Unmanned aerial vehicle trajectory control method and system based on big data

Abstract

The application discloses a big data-based unmanned aerial vehicle track control method and system, belongs to the technical field of unmanned aerial vehicle flight control, and is based on flight track planning and sensor data to acquire real-time flight data and obstacle information of an unmanned aerial vehicle, compares real-time flight states with planned flight states, evaluates flight deviation, constructs an interference evaluation model, introduces environmental wind speed, signal strength and flight deviation into the interference evaluation model to evaluate the interference degree of the unmanned aerial vehicle, constructs an obstacle safety evaluation model, acquires obstacle hardness, shape smoothing coefficient and speed information based on obstacle point clouds and image features, introduces the obstacle hardness, shape smoothing coefficient and speed information into the obstacle safety evaluation model to evaluate the collision safety degree of the obstacle, constructs an unmanned aerial vehicle collision adjustment model, introduces the interference and obstacle safety score of the unmanned aerial vehicle into the model to evaluate a safe contact angle and adjustment speed, and the safety and reliability of the unmanned aerial vehicle are improved.

Description

Technical Field

[0001] This application belongs to the field of unmanned aerial vehicle (UAV) flight control technology, specifically a UAV trajectory control method and system based on big data. Background Technology

[0002] In recent years, drones have been widely used in aerial surveying, inspection and other fields. With the increasing complexity of application scenarios, the environmental factors and safety risks faced by drones during flight have increased significantly. In particular, under complex conditions such as dynamic obstacles, wind disturbances, and signal interference, traditional obstacle avoidance and control algorithms are insufficient to ensure flight safety.

[0003] In existing technologies, drone obstacle avoidance and path planning mainly rely on visual sensors, lidar, or ultrasonic sensors to acquire information about the surrounding environment, and then combine this with preset obstacle avoidance algorithms for path correction. These technologies typically determine distance based on geometric spatial relationships and only trigger avoidance actions when obstacles are close. However, in situations with wind disturbances, GNSS (Global Navigation Satellite System) signal interference, or dynamic obstacle movement, some collisions are unavoidable. In cases where collisions are unavoidable, traditional systems usually directly trigger emergency shutdown or crashes, failing to dynamically adjust attitude, contact angle, and velocity according to obstacle characteristics to reduce collision energy and damage.

[0004] This application enables a comprehensive quantitative assessment of the flight status, environmental interference, and obstacle risks of UAVs in complex environments, and achieves energy buffering control for unavoidable collisions through intelligent attitude and speed adjustment, thereby improving the safety and reliability of UAVs. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this application proposes a big data-based method for unmanned aerial vehicle (UAV) trajectory control.

[0006] To achieve the above objectives, this application provides the following technical solution:

[0007] The method and system for drone trajectory control based on big data includes the following specific steps:

[0008] Based on flight trajectory planning and sensor data, real-time flight data and obstacle information of the UAV are obtained, and the real-time flight status is compared with the planned flight status to evaluate flight deviation;

[0009] An interference assessment model was constructed, and environmental wind speed, signal strength, and flight deviation were imported into the interference assessment model to evaluate the degree of interference to the UAV.

[0010] An obstacle safety assessment model is constructed. Based on obstacle point cloud and image features, obstacle hardness, shape smoothness coefficient and velocity information are obtained. The obstacle hardness, shape smoothness coefficient and velocity information are then imported into the obstacle safety assessment model to assess the collision safety level of the obstacle.

[0011] A collision adjustment model for drones is constructed, and the interference and obstacle safety scores of the drones are imported into the model to evaluate the safe contact angle and adjustment speed.

[0012] Preferably, the step of acquiring real-time flight data and obstacle information of the UAV based on flight trajectory planning and sensor data, and comparing the real-time flight status with the planned flight status to evaluate flight deviation includes the following specific steps:

[0013] S11. Obtain the planned flight trajectory of the UAV, including spatial position sequence, flight speed, attitude angles (pitch angle, roll angle, yaw angle) and altitude planning;

[0014] S12. Obtain the three-dimensional point cloud and parameters of obstacles in the flight path through visual sensors and lidar, including obstacle shape, size, distance and height, for preliminary classification and obstacle contour recognition. Obtain the UAV's own attitude, speed and acceleration data through the inertial measurement unit, and at the same time obtain the ambient wind speed during the UAV's flight.

