Unmanned aerial vehicle flight path reconstruction method and system based on big data

Abstract

The invention relates to the field of unmanned aerial vehicle flight control, in particular to an unmanned aerial vehicle flight path reconstruction method and system based on big data, and the method comprises the steps: obtaining the flight state data of an unmanned aerial vehicle and the three-dimensional modeling of the surrounding environment to recognize the position of an obstacle point; constructing a local environment area by taking the current position of the unmanned aerial vehicle as a center, screening out to-be-selected nodes meeting conditions, and calculating the comprehensive priority of each to-be-selected node by using an evaluation function of an A * algorithm; the method comprises the following steps: calculating an estimated influence degree by analyzing a tortuosity degree of a past path of an unmanned aerial vehicle and a stability degree of a current flight state, adjusting a comprehensive priority of a to-be-selected node based on the estimated influence degree, and performing trajectory reconstruction by using an A * algorithm according to the adjusted comprehensive priority. By analyzing the flight stability and path tortuosity of the unmanned aerial vehicle, the path planning is dynamically adjusted, the collision risk is reduced, and the flight safety is improved.

Description

Technical Field

[0001] The present invention relates to the field of unmanned aerial vehicle flight control, and in particular to a method and system for reconstructing the flight trajectory of an unmanned aerial vehicle based on big data. Background Art

[0002] A drone is a device that can fly autonomously in the air. It carries various sensors and actuators to complete specific tasks. Drones are small in size, light in weight, flexible in operation, and low in cost, making them widely used in many fields. The flight control system of a drone is its core part. It controls the flight status of the drone by receiving sensor data and executing instructions.

[0003] Drone flight plays a vital role in the field of modern science and technology. It is widely used in many fields such as agricultural monitoring, power inspection, security monitoring, logistics distribution, etc. The flexibility and efficiency of drones enable them to perform tasks in complex environments without relying on manpower, greatly improving work efficiency and safety. The autonomous flight capability of drones and their ability to respond to emergencies make them an indispensable part of modern technology. In the agricultural field, drones can be used for farmland monitoring to help farmers better manage their crops; in the logistics field, drones can quickly deliver goods and improve efficiency; in the security field, drones can conduct patrol monitoring to ensure safety.

[0004] However, traditional path planning methods, such as the A algorithm, have certain limitations in practical applications. The A algorithm mainly focuses on the static distance between nodes, but does not adequately consider the actual flight status of the UAV (such as speed, acceleration, and attitude angle). In addition, in complex and dynamic environments, path planning based solely on whether there are obstacles at the nodes may not be able to adequately respond to emergencies, thereby increasing flight risks. Therefore, in order to improve the flight safety and reliability of UAVs in complex environments, it is necessary to improve the path planning algorithm so that it can better adapt to the dynamic characteristics of UAVs and environmental changes. Summary of the invention

[0005] In order to solve the problem of how to adjust the path planning of a UAV in real time during flight to cope with environmental changes and uncertainty of flight status, the present invention provides solutions in the following aspects.

[0006] In the first aspect, a method for reconstructing the flight trajectory of a UAV based on big data includes: obtaining the flight status data of the UAV, and performing three-dimensional modeling of the environment around the UAV to obtain the location of obstacle points; constructing a local environmental area with the current position of the UAV as the center, screening out qualified candidate nodes based on the local environmental area, and using the evaluation function of the A* algorithm to calculate the comprehensive priority of each candidate node; obtaining the degree of tortuosity of the control points in the past path of the UAV and the degree of stability of the flight status of the current position of the UAV, taking the ratio between the degree of tortuosity and the degree of stability as the estimated degree of influence, and adjusting the comprehensive priority of the candidate nodes based on the estimated degree of influence, and using the A* algorithm to reconstruct the trajectory according to the adjusted comprehensive priority.

[0007] By acquiring the flight status data of the drone and performing three-dimensional modeling to identify the location of obstacles, the A* algorithm is used to efficiently screen out qualified candidate nodes in the local environment, and the accuracy and optimality of path planning are ensured through the calculation of comprehensive priorities. By analyzing the tortuosity of the past path and the stability of the current flight status, the estimated impact is calculated to adjust the node priority, thereby optimizing the flight trajectory. This not only effectively improves the flight safety of drones in complex environments, but also significantly optimizes the efficiency of path planning, reduces energy consumption, and enhances the system's ability to respond to emergencies, ensuring that drones can complete various tasks stably and reliably.

