Unmanned aerial vehicle control method and system based on artificial intelligence

Abstract

The invention provides an artificial intelligence-based unmanned aerial vehicle control method and system, and the method comprises the steps: carrying out the detection of a trajectory conflict between a formation path and each flight state based on an obstacle avoidance decision mechanism, and obtaining a conflict relation between an unmanned aerial vehicle cluster and a target unmanned aerial vehicle; determining the cooperative stability between the target unmanned aerial vehicle and the unmanned aerial vehicle cluster according to the conflict relationship and the position information of the target unmanned aerial vehicle; determining an aerodynamic disturbing flow when the target unmanned aerial vehicle joins the unmanned aerial vehicle cluster according to the cooperative stability and the dynamic motion characteristics of the unmanned aerial vehicles in the unmanned aerial vehicle cluster, and determining an aerodynamic stability coefficient of the target unmanned aerial vehicle according to the aerodynamic disturbing flow and the cooperative behavior characteristics of the target unmanned aerial vehicle in the unmanned aerial vehicle cluster; and when the pneumatic stability coefficient is lower than a preset stability threshold value, performing obstacle avoidance adjustment on a subsequent formation path of the target unmanned aerial vehicle. Based on the scheme, cooperative stability adjustment of the unmanned aerial vehicles switching into the unmanned aerial vehicle cluster can be realized, so that the flight stability of the unmanned aerial vehicle cluster formation can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of drone path control, and more specifically, to an artificial intelligence-based drone control method and system. Background Art

[0002] With the advancement of UAV automatic control, UAV automatic control started from the initial remote control flight. With the advancement of science and technology, especially the development of computer technology, sensor technology and artificial intelligence, UAVs have gradually achieved a higher level of automation. With the advancement of algorithms, UAVs have begun to adopt autonomous navigation and obstacle avoidance technology, and can independently perform tasks in complex environments. In particular, positioning technology based on GPS and visual sensors makes precise positioning and autonomous flight of UAVs possible. In recent years, with the application of deep learning and multi-sensor fusion technology, the adaptive control capability of UAVs in dynamic environments has been significantly improved, and they can better cope with challenges in flight.

[0003] When a drone joins a cluster, it needs to accurately adjust its position and speed to fit into the cluster formation. However, any small positioning error or path deviation, especially in complex environments, may lead to collisions with other drones or cluster instability. Environmental factors such as airflow changes and wind speed fluctuations may also affect flight stability, making it difficult for the target drone to adapt to the cluster flight mode. In addition, the flight speed, direction and other parameters between the target drone and cluster members may conflict and cause disturbances, thereby increasing the difficulty of the drone's collaborative entry into the drone cluster. Therefore, how to achieve collaborative stability adjustment for drones entering drone clusters, thereby improving the flight stability of drone cluster formations, is a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides an artificial intelligence-based drone control method and system, which can realize the coordinated stability adjustment of a drone entering a drone cluster, thereby improving the flight stability of the drone cluster formation.

[0005] In a first aspect, the present application provides a drone control method based on artificial intelligence, comprising: When the target UAV joins the UAV cluster for formation flight, the flight status of each UAV in the UAV cluster is monitored, and the formation path for the target UAV to join the UAV cluster is determined; Based on the obstacle avoidance decision mechanism, the trajectory conflict between the formation path and each flight state is detected to obtain the conflict relationship between the UAV cluster and the target UAV, and the coordination stability between the target UAV and the UAV cluster is determined according to the conflict relationship and the position information of the target UAV; Determine the aerodynamic interference flow of the target UAV when it joins the UAV cluster according to the cooperative stability and the dynamic motion characteristics of the UAVs in the UAV cluster, and then determine the aerodynamic stability coefficient of the target UAV through the aerodynamic interference flow and the cooperative behavior characteristics of the target UAV in the UAV cluster; When the aerodynamic stability coefficient is lower than a preset stability threshold, an obstacle avoidance adjustment is performed on a subsequent formation path of the target UAV.

[0006] In some embodiments, based on the obstacle avoidance decision mechanism, detecting the trajectory conflict between the formation path and each flight state, and obtaining the conflict relationship between the drone cluster and the target drone specifically includes: Determine all entry conflict points between the drone cluster and the target drone according to the formation path and each flight state; Performing conflict detection on each entry conflict point based on the obstacle avoidance decision mechanism to obtain the obstacle conflict value of each entry conflict point; The conflict relationship between the UAV cluster and the target UAV is determined through all obstacle conflict values.

