Medium-large target posture autonomous control system for intelligent unmanned aerial vehicle

Abstract

The present application relates to unmanned aerial vehicle swing control technical field, disclose a kind of intelligent unmanned aerial vehicle with medium-large target machine attitude autonomous control system, the system includes: parameter acquisition module, for obtaining the real-time attitude data of target machine flight process, extract swing state parameters from real-time attitude data;Swing judging module, for determining whether target machine is in swing state according to swing state parameters;Attitude correction module, for generating corresponding correction compensation when determining that target machine is in swing state based on roll angle and roll change amplitude;Compensation adjustment module, for obtaining current environmental parameters, comparing environmental parameters with historical data, correcting correction compensation;Flight control module, for adjusting the rudder deflection angle of target machine according to attitude compensation amount.The present application realizes the stable control to the flight attitude of target machine.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) sway control technology, and more specifically, to an autonomous attitude control system for medium and large target drones used in intelligent unmanned aerial vehicles. Background Technology

[0002] With the continuous development of unmanned aerial vehicle (UAV) technology, medium and large target drones are widely used in air defense drills, weapons testing, and flight verification due to their advantages such as long flight time, high payload capacity, and rich simulated target characteristics. In actual flight, medium and large target drones usually need to maintain stable flight for a long time in complex airflow environments to ensure the stability of flight trajectory, flight attitude, and target simulation effects.

[0003] However, due to their large size and wide wind-affected area, medium and large target drones are easily affected by environmental factors such as crosswinds, turbulence, and air disturbances during flight, which can lead to deviations in flight attitude, especially persistent swaying in the roll direction. When the swaying amplitude continues to increase, it not only affects the flight stability of the target drone but may also cause flight trajectory deviations, frequent control surface oscillations, and in severe cases, even affect the flight safety of the target drone.

[0004] In existing technologies, attitude control for unmanned aerial vehicles (UAVs) typically employs fixed compensation parameters or single attitude angle control methods. For example, attitude correction is performed solely based on roll, pitch, or yaw angles, with control surfaces adjusted using preset control parameters. While this type of control can achieve a degree of flight attitude stability, it generally lacks the ability to finely identify swaying states, making it difficult to effectively distinguish between sustained swaying and transient environmental disturbances. It is prone to frequently triggering compensation control under short-term airflow fluctuations, leading to repeated control surface adjustments and increasing the risk of mechanical oscillation.

[0005] Therefore, it is necessary to provide an autonomous attitude control system for medium and large target drones for intelligent unmanned aerial vehicles to solve the problems in the existing technology, such as difficulty in accurately distinguishing between continuous swaying and instantaneous environmental disturbances, easy false triggering of compensation control, and insufficient attitude compensation and adaptive capability in complex airflow environments. Summary of the Invention

[0006] In view of this, the present invention proposes an autonomous attitude control system for medium and large target drones for intelligent unmanned aerial vehicles, which aims to solve the problems in the prior art that make it difficult to accurately distinguish between continuous swaying and instantaneous environmental disturbances, that compensation control is prone to false triggering, and that attitude compensation and adaptive capability is insufficient in complex airflow environments.

[0007] This invention proposes an autonomous attitude control system for medium-to-large target drones used in intelligent unmanned aerial vehicles, comprising: The parameter acquisition module is used to acquire real-time attitude data of the target drone during flight and extract yaw state parameters from the real-time attitude data; wherein, the yaw state parameters include roll angle and roll change amplitude. The swaying judgment module is used to determine whether the target machine is in a swaying state based on the swaying state parameters. The attitude correction module is used to generate corresponding correction compensation based on the roll angle and the roll change amplitude when the target drone is determined to be in a swaying state. The compensation adjustment module is used to acquire the current environmental parameters, compare the environmental parameters with historical data, set adjustment coefficients according to the comparison results, and correct the correction compensation amount to obtain the attitude compensation amount. The flight control module is used to adjust the deflection angle of the target drone's control surfaces according to the attitude compensation amount, thereby controlling the target drone's flight attitude.

[0008] Furthermore, the attitude autonomous control system for the medium-to-large target drone used in the intelligent unmanned aerial vehicle also includes: The target drone status assessment module is used to extract pitch and yaw angles from real-time attitude data, and to assess the target drone's flight direction deviation based on the pitch and yaw angles; wherein, The pitch angle is compared with a preset longitudinal angle range. If the pitch angle is within the preset longitudinal angle range, the target drone is in a longitudinally stable state; if the pitch angle exceeds the preset longitudinal angle range, the target drone is determined to be in a longitudinally offset state. The yaw angle is compared with the preset lateral angle range. If the yaw angle is within the preset lateral angle range, the target drone is determined to be in a laterally stable state. If the yaw angle exceeds the preset lateral angle range, the target drone is determined to be in a laterally deflected state. If the target drone is in a stable longitudinal and lateral state, it is determined that the target drone's flight direction has not deviated; otherwise, it is determined that the target drone's flight direction has deviated.

