal based on the fusion angle change.

[0112] In this step, the system generates a new force feedback signal based on the fused angle changes and transmits it to the operator. This force feedback signal update process reflects the two-way interaction between the virtual drone and the operator. The operator can perceive changes in the drone's attitude through the force feedback device and adjust their control strategy and actions accordingly. Simultaneously, the operator's control commands also affect the drone's flight state and attitude control process, forming a closed-loop human-machine interaction system.

[0113] During implementation, the system needs to establish a mapping relationship between the fused angle change and the force feedback signal. This mapping relationship can be linear or nonlinear, depending on the type and characteristics of the force feedback device. For a linear mapping relationship, the system can simply multiply the angle change by a proportional coefficient to obtain the change in the force feedback signal. For a nonlinear mapping relationship, the system can use table lookup, interpolation, or other methods to calculate the change in the force feedback signal based on a pre-calibrated force-angle curve. After obtaining the change in the force feedback signal, the system superimposes it on the original force feedback signal to obtain an updated force feedback signal. The updated force feedback signal is transmitted to the operator through the force feedback device. The operator can judge the change in the drone's posture based on characteristics such as the magnitude, direction, and frequency of the force and make corresponding control responses.

[0114] In the above-described embodiment, a dynamic simulation of the airflow changes caused by the drone's flight is achieved by using a virtual drone as an airflow disturbance source and generating a moving disturbance field. Based on the interaction between the moving disturbance field and the existing airflow channel, the system calculates and updates the dynamic airflow environment, thereby obtaining a feedback disturbance acting on the virtual drone. This feedback disturbance is then integrated with the original angle change to update the force feedback signal, enabling the system to simultaneously reflect the combined impact of the ambient airflow and the drone's own motion on the flight state. This dynamic feedback mechanism, which takes into account the interaction between the drone and the airflow environment, achieves a force feedback effect that is closer to the actual flight state, improving the accuracy and authenticity of the simulation of aerodynamic effects during training.

[0115] The following describes the system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of the physical device structure of a virtual-reality interaction system for a UAV simulation training flight provided in an embodiment of the present application.

[0116] It should be noted that Figure 3 The structure of the system shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0117] like Figure 3 As shown, the system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes, such as the methods described in the above embodiments, based on programs stored in a read-only memory (ROM) 302 or programs loaded from a storage unit 308 into a random access memory (RAM) 303. RAM 303 also stores various programs and data required for system operation. CPU 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to bus 304.

[0118] The following components are connected to the I / O interface 305: an input section 306 including a camera, infrared sensor, and the like; an output section 307 including a liquid crystal display (LCD) and speakers; a storage section 308 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card or a modem. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. Removable media 311, such as a magnetic disk, optical disk, magneto-optical disk, or semiconductor memory, is installed in the drive 310 as needed, so that computer programs read from the media can be installed in the storage section 308 as needed.

[0119] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for executing the methods illustrated in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via the communication section 309 and / or installed from removable media 311. When executed by the central processing unit (CPU) 301, the computer program performs the various functions defined in the present invention.

[0120] It should be noted that the computer-readable medium described in the embodiments of the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, a computer-readable signal medium may include a data signal transmitted in baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal may take any of a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof.

[0121] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram can represent a module, program segment, or part of the code, and the above-mentioned module, program segment, or part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two boxes shown in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or can be implemented using a combination of dedicated hardware and computer instructions.

[0122] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the system described in the above embodiments, or may exist independently and not incorporated into the system. The storage medium carries one or more computer programs, and when executed by a processor of a system, the system implements the methods provided in the above embodiments.

[0123] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0124] As used in the above embodiments, the term “when…” may be interpreted as “if…” or “after…” or “in response to determining…” or “in response to detecting…”, depending on the context. Similarly, the phrases “upon determining…” or “if (stated condition or event) is detected” may be interpreted as “if determining…” or “in response to determining…” or “upon detecting (stated condition or event)” or “in response to detecting (stated condition or event)”, depending on the context.

[0125] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, hard disk, tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive).

