Low-altitude patrol system and method for smart city AI unmanned aerial vehicle

Abstract

The invention discloses a low-altitude patrol system and method for a smart city AI unmanned aerial vehicle, particularly relates to the technical field of unmanned aerial vehicle traffic control, and is used for solving the problem that a dynamic coupling effect caused by airflow interaction is not fully considered when an existing unmanned aerial vehicle cooperatively flies in a dense area. By monitoring the flight state and the relative position of the unmanned aerial vehicle in real time, the dense degree of the unmanned aerial vehicle in a target area is judged, and if the dense degree exceeds a safety threshold value, interaction between the unmanned aerial vehicle and surrounding airflow is analyzed through a nonlinear dynamic model, and possible dynamic coupling effect hidden dangers are evaluated; meanwhile, in combination with phase-space reconstruction and multi-scale analysis, potential interference of ground reflection airflow on the flight path of the unmanned aerial vehicle is evaluated; and whether overall traffic coordination optimization of the target area is carried out is judged, and the trajectory adjustment priority is determined according to the flight path complexity of each unmanned aerial vehicle, so that the flight path conflict is effectively avoided, and the flight safety and execution efficiency of the unmanned aerial vehicle cluster are improved.

Description

Technical Field

[0001] The present invention relates to the field of drone traffic control technology, and more specifically, to a low-altitude patrol system and method for smart city AI drones. Background Art

[0002] With the rapid development of smart cities, the level of intelligence in urban management and services continues to improve. UAV technology has been widely used in the field of urban security patrols. The application of UAVs provides efficient and flexible solutions for urban management, especially in low-altitude patrols and real-time monitoring.

[0003] AI drones, a crucial component of smart cities, leverage artificial intelligence and self-learning capabilities to fly and make decisions autonomously in complex environments. These drones collect real-time data about their surroundings through sensors and utilize big data analytics, machine learning, and other technologies to optimize flight trajectories and autonomously execute missions. However, if missions require real-time navigation of dynamic urban environments, particularly tracking suspicious targets, responding to emergencies, or conducting inspections, a larger number of drones may be required to ensure flexibility and rapid response.

[0004] In existing technologies, when multiple drones fly collaboratively in a dense area, if the dynamic coupling effect caused by airflow interaction is not fully considered, it may cause deviations in the drones' flight stability, speed, and heading, thereby affecting the mission execution effect of the entire drone cluster.

[0005] In order to solve the above problems, a technical solution is now provided. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a low-altitude patrol system and method of a smart city AI drone to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions: A low-altitude patrol method for a smart city AI drone includes the following steps: Monitor the flight status and relative position of drones in real time to determine whether the density of drones in the target area exceeds the safety threshold; When the density of drones in the target area exceeds the safety threshold, a nonlinear dynamic model is established to analyze the interaction between drones and the surrounding airflow, and to assess the potential risks of dynamic coupling effects caused by drone flight in the target area. By combining phase space reconstruction with multi-scale analysis, the spatiotemporal variations of ground-reflected airflow in the target area are analyzed to assess the potential interference of ground-reflected airflow on the flight trajectory of UAVs in the target area. Based on the potential risks of dynamic coupling effects caused by UAV flights in the target area and the potential interference of ground-reflected airflow on the flight trajectory of UAVs in the target area, it is determined whether to conduct overall traffic coordination optimization in the target area; When it is necessary to optimize the overall traffic coordination of the target area, the flight status data of each UAV and other UAVs in the target area are analyzed to evaluate the complexity of each UAV's flight path; The trajectory of each drone needs to be prioritized based on the complexity of the drone's flight path.

[0008] In a preferred embodiment, the flight status and relative position of the drones are monitored in real time to determine whether the density of drones in the target area exceeds a safety threshold, specifically: Collect flight status data of all drones in real time, including position, speed, heading and altitude; Determine whether the drone is within the target area based on flight status data: Compare the number of drones in the target area with the volume of the target area to determine the density of drones in the target area; Based on the comparison between the density of drones in the target area and its corresponding safety threshold, the flight safety hazards of drones in the target area are judged.

[0009] In a preferred embodiment, a nonlinear dynamic model is established to analyze the interaction between the UAV and the surrounding airflow, and to assess the potential risks of dynamic coupling effects caused by UAV flight in the target area. Specifically: Real-time acquisition of airflow data around the drone in the target area, including airflow speed, airflow direction, and turbulence; Based on the UAV's flight status data and surrounding airflow data, a nonlinear dynamic model describing the UAV's motion and force conditions is constructed; The established nonlinear dynamic model is used to calculate the interaction forces between UAVs and the disturbance forces between UAVs and the surrounding airflow. Numerical methods are used to numerically solve the nonlinear dynamic model, simulate the coupling effect between drones and airflow in a high-density flight environment, and evaluate the hidden dangers of dynamic coupling effects caused by drone flight in the target area; the hidden dangers of dynamic coupling effects caused by drone flight in the target area include normal and abnormal ones.

[0010] In a preferred embodiment, the temporal and spatial variations of the ground-reflected airflow in the target area are analyzed by combining phase space reconstruction with multi-scale analysis to assess the potential interference of the ground-reflected airflow on the flight trajectory of the UAV in the target area. Specifically, Real-time acquisition of ground reflected airflow data within the target area; Using the phase space reconstruction method, the ground reflected airflow data is mapped into a high-dimensional phase space to reconstruct the dynamic characteristics and changing laws of the airflow; A multi-scale analysis method is used to process the ground reflected airflow data in high-dimensional phase space at different scales to extract the characteristic information of the ground reflected airflow. Based on the characteristic information of ground reflected airflow, a spatiotemporal variation model of airflow describing ground reflection is established to reflect the dependence of airflow on time and space. The established spatiotemporal airflow variation model is used to evaluate the potential interference degree of ground reflected airflow on the flight trajectory of UAVs in the target area; the potential interference degree of ground reflected airflow on the flight trajectory of UAVs in the target area includes large and normal.