[0008] Preferably, the flight status data includes: speed data and angle data, the speed data includes: linear velocity, angular velocity and acceleration, and the angle data includes: roll angle, pitch angle and yaw angle.

[0009] Preferably, the step of screening out nodes that meet the conditions to be selected includes: The local environment area includes a preset number of adjacent points around the drone, and the directions of the preset number of adjacent points around the drone are respectively used as ray directions, and the angle between each ray direction and the current flight direction of the drone is calculated; Points with angles less than a preset angle are selected as candidate nodes. Among the candidate nodes, the distance between each candidate node and the current position of the drone is calculated and sorted from small to large. From the sorted distance list, a preset number of candidate nodes closest to the current position of the drone are selected as candidate nodes.

[0010] By screening qualified candidate nodes in the local environment and sorting them according to the distance from the current position of the drone, the nearest preset number of nodes are selected as candidate nodes, thus ensuring the local optimality of path planning. This effectively improves the flight safety and path planning efficiency of drones in complex environments.

[0011] The preferred comprehensive priorities include: Taking the current position of the drone as the target node, the actual flight distance from the starting point to the target node is calculated to obtain the actual cost, and the estimated cost from the target node to the end point is calculated. The actual cost is obtained by calculating the sum of the lengths of the two adjacent flight paths from the starting point to the current position of the drone, and the estimated cost is obtained by calculating the straight-line distance from the end point to the target node based on the Euclidean distance. The sum of the actual cost and the estimated cost is taken as the comprehensive priority of the target node.

[0012] By calculating the actual flight distance of the UAV from the starting point to the current position as the actual cost, and calculating the estimated cost from the target node to the end point based on the Euclidean distance, the sum of the two is used as the comprehensive priority, thereby effectively optimizing the path planning and ensuring the safety and efficiency of the UAV flight.

[0013] Preferably, the stability includes: Obtain flight status data corresponding to a preset number of control points before the current position of the drone, wherein the flight status data includes: speed data and angle data; Taking any speed data as reference speed data, calculate the difference between each reference speed data and the mean of the reference speed data, and take the average value of the sum of standard deviations to get the comprehensive speed fluctuation degree; taking any angle data as reference angle data, use the information entropy function to calculate the information entropy of each reference angle data, and take the average value of the sum to get the comprehensive angle complexity; The sum of 1, the comprehensive speed fluctuation degree and the comprehensive angle complexity is added together, and the inverse of the logarithmic function is taken as the stability of the current drone using a logarithmic function.

[0014] By analyzing the speed and angle data of the drone's past path, the comprehensive speed fluctuation and comprehensive angle complexity are calculated, and then the flight stability of the drone is evaluated. This method effectively improves the flight stability of the drone in complex environments and the reliability of path planning.

[0015] Preferably, the tortuosity includes: The preset nearest control points before the current position of the UAV are obtained by least square fitting to obtain a fitting curve. The first-order, second-order and third-order inverse information is extracted from the fitting curve to calculate the curvature and torsion of each control point. The ratio of the curvature of each control point to the average curvature of the area the UAV has traveled through historically is taken as the relative degree of curvature, and the ratio of the torsion of each control point to the maximum torsion of the area the UAV has traveled through historically is taken as the relative degree of distortion. The sum of the relative degrees of curvature and relative degrees of distortion of all control points is averaged as the overall complexity of all control points. The ratio of the turning angle to the pitch angle of each control point is exponentially decayed using a negative exponential function, and the product of the exponentially decayed ratio and the overall complexity is taken as the degree of tortuosity.

[0016] The control points in the UAV's past path are fitted by least squares to obtain a fitting curve, and the first-order, second-order, and third-order derivative information of the curve is used to calculate the curvature and torsion of each control point. The relative bending and twisting degree is evaluated by comparing with historical data, and combined with the exponential decay processing of the turning angle, the overall tortuosity of the path is finally determined, thereby optimizing the flight trajectory of the UAV and improving its adaptability and flight safety in complex environments.