[0009] Furthermore, after assessing the target drone's flight direction deviation based on the pitch and yaw angles, the process includes: If the target drone's flight direction deviates, a direction correction control quantity is generated based on the pitch angle offset and yaw angle offset, and the flight control module is controlled to adjust the deflection direction and deflection angle of the corresponding control surfaces to correct the target drone's flight direction so that the target drone's direction is corrected. If the target drone's flight direction does not deviate, or the target drone's direction returns to normal, the sway detection module determines whether the target drone is in a swaying state.

[0010] Furthermore, when the swing determination module determines whether the target device is in a swinging state based on the swing state parameters, it includes: Acquire the roll angle change data within a preset time period, and calculate the roll change amplitude based on the change data; The roll change amplitude is compared with a preset sway threshold. If the roll change amplitude is less than or equal to the preset sway threshold, the target drone is determined to be in a stable flight state. If the roll change amplitude is greater than the preset sway threshold, the target drone is determined to be in an unstable flight state.

[0011] Furthermore, the determination that the target drone is in an unstable flight state includes: Determine whether the roll angle exhibits a periodic, reciprocating change; When the roll angle changes periodically, the target drone is determined to be in a swaying state, and the attitude correction module is triggered to generate the corresponding correction compensation amount. When the roll angle does not change periodically, the target drone is determined to be in a state of instantaneous disturbance, and the sway state parameters are continuously acquired for reassessment.

[0012] Furthermore, the attitude correction module, when determining that the target drone is in a swaying state, generates a corresponding correction compensation amount based on the roll angle and the roll change amplitude, including: The correction compensation direction is determined based on the current offset direction of the roll angle, so that the compensation direction is opposite to the roll offset direction; The basic compensation amplitude is determined based on the magnitude of the roll change, and the roll change amplitude is directly proportional to the basic compensation amplitude. The correction compensation amount is obtained by combining the correction compensation direction with the basic compensation amplitude.

[0013] Furthermore, the current environmental parameters include: Wind speed, airflow fluctuation amplitude, and intensity of air disturbance.

[0014] Furthermore, the compensation adjustment module is used to compare the environmental parameters with historical data, and when setting the adjustment coefficient based on the comparison result, it includes: The current environmental disturbance level is determined based on the wind speed, airflow fluctuation amplitude, and air disturbance intensity; wherein, the current environmental disturbance level includes the current wind speed level, the current airflow fluctuation level, and the current air disturbance level; The current wind speed level is determined by comparing the wind speed with a preset wind speed range; the current wind speed levels are ranked from low to high as level one, level two, and level three. The current airflow fluctuation level is determined by comparing the airflow fluctuation amplitude with a preset fluctuation range; wherein the current airflow fluctuation level is successively level one, level two, and level three. The current air disturbance level is determined by comparing the air disturbance intensity with a preset intensity range; wherein the current air disturbance level is successively level one, level two, and level three. The current environmental disturbance level is compared with historical data, and an adjustment coefficient is set based on the comparison results.

[0015] Furthermore, when comparing the current environmental disturbance level with historical data and setting the adjustment coefficient based on the comparison result, the method further includes: Filter historical data that is the same as the current environmental disturbance level from the historical data; and obtain the historical adjustment coefficient from the same historical data, and use the historical adjustment coefficient as the adjustment coefficient; If there is no historical data in the historical data that is the same as the current environmental disturbance level, then the similarity between the wind speed, airflow fluctuation amplitude, and air disturbance intensity and the historical wind speed, historical airflow fluctuation amplitude, and historical air disturbance intensity in the historical data is calculated, the similarity is sorted in descending order, and the maximum similarity value is extracted; the historical adjustment coefficient corresponding to the maximum similarity value is used as the adjustment coefficient.

[0016] Furthermore, the compensation adjustment module is used to correct the correction compensation amount to obtain the attitude compensation amount, including: The attitude compensation amount includes the compensation direction and the compensation value; wherein... The compensation direction in the attitude compensation amount is the same as the correction compensation direction; The compensation value in the attitude compensation amount is the product of the basic compensation amplitude and the adjustment coefficient.

[0017] Compared with existing technologies, the advantages of this invention are as follows: This invention acquires the target drone's attitude data in real time during flight through a parameter acquisition module, extracts the roll angle and roll change amplitude as sway state parameters, and then uses a sway judgment module to determine whether the target drone is in a sway state, thereby enabling timely identification of lateral oscillations during flight; after detecting that the target drone is in a sway state, the attitude correction module generates a corresponding correction compensation amount based on the roll angle and roll change amplitude, making the compensation direction opposite to the roll offset direction, and dynamically adjusts the compensation intensity according to the sway amplitude, thereby achieving active suppression of the sway trend; at the same time, the compensation amount adjustment module further acquires environmental parameters such as wind speed, airflow fluctuation amplitude, and air disturbance intensity, and corrects the correction compensation amount in combination with historical environmental data, enabling the system to adaptively adjust the compensation intensity according to different environmental disturbance conditions, avoiding problems of insufficient or excessive compensation due to sudden environmental changes; finally, the flight control module dynamically adjusts the target drone's control surface deflection angle according to the attitude compensation amount, thereby achieving stable control of the target drone's flight attitude and improving the flight stability, anti-disturbance capability, and attitude control accuracy of medium and large target drones in complex airflow environments. Attached Figure Description