[0011] In a preferred embodiment, based on the potential risks of dynamic coupling effects caused by drone flights in the target area and the potential interference of ground-reflected airflow on the flight trajectory of drones in the target area, it is determined whether to perform overall traffic coordination optimization in the target area, specifically: When the hidden dangers of dynamic coupling effects caused by UAV flight in the target area are normal, and the potential interference degree of ground reflected airflow on the flight trajectory of UAV in the target area is normal, it is determined that the overall traffic coordination optimization of the target area will not be carried out; otherwise, it is determined that the overall traffic coordination optimization of the target area will be carried out.

[0012] In a preferred embodiment, when overall traffic coordination optimization of a target area is required, the flight status data of each UAV and other UAVs in the target area are analyzed to evaluate the complexity of each UAV's flight path, specifically: Calculate the relative position and speed difference between each UAV and other UAVs based on the flight status data; By analyzing the relative positions and speed differences between drones, possible flight path conflicts and interference situations can be identified: for two drones whose distance between them is less than a preset safety range, all drone pairs whose speed difference is less than the preset speed difference are marked; The flight path complexity of each UAV is evaluated based on flight path conflicts and interference situations.

[0013] In a preferred embodiment, the flight path complexity of each UAV is evaluated based on flight path conflicts and interference conditions, specifically: Calculate the path complexity factor of each UAV, and its expression is: ;in, is the path complexity factor, is the number of other drones that have path conflicts with the drone, is the number of other drones that have path conflicts with the drone; Indicates the The first drone and the second drone that has a path conflict with it The speed difference between the drones It is The first drone and the second drone that has a path conflict with it The distance between the drones, is a constant.

[0014] In a preferred embodiment, the priority of each drone's trajectory to be adjusted is determined based on the complexity of the drone's flight path, specifically: Calculate the adjustment priority value, the expression is: ;in, It is Adjust the priority value of each drone, It is Adjust the priority weight of each drone; The larger the adjustment priority value, the higher the priority of the drone's trajectory adjustment. The drones are sorted from large to small based on the adjustment priority value, and the trajectory of the drone with the highest ranking is adjusted first.

[0015] On the other hand, the present invention provides a low-altitude patrol system for AI drones in smart cities, including a density monitoring module, a coupling effect analysis module, a ground effect analysis module, a comprehensive traffic optimization module, a path complexity assessment module, and a trajectory priority determination module; Density monitoring module: monitors the flight status and relative position of drones in real time to determine whether the density of drones in the target area exceeds the safety threshold; Coupling Effect Analysis Module: When the density of drones in the target area exceeds the safety threshold, a nonlinear dynamic model is established to analyze the interaction between drones and the surrounding airflow, assessing the potential risks of dynamic coupling effects caused by drone flight in the target area. Ground Effect Analysis Module: When the density of drones in the target area exceeds the safety threshold, the module analyzes the spatiotemporal variations of ground-reflected airflow within the target area through a combination of phase space reconstruction and multi-scale analysis to assess the potential interference of ground-reflected airflow on the flight paths of drones within the target area. Traffic Comprehensive Optimization Module: This module determines whether to optimize the overall traffic coordination in the target area based on the potential risks of dynamic coupling effects caused by UAV flights in the target area and the potential interference of ground-reflected airflow on the flight trajectory of UAVs in the target area. Path complexity assessment module: When the overall traffic coordination optimization of the target area is required, the flight status data of each drone and other drones in the target area are analyzed to assess the flight path complexity of each drone; Trajectory priority determination module: Determines the priority of each drone's trajectory based on the complexity of the drone's flight path.

[0016] The technical effects and advantages of the low-altitude patrol system and method of a smart city AI drone of the present invention are as follows: 1. By real-time monitoring of the flight status and relative positions of drones, it is possible to effectively determine whether the density of drones in the target area exceeds the safety threshold, thereby reducing flight path conflicts or interference caused by the density of drones. By analyzing the flight status data between drones in dense areas, potential conflict risks can be discovered in a timely manner during the planning stage of the drone flight trajectory, ensuring that drones' autonomous flight in complex environments is safer and more efficient. In addition, based on the nonlinear dynamic model, the interaction between drones and surrounding airflow can be analyzed to assess the potential dynamic coupling effect risks caused by drone flight in the target area, providing protection for the safety of drone swarm flight. Combined with phase space reconstruction and multi-scale analysis, it is possible to deeply analyze the spatiotemporal changes of ground-reflected airflow, evaluate its potential interference with drone flight trajectories, and further improve the accuracy and stability of flight missions, thereby ensuring the efficient execution and rapid response of AI drones in dynamic urban environments.