[0015] S13. During trajectory execution, the real-time flight status is compared and analyzed with the planned flight status to evaluate flight deviations, and the position deviation, attitude deviation and speed deviation are calculated. The position deviation is the difference between the horizontal and vertical distances between the current position of the UAV and the trajectory planning point. The attitude deviation is the deviation between the current roll angle, pitch angle and yaw angle of the UAV and the trajectory planning attitude angle. The speed deviation is the difference between the instantaneous speed of the UAV and the trajectory planning speed.

[0016] Preferably, the construction of the interference assessment model, which incorporates environmental wind speed, signal strength, and flight deviation into the interference assessment model to evaluate the degree of interference to the UAV, includes the following specific steps:

[0017] S21. Substitute the ambient wind speed during the drone's flight into the wind force influence acceleration evaluation formula to calculate the acceleration of the drone caused by the wind force. The wind force influence acceleration evaluation formula is as follows: Where m is the mass of the UAV and D is the drag coefficient. Let A be the air density and A be the windward area of ​​the drone. The relative wind speed of the drone is the difference between the wind speed and the wind speed of the drone.

[0018] S22. Substitute the GNSS signal strength into the signal interference assessment formula to evaluate the signal interference on the UAV. The signal interference assessment formula is as follows: ,in, The current GNSS signal strength, The signal strength is normal, and k is the signal interference influence coefficient. When the signal strength decreases, the signal interference increases, indicating that the signal interference is stronger.

[0019] S23. Substitute the effects of wind on acceleration and signal interference into the comprehensive interference assessment formula to evaluate the interference experienced by the UAV. The comprehensive interference assessment formula is as follows: ,in, These are the position deviation, attitude deviation, and velocity deviation during flight. The maximum wind disturbance acceleration that the drone can withstand. As the weight for wind disturbance acceleration, The signal interference weight is the overall interference. The greater the overall interference, the stronger the interference to the drone, the more serious the deviation from the trajectory, and the higher the risk level.

[0020] Preferably, the construction of the obstacle safety assessment model, based on obstacle point cloud and image features, to obtain obstacle hardness, shape smoothness coefficient, and velocity information, and to import the obstacle hardness, shape smoothness coefficient, and velocity information into the obstacle safety assessment model to assess the collision safety level of the obstacle, includes the following specific steps:

[0021] S31. Construct an obstacle hardness database and map obstacle materials to hardness scores, where the obstacle hardness score H∈[0,1], 0 represents extremely soft and 1 represents extremely hard. Use a camera to acquire obstacle images, perform color, texture and shape feature analysis on the images, determine the material type, and compare it with the obstacle hardness database to obtain the obstacle hardness.

[0022] S32. Obtain the obstacle point cloud set, use the convex hull algorithm to obtain the convex hull patch set, select a vertex on the patch as a reference point, calculate the vector difference with other vertices respectively, for polygonal patches, divide the polygon into several triangles, determine the plane of each triangle one by one, determine the position and direction of the patch plane through two edge vectors, according to the determined plane, use vector operation to obtain the direction perpendicular to the plane, obtain the plane normal vector through cross product, and normalize the plane normal vector, calculate the angle between the normal vectors of each pair of adjacent convex hull patches, and calculate the average angle change rate of the obstacle, normalize the average angle change rate to the shape smoothing coefficient through the exponential function;

[0023] S33. For dynamic obstacles, the velocity of the dynamic obstacle is calculated through the position change of consecutive frames. For static obstacles, the velocity is 0. The obstacle's hardness, shape smoothness coefficient, and velocity are substituted into the obstacle safety scoring formula to evaluate the obstacle's collision safety level. The obstacle safety scoring formula is as follows: Where H is the obstacle hardness and S is the obstacle shape smoothness coefficient. For the flight speed of the drone, The speed of the obstacle's movement. The maximum flight speed of the drone, The speed of the drone relative to the obstacle. The distance between the obstacle and the drone's current deviation from its direction. For reference distance, and The weights are set according to the drone mission and design requirements.

[0024] Preferably, the construction of the UAV collision adjustment model, which imports the interference experienced by the UAV and the obstacle safety score into the model to evaluate the safe contact angle and adjustment speed, includes the following specific steps:

[0025] S41. Compare the comprehensive interference assessment value with the high-risk collision threshold. If the high-risk collision threshold is exceeded, obstacle avoidance is no longer feasible. Scan obstacles around the trajectory in real time, calculate the safety index of each obstacle, select the obstacle with the highest comprehensive score as the buffer collision target, and adjust the drone's attitude and speed to minimize the collision energy.