[0017] Preferably, the turning angle includes: In the initial path, the arccosine function is used to calculate the ratio between the dot product of the vector between two adjacent control points and the product of the modulus lengths of the adjacent vectors to obtain the degree of direction change between the two adjacent control points, which is the turning angle.

[0018] Preferably, the step of adjusting the comprehensive priority of the candidate nodes based on the estimated impact of the drone includes: The comprehensive priority of each node is corrected by multiplying the estimated impact of each node by the obstacle avoidance cost to obtain the adjusted comprehensive priority.

[0019] Preferably, the obstacle avoidance cost includes: The sum of the distance between each node and the nearest obstacle in the three-dimensional modeling and the hyperparameter is taken as the obstacle avoidance cost.

[0020] In a second aspect, a UAV flight trajectory reconstruction system based on big data includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned UAV flight trajectory reconstruction method based on big data is implemented.

[0021] The present invention has the following effects: 1. The present invention can timely detect obstacles and avoid them by acquiring the flight status data of the drone and the three-dimensional modeling of the surrounding environment in real time. At the same time, by analyzing the flight stability and path tortuosity of the drone, the path planning is dynamically adjusted, which reduces the collision risk caused by environmental changes and uncertainty of flight status, and improves the flight safety of the drone.

[0022] 2. The present invention is based on the evaluation function of the A* algorithm and the comprehensive priority adjustment, which can optimize the flight path of the UAV and reduce unnecessary flight distance and energy consumption. Through least squares fitting and curvature and torsion calculation, the smoothness of the path is further optimized, the energy loss during the flight process is reduced, and the flight efficiency is improved.

[0023] 3. The present invention dynamically adjusts the path planning through the flight status of the UAV and environmental changes, enhancing the system's ability to adapt to complex environments and emergencies. Through big data analysis and real-time adjustment, the robustness of the system is improved, ensuring that the UAV can stably and reliably complete flight missions under various complex conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 It is a method flow chart of steps S1 to S3 in a method for reconstructing the flight trajectory of a UAV based on big data in an embodiment of the present invention.

[0025] Figure 2 It is a structural block diagram of a UAV flight trajectory reconstruction system based on big data in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments.

[0027] Reference Figure 1 A method for reconstructing the flight trajectory of a UAV based on big data includes steps S1 to S3, which are as follows: S1: Obtain the flight status data of the drone, perform three-dimensional modeling of the drone's surrounding environment, and obtain the location of the obstacle point.

[0028] Among them, the flight status data includes but is not limited to: the speed data and angle data of the UAV, the speed data includes: linear velocity, angular velocity and acceleration, the angle data includes: roll angle, pitch angle, yaw angle, the preset acquisition frequency is 10Hz, and the Kalman filter is used to fuse IMU, GPS and barometer data to calculate the six-degree-of-freedom posture, speed and acceleration data of the UAV in real time; the dynamic obstacle grid map is constructed through the joint calibration of lidar point cloud and visual SLAM.

[0029] The 3D model of the drone's surroundings is constructed by using sensor data (such as LiDAR point cloud, visual SLAM, etc.). The 3D space is divided into cubes (voxels), each of which represents a node.

[0030] Each node contains the following information: the coordinates of the node in three-dimensional space and whether the node is occupied by an obstacle. It should be noted that the node is the basic unit of path planning, representing the point that the drone may pass through. Through the status information of the node, the drone can understand the layout of the surrounding environment and the distribution of obstacles.

[0031] Taking the current position of the drone as the center, a local range is set to screen out candidate nodes that meet the conditions. These nodes represent the possible positions that the drone may fly to at the next moment. The candidate nodes are selected from the nodes and are candidate points that meet the dynamic constraints of the drone and the obstacle avoidance requirements. The A* algorithm is used to obtain the comprehensive priority of each candidate node, and based on the comprehensive priority, it is determined which candidate node is the control point. The control point is a key point selected from the nodes and is used to define the flight path of the drone.