[0017] 2. When the density of drones in the target area exceeds the safety threshold, the present invention prioritizes flight trajectory adjustment based on the complexity of the flight path to ensure that drones with critical tasks can adjust their trajectories first, avoid heading deviation or conflict, and improve the cluster's collaborative capabilities; the priority is calculated and adjusted based on the complexity of the flight path of each drone, making the trajectory adjustment more scientific and reasonable, avoiding unnecessary interference and congestion, and optimizing overall flight efficiency; in actual applications, through precise flight path analysis and optimization, the present invention can effectively improve the execution efficiency of low-altitude patrol tasks of AI drones in smart cities, reduce risks during flight, and ensure that drone clusters can collaboratively perform tasks such as patrol, monitoring, and emergency response, thereby significantly improving the level of intelligent urban management and public safety protection capabilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a schematic diagram of a low-altitude patrol method for a smart city AI drone according to the present invention; Figure 2 This is a structural schematic diagram of a low-altitude patrol system for a smart city AI drone in the present invention. DETAILED DESCRIPTION

[0019] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention. Example

[0020] The present invention provides a low-altitude patrol method for AI drones in smart cities, which aims to solve problems such as flight path conflicts, dynamic coupling effects, and ground-reflected airflow interference that may occur in the flight of urban drone clusters, and belongs to the category of traffic control systems for aerial vehicles. By real-time monitoring of the flight status, relative position, and flight path complexity of drones, the present invention can accurately coordinate and optimize drones in the target area, avoid mutual interference between aircraft, and ensure the smooth progress of the mission. In particular, in dense areas or complex environments, a nonlinear dynamic model is used to analyze the interaction between drones and surrounding airflow, and the potential impact of airflow on flight trajectories is evaluated through phase space reconstruction and multi-scale analysis, thereby realizing dynamic management and optimization of drone flight status. In addition, the present invention focuses on the coordinated flight and mutual obstacle avoidance of drone groups, and involves the coordinated control of cluster drones in complex flight environments. It is not limited to the control of a single aircraft, but emphasizes the path coordination between multiple drones and the dynamic adaptation of the flight environment, which belongs to the category of aerial vehicle traffic control.

[0021] Figure 1 The present invention provides a low-altitude patrol method for a smart city AI drone, which includes the following steps: Monitor the flight status and relative position of drones in real time to determine whether the density of drones in the target area exceeds the safety threshold.

[0022] When the density of drones in the target area exceeds the safety threshold, a nonlinear dynamic model is established to analyze the interaction between drones and the surrounding airflow, and to evaluate the potential risks of dynamic coupling effects caused by drone flight in the target area. By combining phase space reconstruction with multi-scale analysis, the spatiotemporal changes of ground-reflected airflow in the target area are analyzed, and the potential degree of interference of ground-reflected airflow on the flight trajectory of drones in the target area is evaluated.

[0023] Based on the hidden dangers of dynamic coupling effects caused by drone flights in the target area and the potential interference of ground reflected airflow on the flight trajectory of drones in the target area, it is determined whether to carry out overall traffic coordination optimization in the target area.

[0024] When overall traffic coordination optimization of the target area is required, the flight status data of each UAV in the target area and other UAVs are analyzed to evaluate the complexity of the flight path of each UAV.

[0025] The trajectory of each drone needs to be prioritized based on the complexity of the drone's flight path.

[0026] Monitor the flight status and relative position of drones in real time to determine whether the density of drones in the target area exceeds the safety threshold. Specifically: Collect flight status data of all drones in real time, including position, speed, heading and flight altitude: Through sensors and positioning systems (such as the Global Positioning System (GPS), Inertial Measurement Unit (IMU), and radar), real-time flight status data of each drone is obtained, including: Position: The three-dimensional coordinates of the drone in space, usually expressed in a geographic coordinate system or a local coordinate system; Speed: The instantaneous speed of the drone in space, usually including lateral, longitudinal and vertical speed components; Heading: The flight direction of the drone, usually expressed as heading angle, which is the angle relative to north; Flight altitude: The height of the drone relative to the ground, usually expressed as altitude.

[0027] Determine whether the drone is within the target area based on flight status data: 2D Plane Determination (for fixed plane areas): The drone's plane position coordinates (X, Y) are compared with the plane boundary coordinates of the target area. If the X, Y coordinates fall within the target area, the drone is considered to be within the target area.

[0028] Three-dimensional spatial judgment (for areas with flight altitude): For target areas with altitude requirements, in addition to the plane coordinates, the flight altitude Z must also be considered. By judging whether the drone's altitude Z is within the vertical range of the target area, it is further determined whether it is within the target area.

[0029] Among them, the target area refers to the ground area or air area involved in the UAV's low-altitude patrol mission. The flight status and relative position of the UAV in this area need to be monitored and evaluated in real time. The scope and specific location of the target area can be dynamically defined according to specific mission requirements, such as a specific area of ​​the city, the airspace around important buildings, or a designated flight route.

[0030] Compare the number of drones in the target area with the volume of the target area to determine the density of drones in the target area: According to determining which drones are located in the target area, all drones in the target area are counted to obtain the number of drones in the target area.

[0031] The ratio of the number of drones in the target area to the volume of the target area is marked as the drone density.

[0032] Based on the comparison between the density of drones in the target area and the corresponding safety threshold, the flight safety hazards of drones in the target area are judged: If the density of drones in the target area is greater than the corresponding safety threshold, it is determined that the flight safety hazard of drones in the target area is greater.

[0033] If the density of drones in the target area is less than or equal to the corresponding safety threshold, it is determined that the flight safety hazards of drones in the target area are normal.

[0034] By establishing a nonlinear dynamic model to analyze the interaction between the UAV and the surrounding airflow, the potential risks of dynamic coupling effects caused by UAV flight in the target area are assessed. Specifically: Acquire the surrounding airflow data of the drone in the target area in real time. The surrounding airflow data includes airflow speed, airflow direction and turbulence: Air velocity: The air velocity at any location within the target area, expressed as a three-dimensional vector consisting of velocity components along the X, Y, and Z axes.

[0035] Airflow direction: The direction of airflow at different spatial locations, expressed as an angle relative to a reference direction, to ensure that the overall direction of the airflow is reflected.

[0036] Turbulence: The degree of irregular disturbance in the airflow, reflecting the instability of the airflow. It is usually expressed by turbulence intensity, which records the changes in turbulence at various locations.