[0007] In some embodiments, determining the cooperative stability between the target drone and the drone cluster according to the conflict relationship and the position information of the target drone specifically includes: Obtain the location information of the target drone and the distribution information of drones in the drone cluster; Determine the conflict influencing factor between the target UAV and the UAV cluster according to the conflict relationship; The response conflict of the drone cluster to the cut-in operation of the target drone is determined by the location information of the target drone and the distribution information of the drones in the drone cluster; The coordination stability between the target UAV and the UAV cluster is determined according to the conflict influencing factor and the response conflict.

[0008] In some embodiments, determining the aerodynamic interference flow of the target drone when joining the drone cluster according to the cooperative stability and the dynamic motion characteristics of the drones in the drone cluster specifically includes: Obtain the dynamic motion characteristics of drones in a drone cluster; Determine the airflow internal disturbance domain of the drone cluster according to the dynamic motion characteristics of the drones in the drone cluster; Based on the airflow internal disturbance domain and the collaborative stability, the aerodynamics of the target UAV when joining the UAV cluster is simulated to obtain the aerodynamic interference flow of the target UAV when joining the UAV cluster.

[0009] In some embodiments, determining the aerodynamic stability coefficient of the target UAV by using the aerodynamic interference flow and the cooperative behavior characteristics of the target UAV in the UAV cluster specifically includes: Obtain the coordinated behavior characteristics of the target UAV in the UAV swarm and the flight strategy of the UAV swarm; Predict the formation flight trajectory of target UAVs based on their collaborative behavior characteristics in the UAV swarm and the flight strategy of the UAV swarm; Determining the aerodynamic stability value of each control surface in the target UAV according to the formation flight trajectory and the aerodynamic interference flow; The aerodynamic stability coefficient of the target UAV is determined based on all aerodynamic stability values.

[0010] In some embodiments, determining the aerodynamic stability value of each control surface in the target UAV according to the formation flight trajectory and the aerodynamic interference flow specifically includes: Determine the aerodynamic torque coefficient of the target UAV through the aerodynamic interference flow; For each control surface in the target UAV, determining a force sequence of the control surface according to the formation flight trajectory; The aerodynamic stability value of the control surface is determined by the force sequence and the aerodynamic moment coefficient, and then the aerodynamic stability value of each control surface in the target UAV is obtained.

[0011] In some embodiments, obstacle avoidance adjustment of the subsequent formation path of the target UAV is performed by adjusting the speed and angle of the subsequent formation path of the target UAV based on a trajectory optimization mechanism of disturbance feedback.

[0012] In a second aspect, the present application provides an artificial intelligence-based drone control system, comprising: A monitoring module is used to monitor the flight status of each drone in the drone cluster when the target drone joins the drone cluster for formation flight, and determine the formation path for the target drone to join the drone cluster; A processing module is used to detect the trajectory conflict between the formation path and each flight state based on the obstacle avoidance decision mechanism, obtain the conflict relationship between the UAV cluster and the target UAV, and determine the coordination stability between the target UAV and the UAV cluster according to the conflict relationship and the position information of the target UAV; The processing module is also used to determine the aerodynamic interference flow of the target UAV when it joins the UAV cluster according to the cooperative stability and the dynamic motion characteristics of the UAVs in the UAV cluster, and then determine the aerodynamic stability coefficient of the target UAV through the aerodynamic interference flow and the cooperative behavior characteristics of the target UAV in the UAV cluster; The execution module is used to adjust the subsequent formation path of the target UAV to avoid obstacles when the aerodynamic stability coefficient is lower than a preset stability threshold.

[0013] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned artificial intelligence-based drone control method.

[0014] In a fourth aspect, the present application provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned artificial intelligence-based drone control method when executed.

[0015] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects: The present application provides an artificial intelligence-based drone control method and system. When a target drone joins a drone cluster for formation flight, the flight status of each drone in the drone cluster is monitored, and a formation path for the target drone to join the drone cluster is determined; based on an obstacle avoidance decision mechanism, the trajectory conflict between the formation path and each flight status is detected to obtain a conflict relationship between the drone cluster and the target drone, and the collaborative stability between the target drone and the drone cluster is determined based on the conflict relationship and the position information of the target drone; the aerodynamic interference flow of the target drone when joining the drone cluster is determined based on the collaborative stability and the dynamic motion characteristics of the drones in the drone cluster, and then the aerodynamic stability coefficient of the target drone is determined through the aerodynamic interference flow and the collaborative behavior characteristics of the target drone in the drone cluster; when the aerodynamic stability coefficient is lower than a preset stability threshold, obstacle avoidance adjustment is performed on the subsequent formation path of the target drone.