[0026] S42. Substitute the obstacle shape smoothness coefficient and buffer coefficient into the safe contact angle calculation formula to calculate the contact angle with the minimum collision risk. The safe contact angle calculation formula is as follows: ,in, The maximum permissible tilt angle for the drone. To ensure the minimum permissible tilt angle for the drone, a slight preparatory movement is required. The smaller the value, the higher the obstacle buffering capacity, allowing for a smaller tilt angle. By adjusting the drone's pitch and roll angles, the key components of the aircraft can be oriented away from obstacles, reducing direct impact.

[0027] S43. Substitute the combined interference into the speed adjustment formula to adjust the collision speed. The speed adjustment formula is as follows: ,in, This is a speed adjustment coefficient; the speed decreases as the disturbance increases, thereby reducing the collision kinetic energy.

[0028] The big data-based UAV trajectory control system is implemented based on the aforementioned big data-based UAV trajectory control method, and specifically includes:

[0029] The data acquisition module is used to acquire real-time flight data and obstacle information of the UAV through flight trajectory planning and sensor data, and compare the real-time flight status with the planned flight status to evaluate flight deviation;

[0030] The interference assessment module is used to assess the degree of interference to the UAV based on ambient wind speed, signal strength, and flight deviation.

[0031] The obstacle safety assessment module is used to obtain obstacle hardness, shape smoothness coefficient and velocity information through obstacle point cloud and image features, and to assess the collision safety level of the obstacle through obstacle hardness, shape smoothness coefficient and velocity information;

[0032] The drone collision adjustment module is used to assess the safe contact angle and adjust the speed based on the interference and obstacle safety scores encountered by the drone.

[0033] An electronic device includes: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0034] The processor executes the above-mentioned big data-based drone trajectory control method by calling the computer program stored in the memory.

[0035] A computer-readable storage medium is characterized by storing instructions that, when executed on a computer, cause the computer to perform the aforementioned big data-based drone trajectory control method.

[0036] Compared with the prior art, the beneficial effects of this application are:

[0037] This application acquires real-time flight data and obstacle information of UAVs based on flight trajectory planning and sensor data. It compares the real-time flight state with the planned flight state to evaluate flight deviations, constructs an interference assessment model, and imports environmental wind speed, signal strength, and flight deviation into the interference assessment model to evaluate the degree of interference to the UAV. It also constructs an obstacle safety assessment model, and acquires obstacle hardness, shape smoothness coefficient, and speed information based on obstacle point cloud and image features. It imports the obstacle hardness, shape smoothness coefficient, and speed information into the obstacle safety assessment model to evaluate the collision safety level of obstacles. Finally, it constructs a UAV collision adjustment model, and imports the interference experienced by the UAV and obstacle safety scores into the model to evaluate the safe contact angle and adjustment speed, thereby improving the safety and reliability of the UAV. Attached Figure Description

[0038] Figure 1 This is a schematic diagram of the overall process of the UAV trajectory control method based on big data in this application;

[0039] Figure 2This is a collision assessment diagram for the drone in this application;

[0040] Figure 3 This is a flowchart illustrating the calculation of the safe contact angle for this application;

[0041] Figure 4 This is a schematic diagram of the overall framework of the UAV trajectory control system based on big data in this application. Detailed Implementation

[0042] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0043] Example 1

[0044] Please see Figure 1 - Figure 3 This application provides an embodiment of a drone trajectory control method based on big data, which includes the following specific steps:

[0045] Based on flight trajectory planning and sensor data, real-time flight data and obstacle information of the UAV are obtained, and the real-time flight status is compared with the planned flight status to evaluate flight deviation;

[0046] An interference assessment model was constructed, and environmental wind speed, signal strength, and flight deviation were imported into the interference assessment model to evaluate the degree of interference to the UAV.

[0047] An obstacle safety assessment model is constructed. Based on obstacle point cloud and image features, obstacle hardness, shape smoothness coefficient and velocity information are obtained. The obstacle hardness, shape smoothness coefficient and velocity information are then imported into the obstacle safety assessment model to assess the collision safety level of the obstacle.

[0048] A collision adjustment model for drones is constructed, and the interference and obstacle safety scores of the drones are imported into the model to evaluate the safe contact angle and adjustment speed.