[0032] It should be noted that in the process of obtaining the control points of the drone flight trajectory by the A* algorithm, the stability of the drone flight state is often ignored. If the drone flight is not stable enough and there is a certain deviation from the preset route, it may collide with the obstacles in the scene and cause danger. Therefore, the smoothness of the flight is judged through the recent flight state of the drone, and the degree of path tortuosity is obtained according to the control points passed by the current drone flight. Based on this, the adaptive calculation of the preference degree of each node is carried out to ensure the safe operation of the drone.

[0033] S2: Construct a local environment area with the current position of the drone as the center, screen out candidate nodes that meet the conditions based on the local environment area, and use the evaluation function of the A* algorithm to calculate the comprehensive priority of each candidate node.

[0034] Screen out candidate nodes that meet the conditions, including: The local environment area contains a preset number of adjacent points around the drone. Respectively, taking the directions of the preset number of adjacent points around as the ray directions, calculate the angle between each ray direction and the current flight direction of the drone. Select the points with an angle less than the preset angle as candidate nodes. Among the candidate nodes, calculate the distance between each candidate node and the current position of the drone, and sort them from small to large. Select the preset number of candidate nodes with the closest distance to the current position of the drone from the sorted distance list as candidate nodes.

[0035] Exemplarily, the local environment area is a cubic block of size, where the cubic block area contains 26 adjacent points (including the center point) around the drone. Respectively, taking the directions of the 26 adjacent points around as the ray directions, according to the maximum pitch angle in the dynamic constraints as , mark the 9 candidate nodes with the angle between the ray direction and the drone flight direction less than and the smallest distance as candidate nodes.

[0036] The comprehensive priority includes: Taking the current position of the drone as the target node, the actual flight distance from the starting point to the target node is calculated to obtain the actual cost, and the estimated cost from the target node to the end point is calculated. The actual cost is obtained by calculating the sum of the lengths of the two adjacent flight paths from the starting point to the current position of the drone, and the estimated cost is obtained by calculating the straight-line distance from the end point to the target node based on the Euclidean distance. The sum of the actual cost and the estimated cost is taken as the comprehensive priority of the target node.

[0037] Specifically, the comprehensive priority satisfies the following relationship: ; In the formula, Representation Node The overall priority of Representation Node The actual cost of the distance from the starting point, Representation Node The estimated cost to reach the destination.

[0038] The estimated cost is the heuristic function of the A* algorithm. The main function of the heuristic function is to provide a cost estimate from the current node to the target node to guide the search process, which can help the algorithm quickly converge to the optimal path and reduce unnecessary searches. The A* algorithm is a well-known technology in the art and will not be described in detail.

[0039] It should be noted that the stability of the flight state during the operation of the drone greatly affects the decision-making of the drone in the process of trajectory reconstruction. Therefore, it is necessary to evaluate the stability of the area where the drone has flown in the recent period of time. The specific steps are as follows: S3: Obtain the degree of tortuosity of the control points in the UAV's past path and the stability of the flight state of the UAV's current position, take the ratio between the degree of tortuosity and the degree of stability as the estimated degree of influence, and adjust the comprehensive priority of the candidate nodes based on the estimated degree of influence. Use the A* algorithm to reconstruct the trajectory according to the adjusted comprehensive priority.

[0040] The stability levels include: Obtain flight status data corresponding to a preset number of control points before the current position of the drone, wherein the flight status data includes: speed data and angle data; Taking any speed data as reference speed data, calculate the difference between each reference speed data and the mean of the reference speed data, and take the average value of the sum of standard deviations to get the comprehensive speed fluctuation degree; taking any angle data as reference angle data, use the information entropy function to calculate the information entropy of each reference angle data, and take the average value of the sum to get the comprehensive angle complexity; The sum of 1, the comprehensive speed fluctuation degree and the comprehensive angle complexity is added together, and the inverse of the logarithmic function is taken as the stability of the current drone using a logarithmic function.

[0041] For example, the flight status data of the first 30 control points of the current position of the drone are matched, including the speed data and angle data of the first 30 control points. It should also be noted that when the control points are acquired from the starting point by the A* algorithm, if the number of control points flown before the current position of the drone is less than 30, only the flight status data of the control points flown before the current position of the drone are analyzed.