[0018] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a functional block diagram of the attitude autonomous control system for medium and large target drones used in intelligent unmanned aerial vehicles, provided in an embodiment of the present invention. Detailed Implementation

[0019] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0020] In some embodiments of this application, see Figure 1 As shown, this embodiment provides an autonomous attitude control system for medium-to-large target drones used in intelligent unmanned aerial vehicles, including: The parameter acquisition module is used to acquire real-time attitude data of the target drone during flight and extract yaw state parameters from the real-time attitude data; wherein, the yaw state parameters include roll angle and roll change amplitude. The swaying judgment module is used to determine whether the target machine is in a swaying state based on the swaying state parameters. The attitude correction module is used to generate corresponding correction compensation based on the roll angle and the roll change amplitude when the target drone is determined to be in a swaying state. The compensation adjustment module is used to acquire the current environmental parameters, compare the environmental parameters with historical data, set adjustment coefficients according to the comparison results, and correct the correction compensation amount to obtain the attitude compensation amount. The flight control module is used to adjust the deflection angle of the target drone's control surfaces according to the attitude compensation amount, thereby controlling the target drone's flight attitude.

[0021] Understandably, this invention acquires the target drone's attitude data in real time during flight through a parameter acquisition module, extracts the roll angle and roll change amplitude as sway state parameters, and then uses a sway judgment module to determine whether the target drone is in a swaying state, thereby enabling timely identification of lateral oscillations during flight. Upon detecting a swaying state, the attitude correction module generates a corresponding correction compensation amount based on the roll angle and roll change amplitude, ensuring the compensation direction is opposite to the roll offset direction, and dynamically adjusts the compensation intensity according to the sway amplitude, thereby actively suppressing the swaying trend. Simultaneously, the compensation adjustment module further acquires environmental parameters such as wind speed, airflow fluctuation amplitude, and air disturbance intensity, and corrects the correction compensation amount based on historical environmental data, enabling the system to adaptively adjust the compensation intensity according to different environmental disturbance conditions, avoiding insufficient or excessive compensation due to sudden environmental changes. Finally, the flight control module dynamically adjusts the target drone's control surface deflection angle based on the attitude compensation amount, thereby achieving stable control of the target drone's flight attitude and improving the flight stability, anti-disturbance capability, and attitude control accuracy of medium and large target drones in complex airflow environments.

[0022] In some specific embodiments of this application, the attitude autonomous control system for medium and large target drones used in intelligent unmanned aerial vehicles further includes: The target drone status assessment module is used to extract pitch and yaw angles from real-time attitude data, and to assess the target drone's flight direction deviation based on the pitch and yaw angles; wherein, The pitch angle is compared with a preset longitudinal angle range. If the pitch angle is within the preset longitudinal angle range, the target drone is in a longitudinally stable state; if the pitch angle exceeds the preset longitudinal angle range, the target drone is determined to be in a longitudinally offset state. The yaw angle is compared with the preset lateral angle range. If the yaw angle is within the preset lateral angle range, the target drone is determined to be in a laterally stable state. If the yaw angle exceeds the preset lateral angle range, the target drone is determined to be in a laterally deflected state. If the target drone is in a stable longitudinal and lateral state, it is determined that the target drone's flight direction has not deviated; otherwise, it is determined that the target drone's flight direction has deviated.

[0023] Understandably, by extracting pitch and yaw angles from real-time attitude data through the target drone state assessment module and comparing them with preset longitudinal and lateral angle ranges respectively, the system can determine whether the target drone is in a longitudinally and laterally stable state. This allows for prioritizing identification of any deviation in the target drone's flight direction before yaw control, enabling the system to correct the flight direction first and then control the yaw state. This avoids the problem of control confusion caused by the superposition of flight direction deviation and roll yaw, improving the overall flight stability and directional control accuracy of the target drone. Simultaneously, by independently judging the pitch and yaw angles, the system can quickly distinguish whether the target drone is in a longitudinal, lateral, or combined deviation state, thus executing corresponding correction control for different deviation states and improving attitude adjustment efficiency. For example, when the target drone yaws in a crosswind environment, the yaw angle will first exceed the preset lateral angle range. At this time, the system will prioritize triggering directional correction control to restore the target drone's direction to stability before executing yaw suppression control, thereby reducing the control delay caused by the simultaneous correction of multiple attitude errors.

[0024] In some specific embodiments, the preset longitudinal angle range and the preset lateral angle range can be set according to the target drone model, flight mission and flight speed. For example, the preset longitudinal angle range can be set to ±5° and the preset lateral angle range can be set to ±8°. When the target drone is in high-speed flight, the corresponding angle range can be appropriately reduced to improve the accuracy of flight direction control. In low-speed cruise state, the corresponding angle range can be appropriately expanded to reduce the control surface oscillation problem caused by frequent corrections.