[0049] In this embodiment, it is necessary to specifically explain that the process of acquiring real-time flight data and obstacle information of the UAV based on flight trajectory planning and sensor data, and comparing the real-time flight status with the planned flight status to evaluate flight deviation includes the following specific steps:

[0050] S11. Obtain the planned flight trajectory of the UAV, including spatial position sequence, flight speed, attitude angles (pitch angle, roll angle, yaw angle) and altitude planning;

[0051] S12. Obtain the three-dimensional point cloud and parameters of obstacles in the flight path through visual sensors and lidar, including obstacle shape, size, distance and height, for preliminary classification and obstacle contour recognition. Obtain the UAV's own attitude, speed and acceleration data through the inertial measurement unit for data correction and obstacle motion evaluation. At the same time, obtain the ambient wind speed during the UAV's flight.

[0052] S13. During trajectory execution, the real-time flight status is compared and analyzed with the planned flight status to evaluate flight deviations, and the position deviation, attitude deviation, and velocity deviation are calculated. The position deviation is the difference between the horizontal and vertical distances between the current position of the UAV and the trajectory planning point. The attitude deviation is the deviation between the current roll angle, pitch angle, and yaw angle of the UAV and the trajectory planning attitude angle. The velocity deviation is the difference between the instantaneous velocity of the UAV and the trajectory planning velocity. The deviations are used to measure the impact of interference on flight.

[0053] In this embodiment, it is necessary to specifically explain that constructing an interference assessment model and incorporating environmental wind speed, signal strength, and flight deviation into the model to assess the degree of interference to the UAV includes the following specific steps:

[0054] S21. Substitute the ambient wind speed during the drone's flight into the wind force influence acceleration evaluation formula to calculate the acceleration of the drone caused by the wind force. The wind force influence acceleration evaluation formula is as follows: Where m is the mass of the UAV and D is the drag coefficient, obtained through experiments and simulations. Let A be the air density and A be the windward area of ​​the drone. The relative wind speed of the drone is the difference between the wind speed and the drone's wind speed. The formula for evaluating the wind force's impact on acceleration is a variation of the classic aerodynamic drag formula, used to evaluate the instantaneous force of wind on the drone.

[0055] S22. Substitute the GNSS signal strength into the signal interference assessment formula to evaluate the signal interference on the UAV. The signal interference assessment formula is as follows: ,in, The current GNSS signal strength, The signal strength is normal, and k is the signal interference influence coefficient. When the signal strength decreases, the signal interference increases, indicating that the signal interference is stronger.

[0056] S23. Substitute the effects of wind on acceleration and signal interference into the comprehensive interference assessment formula to evaluate the interference experienced by the UAV. The comprehensive interference assessment formula is as follows: ,in, These are the position deviation, attitude deviation, and velocity deviation during flight. The maximum wind disturbance acceleration that the drone can withstand. As the weight for wind disturbance acceleration, As a signal interference weight, the greater the overall interference, the stronger the interference to the drone, the more serious the deviation from the trajectory, and the higher the risk level. Wind disturbance and signal interference are quantified into acceleration and signal strength indicators, and the spatial, attitude and speed deviations of the drone from the trajectory are integrated into a unified deviation amount to comprehensively assess the interference situation.

[0057] In this embodiment, it is necessary to specifically explain that constructing an obstacle safety assessment model, based on obstacle point cloud and image features, to obtain obstacle hardness, shape smoothness coefficient, and velocity information, and importing the obstacle hardness, shape smoothness coefficient, and velocity information into the obstacle safety assessment model to assess the collision safety level of the obstacle, includes the following specific steps:

[0058] S31. Construct an obstacle hardness database and map obstacle materials to hardness scores, where the obstacle hardness score H∈[0,1], 0 represents extremely soft and 1 represents extremely hard. Use a camera to acquire obstacle images, perform color, texture and shape feature analysis on the images, determine the material type, and compare it with the obstacle hardness database to obtain the obstacle hardness.