[0016] It can be seen that in the present application, when the aerodynamic stability coefficient is lower than the preset stability threshold, the subsequent formation path of the target UAV is adjusted to avoid obstacles; first, the collaborative stability is determined to obtain a quantitative indicator reflecting the safety and stability of the cut-in operation, thereby effectively identifying the potential stability problems of the target UAV when interacting with the UAVs in the cluster. By accurately calculating the collaborative stability, the parameters that may interfere with the flight trajectory of the target UAV can be identified, which can provide data support for subsequent stability adjustments, so that the UAV's flight control system can predict and quickly adjust the position and speed of the target UAV, prevent cluster instability caused by small errors or conflicts, and improve the collaborative stability of the UAV cluster flight, thereby improving the overall stability of the UAV cluster formation flight; then, determine By determining the aerodynamic stability coefficient, the UAV's ability to maintain attitude and trajectory stability through control surface torque balance can be obtained, which is helpful to optimize the motion parameters of the target UAV in the process of joining the cluster, so that it can smoothly integrate into the cluster formation and avoid flight instability or collision caused by aerodynamic instability. Especially under complex environmental conditions, the aerodynamic stability coefficient of the target UAV can be dynamically adjusted considering the collaborative behavior characteristics, which can further optimize the stability of the formation flight, thereby ensuring that the target UAV can not only effectively avoid potential interference in the cluster, but also maintain stable operation in complex environments, thereby improving the overall flight stability of the UAV cluster formation; in summary, based on the above scheme, the collaborative stability adjustment of the UAV entering the UAV cluster can be realized, thereby improving the flight stability of the UAV cluster formation. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0018] Figure 1 is an exemplary flow chart of an artificial intelligence-based drone control method according to some embodiments of the present application; Figure 2 is a line drawing of a quadrotor drone shown in some embodiments of the present application; Figure 3 is a schematic diagram of a process for determining an aerodynamic stability coefficient according to some embodiments of the present application; Figure 4 is a schematic diagram of the structure of an artificial intelligence-based drone control system according to some embodiments of the present application; Figure 5It is a structural schematic diagram of a computer device for implementing an artificial intelligence-based drone control method according to some embodiments of the present application. DETAILED DESCRIPTION

[0019] In order to better understand the technical solution of the present application, the technical solution of the present application will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0020] refer to Figure 1 , which is an exemplary flow chart of an artificial intelligence-based drone control method according to some embodiments of the present application. The artificial intelligence-based drone control method mainly includes the following steps: In step 101, when the target drone joins the drone cluster for formation flight, the flight status of each drone in the drone cluster is monitored, and a formation path for the target drone to join the drone cluster is determined.

[0021] It should be noted that in this application, the flight state refers to the dynamic parameters of the UAV in the air, including speed, heading angle, pitch angle and altitude; the formation path refers to the complete path of the target UAV from entering to stably joining the cluster.

[0022] In specific implementation, the flight status of each drone in the human-machine cluster can be monitored through drone-mounted sensors (such as IMU, GPS), and the flight path of the target drone when it joins the cluster can be captured. The flight path includes position information, speed and trajectory curve, and the flight path is used as the formation path for the target drone to join the drone cluster.

[0023] In some embodiments, reference Figure 2 As described, the figure is a line drawing of a four-rotor drone shown in some embodiments of the present application. The main body of the drone in the figure is composed of four main parts: a central fuselage, four rotors, four motors and possible sensors or camera modules. The central fuselage is rectangular and may be made of lightweight materials to reduce weight and improve flight efficiency. A rotor is connected to each of the four corners of the fuselage. These rotors are driven by motors to provide lift and thrust for the drone. Each rotor is directly driven by a motor, which is connected to the rotor shaft through a reduction gear to ensure that the rotor rotates at an appropriate speed. The rotor is streamlined in design, which helps to reduce air resistance and improve flight stability.

[0024] At the bottom of the drone is a support structure for stable flight or ground operations. The support structure contains a landing device and sensors. The landing device includes shock absorbers and wheels to facilitate safe landing on various terrains. The sensors include a GPS module, a barometer and a visual system. The sensors are used to navigate, locate and avoid obstacles for the drone. The front of the drone is equipped with a camera or other types of sensors for capturing images or videos, which is very useful in aerial photography, monitoring or search and rescue missions. The overall design emphasizes the versatility and adaptability of the drone, enabling it to play a role in a variety of application scenarios.

[0025] In step 102, based on the obstacle avoidance decision mechanism, the trajectory conflict between the formation path and each flight state is detected to obtain the conflict relationship between the UAV cluster and the target UAV, and the collaborative stability between the target UAV and the UAV cluster is determined according to the conflict relationship and the position information of the target UAV.