[0042] Specifically, the stability of the drone satisfies the following relationship: ; In the formula, Indicates the stability of the drone's current operation. Indicates the number of reference data. Indicates The control point Reference speed data, Indicates The average value of the reference speed data, Indicates The standard deviation of the reference speed data, Indicates Reference angle data, Expressed as a natural constant is the logarithmic function of the base, represents the information entropy function.

[0043] That is to say, Indicates the three speed data of the drone ( , corresponding to linear velocity, angular velocity and acceleration respectively). The higher the comprehensive speed fluctuation, the more unstable the UAV’s flight is. Represents the three angle data of the drone ( , corresponding to the pitch angle, roll angle and yaw angle respectively). If the changes of the three attitude angles are very complex (high information entropy), it means that the flight attitude of the drone is unstable. If the changes of the three attitude angles are very simple (low information entropy), it means that the flight attitude of the drone is stable.

[0044] By adding the speed fluctuation and the angle complexity, we get a comprehensive instability. Adding 1 to the denominator in the formula can ensure that the result of the formula is always positive, avoiding negative values ​​or zero, and can more clearly distinguish the degree of stability under different flight conditions.

[0045] In addition, another embodiment further includes: Obtain flight status data corresponding to a preset number of control points before the current position of the drone, wherein the flight status data includes: speed data and angle data; Taking any speed data as reference speed data, respectively calculate the difference between each reference speed data and the mean of the reference speed data, and divide it by the average value of the sum of standard deviations to obtain the comprehensive speed fluctuation degree; taking any angle data as reference angle data, respectively calculate the difference between each reference angle data and the mean of the reference angle data, and divide it by the average value of the sum of standard deviations to obtain the comprehensive angle complexity; The sum of 1, the comprehensive speed fluctuation degree and the comprehensive angle complexity is added together, and the inverse of the logarithmic function is taken as the stability of the current drone using a logarithmic function.

[0046] Specifically, the stability of the drone satisfies the following relationship: ; In the formula, Indicates the stability of the drone's current operation. Indicates the number of reference data. Indicates The control point Reference speed data, Indicates The average value of the reference speed data, Indicates The standard deviation of the reference speed data, Indicates Reference angle data, Expressed as a natural constant is the logarithmic function of the base, represents the information entropy function.

[0047] It should be noted that in addition to judging the stability of the drone based on the reference data in the past period of time, the tortuosity of the path corresponding to the control point in the past period of time should also be judged as the tortuosity of the path at the next moment, and the probability of fluctuations in the drone may be analyzed next.

[0048] The tortuosity levels include: The preset nearest control points before the current position of the UAV are obtained by least square fitting to obtain a fitting curve. The first-order, second-order and third-order inverse information is extracted from the fitting curve to calculate the curvature and torsion of each control point. The ratio of the curvature of each control point to the average curvature of the area the UAV has traveled through historically is taken as the relative degree of curvature, and the ratio of the torsion of each control point to the maximum torsion of the area the UAV has traveled through historically is taken as the relative degree of distortion. The sum of the relative degrees of curvature and relative degrees of distortion of all control points is averaged as the overall complexity of all control points. The ratio of the turning angle to the pitch angle of each control point is exponentially decayed using a negative exponential function, and the product of the exponentially decayed ratio and the overall complexity is taken as the degree of tortuosity.

[0049] That is to say, the preset number of nearest neighbors is 10, that is, to obtain the 10 control points closest to the current drone control point sequence index. It should be noted that the preset number of nearest control points is to fit the flight path, which is convenient for calculating the curvature and torsion of each control point. However, the calculation of the path tortuosity at the next moment is still based on the analysis of the first 30 control points of the current drone position. The maximum pitch angle in the dynamic constraint is , pitch angle As a reference angle, it reflects the dynamic constraints of the drone. This means that the drone can withstand greater changes in pitch angle, so the turning angle has a relatively small impact on flight stability. The turning angle is weighted using a negative exponential function. The larger the turning angle, the smaller the weight, which means the path is more tortuous at that point and has a greater impact on flight stability.

[0050] Specifically, the degree of tortuosity satisfies the following relationship: ; in, Indicates the tortuosity of the drone’s path at the next moment. represents the number of control points, Indicates The curvature of the control points, Indicates The torsion of the control point, Represents the average curvature of the area the drone has traveled through historically, Indicates the maximum torsion of the area the drone has traveled through historically. Indicates The turning angle of the control point, represents the pitch angle in the dynamic constraint, Represented by natural numbers An exponential function with base .