[0059] S32. Obtain the obstacle point cloud set, use the convex hull algorithm to obtain the convex hull patch set, select a vertex on the patch as a reference point, calculate the vector difference with other vertices respectively, for polygonal patches, divide the polygon into several triangles, determine the plane of each triangle one by one, determine the position and direction of the patch plane through two edge vectors, according to the determined plane, use vector operation to obtain the direction perpendicular to the plane, obtain the plane normal vector through cross product, and normalize the plane normal vector, calculate the angle between the normal vectors of each pair of adjacent convex hull patches, and calculate the average angle change rate of the obstacle, normalize the average angle change rate to the shape smoothing coefficient through the exponential function;

[0060] S33. For dynamic obstacles, the velocity of the dynamic obstacle is calculated through the position change of consecutive frames. For static obstacles, the velocity is 0. The obstacle's hardness, shape smoothness coefficient, and velocity are substituted into the obstacle safety scoring formula to evaluate the obstacle's collision safety level. The obstacle safety scoring formula is as follows: Where H is the obstacle hardness and S is the obstacle shape smoothness coefficient. For the flight speed of the drone, The speed of the obstacle's movement. The maximum flight speed of the drone, The speed of the drone relative to the obstacle. The distance between the obstacle and the drone's current deviation from its direction. For reference distance, and The weights are set according to the drone mission and design requirements.

[0061] In this embodiment, it is necessary to specifically explain that constructing a drone collision adjustment model and importing the interference experienced by the drone and the obstacle safety score into the model to evaluate the safe contact angle and adjustment speed includes the following specific steps:

[0062] S41. Compare the comprehensive interference assessment value with the high-risk collision threshold. If the high-risk collision threshold is exceeded, obstacle avoidance is no longer feasible. Scan obstacles around the trajectory in real time, calculate the safety index of each obstacle, select the obstacle with the highest comprehensive score as the buffer collision target, and adjust the drone's attitude and speed to minimize the collision energy.

[0063] S42. Substitute the obstacle shape smoothness coefficient and buffer coefficient into the safe contact angle calculation formula to calculate the contact angle with the minimum collision risk. The safe contact angle calculation formula is as follows: ,in, The maximum permissible tilt angle for the drone. To ensure the minimum permissible tilt angle for the drone, a slight preparatory movement is required. The smaller the value, the higher the obstacle buffering capacity, allowing for a smaller tilt angle. By adjusting the pitch and roll angles of the drone, the key components of the aircraft are directed away from the obstacle, reducing direct impact. By controlling the contact angle, the drone tilts as much as possible to avoid contact with hard and sharp obstacles, minimizing the impact area of ​​the drone, reducing the transfer of kinetic energy to the core components, protecting the core components, and reducing collision damage.

[0064] S43. Substitute the combined interference into the speed adjustment formula to adjust the collision speed. The speed adjustment formula is as follows: ,in, This is a speed adjustment coefficient; the speed decreases as the disturbance increases, thereby reducing the collision kinetic energy.

[0065] It should be noted that the values ​​of various setting parameters in this embodiment are obtained as follows: acquire representative historical flight data of drones during flight, acquire historical drone collision data, hire experts to manually judge the degree of drone collision, and substitute the acquired historical data into the calculation results and judgment results of each step in this embodiment, and then substitute them into the fitting software to output the values ​​of various setting parameters that meet the highest judgment accuracy.

[0066] The advantages of this embodiment compared to the prior art are:

[0067] This application acquires real-time flight data and obstacle information of UAVs based on flight trajectory planning and sensor data. It compares the real-time flight state with the planned flight state to evaluate flight deviations, constructs an interference assessment model, and imports environmental wind speed, signal strength, and flight deviation into the interference assessment model to evaluate the degree of interference to the UAV. It also constructs an obstacle safety assessment model, and acquires obstacle hardness, shape smoothness coefficient, and speed information based on obstacle point cloud and image features. It imports the obstacle hardness, shape smoothness coefficient, and speed information into the obstacle safety assessment model to evaluate the collision safety level of obstacles. Finally, it constructs a UAV collision adjustment model, and imports the interference experienced by the UAV and obstacle safety scores into the model to evaluate the safe contact angle and adjustment speed, thereby improving the safety and reliability of the UAV.

[0068] Example 2

[0069] like Figure 4 As shown, the UAV trajectory control system based on big data is implemented based on the aforementioned UAV trajectory control method based on big data. Specifically, it includes a data acquisition module, an interference assessment module, an obstacle safety assessment module, and a UAV collision adjustment module. The data acquisition module acquires real-time flight data and obstacle information of the UAV through flight trajectory planning and sensor data, and compares the real-time flight state with the planned flight state to assess flight deviation. The interference assessment module assesses the degree of interference experienced by the UAV based on environmental wind speed, signal strength, and flight deviation. The obstacle safety assessment module acquires obstacle hardness, shape smoothness coefficient, and speed information through obstacle point clouds and image features, and assesses the collision safety level of obstacles based on these parameters. The UAV collision adjustment module assesses the safe contact angle and adjusts the speed based on the interference experienced by the UAV and the obstacle safety score.