[0026] In some embodiments, based on the obstacle avoidance decision mechanism, the trajectory conflict between the formation path and each flight state is detected, and the conflict relationship between the drone cluster and the target drone is obtained, which can be achieved by the following steps: Determine all entry conflict points between the drone cluster and the target drone according to the formation path and each flight state; Performing conflict detection on each entry conflict point based on the obstacle avoidance decision mechanism to obtain the obstacle conflict value of each entry conflict point; The conflict relationship between the UAV cluster and the target UAV is determined through all obstacle conflict values.

[0027] It should be noted that in this application, the conflict relationship represents the distribution of conflict points and their threat level between the target UAV and the UAV cluster during the entry process; the obstacle avoidance decision mechanism refers to a strategy to avoid conflicts by planning the UAV trajectory through an algorithm; the entry conflict point refers to the key point where the target UAV and the UAV cluster may have a path conflict; the obstacle conflict value is a quantitative indicator to measure the threat level of obstacles at the entry conflict point.

[0028] In the specific implementation, first, the formation path and each flight state can be used to geometrically model the drone cluster and the target drone. The possible intersection points of the formation path and the flight trajectory of the drones in the drone cluster are marked as entry conflict points through the existing motion equations, and all the entry conflict points between the drone cluster and the target drone can be obtained; then, for each entry conflict point, the relative distance, relative speed and direction of the entry conflict point are quantified based on the obstacle avoidance decision mechanism to determine the severity of the conflict. The quantification result can be used as the obstacle conflict value of the entry conflict point. The obstacle conflict value of each entry conflict point can be obtained in the above manner; finally, the set of all obstacle conflict values ​​can be used as the conflict relationship between the drone cluster and the target drone.

[0029] In some embodiments, determining the coordination stability between the target drone and the drone cluster according to the conflict relationship and the position information of the target drone can be achieved by using the following steps: Obtain the location information of the target drone and the distribution information of drones in the drone cluster; Determine the conflict influencing factor between the target UAV and the UAV cluster according to the conflict relationship; The response conflict of the drone cluster to the cut-in operation of the target drone is determined by the location information of the target drone and the distribution information of the drones in the drone cluster; The coordination stability between the target UAV and the UAV cluster is determined according to the conflict influencing factor and the response conflict.

[0030] It should be noted that in the present application, collaborative stability is a quantitative indicator reflecting the collaborative stability of the UAV's entry operation; UAV distribution information refers to the collection of spatial positions and dynamic states of all UAVs in the UAV cluster; the conflict impact factor is a quantitative indicator reflecting the severity of the conflict between UAVs; and the response conflict refers to the dynamic environmental changes caused to the target UAV by the cluster UAV during the entry process.

[0031] In specific implementation, first, the position coordinates of the target UAV can be obtained in real time through the positioning module of the target UAV, and the current position information and motion state of the UAVs in the UAV cluster are collected as the distribution information of the UAVs in the UAV cluster; secondly, the conflict critical value of the UAV when entering the cluster is preset through a large number of UAV cut-in simulation experiments combined with historical experience. For each cut-in conflict point, the absolute value of the difference between the obstacle conflict value and the conflict critical value of the cut-in conflict point in the conflict relationship is divided by the conflict critical value as the conflict impact value of the cut-in conflict point. The conflict impact value of each cut-in conflict point can be obtained by the above method, and the mean of all conflict impact values ​​can be used as the conflict impact factor between the target UAV and the UAV cluster; then, a kinematics-based response model is initialized, and the position information of the target UAV is used as the response evaluation position of the target UAV in the response model, and the distribution information of the UAVs in the UAV cluster is used as the external influencing factor of the target UAV in the response model. The response model is used to perform conflict evaluation on the cut-in operation of the UAV cluster on the target UAV, and the result of the response evaluation can be used as the response conflict of the UAV cluster to the cut-in operation of the target UAV; finally, the product of the response conflict and the conflict impact factor can be used as the cooperative stability between the target UAV and the UAV cluster.

[0032] In step 103, the aerodynamic interference flow of the target UAV when joining the UAV cluster is determined according to the collaborative stability and the dynamic motion characteristics of the UAVs in the UAV cluster, and then the aerodynamic stability coefficient of the target UAV is determined through the aerodynamic interference flow and the collaborative behavior characteristics of the target UAV in the UAV cluster.

[0033] In some embodiments, determining the aerodynamic interference flow of the target UAV when joining the UAV cluster according to the cooperative stability and the dynamic motion characteristics of the UAVs in the UAV cluster can be achieved by the following steps: Obtain the dynamic motion characteristics of drones in a drone cluster; Determine the airflow internal disturbance domain of the drone cluster according to the dynamic motion characteristics of the drones in the drone cluster; Based on the airflow internal disturbance domain and the collaborative stability, the aerodynamics of the target UAV when joining the UAV cluster is simulated to obtain the aerodynamic interference flow of the target UAV when joining the UAV cluster.