[0037] Based on the UAV's flight status data and surrounding airflow data, a nonlinear dynamic model describing the UAV's motion and force conditions is constructed: Define the three-dimensional coordinate position of the UAV in the target area as , Represents the current position of the drone; the velocity vector of the drone is defined as , Represent the velocity components of the drone in the X, Y, and Z axis directions respectively.

[0038] Assume that the airflow in the target area exerts a disturbance force on each drone. This force includes the influence of the speed and direction of the airflow on the movement of the drone, expressed as a three-dimensional vector In the form of Acts on the movement of the drone in the X, Y and Z directions respectively.

[0039] The equation of motion for the drone is based on Newton's second law and is expressed as: ;in, Indicates the quality of the drone, Indicates the thrust of the drone itself.

[0040] The turbulence intensity parameter is introduced and the influence of turbulence on the trajectory of the UAV is calculated through the turbulence intensity function. The influence of turbulence on the UAV motion is reflected in The wave characteristics of the dynamic range are directly affected by the UAV's motion equation.

[0041] The turbulence intensity function is calculated based on the turbulence characteristics of the airflow. It is usually obtained by measuring or estimating the turbulence intensity of the surrounding airflow. Turbulence intensity refers to the degree of irregular fluctuations in the airflow and is usually expressed as the ratio of the standard deviation of the airflow velocity to the average velocity. In this model, the turbulence intensity function reflects the impact of turbulence on the flight of the UAV at a specific location. The specific calculation usually relies on real-time airflow sensor data, combined with fluid mechanics theory and experimental data, and the function is estimated through numerical simulation or analytical methods. This function is used to quantify the disturbing effect of turbulence on the movement of the UAV, especially its dynamic behavior in a high-turbulence environment.

[0042] The established nonlinear dynamic model is used to calculate the interaction force between drones and the disturbance force between drones and the surrounding airflow: Assuming that the interaction force between any two UAVs is related to their relative distance, its expression is: ;in, represents the interaction force between any two UAVs; is a constant, representing the strength coefficient of the interaction force; is the unit direction vector between the two UAV positions, pointing in the direction of their relative positions; Indicates the distance between two drones.

[0043] The disturbance force generated by the airflow on each UAV is calculated using the established airflow data. The expression is: ;in, It is the disturbance force of airflow on the drone. is the airflow disturbance intensity coefficient, is the velocity component of the airflow at the current position, and the formula of the disturbance force of the airflow on the drone is The symbol represents the multiplication of a scalar and a vector.

[0044] Numerical methods are used to solve nonlinear dynamic models, simulate the coupling effects between drones and airflow in high-density flight environments, and assess the potential risks of dynamic coupling effects caused by drone flight in the target area: After establishing a nonlinear dynamic model, a numerical method was used to solve the model to simulate the coupling effect between the drone and the airflow. Because the model involves complex interactions between multiple drones and the disturbance force of the airflow, numerical calculations are required to solve the equations.

[0045] Numerical solution: Common numerical methods, such as the finite difference method or the Runge-Kutta method, are used to numerically solve the dynamic model. During the solution process, the time step is set to improve the accuracy of the calculation.

[0046] Coupling Effect Simulation: During the solution process, the coupling between the drone and the airflow is analyzed, especially the changes in flight state under high density. The results of the numerical solution will be used to evaluate the impact of dynamic coupling on flight trajectory and stability.

[0047] Based on the interaction force between UAVs, the turbulence intensity function, and the disturbance force of airflow on UAVs, the average interaction force between UAVs in the target area, the average turbulence intensity function value in the target area, and the average disturbance force of airflow on UAVs in the target area are calculated.

[0048] The average interaction force between drones in the target area is compared with its corresponding preset threshold, the average turbulence intensity function value in the target area is compared with its corresponding preset threshold, and the average value of the disturbance force of the airflow on the drones in the target area is compared with its corresponding preset threshold.

[0049] If the average interaction force between drones in the target area is less than or equal to its corresponding preset threshold, the average turbulence intensity function value in the target area is less than or equal to its corresponding preset threshold, and the average turbulence intensity function value in the target area is less than or equal to its corresponding preset threshold, then the hidden danger of the dynamic coupling effect caused by drone flight in the target area is judged to be normal; otherwise, the hidden danger of the dynamic coupling effect caused by drone flight in the target area is judged to be abnormal.

[0050] Among them, the preset threshold value corresponding to the average interaction force between drones in the target area is set based on the type of drone, flight mode and density, usually through historical data analysis or simulation model evaluation to ensure that the interaction force between drones does not exceed the safety limit to avoid collision or unstable flight. The preset threshold value corresponding to the average turbulence intensity function value in the target area is set according to the characteristics of the meteorological environment in the target area and the stability requirements of drone flight. It is usually combined with meteorological forecast data and turbulence models to ensure that the turbulence intensity does not cause excessive disturbance to the drone flight trajectory. The preset threshold value corresponding to the average value of the disturbance force of the airflow on the drone in the target area is set according to the airflow characteristics in the target area, taking into account factors such as airflow speed, direction and turbulence level, to ensure that the airflow disturbance force is within a safe range and avoid excessive airflow causing the drone to lose control or unstable flight.

[0051] By combining phase space reconstruction with multi-scale analysis to analyze the spatiotemporal variations of ground-reflected airflow in the target area, the potential interference of ground-reflected airflow on the flight trajectory of UAVs in the target area is evaluated. Specifically: Real-time acquisition of ground reflected airflow data within the target area: Ground reflected airflow refers to the airflow generated by reflection or disturbance on the ground surface, which affects the airflow distribution and movement state in the surrounding environment.