[0051] That is to say, The curvature and torsion at each control point in the past path are used to calculate the tortuosity. The greater the curvature and torsion, the greater the tortuosity of the path. The degree of tortuosity is measured in part by the turning angle of the path control point. The larger the turning angle, the smoother the path is and the smaller the tortuosity is.

[0052] The curvature at the current control point is greater than the historical average curvature, indicating that the path is more curved at this point than the UAV usually encounters. The curvature at the current control point is equal to the historical average curvature, indicating that the path is as curved at this point as the UAV usually encounters. The curvature at the current control point is less than the historical average curvature, indicating that the path is less curved at this point than the UAV usually encounters.

[0053] The torsion at the current control point is greater than the historical maximum torsion, indicating that the degree of distortion of the path at this point exceeds the maximum distortion encountered in the drone's historical flight. The torsion at the current control point is equal to the historical maximum torsion, indicating that the degree of distortion of the path at this point is equivalent to the maximum distortion encountered in the drone's historical flight. The torsion at the current control point is less than the historical maximum torsion, indicating that the degree of distortion of the path at this point is less than the maximum distortion encountered in the drone's historical flight.

[0054] It should be noted that the calculation of the curvature and torsion of the control point is a well-known technique to those skilled in the art and will not be described in detail.

[0055] Turning angles include: In the initial path, the arccosine function is used to calculate the ratio between the dot product of the vector between two adjacent control points and the product of the modulus lengths of the adjacent vectors to obtain the degree of direction change between the two adjacent control points, which is the turning angle.

[0056] Specifically, the turning angle satisfies the following relationship: ; In the formula, Indicates The turning angle of the control point, represents the arccosine function, Indicates A vector of control points, Indicates A vector of control points, Represents the magnitude of a vector.

[0057] That is to say, Indicates the degree of change in the direction of the path between two adjacent control points. The larger the turning angle, the more tortuous the path is at the control point. The vector dot product result reflects the similarity between the two vectors.

[0058] The sum of the distance between each node and the nearest obstacle in the three-dimensional modeling and the hyperparameter is taken as the obstacle avoidance cost.

[0059] Specifically, the obstacle avoidance cost satisfies the following relationship: ; In the formula, Representation Node The obstacle avoidance cost, Representation Node The distance to the nearest obstacle, represents a hyperparameter.

[0060] For example, , to prevent the denominator from being zero.

[0061] The comprehensive priority of each node is corrected by multiplying the estimated impact of each node by the obstacle avoidance cost to obtain the adjusted comprehensive priority.

[0062] Specifically, the adjusted comprehensive priority satisfies the following relationship: ; In the formula, Represents the adjusted node The overall priority of Representation Node The overall priority of Indicates the estimated impact, Representation Node obstacle avoidance cost.

[0063] The present invention also provides a UAV flight trajectory reconstruction system based on big data. Figure 2 As shown, the system includes a processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for reconstructing the flight trajectory of a UAV based on big data according to the first aspect of the present invention is implemented. The system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, whose settings and functions are known in the art, and therefore will not be described in detail here.

[0064] It should be noted that, for those skilled in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these modifications and improvements all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for reconstructing UAV flight trajectory based on big data, characterized in that: include: Obtain the flight status data of the drone, perform 3D modeling of the drone's surroundings, and obtain the location of obstacles; A local environment area is constructed with the current position of the drone as the center. Based on the local environment area, qualified nodes are selected, and the comprehensive priority of each candidate node is calculated using the evaluation function of the A* algorithm. The degree of tortuosity of the control points in the UAV's past path and the stability of the flight state of the UAV's current position are obtained, and the ratio between the degree of tortuosity and the degree of stability is used as the estimated degree of influence. Based on the estimated degree of influence, the comprehensive priority of the candidate nodes is adjusted, and the trajectory is reconstructed using the A* algorithm according to the adjusted comprehensive priority.

2. The method for reconstructing the flight trajectory of an unmanned aerial vehicle based on big data according to claim 1, characterized in that: The flight status data includes: speed data and angle data. The speed data includes: linear velocity, angular velocity and acceleration. The angle data includes: roll angle, pitch angle and yaw angle.