[0070] Example 3

[0071] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0072] The processor executes the aforementioned big data-based drone trajectory control method by calling computer programs stored in memory.

[0073] The electronic device can vary considerably depending on its configuration or performance. It may include one or more Central Processing Units (CPUs) and one or more memories, wherein the memory stores at least one computer program, which is loaded and executed by the processor to implement the big data-based UAV trajectory control method provided in the above-described embodiment of the big data-based UAV trajectory control method. The electronic device may also include other components for implementing its functions; for example, it may have wired or wireless network interfaces and input / output interfaces for data input and output. Details will not be elaborated upon in this embodiment.

[0074] Example 4

[0075] This embodiment proposes a computer-readable storage medium on which an erasable and rewritable computer program is stored.

[0076] When the computer program runs on the computer device, it causes the computer device to execute the above-mentioned drone trajectory control method based on big data.

[0077] For example, computer-readable storage media can be read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CD-ROM), magnetic tape, floppy disk, and optical data storage devices.

[0078] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. A computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions according to the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. Computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired network and / or wireless network. A computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. Available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media can be solid-state drives (SSDs).

Claims

1. A drone trajectory control method based on big data, characterized in that, It includes the following specific steps: Based on flight trajectory planning and sensor data, real-time flight data and obstacle information of UAVs are acquired, and the real-time flight status is compared with the planned flight status to evaluate flight deviation; An interference assessment model was constructed, and environmental wind speed, signal strength, and flight deviation were imported into the interference assessment model to evaluate the degree of interference to the UAV. An obstacle safety assessment model is constructed. Based on obstacle point cloud and image features, obstacle hardness, shape smoothness coefficient and velocity information are obtained. The obstacle hardness, shape smoothness coefficient and velocity information are then imported into the obstacle safety assessment model to assess the collision safety level of the obstacle. A drone collision adjustment model is constructed, incorporating the interference experienced by the drone and obstacle safety scores into the model to evaluate the safe contact angle and adjustment speed. The specific steps include: comparing the comprehensive interference assessment value with a high-risk collision threshold; if the threshold is exceeded, obstacle avoidance is no longer feasible; real-time scanning of obstacles around the trajectory; calculating the safety index of each obstacle; selecting the obstacle with the highest comprehensive score as the buffer collision target; adjusting the drone's attitude and speed to minimize collision energy; and substituting the obstacle shape smoothness coefficient and buffer coefficient into the safe contact angle calculation formula to calculate the contact angle with the lowest collision risk. The safe contact angle calculation formula is as follows: ,in, The maximum permissible tilt angle for the drone. Let R be the minimum permissible tilt angle for the drone, and R be the obstacle safety score. The collision speed is adjusted by substituting the comprehensive interference into the speed adjustment formula, where the speed adjustment formula is: ,in, For speed adjustment coefficient, For the flight speed of the drone, This is the comprehensive interference assessment value.

2. The UAV trajectory control method based on big data as described in claim 1, characterized in that, The process of acquiring real-time flight data and obstacle information of the UAV based on flight trajectory planning and sensor data, and comparing the real-time flight status with the planned flight status to evaluate flight deviation includes the following specific steps: S11. Obtain the planned flight trajectory of the UAV, including spatial position sequence, flight speed, attitude angle and altitude planning; S12. Obtain the three-dimensional point cloud and parameters of obstacles in the flight path through visual sensors and lidar, including the shape, size, distance and height of the obstacles; obtain the attitude, speed and acceleration data of the UAV itself through the inertial measurement unit; and obtain the ambient wind speed during the flight of the UAV. S13. During trajectory execution, the real-time flight status is compared and analyzed with the planned flight status to evaluate flight deviations, and the position deviation, attitude deviation and speed deviation are calculated. The position deviation is the difference between the horizontal and vertical distances between the current position of the UAV and the trajectory planning point. The attitude deviation is the deviation between the current roll angle, pitch angle and yaw angle of the UAV and the trajectory planning attitude angle. The speed deviation is the difference between the instantaneous speed of the UAV and the trajectory planning speed.