[0025] In some specific embodiments of this application, the step of evaluating the flight direction deviation of the target drone based on the pitch angle and yaw angle includes: If the target drone's flight direction deviates, a direction correction control quantity is generated based on the pitch angle offset and yaw angle offset, and the flight control module is controlled to adjust the deflection direction and deflection angle of the corresponding control surfaces to correct the target drone's flight direction so that the target drone's direction is corrected. If the target drone's flight direction does not deviate, or the target drone's direction returns to normal, the sway detection module determines whether the target drone is in a swaying state.

[0026] Understandably, by generating directional correction control quantities based on pitch and yaw angle offsets when the target drone's flight direction deviates, and controlling the flight control module to adjust the deflection direction and angle of the corresponding control surfaces to correct the target drone's flight direction, and then using a yaw judgment module to determine whether the target drone is in a yaw state after the target drone's direction is corrected, it is possible to achieve phased control of flight direction correction and yaw suppression. This avoids control coupling problems when flight direction deviation and roll yaw are corrected simultaneously, and improves flight attitude control stability and directional correction accuracy. By executing directional correction control first and then yaw state judgment, it is also possible to reduce mechanical oscillations and control delays caused by frequent reverse deflection of control surfaces, and improve the anti-disturbance capability and flight reliability of medium and large target drones in complex airflow environments.

[0027] Furthermore, in some specific embodiments, when the target drone is affected by crosswinds, the yaw angle first deviates from the preset lateral angle range. At this time, the system generates a directional correction control quantity based on the yaw angle offset and controls the rudder to deflect in the opposite direction of the offset so that the target drone's flight direction returns to normal. After the flight direction is restored, the system continuously acquires the roll angle and roll change amplitude through the yaw judgment module to determine whether the target drone has periodic lateral yaw. If yaw exists, a corresponding correction compensation quantity is further generated to suppress the yaw attitude of the target drone, thereby achieving phased stable control of flight direction deviation and roll yaw.

[0028] In some specific embodiments of this application, when the swing determination module is used to determine whether the target drone is in a swinging state based on the swing state parameters, it includes: Acquire the roll angle change data within a preset time period, and calculate the roll change amplitude based on the change data; The roll change amplitude is compared with a preset sway threshold. If the roll change amplitude is less than or equal to the preset sway threshold, the target drone is determined to be in a stable flight state. If the roll change amplitude is greater than the preset sway threshold, the target drone is determined to be in an unstable flight state.

[0029] Understandably, by acquiring data on the change of roll angle within a preset time period, calculating the roll change amplitude based on the data, and then comparing the roll change amplitude with a preset sway threshold, it is possible to quickly determine the stability of the target drone's current flight state, thereby promptly identifying whether the target drone exhibits a lateral swaying trend.

[0030] When the roll change is less than or equal to the preset sway threshold, the target drone is determined to be in a stable flight state, indicating that the current roll attitude change is within a controllable range and no additional compensation control is required. However, when the roll change exceeds the preset sway threshold, the target drone is determined to be in an unstable flight state, thereby triggering subsequent attitude correction and compensation control in a timely manner to prevent the roll sway from further expanding and causing flight attitude instability. At the same time, judging by the roll change amplitude rather than a single roll angle can also avoid misjudgment caused by short-term attitude fluctuations, improving the accuracy of sway recognition and the reliability of flight stability control.

[0031] In a specific embodiment, the system continuously collects roll angle change data within a preset time period of 0.5 seconds. When the roll angle changes from 2° to 9°, the roll change amplitude is calculated to be 7°. If the current preset yaw threshold is 5°, since the roll change amplitude is greater than the preset yaw threshold, the target drone is determined to be in an unstable flight state, and the attitude correction module is further triggered to generate the corresponding correction compensation amount. When the roll angle changes only from 2° to 4°, the corresponding roll change amplitude is 2°. Since it does not exceed the preset yaw threshold, the target drone is determined to be in a stable flight state, thereby avoiding unnecessary control surface compensation actions and improving the operational stability of the flight control system.

[0032] Specifically, the preset sway threshold can be set according to the target drone model, airframe size, flight speed, and flight mission. For example, for medium to large high-speed target drones, the preset sway threshold can be set to 3°–5° to improve flight attitude control accuracy and prevent rapid expansion of roll sway during high-speed flight. For target drones in low-speed cruise mode, the preset sway threshold can be appropriately set to 5°–8° to reduce control surface oscillation caused by frequent attitude corrections. In addition, the preset sway threshold can be dynamically adjusted according to the intensity of environmental disturbances. For example, in strong wind conditions, the preset sway threshold can be appropriately increased to reduce false triggering caused by instantaneous airflow fluctuations.

[0033] In some specific embodiments of this application, determining that the target drone is in an unstable flight state includes: Determine whether the roll angle exhibits a periodic, reciprocating change; When the roll angle changes periodically, the target drone is determined to be in a swaying state, and the attitude correction module is triggered to generate the corresponding correction compensation amount. When the roll angle does not change periodically, the target drone is determined to be in a state of instantaneous disturbance, and the sway state parameters are continuously acquired for reassessment.