[0052] Real-time collection of ground-reflected airflow data. Sensors are distributed at different locations in the target area to accurately obtain the characteristics of airflow at each spatial location. Ground-reflected airflow data includes the following: Airflow velocity: describes the speed of the ground-reflected airflow in space, which is divided into horizontal and vertical components at each sampling point.

[0053] Airflow direction: Indicates the direction of airflow reflected from the ground, usually described by relative angles (such as the angle relative to north).

[0054] Turbulence intensity: It indicates the disturbance intensity of airflow reflected from the ground, and reflects the instability of airflow in space.

[0055] Using the phase space reconstruction method, the ground reflected airflow data is mapped into a high-dimensional phase space to reconstruct the dynamic characteristics and changing laws of the airflow: The purpose of phase space reconstruction is to transform the original one-dimensional or multi-dimensional ground reflected airflow data into a higher-dimensional space so that the dynamic characteristics and changing laws of the ground reflected airflow can be revealed.

[0056] The specific method is as follows: Choose an appropriate embedding dimension: Set the embedding dimension of the phase space. Assume the embedding dimension is , then each sampling point in the original ground reflected airflow data will be mapped to a dimensional vector.

[0057] Set time delay: Set time delay Used to reconstruct the phase space. The time delay setting can be determined through data analysis or empirical values ​​to ensure that the points in the phase space can effectively represent the dynamic characteristics of the airflow.

[0058] Construct phase space vector: For the ground reflection airflow data of each sampling point, according to the time delay and embedding dimension , construct the phase space vector, expressed as: ;in, Represents the airflow state vector in phase space, including Dimensional airflow status information; Represents the sampling value of ground reflected airflow data, Represents a time variable.

[0059] A multi-scale analysis method is used to process the ground reflected airflow data in the high-dimensional phase space at different scales to extract the characteristic information of the ground reflected airflow: The purpose of multi-scale analysis is to extract the characteristic information of ground reflected airflow at different time scales and spatial scales in order to fully understand the temporal and spatial variation characteristics of airflow.

[0060] Multiple time scales and spatial scales are set to capture the changing characteristics of airflow at different levels.

[0061] At each scale, the airflow data in the high-dimensional phase space is processed to extract the airflow characteristics at that scale. For example, at a smaller scale, the instantaneous change information of the airflow can be extracted; at a larger scale, the overall trend of the airflow can be obtained.

[0062] The characteristic information of the ground reflected airflow is extracted at each scale, and the key characteristic vector of the ground reflected airflow is obtained by calculation, which includes characteristics such as the changing trend of airflow velocity and fluctuation of turbulence intensity.

[0063] Based on the characteristic information of the ground reflected airflow, a spatiotemporal variation model of the airflow describing the ground reflection is established to reflect the dependence of the airflow on time and space: Based on the key characteristic vectors of ground-reflected airflow extracted through multi-scale analysis, a spatiotemporal variation model of airflow describing ground reflection is established. The task of this model is to characterize the temporal and spatial distribution of ground-reflected airflow and reflect the potential impact of airflow on the flight trajectory of UAVs.

[0064] Set time variables and space coordinates Indicates the distribution of airflow.

[0065] The spatiotemporal variation model of airflow is constructed based on the key characteristic vectors of the ground reflected airflow, which can be expressed as: ;in, It is a temporal and spatial variation model of airflow, which represents the velocity vector of the airflow reflected from the ground and describes the temporal and spatial variation characteristics of the airflow.

[0066] It represents the velocity component of the ground reflected airflow along the X axis (usually the east-west direction) in the target area. It represents the velocity component of the ground reflected airflow along the Y axis (usually the north-south direction) in the target area. It represents the velocity component of the ground reflected airflow along the Z axis (usually the vertical direction) in the target area.

[0067] represents the horizontal component velocity of the airflow along the X axis in the target area, It represents the horizontal component velocity of the airflow along the Y axis in the target area. It represents the vertical component velocity of the airflow along the Z axis in the target area.

[0068] The established spatiotemporal airflow variation model is used to evaluate the potential interference of ground-reflected airflow on the flight trajectory of UAVs in the target area: For UAVs in the target area, the ground effect interference index is calculated using the spatiotemporal airflow variation model, and its expression is: ;in, is the ground effect interference index, is the number of drones in the target area, is the number of the drone in the target area, Indicates that the ground reflected airflow is The velocity vector of the UAV position, Indicates the The velocity vector of each drone, is the arccosine function (used to calculate the angle between the airflow and the flight direction of the drone).

[0069] Among them, the ground effect interference index formula is Represents the dot product operation between two vectors. The dot product is the sum of the products of the corresponding components of the two vectors.

[0070] The larger the ground effect interference index, the greater the degree of change in the ground reflected airflow, which usually means that the airflow is more volatile and unstable, thus having a greater impact on the flight trajectory of the UAV. The greater the potential interference of the ground reflected airflow on the flight trajectory of the UAV in the target area.

[0071] Set the ground effect interference threshold and compare the ground effect interference index with the ground effect interference threshold: When the ground effect interference index is greater than the ground effect interference threshold, it is determined that the ground reflected airflow has a high potential interference degree on the UAV flight trajectory in the target area, indicating that the intensity or volatility of the ground reflected airflow has a significant impact on the UAV flight in the target area. This indicates that the ground reflected airflow in the target area has a strong interference effect, which may cause the UAV flight trajectory to deviate or become unstable, increasing the flight risk.