[0034] It should be noted that, in the present application, aerodynamic interference flow refers to the flow field changes of the target UAV caused by the interaction between the disturbance domain within the cluster airflow and its own aerodynamic characteristics; the disturbance domain within the airflow refers to the area where airflow disturbance is formed during the flight of the UAV cluster; the dynamic motion characteristics refer to the motion state parameters of the UAV during the flight, and the dynamic motion characteristics include speed, acceleration and heading.

[0035] In the specific implementation, first, the speed, acceleration and heading of each drone in the drone cluster are collected in real time through the monitoring module of each drone in the drone cluster, and the set of speed, acceleration and heading can be used as the dynamic motion characteristics of the drones in the drone cluster; then, the speed, acceleration and heading of each drone in the dynamic motion characteristics are constructed as a motion characteristic matrix of the drone cluster, and the differential wake of each drone and its corresponding airflow disturbance area during cluster flight are simulated based on fluid dynamics theory combined with the motion characteristic matrix, and the airflow disturbance area of ​​the wake of each drone is superimposed as the airflow internal disturbance domain of the drone cluster; finally, the known aerodynamic characteristics (lift coefficient, drag coefficient, torque coefficient) of the target drone can be used to construct an aerodynamic response model based on fluid dynamics, and the airflow internal disturbance domain is used as the environmental parameter in the aerodynamic response model, and the cooperative stability is used as the correlation parameter between drones in the aerodynamic response model. The aerodynamic response model is used to simulate the change of aerodynamic performance of the target drone when it joins the drone cluster, and the simulation result is used as the aerodynamic disturbance flow of the target drone when it joins the drone cluster.

[0036] In some embodiments, the aerodynamic stability coefficient of the target UAV is determined by the aerodynamic interference flow and the cooperative behavior characteristics of the target UAV in the UAV cluster, referring to Figure 3 As described above, the figure is a schematic diagram of a process for determining the aerodynamic stability coefficient in some embodiments of the present application. In this embodiment, the aerodynamic stability coefficient can be determined by the following steps: In step 1031, the cooperative behavior characteristics of the target UAV in the UAV cluster and the flight strategy of the UAV cluster are obtained; In step 1032, the formation flight trajectory of the target UAV is predicted based on the cooperative behavior characteristics of the target UAV in the UAV cluster and the flight strategy of the UAV cluster; In step 1033, the aerodynamic stability value of each control surface in the target UAV is determined according to the formation flight trajectory and the aerodynamic interference flow; In step 1034, the aerodynamic stability coefficient of the target UAV is determined based on all aerodynamic stability values.

[0037] It should be noted that, in the present application, the collaborative behavior characteristics are used to describe the characteristics of the coordinated action behavior between the target UAV and the UAVs in the UAV cluster; the flight strategy is the cluster flight rules and target path instructions set by the pilot UAV or the cluster command system; in the specific implementation of step 1031, the collaborative behavior characteristics of the target UAV in the UAV cluster and the flight strategy of the UAV cluster can be obtained in the following way, namely: the real-time position, speed, acceleration, direction and attitude of the target UAV are collected, and the set of real-time position, speed, acceleration, direction and attitude can be used as the collaborative behavior characteristics of the target UAV in the UAV cluster, and the flight strategy of the UAV cluster can be obtained in the central console of the pilot UAV in the UAV cluster.

[0038] In the specific implementation of step 1032, the formation flight trajectory of the target UAV is predicted based on the collaborative behavior characteristics of the target UAV in the UAV cluster and the flight strategy of the UAV cluster. This can be achieved in the following manner, namely: initialize a trajectory prediction model based on reinforcement learning, use the collaborative behavior characteristics of the target UAV in the UAV cluster as the behavior characteristics of the target UAV in the trajectory prediction model, use the flight strategy of the UAV cluster as the formation strategy of the target UAV in the trajectory prediction model, use the trajectory prediction model to predict the flight trajectory of the target UAV in the cluster formation, and the predicted flight trajectory can be used as the formation flight trajectory of the target UAV, wherein the formation flight trajectory refers to the dynamic path that the target UAV should follow in cluster flight, which is used to maintain a coordinated relationship and spatial interval with other UAVs in the UAV cluster.