[0034] Understandably, by further determining whether the roll angle exhibits periodic reciprocating changes after identifying the target drone as being in an unstable flight state, a more refined distinction can be made between the target drone's current abnormal roll state and the state of actual swaying and instantaneous airflow disturbance. When the roll angle exhibits periodic reciprocating changes, it indicates that the target drone has formed a continuous lateral oscillation trend. At this time, the attitude correction module is triggered to generate a corresponding correction compensation amount, which can suppress the swaying trend in a timely manner and prevent the swaying amplitude from continuously increasing and causing flight attitude instability. When the roll angle does not exhibit periodic reciprocating changes, it is determined that the target drone is only affected by short-term environmental disturbances, and the swaying state parameters are continuously acquired for re-evaluation. This avoids the system from mistakenly triggering compensation control for instantaneous disturbances, reduces the mechanical oscillation problem caused by frequent control surface adjustments, and improves the stability and anti-interference capability of flight attitude control.

[0035] Specifically, after detecting that the roll change exceeds the preset sway threshold, the system further analyzes the roll angle change trend over multiple consecutive sampling periods. When the roll angle exhibits a repetitive "left-right-left" pattern over multiple sampling periods, it can be determined that the roll angle is undergoing periodic reciprocating changes, thus indicating that the target aircraft is in a swaying state. The system then triggers the attitude correction module to generate a corresponding correction compensation amount to control the control surfaces to deflect in the opposite direction of the roll offset, thereby reducing the sway amplitude. Conversely, when the roll angle suddenly increases only within a single sampling period and then quickly returns to a stable range, the system determines that the target aircraft is in a state of transient disturbance, such as being affected by local turbulence or short-term crosswinds. In this case, the system does not immediately initiate compensation control but continuously acquires subsequent sway state parameters for reassessment, thereby reducing the probability of misjudgment and improving the stable operation capability of the flight control system.

[0036] In some specific embodiments of this application, the attitude correction module is used to generate a corresponding correction compensation amount based on the roll angle and the roll change amplitude when it is determined that the target drone is in a swaying state, including: The correction compensation direction is determined based on the current offset direction of the roll angle, so that the compensation direction is opposite to the roll offset direction; The basic compensation amplitude is determined based on the magnitude of the roll change, and the roll change amplitude is directly proportional to the basic compensation amplitude. The correction compensation amount is obtained by combining the correction compensation direction with the basic compensation amplitude.

[0037] Understandably, by determining the correction compensation direction based on the current roll angle offset direction and making the compensation direction opposite to the roll offset direction, the target drone can quickly obtain a reverse correction force when lateral swaying occurs, thereby reducing the roll offset trend. By determining the base compensation amplitude based on the magnitude of the roll change and making the roll change amplitude proportional to the base compensation amplitude, the compensation intensity can be dynamically adjusted according to the current sway intensity. This ensures that the greater the sway amplitude, the higher the corresponding compensation intensity, thus avoiding the problem of insufficient or excessive compensation in fixed compensation methods under different sway states. Furthermore, by combining the correction compensation direction with the base compensation amplitude to generate the correction compensation amount, synchronous dynamic adjustment of the compensation direction and compensation intensity can be achieved, improving the target drone's flight attitude control accuracy and roll sway suppression effect, and enhancing flight stability and anti-disturbance capability in complex airflow environments.

[0038] In one specific embodiment, when the system detects that the target drone's roll angle has shifted 6° to the left and the roll change amplitude is 8°, the attitude correction module first determines that the current roll offset direction is to the left, and therefore sets the correction compensation direction to the right. Subsequently, it generates a corresponding basic compensation amplitude based on the roll change amplitude of 8°, for example, generating a compensation amplitude level of "high compensation level". Then, it combines the right compensation direction with the high compensation level to generate a correction compensation amount, and controls the flight control module to adjust the corresponding control surfaces to deflect to the right to reduce the target drone's roll angle offset. When the roll change amplitude is small, a lower compensation amplitude is generated accordingly, thereby avoiding excessive control surface deflection that could lead to new flight oscillation problems and improving the stability of attitude compensation control.

[0039] In some specific embodiments of this application, the current environmental parameters include: Wind speed, airflow fluctuation amplitude, and intensity of air disturbance.

[0040] In some specific embodiments of this application, the compensation adjustment module is used to compare the environmental parameters with historical data, and when setting the adjustment coefficient based on the comparison result, it includes: The current environmental disturbance level is determined based on the wind speed, airflow fluctuation amplitude, and air disturbance intensity; wherein, the current environmental disturbance level includes the current wind speed level, the current airflow fluctuation level, and the current air disturbance level; The current wind speed level is determined by comparing the wind speed with a preset wind speed range; the current wind speed levels are ranked from low to high as level one, level two, and level three. The current airflow fluctuation level is determined by comparing the airflow fluctuation amplitude with a preset fluctuation range; wherein the current airflow fluctuation level is successively level one, level two, and level three. The current air disturbance level is determined by comparing the air disturbance intensity with a preset intensity range; wherein the current air disturbance level is successively level one, level two, and level three. The current environmental disturbance level is compared with historical data, and an adjustment coefficient is set based on the comparison results.