[0072] When the ground effect interference index is less than or equal to the ground effect interference threshold, it is determined that the potential interference level of the ground reflected airflow on the UAV's flight trajectory in the target area is normal, indicating that the intensity and volatility of the ground reflected airflow are within an acceptable range and will not cause significant interference to the UAV's flight trajectory. This indicates that the airflow conditions in the target area are relatively stable, the flight environment is relatively safe, and the aircraft can fly normally without the need for additional airflow adjustments or flight path optimization.

[0073] The ground effect interference threshold is determined based on historical data analysis of ground-reflected airflow within the target area, combined with drone flight safety standards and environmental factors. This threshold takes into account fluctuations in airflow intensity, turbulence, and reflective effects, ensuring that flights within this range will not significantly interfere with the drone's flight trajectory. The threshold should be sensitive enough to provide timely warnings when airflow disturbances exceed the specified threshold.

[0074] Based on the potential risks of dynamic coupling effects caused by UAV flights in the target area and the potential interference of ground-reflected airflow on the flight trajectory of UAVs in the target area, it is determined whether to conduct overall traffic coordination optimization in the target area. Specifically: When the hidden dangers of dynamic coupling effects caused by UAV flight in the target area are normal, and the potential interference degree of ground reflected airflow on the flight trajectory of UAV in the target area is normal, it is determined that the overall traffic coordination optimization of the target area will not be carried out; otherwise, it is determined that the overall traffic coordination optimization of the target area will be carried out.

[0075] By assessing the potential risks of dynamic coupling effects and the degree of interference of ground-reflected airflow on drone flight, it is determined whether traffic coordination optimization is necessary, ensuring that coordination is initiated only when necessary to improve efficiency and safety. Specifically, when the interaction force between drones and the influence of surrounding airflow are within the safety threshold, and the disturbance of ground-reflected airflow does not significantly interfere with the flight trajectory, no optimization is performed, allowing drones to perform tasks according to established paths and strategies, thereby reducing unnecessary adjustments and improving flight efficiency. If the evaluation results show that any one item is out of the normal range, the overall traffic coordination optimization is initiated, and by adjusting the flight path, speed or altitude, a safe flight environment is provided for all drones in the target area, reducing flight instability and potential collision risks. This optimization mechanism takes into account both safety and efficiency, ensuring the stable flight of drones in complex environments.

[0076] When it is determined that the target area requires overall traffic coordination optimization, the following specific measures can be taken to optimize the flight paths and dynamics of drones within the target area to ensure flight safety and improve mission efficiency: Based on the assessment results, the flight paths of drones within the target area are adjusted to avoid densely populated areas or those with potential interference. For example, by optimizing the path planning algorithm, drones are forced to avoid areas with strong airflow interference or dynamic coupling effects, ensuring that the interaction forces between drones remain within a safe range.

[0077] The drones' flight altitude is dynamically adjusted within the area based on real-time data. If ground-reflected air currents are strong or could cause interference, the flight altitude can be adjusted to avoid these effects while ensuring that drones remain within a safe distance from each other.

[0078] Adjust the flight speed and relative flight time intervals of drones, especially in high-density areas. By reducing flight speed, reducing the relative speed between drones, or adjusting the takeoff and arrival times of drones, avoid too many drones congregating in the target area at the same time, thereby reducing the impact of dynamic coupling effects and ground-reflected airflow on flight trajectories.

[0079] The intelligent obstacle avoidance system between drones uses set rules or AI algorithms to analyze the surrounding environment in real time, including the movements of other drones, airflow changes, and possible obstacles. When a drone detects an impending conflict or interference, it automatically makes avoidance adjustments to maintain safe and smooth flight.

[0080] The introduction of a distributed decision-making algorithm enables coordinated control of all drones within a target area, enabling real-time dynamic adjustments based on shared state and environmental perception data. These adjustments can include position, speed, and heading, ensuring inter-drone collaboration and flight safety.

[0081] When it is necessary to optimize the overall traffic coordination in the target area, the flight status data of each UAV and other UAVs in the target area are analyzed to evaluate the complexity of each UAV's flight path, specifically: Calculate the relative position and velocity difference between each drone and other drones based on the flight status data: For each pair of drones within the target area, the flight status data is used to determine the spatial position difference between the two drones and determine their distance and direction. This step helps identify whether the drones are within close range of each other, facilitating subsequent analysis.

[0082] For each pair of drones, their speed information is compared to determine the speed difference between them. This reflects the difference in the motion state of the two drones and helps analyze their relative motion trends.

[0083] By analyzing the relative position and speed differences between drones, possible flight path conflicts and interference situations can be identified: The distance between each pair of drones is analyzed. If the distance between two drones is less than the preset safety range, it is judged that there is a high risk of approaching each other, and their relative speed needs to be further analyzed.

[0084] For two drones whose distance between them is less than the preset safety range, their speed difference is further analyzed. If the speed difference between the two drones is less than the preset speed difference, that is, they are approaching in the same direction, there is a possibility of flight path conflict or interference.

[0085] All drone pairs whose speed difference is less than the preset speed difference are marked as the basis for subsequent evaluation of the complexity of the flight path.

[0086] Among them, the preset safety range is a set maximum distance value, which indicates the minimum safe distance that must be maintained between two drones. This value is determined according to the nature of the flight mission, the operating specifications of the drone, and the safety requirements of the airspace. For example, for commercial drones or multi-rotor drones commonly used in drone flight missions, the preset safety range may be set to 50 meters, 100 meters, or even larger. The setting of the preset speed difference is based on the type of drone, the nature of the flight mission, and the safety standards of the airspace. Generally speaking, the preset speed difference takes into account the maximum flight speed, maneuverability, and safe operating range of the drone. Common setting values ​​may be between 10 kilometers per hour and 30 kilometers per hour to ensure effective separation of flight paths.