[0039] Preferably, in some embodiments of step 1033, determining the aerodynamic stability value of each control surface in the target UAV according to the formation flight trajectory and the aerodynamic interference flow can be implemented by the following steps: Determine the aerodynamic torque coefficient of the target UAV through the aerodynamic interference flow; For each control surface in the target UAV, determining a force sequence of the control surface according to the formation flight trajectory; The aerodynamic stability value of the control surface is determined by the force sequence and the aerodynamic moment coefficient, and then the aerodynamic stability value of each control surface in the target UAV is obtained.

[0040] It should be noted that the aerodynamic stability value represents the torque balance of each control surface in the UAV in a complex aerodynamic environment. In specific implementation, first, the aerodynamic torque formula in the existing mathematical model can be used to calculate the aerodynamic torque coefficient of the aerodynamic interference flow on the target UAV. Then, for each control surface in the target UAV, the UAV flight simulation algorithm is used to simulate the force acting on the control surface at each trajectory change in the formation flight trajectory. The force includes lift, drag and deflection angle, and all forces are arranged in the time sequence of the formation flight trajectory as a force sequence of the control surface. Finally, the product of the standard deviation of the difference between adjacent forces in the force sequence and the aerodynamic torque coefficient can be used as the aerodynamic stability value of the control surface. The aerodynamic stability value of each control surface in the target UAV can be obtained in the above manner.

[0041] In the specific implementation of step 1034, the aerodynamic stability coefficient of the target UAV can be determined based on all the aerodynamic stability values ​​in the following manner, namely: the degree of influence of each control surface in the target UAV on the flight stability can be used as the weight of the corresponding aerodynamic stability value, and the weighted average of all aerodynamic stability values ​​is calculated as the aerodynamic stability coefficient of the target UAV. It should be noted that in the present application, the aerodynamic stability coefficient represents the ability of the UAV to maintain attitude and trajectory stability through control surface torque balance.

[0042] In step 104, when the aerodynamic stability coefficient is lower than a preset stability threshold, obstacle avoidance adjustment is performed on the subsequent formation path of the target UAV.

[0043] It should be noted that in this application, the stability threshold is a parameter for determining whether the UAV can maintain stability during flight. Specifically, the stability threshold refers to the critical value of the aerodynamic stability coefficient indicator. When the aerodynamic stability coefficient is lower than the threshold, it means that the UAV is facing the risk of instability and intervention is required to avoid unstable flight. The stability threshold can be preset based on historical experience and the stability performance of the UAV.

[0044] In some embodiments, obstacle avoidance adjustment of the subsequent formation path of the target UAV is based on a trajectory optimization mechanism of disturbance feedback to adjust the speed and angle of the subsequent formation path of the target UAV; in specific implementation, when the aerodynamic stability coefficient is lower than a preset stability threshold, the target UAV maintains the current formation path for flight, and when the aerodynamic stability coefficient is lower than the preset stability threshold, the trajectory optimization mechanism based on disturbance feedback adjusts the speed and angle of the subsequent formation path of the target UAV until the aerodynamic stability coefficient is greater than or equal to the preset stability threshold.

[0045] In the present application, when the aerodynamic stability coefficient is lower than a preset stability threshold, the subsequent formation path of the target UAV is adjusted to avoid obstacles; first, the collaborative stability is determined to obtain a quantitative indicator reflecting the safety and stability of the cut-in operation, thereby effectively identifying the potential stability problems of the target UAV when interacting with the UAVs in the cluster. By accurately calculating the collaborative stability, the parameters that may interfere with the flight trajectory of the target UAV can be identified, which can provide data support for subsequent stability adjustments, so that the UAV's flight control system can predict and quickly adjust the position and speed of the target UAV, prevent cluster instability caused by small errors or conflicts, and improve the collaborative stability of the UAV cluster flight, thereby improving the overall stability of the UAV cluster formation flight; then, the aerodynamic stability is determined. The dynamic stability coefficient can obtain the ability of the UAV to maintain attitude and trajectory stability through control surface torque balance, which is helpful to optimize the motion parameters of the target UAV in the process of joining the cluster, so that it can smoothly integrate into the cluster formation and avoid flight instability or collision caused by aerodynamic instability. Especially under complex environmental conditions, the aerodynamic stability coefficient of the target UAV can be dynamically adjusted considering the collaborative behavior characteristics, which can further optimize the stability of the formation flight, thereby ensuring that the target UAV can not only effectively avoid potential interference in the cluster, but also maintain stable operation in complex environments, thereby improving the overall flight stability of the UAV cluster formation; in summary, based on the above scheme, the collaborative stability adjustment of the UAV entering the UAV cluster can be realized, thereby improving the flight stability of the UAV cluster formation.