3. The UAV trajectory control method based on big data as described in claim 2, characterized in that, The construction of the interference assessment model, which incorporates environmental wind speed, signal strength, and flight deviation to evaluate the degree of interference to the UAV, includes the following specific steps: S21. Substitute the ambient wind speed during the drone's flight into the wind force influence acceleration evaluation formula to calculate the acceleration of the drone caused by the wind force. The wind force influence acceleration evaluation formula is as follows: Where m is the mass of the UAV and D is the drag coefficient. Let A be the air density and A be the windward area of ​​the drone. The relative wind speed of the drone; S22. Substitute the GNSS signal strength into the signal interference assessment formula to evaluate the signal interference on the UAV. The signal interference assessment formula is as follows: ,in, The current GNSS signal strength, The signal strength is normal, and k is the signal interference coefficient. S23. Substitute the effects of wind on acceleration and signal interference into the comprehensive interference assessment formula to evaluate the interference experienced by the UAV. The comprehensive interference assessment formula is as follows: ,in, Let i represent the position deviation, attitude deviation, and velocity deviation during flight, respectively. The deviation weights are the values ​​corresponding to different values ​​of i. This is the maximum wind disturbance acceleration that the drone can withstand. As the weight for wind disturbance acceleration, This represents the signal interference weight.

4. The UAV trajectory control method based on big data as described in claim 3, characterized in that, The construction of the obstacle safety assessment model, based on obstacle point cloud and image features, obtains obstacle hardness, shape smoothness coefficient, and velocity information. Importing this information into the obstacle safety assessment model to evaluate the collision safety level of the obstacle includes the following specific steps: S31. Construct an obstacle hardness database, map obstacle materials to hardness scores, use a camera to acquire obstacle images, perform color, texture, and shape feature analysis on the images, determine the material type, and compare it with the obstacle hardness database to obtain the obstacle hardness. S32. Obtain the obstacle point cloud set, use the convex hull algorithm to obtain the convex hull patch set, select a vertex on the patch as a reference point, calculate the vector difference with other vertices respectively, for polygonal patches, divide the polygon into several triangles, determine the plane of each triangle one by one, determine the position and direction of the patch plane through two edge vectors, according to the determined plane, use vector operation to obtain the direction perpendicular to the plane, obtain the plane normal vector through cross product, and normalize the plane normal vector, calculate the angle between the normal vectors of each pair of adjacent convex hull patches, and calculate the average angle change rate of the obstacle, normalize the average angle change rate to the shape smoothing coefficient through the exponential function; S33. For dynamic obstacles, the velocity of the dynamic obstacle is calculated through the position change of consecutive frames. For static obstacles, the velocity is 0. The obstacle's hardness, shape smoothness coefficient, and velocity are substituted into the obstacle safety scoring formula to evaluate the obstacle's collision safety level. The obstacle safety scoring formula is as follows: Where H is the obstacle hardness and S is the obstacle shape smoothness coefficient. For the flight speed of the drone, The speed of the obstacle's movement. The maximum flight speed of the drone, The speed of the drone relative to the obstacle. The distance between the obstacle and the drone's current deviation from its direction. For reference distance, , and For weights.

5. A big data-based UAV trajectory control system, implemented based on the big data-based UAV trajectory control method as described in any one of claims 1-4, characterized in that, Specifically, it includes: The data acquisition module is used to acquire real-time flight data and obstacle information of the UAV through flight trajectory planning and sensor data, and compare the real-time flight status with the planned flight status to evaluate flight deviation; The interference assessment module is used to assess the degree of interference to the UAV based on ambient wind speed, signal strength, and flight deviation. The obstacle safety assessment module is used to obtain obstacle hardness, shape smoothness coefficient and velocity information through obstacle point cloud and image features, and to assess the collision safety level of the obstacle through obstacle hardness, shape smoothness coefficient and velocity information; The drone collision adjustment module is used to assess the safe contact angle and adjust the speed based on the interference and obstacle safety scores encountered by the drone.

6. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; The processor is characterized in that it executes the big data-based drone trajectory control method as described in any one of claims 1-4 by calling a computer program stored in the memory.

7. A computer-readable storage medium, characterized in that, The system stores instructions that, when executed on a computer, cause the computer to perform the big data-based drone trajectory control method as described in any one of claims 1-4.

Images