[0041] Understandably, by setting the current environmental parameters to wind speed, airflow fluctuation amplitude, and air disturbance intensity, and determining the current environmental disturbance level based on the corresponding parameters, the system can conduct a multi-dimensional comprehensive assessment of the external flight environment, thereby more accurately identifying the degree of influence of the current environment on the target drone's flight attitude.

[0042] Meanwhile, by determining the current wind speed level, current airflow fluctuation level, and current air disturbance level, and further comparing the current environmental disturbance level with historical data, the system can also dynamically set adjustment coefficients using the corresponding compensation control experience under historical conditions. This allows the system to adaptively adjust the attitude compensation intensity according to different environmental conditions, avoiding the problem of insufficient or excessive compensation in complex environments under fixed compensation modes.

[0043] Furthermore, by classifying environmental levels, the standardization of environmental disturbance identification can be improved, enabling the flight control module to quickly increase attitude compensation intensity in high-disturbance environments and appropriately reduce compensation amplitude in low-disturbance environments. This improves the flight stability, anti-disturbance capability, and attitude control accuracy of medium and large target drones in complex airflow environments.

[0044] Preferably, the air disturbance intensity can be determined based on the wind speed change per unit time; with 1 second as the statistical period, when the wind speed change is less than 2 m / s, the air disturbance intensity is determined to be level one; when the wind speed change is between 2 m / s and 5 m / s, the air disturbance intensity is determined to be level two; and when the wind speed change is greater than 5 m / s, the air disturbance intensity is determined to be level three.

[0045] In one specific embodiment, when the system detects a current wind speed of 12 m / s, an airflow fluctuation amplitude of 7°, and a wind speed change of 6 m / s (air disturbance intensity), the current wind speed level, the current airflow fluctuation level, and the current air disturbance level can be determined as level three, respectively. Subsequently, the system compares the current environmental disturbance level with historical data. If there is a historical adjustment coefficient for the same environmental level in the historical data, the corresponding historical adjustment coefficient is directly called to correct the compensation amount, thereby improving the compensation control capability under high disturbance environment. When the environmental level is low, a lower adjustment coefficient is used to reduce the mechanical oscillation problem caused by frequent control surface adjustments and improve flight control stability.

[0046] Specifically, the preset wind speed range, preset fluctuation range, and preset intensity range can be set according to the target drone model, airframe size, flight altitude, and flight mission. For example, the preset wind speed range can be divided into Level 1 wind speed (0–5 m / s), Level 2 wind speed (5–10 m / s), and Level 3 wind speed (greater than 10 m / s); the preset fluctuation range can be divided into Level 1 airflow fluctuation (0°–3°), Level 2 airflow fluctuation (3°–6°), and Level 3 airflow fluctuation (greater than 6°); the preset intensity range can be divided into three levels of air disturbance: Level 1 disturbance, Level 2 disturbance, and Level 3 disturbance. Furthermore, the corresponding ranges can be dynamically adjusted according to the flight speed; for example, the threshold values ​​for each level can be appropriately lowered during high-speed flight to improve the sensitivity of environmental disturbance identification.

[0047] In some specific embodiments of this application, when comparing the current environmental disturbance level with historical data and setting the adjustment coefficient based on the comparison result, the method further includes: Filter historical data that is the same as the current environmental disturbance level from the historical data; and obtain the historical adjustment coefficient from the same historical data, and use the historical adjustment coefficient as the adjustment coefficient; If there is no historical data in the historical data that is the same as the current environmental disturbance level, then the similarity between the wind speed, airflow fluctuation amplitude, and air disturbance intensity and the historical wind speed, historical airflow fluctuation amplitude, and historical air disturbance intensity in the historical data is calculated, the similarity is sorted in descending order, and the maximum similarity value is extracted; the historical adjustment coefficient corresponding to the maximum similarity value is used as the adjustment coefficient.

[0048] Understandably, by filtering historical data with the same disturbance level as the current environment and directly obtaining the corresponding historical adjustment coefficients as the current adjustment coefficients, the system can prioritize calling verified and effective historical compensation control parameters, thereby improving the response speed and stability of attitude compensation control. When no data with the exact same disturbance level as the current environment exists in the historical data, further calculation of the similarity between the current wind speed, airflow fluctuation amplitude, and air disturbance intensity and historical environmental parameters, and extraction of the historical adjustment coefficient corresponding to the maximum similarity value as the current adjustment coefficient, enables the system to quickly obtain relatively reasonable compensation parameters based on similar environmental conditions even in the absence of perfectly matching environmental data, thereby improving the environmental adaptability in complex environments. In addition, the similarity matching method can also avoid the problem of re-tuning a large number of parameters every time a new environment appears, improving the flight control system's adaptability to unknown disturbance environments and the reliability of attitude control.