[0046] In addition, in another aspect of the present application, in some embodiments, the present application provides a drone control system based on artificial intelligence, referring to Figure 4 , which is a schematic diagram of the structure of an artificial intelligence-based drone control system according to some embodiments of the present application. The artificial intelligence-based drone control system includes: a monitoring module 201, a processing module 202 and an execution module 203, which are described as follows: Monitoring module 201: In the present application, monitoring module 201 is mainly used to monitor the flight status of each drone in the drone cluster when the target drone joins the drone cluster for formation flight, and determine the formation path for the target drone to join the drone cluster; Processing module 202, in the present application, is used to detect the trajectory conflict between the formation path and each flight state based on the obstacle avoidance decision mechanism, obtain the conflict relationship between the drone cluster and the target drone, and determine the collaborative stability between the target drone and the drone cluster according to the conflict relationship and the position information of the target drone; It should be noted that the processing module 202 is also used to determine the aerodynamic interference flow of the target UAV when joining the UAV cluster according to the cooperative stability and the dynamic motion characteristics of the UAVs in the UAV cluster, and then determine the aerodynamic stability coefficient of the target UAV through the aerodynamic interference flow and the cooperative behavior characteristics of the target UAV in the UAV cluster; Execution module 203, in the present application, execution module 203 is mainly used to perform obstacle avoidance adjustment on the subsequent formation path of the target UAV when the aerodynamic stability coefficient is lower than a preset stability threshold.

[0047] The above describes in detail the examples of the artificial intelligence-based drone control method and system provided in the embodiments of the present application. It can be understood that in order to realize the above functions, the corresponding device includes hardware structures and / or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0048] In some embodiments, the present application also provides a computer device, comprising a memory and a processor, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the above-mentioned artificial intelligence-based drone control method.

[0049] In some embodiments, reference Figure 5 , the dotted line in the figure indicates that the unit or the module is optional. The figure is a schematic diagram of the structure of a computer device for implementing an artificial intelligence-based drone control method according to an embodiment of the present application. The artificial intelligence-based drone control method described in the above embodiment can be implemented by Figure 5 The computer device shown in the figure is implemented, and the computer device includes at least one processor 301, a memory 302 and at least one communication unit 305. The computer device can be a terminal device, a server or a chip.

[0050] The processor 301 may be a general-purpose processor or a special-purpose processor. For example, the processor 301 may be a central processing unit (CPU), which may be used to control the computer device, execute software programs, and process data of the software programs. The computer device may also include a communication unit 305 to implement signal input (reception) and output (transmission).

[0051] For example, the computer device may be a chip, the communication unit 305 may be an input and / or output circuit of the chip, or the communication unit 305 may be a communication interface of the chip, and the chip may be a component of a terminal device, a network device, or other devices.

[0052] For another example, the computer device may be a terminal device or a server, and the communication unit 305 may be a transceiver of the terminal device or the server, or the communication unit 305 may be a transceiver circuit of the terminal device or the server.

[0053] The computer device may include one or more memories 302, on which a program 304 is stored. The program 304 can be executed by the processor 301 to generate instructions 303, so that the processor 301 performs the method described in the above method embodiment according to the instructions 303. Optionally, data (such as a target audit model) can also be stored in the memory 302. Optionally, the processor 301 can also read the data stored in the memory 302, and the data can be stored at the same storage address as the program 304, or the data can be stored at a different storage address from the program 304.

[0054] The processor 301 and the memory 302 may be provided separately or integrated together, for example, integrated on a system on chip (SOC) of the terminal device.

[0055] It should be understood that each step of the above method embodiment can be completed by a hardware-based logic circuit or software-based instructions in the processor 301. The processor 301 can be a CPU, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, such as discrete gates, transistor logic devices, or discrete hardware components.

[0056] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0057] For example, in some embodiments, the present application also provides a computer-readable storage medium, in which instructions or codes are stored. When the instructions or codes are run on a computer, the computer implements the above-mentioned artificial intelligence-based drone control method when executed.

[0058] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0059] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A drone control method based on artificial intelligence, characterized in that: The steps include: When the target UAV joins the UAV cluster for formation flight, the flight status of each UAV in the UAV cluster is monitored, and the formation path for the target UAV to join the UAV cluster is determined; Based on the obstacle avoidance decision mechanism, the trajectory conflict between the formation path and each flight state is detected to obtain the conflict relationship between the UAV cluster and the target UAV, and the coordination stability between the target UAV and the UAV cluster is determined according to the conflict relationship and the position information of the target UAV; Determine the aerodynamic interference flow of the target UAV when it joins the UAV cluster according to the cooperative stability and the dynamic motion characteristics of the UAVs in the UAV cluster, and then determine the aerodynamic stability coefficient of the target UAV through the aerodynamic interference flow and the cooperative behavior characteristics of the target UAV in the UAV cluster; When the aerodynamic stability coefficient is lower than a preset stability threshold, an obstacle avoidance adjustment is performed on a subsequent formation path of the target UAV.