[0087] Assess the flight path complexity of each drone based on flight path conflicts and interference scenarios: Calculate the path complexity factor of each UAV, and its expression is: ;in, is the path complexity factor, is the number of other drones that have path conflicts with the drone, that is, the number of drone pairs whose speed difference is less than the preset speed difference; is the number of other drones that have path conflicts with the drone; Indicates the The first drone and the second drone that has a path conflict with it The speed difference between the drones reflects their proximity in movement trends; It is The first drone and the second drone that has a path conflict with it The distance between drones; It is a constant, such as 0.01, to avoid the formula being undefined when the distance is zero.

[0088] The larger the path complexity factor, the more potential conflicts affect the flight path of the UAV, and therefore the higher the flight path complexity.

[0089] The trajectory of each drone needs to be prioritized based on the complexity of the drone's flight path. Specifically: Calculate the adjustment priority value, the expression is: ;in, It is Adjust the priority value of each drone, It is Adjust the priority weight of each drone.

[0090] Among them, the adjustment priority weight of the drone is adjusted according to factors such as the type of drone, mission importance, and flight risks faced.

[0091] The larger the adjustment priority value, the higher the priority of the drone's trajectory adjustment. The drones are sorted from large to small based on the adjustment priority value, and the trajectory of the drone with the highest ranking is adjusted first.

[0092] Drones ranked higher are typically those at higher risk of path conflicts or requiring more adjustments. Each drone's flight path is adjusted individually, including heading, altitude, or speed, to avoid conflicts or interference with other drones.

[0093] In this way, it is possible to ensure that drones with the greatest potential risk or requiring higher adjustments are addressed first, thereby optimizing overall flight safety and traffic coordination. Example

[0094] The difference between Example 2 of the present invention and Example 1 is that this example introduces a low-altitude patrol system for a smart city AI drone.

[0095] Figure 2 A structural schematic diagram of a low-altitude patrol system for a smart city AI drone is given in the present invention. A low-altitude patrol system for a smart city AI drone includes a density monitoring module, a coupling effect analysis module, a ground effect analysis module, a comprehensive traffic optimization module, a path complexity assessment module, and a trajectory priority determination module.

[0096] Density monitoring module: monitors the flight status and relative position of drones in real time to determine whether the density of drones in the target area exceeds the safety threshold.

[0097] Coupling effect analysis module: When the density of drones in the target area exceeds the safety threshold, a nonlinear dynamic model is established to analyze the interaction between drones and the surrounding airflow, and to assess the potential risks of dynamic coupling effects caused by drone flight in the target area.

[0098] Ground Effect Analysis Module: When the density of drones in the target area exceeds the safety threshold, the spatiotemporal changes of ground-reflected airflow in the target area are analyzed by combining phase space reconstruction with multi-scale analysis to assess the potential interference of ground-reflected airflow on the flight trajectory of drones in the target area.

[0099] Comprehensive traffic optimization module: Based on the hidden dangers of dynamic coupling effects caused by drone flights in the target area and the potential interference of ground reflected airflow on the flight trajectory of drones in the target area, it is determined whether to conduct overall traffic coordination optimization in the target area.

[0100] Path complexity assessment module: When it is necessary to optimize the overall traffic coordination of the target area, the flight status data of each drone in the target area and other drones are analyzed to evaluate the complexity of the flight path of each drone.

[0101] Trajectory priority determination module: Determines the priority of each drone's trajectory based on the complexity of the drone's flight path.

[0102] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field according to actual conditions.

[0103] The above embodiments can be implemented in whole or in part via software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in the embodiments of this application are fully or partially performed. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0104] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software 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 beyond the scope of this application.

[0105] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0106] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0107] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected to achieve the purpose of this embodiment according to actual needs.

[0108] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0109] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0110] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

[0111] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A low-altitude patrol method for a smart city AI drone, characterized in that: The steps include: Monitor the flight status and relative position of drones in real time to determine whether the density of drones in the target area exceeds the safety threshold; When the density of drones in the target area exceeds the safety threshold, a nonlinear dynamic model is established to analyze the interaction between drones and the surrounding airflow, and to assess the potential risks of dynamic coupling effects caused by drone flight in the target area. The temporal and spatial changes of ground reflected airflow in the target area are analyzed by combining phase space reconstruction with multi-scale analysis to evaluate the potential interference of ground reflected airflow on the flight trajectory of UAVs in the target area. Based on the potential risks of dynamic coupling effects caused by UAV flight in the target area and the potential interference of ground reflected airflow on the flight trajectory of UAVs in the target area, it is determined whether to conduct overall traffic coordination optimization in the target area; When the overall traffic coordination optimization of the target area is required, the flight status data of each UAV and other UAVs in the target area are analyzed to evaluate the complexity of the flight path of each UAV; The trajectory of each drone needs to be prioritized based on the complexity of the drone's flight path.

2. According to claim 1, a low-altitude patrol method of a smart city AI drone is characterized in that: Monitor the flight status and relative position of drones in real time to determine whether the density of drones in the target area exceeds the safety threshold. Specifically: Collect the flight status data of all drones in real time, including position, speed, heading and flight altitude; Determine whether the drone is within the target area based on the flight status data: Compare the number of drones located in the target area with the volume of the target area to determine the density of drones in the target area; Based on the comparison between the density of drones in the target area and its corresponding safety threshold, the flight safety hazards of drones in the target area are judged.