[0049] In one specific embodiment, when the system detects a current wind speed of 9 m / s, an airflow fluctuation amplitude of 5°, and a wind speed change of 6 m / s (air disturbance intensity), the system first searches the historical database for historical data corresponding to the environmental disturbance level. If historical data for "wind speed level 2, airflow fluctuation level 2, and air disturbance level 2" exists in the historical database, the corresponding historical adjustment coefficient is directly extracted as the current adjustment coefficient. When no identical combination of environmental levels exists in the database, the system further calculates the difference between the current wind speed and the historical wind speed, the difference between the current airflow fluctuation amplitude and the historical airflow fluctuation amplitude, and the difference between the current air disturbance intensity and the historical air disturbance intensity, and then calculates the comprehensive difference. The similarity of environmental parameters is determined. For example, when a set of historical data corresponds to a wind speed of 8 m / s, an airflow fluctuation amplitude of 4.5°, and a wind speed change of 6 m / s (air disturbance intensity), the similarity is calculated using the Euclidean distance formula. Since this set of historical data has the highest similarity to the current environmental parameters, it is determined that this set of historical data is closest to the current environmental parameters, and the historical adjustment coefficient corresponding to this set of historical data is extracted as the current adjustment coefficient. Then, the compensation adjustment module uses the adjustment coefficient to correct the current correction compensation amount, generate the attitude compensation amount, and output it to the flight control module to control the corresponding control surfaces to perform attitude correction, thereby improving the attitude stability control capability of the target drone in the current complex disturbance environment.

[0050] In some specific embodiments of this application, the compensation adjustment module is used to correct the correction compensation amount to obtain the attitude compensation amount, including: The attitude compensation amount includes the compensation direction and the compensation value; wherein... The compensation direction in the attitude compensation amount is the same as the correction compensation direction; The compensation value in the attitude compensation amount is the product of the basic compensation amplitude and the adjustment coefficient.

[0051] Understandably, by setting the attitude compensation amount to include both the compensation direction and the compensation value, and ensuring that the compensation direction in the attitude compensation amount is the same as the correction compensation direction, it is possible to guarantee that the compensation control always proceeds in the opposite direction of the roll offset, thereby improving the directional accuracy of the target drone's sway correction. By setting the compensation value in the attitude compensation amount to the product of the basic compensation amplitude and the adjustment coefficient, the compensation intensity can be dynamically adjusted based on the current environmental disturbance conditions on the basis of the original sway compensation. This allows the system to not only determine the basic compensation intensity based on the roll change amplitude, but also to further amplify or reduce the compensation amplitude according to the level of environmental disturbance, thereby avoiding the problems of insufficient compensation in strong disturbance environments or excessive compensation in low disturbance environments. In addition, by generating the final compensation value using the method of "basic compensation amplitude × adjustment coefficient", the flexibility and environmental adaptability of the compensation control can be improved, enabling medium and large target drones to maintain good flight attitude stability and anti-disturbance capability under different flight environments.

[0052] In one specific embodiment, when the system detects that the target drone's roll angle has shifted to the left and the basic compensation amplitude corresponding to the roll change is 4, the attitude correction module first determines the correction compensation direction to the right. Subsequently, the compensation adjustment module obtains the corresponding adjustment coefficient of 1.5 based on the comparison results of the current environmental parameters and historical data. Then, the basic compensation amplitude of 4 is multiplied by the adjustment coefficient of 1.5 to obtain a compensation value of 6, and the right compensation direction is combined with the compensation value of 6 to generate the attitude compensation amount. Finally, the flight control module controls the corresponding control surface to deflect to the right according to the attitude compensation amount to improve the roll suppression capability in complex airflow environments. When the environmental disturbance is small, the adjustment coefficient can be reduced accordingly, thereby reducing the compensation value and avoiding excessive control surface deflection that could lead to new flight oscillation problems.

[0053] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program goods. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program goods embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0054] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program goods according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0055] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0056] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0057] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. An autonomous attitude control system for medium-to-large target drones used in intelligent unmanned aerial vehicles, characterized in that, include: The parameter acquisition module is used to acquire real-time attitude data of the target drone during flight and extract yaw state parameters from the real-time attitude data; wherein, the yaw state parameters include roll angle and roll change amplitude. The swaying judgment module is used to determine whether the target machine is in a swaying state based on the swaying state parameters. The attitude correction module is used to generate corresponding correction compensation based on the roll angle and the roll change amplitude when the target drone is determined to be in a swaying state. The compensation adjustment module is used to acquire the current environmental parameters, compare the environmental parameters with historical data, set adjustment coefficients according to the comparison results, and correct the correction compensation amount to obtain the attitude compensation amount. The flight control module is used to adjust the deflection angle of the target drone's control surfaces according to the attitude compensation amount, thereby controlling the target drone's flight attitude.

2. The attitude autonomous control system for medium and large target drones used in intelligent unmanned aerial vehicles according to claim 1, characterized in that, The autonomous attitude control system for medium and large target drones used in intelligent unmanned aerial vehicles also includes: The target drone status assessment module is used to extract pitch and yaw angles from real-time attitude data, and to assess the target drone's flight direction deviation based on the pitch and yaw angles; wherein, The pitch angle is compared with a preset longitudinal angle range. If the pitch angle is within the preset longitudinal angle range, the target drone is in a longitudinally stable state; if the pitch angle exceeds the preset longitudinal angle range, the target drone is determined to be in a longitudinally offset state. The yaw angle is compared with the preset lateral angle range. If the yaw angle is within the preset lateral angle range, the target drone is determined to be in a laterally stable state. If the yaw angle exceeds the preset lateral angle range, the target drone is determined to be in a laterally deflected state. If the target drone is in a stable longitudinal and lateral state, it is determined that the target drone's flight direction has not deviated; otherwise, it is determined that the target drone's flight direction has deviated.