2. The method according to claim 1, characterized in that Based on the obstacle avoidance decision mechanism, the trajectory conflicts between the formation path and each flight state are detected, and the conflict relationship between the UAV cluster and the target UAV is obtained, which specifically includes: Determine all entry conflict points between the drone cluster and the target drone according to the formation path and each flight state; Performing conflict detection on each entry conflict point based on the obstacle avoidance decision mechanism to obtain the obstacle conflict value of each entry conflict point; The conflict relationship between the UAV cluster and the target UAV is determined through all obstacle conflict values.

3. The method according to claim 1, characterized in that Determining the coordination stability between the target UAV and the UAV cluster according to the conflict relationship and the position information of the target UAV specifically includes: Obtain the location information of the target drone and the distribution information of drones in the drone cluster; Determine the conflict influencing factor between the target UAV and the UAV cluster according to the conflict relationship; The response conflict of the drone cluster to the cut-in operation of the target drone is determined by the location information of the target drone and the distribution information of the drones in the drone cluster; The coordination stability between the target UAV and the UAV cluster is determined according to the conflict influencing factor and the response conflict.

4. The method according to claim 1, characterized in that Determining the aerodynamic interference flow of the target UAV when joining the UAV cluster according to the cooperative stability and the dynamic motion characteristics of the UAVs in the UAV cluster specifically includes: Obtain the dynamic motion characteristics of drones in a drone cluster; Determine the airflow internal disturbance domain of the drone cluster according to the dynamic motion characteristics of the drones in the drone cluster; Based on the airflow internal disturbance domain and the collaborative stability, the aerodynamics of the target UAV when joining the UAV cluster is simulated to obtain the aerodynamic interference flow of the target UAV when joining the UAV cluster.

5. The method according to claim 1, characterized in that Determining the aerodynamic stability coefficient of the target UAV through the aerodynamic interference flow and the cooperative behavior characteristics of the target UAV in the UAV cluster specifically includes: Obtain the coordinated behavior characteristics of the target UAV in the UAV swarm and the flight strategy of the UAV swarm; Predict the formation flight trajectory of target UAVs based on their collaborative behavior characteristics in the UAV swarm and the flight strategy of the UAV swarm; Determining the aerodynamic stability value of each control surface in the target UAV according to the formation flight trajectory and the aerodynamic interference flow; The aerodynamic stability coefficient of the target UAV is determined based on all aerodynamic stability values.

6. The method according to claim 5, characterized in that Determining the aerodynamic stability value of each control surface in the target UAV according to the formation flight trajectory and the aerodynamic interference flow specifically includes: Determine the aerodynamic torque coefficient of the target UAV through the aerodynamic interference flow; For each control surface in the target UAV, determining a force sequence of the control surface according to the formation flight trajectory; The aerodynamic stability value of the control surface is determined by the force sequence and the aerodynamic moment coefficient, and then the aerodynamic stability value of each control surface in the target UAV is obtained.

7. The method according to claim 1, characterized in that Obstacle avoidance adjustment of the subsequent formation path of the target UAV is based on the trajectory optimization mechanism of disturbance feedback to adjust the speed and angle of the subsequent formation path of the target UAV.

8. An artificial intelligence-based drone control system, characterized in that: include: A monitoring module is used to monitor the flight status of each drone in the drone cluster when the target drone joins the drone cluster for formation flight, and determine the formation path for the target drone to join the drone cluster; A processing module is used to detect the trajectory conflict between the formation path and each flight state based on the obstacle avoidance decision mechanism, obtain the conflict relationship between the UAV cluster and the target UAV, and determine the coordination stability between the target UAV and the UAV cluster according to the conflict relationship and the position information of the target UAV; The processing module is also used to determine the aerodynamic interference flow of the target UAV when it joins the UAV cluster according to the cooperative stability and the dynamic motion characteristics of the UAVs in the UAV cluster, and then determine the aerodynamic stability coefficient of the target UAV through the aerodynamic interference flow and the cooperative behavior characteristics of the target UAV in the UAV cluster; The execution module is used to adjust the subsequent formation path of the target UAV to avoid obstacles when the aerodynamic stability coefficient is lower than a preset stability threshold.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory is used to store a computer program, and the processor is used to call and run the computer program from the memory, so that the computer device executes the artificial intelligence-based drone control method described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions or codes, and when the instructions or codes are executed on a computer, the computer implements the artificial intelligence-based drone control method as described in any one of claims 1 to 7.

Images