3. A low-altitude patrol method for a smart city AI drone according to claim 2, characterized in that: By establishing a nonlinear dynamic model to analyze the interaction between the UAV and the surrounding airflow, the potential risks of dynamic coupling effects caused by UAV flight in the target area are evaluated, specifically: Real-time acquisition of the surrounding airflow data of the drone in the target area, including airflow speed, airflow direction and turbulence; Based on the flight status data of the UAV and the surrounding airflow data, a nonlinear dynamic model describing the motion and force of the UAV is constructed; The established nonlinear dynamic model is used to calculate the interaction forces between UAVs and the disturbance forces between UAVs and the surrounding airflow. Numerical methods are used to numerically solve the nonlinear dynamic model, simulate the coupling effect between UAVs and airflow in a high-density flight environment, and evaluate the hidden dangers of dynamic coupling effects caused by UAV flight in the target area; the hidden dangers of dynamic coupling effects caused by UAV flight in the target area include normal and abnormal.

4. The low-altitude patrol method of a smart city AI drone according to claim 3 is characterized in that: The temporal and spatial changes of the ground reflected airflow in the target area are analyzed by combining phase space reconstruction with multi-scale analysis to evaluate the potential interference of the ground reflected airflow on the flight trajectory of the UAV in the target area. Specifically: Acquire the ground reflected airflow data in the target area in real time; Using the phase space reconstruction method, the ground reflected airflow data is mapped to the high-dimensional phase space to reconstruct the dynamic characteristics and change laws of the airflow; The multi-scale analysis method is used to process the ground reflected airflow data in the high-dimensional phase space at different scales to extract the characteristic information of the ground reflected airflow. Based on the characteristic information of the ground reflected airflow, a model describing the spatiotemporal variation of the ground reflected airflow is established to reflect the dependence of the airflow on time and space. The established spatiotemporal airflow variation model is used to evaluate the potential interference degree of ground reflected airflow on the flight trajectory of UAVs in the target area; the potential interference degree of ground reflected airflow on the flight trajectory of UAVs in the target area includes large and normal.

5. The low-altitude patrol method of a smart city AI drone according to claim 4 is characterized in that: Based on the potential risks of dynamic coupling effects caused by UAV flight in the target area and the potential interference of ground reflected airflow on the flight trajectory of UAVs in the target area, it is determined whether to conduct overall traffic coordination optimization in the target area, specifically: When the hidden dangers of dynamic coupling effects caused by UAV flight in the target area are normal, and the potential interference degree of ground reflected airflow on the flight trajectory of UAV in the target area is normal, it is determined not to perform overall traffic coordination optimization of the target area; otherwise, it is determined to perform overall traffic coordination optimization of the target area.

6. The low-altitude patrol method of a smart city AI drone according to claim 5 is characterized in that: When the overall traffic coordination optimization of the target area is required, the flight status data of each UAV and other UAVs in the target area are analyzed to evaluate the complexity of the flight path of each UAV, specifically: Calculate the relative position and speed difference between each UAV and other UAVs based on the flight status data; By analyzing the relative positions and speed differences between drones, possible flight path conflicts and interference situations can be identified: for two drones that meet the requirement that the distance between the two drones is less than the preset safety range, all drone pairs that meet the requirement that the speed difference is less than the preset speed difference are marked; Assess the flight path complexity of each UAV based on flight path conflicts and interference situations.

7. A low-altitude patrol method for a smart city AI drone according to claim 6, characterized in that: The flight path complexity of each UAV is evaluated based on flight path conflicts and interferences, specifically: Calculate the path complexity factor of each drone, and its expression is: ;in, is the path complexity factor, is the number of other drones that have path conflicts with the drone, is the ID of other drones that have path conflicts with the drone; Indicates The first drone and the second drone that has a path conflict with it The speed difference between the drones It is The first drone and the second drone that has a path conflict with it The distance between the drones, is a constant.

8. The low-altitude patrol method of a smart city AI drone according to claim 7 is characterized in that: The trajectory of each drone needs to be prioritized based on the complexity of the drone's flight path, specifically: Calculate the adjustment priority value, the expression is: ;in, It is The adjustment priority value of each drone, It is Adjust the priority weight of each drone; The larger the adjustment priority value, the higher the priority of the drone's trajectory that needs to be adjusted. The drones are sorted from large to small based on the adjustment priority value, and the trajectory of the drone with the highest order is adjusted first.

9. A low-altitude patrol system for a smart city AI drone, used to implement a low-altitude patrol method for a smart city AI drone as described in any one of claims 1 to 8, characterized in that: It includes density monitoring module, coupling effect analysis module, ground effect analysis module, traffic comprehensive optimization module, path complexity assessment module and trajectory priority determination module; Density monitoring module: monitors the flight status and relative position of drones in real time to determine whether the density of drones in the target area exceeds the safety threshold; Coupling effect analysis module: When the density of drones in the target area exceeds the safety threshold, the interaction between drones and surrounding airflow is analyzed by establishing a nonlinear dynamic model to assess the potential risks of dynamic coupling effects caused by drone flight in the target area. Ground effect analysis module: When the density of drones in the target area exceeds the safety threshold, the spatiotemporal changes of ground reflected airflow in the target area are analyzed by combining phase space reconstruction with multi-scale analysis to assess the potential interference of ground reflected airflow on the flight trajectory of drones in the target area. Traffic comprehensive optimization module: Based on the potential risks of dynamic coupling effects caused by UAV flight in the target area and the potential interference of ground reflected airflow on the flight trajectory of UAVs in the target area, it is determined whether to coordinate and optimize the overall traffic in the target area; Path complexity assessment module: When the overall traffic coordination optimization of the target area is required, the flight status data of each drone and other drones in the target area are analyzed to assess the complexity of the flight path of each drone; Trajectory priority determination module: Determine the priority of each drone's trajectory based on the complexity of the drone's flight path.

Images