[0126] Those skilled in the art will appreciate that all or part of the process steps in the above-described method embodiments can be implemented by a computer program instructing the relevant hardware. The program can be stored in a computer-readable storage medium, and when executed, the program can include the process steps in the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A virtual-reality interaction method for simulated training flight of a UAV, characterized in that: include: dividing airflow channels in a predetermined geographical area according to terrain elevation data of the predetermined geographical area and principles of fluid mechanics; Performing nonlinear interpolation calculation on the real-time meteorological data according to the position of each preset detection point in the airflow channel to obtain meteorological data of each preset detection point; generating an airflow disturbance characteristic diagram according to the meteorological data of each of the preset detection points; Dividing the preset geographical area into a stable airflow area, a weak disturbance area, and a strong disturbance area based on the airflow disturbance characteristic map, and setting area transition buffer zones between the stable airflow area, the weak disturbance area, and the strong disturbance area respectively; When it is determined based on the real-time position coordinates of the virtual drone in the virtual training environment that the virtual drone enters the area conversion buffer zone, the pitch angle, roll angle, and yaw angle of the virtual drone are adjusted by a preset incremental coefficient at a preset time interval to obtain an angle change amount; The angle variation is converted into a force feedback signal and fed back to the operator through a force feedback device.

2. The method according to claim 1, characterized in that The dividing of the airflow channels in the preset geographical area according to the terrain elevation data of the preset geographical area and the principles of fluid mechanics specifically includes: Converting the terrain elevation data of the preset geographical area into three-dimensional grid data; Extracting ridge lines and valley lines based on the three-dimensional grid data; Dividing the preset geographical area into a plurality of sub-areas based on the ridgeline; In each of the sub-areas, the direction of airflow movement is calculated based on the principles of fluid mechanics; According to the airflow movement direction, adjacent grid units with the same airflow movement trend are combined to form a plurality of airflow channels.

3. The method according to claim 1, characterized in that The pitch angle, roll angle and yaw angle of the virtual drone are adjusted by a preset incremental coefficient at a preset time interval to obtain an angle change, specifically including: Determining the difference in airflow disturbance characteristics between areas on both sides of the regional transition buffer zone; Calculating a target attitude angle according to the airflow disturbance characteristic difference, wherein the target attitude angle includes a target pitch angle, a target roll angle, and a target yaw angle; Obtaining a preset increment coefficient at the current moment according to a preset time interval, wherein the preset increment coefficient has a value range of 0 to 1; The difference between the target attitude angle and the current attitude angle is multiplied by the preset incremental coefficient to obtain an angle change, where the angle change includes a pitch angle change, a roll angle change, and a yaw angle change.

4. The method according to claim 1, wherein After converting the angle variation into a force feedback signal and feeding it back to the operator via a force feedback device, the method further includes: Using the virtual drone as an airflow disturbance source, generating a moving disturbance field centered on the virtual drone; Based on the interaction between the moving disturbance field and the airflow channel in the preset geographical area, a dynamic airflow environment is formed; Calculating a feedback disturbance acting on the virtual drone according to the dynamic airflow environment; Fusing the feedback disturbance with the angle variation to obtain a fused angle variation; The force feedback signal is updated based on the fusion angle change.

5. The method according to claim 4, characterized in that The forming of a dynamic airflow environment based on the interaction between the mobile disturbance field and the airflow channel in the preset geographical area specifically includes: Calculating the disturbance propagation direction of the moving disturbance field in each of the airflow channels; Determining the disturbance intensity of the moving disturbance field on each of the airflow channels according to the disturbance propagation direction; Superimposing the disturbance intensity with the original airflow characteristics of each of the airflow channels to obtain a superposition result, and calculating new airflow distribution data based on the superposition result; A dynamic airflow environment is generated according to the new airflow distribution data.

6. The method according to claim 5, characterized in that Generating a dynamic airflow environment according to the new airflow distribution data specifically includes: Extracting the airflow gradient between each airflow area and calculating the rate of change of the airflow gradient over time; determining transition characteristics between airflow regions based on the rate of change; The continuous airflow field generated based on the transition characteristics is used as a dynamic airflow environment.

7. The method according to claim 4, characterized in that The calculating of the feedback disturbance acting on the virtual drone according to the dynamic airflow environment specifically includes: Obtaining the airflow speed and direction at the location of the virtual drone in the dynamic airflow environment; Calculating the force exerted by the airflow velocity and direction on each force-bearing surface of the virtual drone; Calculate the resultant moment according to the forces and positions of the points of action on each of the force-bearing surfaces; The attitude angle variation obtained by converting the synthetic torque is used as a feedback disturbance acting on the virtual drone.

8. A virtual-reality interactive system for simulated training flight of unmanned aerial vehicles, characterized in that: The system comprises: One or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the system to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instructions are executed on a system, the system is caused to perform the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product is run on a system, the system is caused to perform the method according to any one of claims 1 to 7.

Images