3. The attitude autonomous control system for medium and large target drones used in intelligent unmanned aerial vehicles according to claim 2, characterized in that, The process of evaluating the target drone's flight direction deviation based on the pitch and yaw angles includes: If the target drone's flight direction deviates, a direction correction control quantity is generated based on the pitch angle offset and yaw angle offset, and the flight control module is controlled to adjust the deflection direction and angle of the corresponding control surfaces to correct the target drone's flight direction so that the target drone's direction is corrected. If the target drone's flight direction does not deviate, or the target drone's direction returns to normal, the sway detection module determines whether the target drone is in a swaying state.

4. The attitude autonomous control system for medium and large target drones for intelligent unmanned aerial vehicles according to claim 1, characterized in that, The swing determination module is used to determine whether the target machine is in a swinging state based on the swing state parameters, including: Acquire the roll angle change data within a preset time period, and calculate the roll change amplitude based on the change data; The roll change amplitude is compared with a preset sway threshold. If the roll change amplitude is less than or equal to the preset sway threshold, the target drone is determined to be in a stable flight state. If the roll change amplitude is greater than the preset sway threshold, the target drone is determined to be in an unstable flight state.

5. The attitude autonomous control system for medium and large target drones used in intelligent unmanned aerial vehicles according to claim 4, characterized in that, The determination that the target drone is in an unstable flight state includes: Determine whether the roll angle exhibits a periodic, reciprocating change; When the roll angle changes periodically, the target drone is determined to be in a swaying state, and the attitude correction module is triggered to generate the corresponding correction compensation amount. When the roll angle does not change periodically, the target drone is determined to be in a state of instantaneous disturbance, and the sway state parameters are continuously acquired for reassessment.

6. The attitude autonomous control system for medium and large target drones for intelligent unmanned aerial vehicles according to claim 5, characterized in that, The attitude correction module is used to generate a corresponding correction compensation amount based on the roll angle and the roll change amplitude when it is determined that the target drone is in a swaying state, including: The correction compensation direction is determined based on the current offset direction of the roll angle, so that the compensation direction is opposite to the roll offset direction; The basic compensation amplitude is determined based on the magnitude of the roll change, and the roll change amplitude is directly proportional to the basic compensation amplitude. The correction compensation amount is obtained by combining the correction compensation direction with the basic compensation amplitude.

7. The attitude autonomous control system for medium and large target drones for intelligent unmanned aerial vehicles according to claim 6, characterized in that, The current environment parameters include: Wind speed, airflow fluctuation amplitude, and intensity of air disturbance.

8. The attitude autonomous control system for medium and large target drones for intelligent unmanned aerial vehicles according to claim 7, characterized in that, The compensation adjustment module is used to compare the environmental parameters with historical data, and when setting the adjustment coefficient based on the comparison results, it includes: The current environmental disturbance level is determined based on the wind speed, airflow fluctuation amplitude, and air disturbance intensity; wherein, the current environmental disturbance level includes the current wind speed level, the current airflow fluctuation level, and the current air disturbance level; The current wind speed level is determined by comparing the wind speed with a preset wind speed range; the current wind speed levels are ranked from low to high as level one, level two, and level three. The current airflow fluctuation level is determined by comparing the airflow fluctuation amplitude with a preset fluctuation range; wherein the current airflow fluctuation level is successively level one, level two, and level three. The current air disturbance level is determined by comparing the air disturbance intensity with a preset intensity range; wherein the current air disturbance level is successively level one, level two, and level three. The current environmental disturbance level is compared with historical data, and an adjustment coefficient is set based on the comparison results.

9. The attitude autonomous control system for medium and large target drones used in intelligent unmanned aerial vehicles according to claim 8, characterized in that, When comparing the current environmental disturbance level with historical data and setting adjustment coefficients based on the comparison results, the method further includes: Filter historical data that is the same as the current environmental disturbance level from the historical data; and obtain the historical adjustment coefficient from the same historical data, and use the historical adjustment coefficient as the adjustment coefficient; If there is no historical data in the historical data that is the same as the current environmental disturbance level, then the similarity between the wind speed, airflow fluctuation amplitude, and air disturbance intensity and the historical wind speed, historical airflow fluctuation amplitude, and historical air disturbance intensity in the historical data is calculated, the similarity is sorted in descending order, and the maximum similarity value is extracted; the historical adjustment coefficient corresponding to the maximum similarity value is used as the adjustment coefficient.

10. The attitude autonomous control system for medium and large target drones for intelligent unmanned aerial vehicles according to claim 9, characterized in that, The compensation adjustment module is used to correct the calibration compensation amount to obtain the attitude compensation amount, including: The attitude compensation amount includes the compensation direction and the compensation value; wherein... The compensation direction in the attitude compensation amount is the same as the correction compensation direction; The compensation value in the attitude compensation amount is the product of the basic compensation amplitude and the adjustment coefficient.

Images