3. The method for reconstructing the flight trajectory of an unmanned aerial vehicle based on big data according to claim 1, characterized in that: The step of screening out nodes to be selected that meet the conditions includes: The local environment area includes a preset number of adjacent points around the drone, and the directions of the preset number of adjacent points around the drone are respectively used as ray directions, and the angle between each ray direction and the current flight direction of the drone is calculated; Points with angles less than a preset angle are selected as candidate nodes. Among the candidate nodes, the distance between each candidate node and the current position of the drone is calculated and sorted from small to large. From the sorted distance list, a preset number of candidate nodes closest to the current position of the drone are selected as candidate nodes.

4. The method for reconstructing the flight trajectory of an unmanned aerial vehicle based on big data according to claim 1, characterized in that: Comprehensive priorities, including: Taking the current position of the drone as the target node, the actual flight distance from the starting point to the target node is calculated to obtain the actual cost, and the estimated cost from the target node to the end point is calculated. The actual cost is obtained by calculating the sum of the lengths of the two adjacent flight paths from the starting point to the current position of the drone, and the estimated cost is obtained by calculating the straight-line distance from the end point to the target node based on the Euclidean distance. The sum of the actual cost and the estimated cost is taken as the comprehensive priority of the target node.

5. The method for reconstructing the flight trajectory of an unmanned aerial vehicle based on big data according to claim 1, characterized in that: The stability levels include: Obtain flight status data corresponding to a preset number of control points before the current position of the drone, wherein the flight status data includes: speed data and angle data; Taking any speed data as reference speed data, calculate the difference between each reference speed data and the mean of the reference speed data, and take the average value of the sum of standard deviations to get the comprehensive speed fluctuation degree; taking any angle data as reference angle data, use the information entropy function to calculate the information entropy of each reference angle data, and take the average value of the sum to get the comprehensive angle complexity; The sum of 1, the comprehensive speed fluctuation degree and the comprehensive angle complexity is added together, and the inverse of the logarithmic function is taken as the stability of the current drone using a logarithmic function.

6. The method for reconstructing the flight trajectory of an unmanned aerial vehicle based on big data according to claim 1, characterized in that: The degree of tortuosity includes: The preset nearest control points before the current position of the UAV are obtained by least square fitting to obtain a fitting curve. The first-order, second-order and third-order inverse information is extracted from the fitting curve to calculate the curvature and torsion of each control point. The ratio of the curvature of each control point to the average curvature of the area the UAV has traveled through historically is taken as the relative degree of curvature, and the ratio of the torsion of each control point to the maximum torsion of the area the UAV has traveled through historically is taken as the relative degree of distortion. The sum of the relative degrees of curvature and relative degrees of distortion of all control points is averaged as the overall complexity of all control points. The ratio of the turning angle to the pitch angle of each control point is exponentially decayed using a negative exponential function, and the product of the exponentially decayed ratio and the overall complexity is taken as the degree of tortuosity.

7. The method for reconstructing the flight trajectory of an unmanned aerial vehicle based on big data according to claim 6, characterized in that: The turning angles include: In the initial path, the arccosine function is used to calculate the ratio between the dot product of the vector between two adjacent control points and the product of the modulus lengths of the adjacent vectors to obtain the degree of direction change between the two adjacent control points, which is the turning angle.

8. The method for reconstructing the flight trajectory of an unmanned aerial vehicle based on big data according to claim 1, characterized in that: The comprehensive priority of the candidate nodes is adjusted based on the estimated impact of the drone, including: The comprehensive priority of each node is corrected by multiplying the estimated impact of each node by the obstacle avoidance cost to obtain the adjusted comprehensive priority.

9. The method for reconstructing the flight trajectory of an unmanned aerial vehicle based on big data according to claim 8, characterized in that: The obstacle avoidance cost includes: The sum of the distance between each node and the nearest obstacle in the three-dimensional modeling and the hyperparameter is taken as the obstacle avoidance cost.

10. A UAV flight trajectory reconstruction system based on big data, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the method for reconstructing the flight trajectory of a UAV based on big data according to any one of claims 1 to 9 is implemented.

Images