Aircraft trajectory prediction and correction method and device, electronic equipment and medium

Abstract

The application relates to the technical field of unmanned aerial vehicles, and discloses an aircraft flight path prediction and correction method and device, an electronic device and a medium. The method comprises the following steps: acquiring a planned flight path of an aircraft and current flight data of the aircraft, wherein the current flight data comprises a current position of the aircraft; processing the flight data based on a motion model to obtain an initial predicted flight path of the aircraft; and correcting the initial predicted flight path based on a relative position relationship between the current position of the aircraft and the planned flight path to obtain a target predicted flight path. Through the method, the accuracy of aircraft flight path prediction can be improved, and low-altitude flight safety can be effectively ensured.

Description

Technical Field

[0001] This application relates to the field of unmanned aerial vehicle control technology, and in particular to a method, device, electronic equipment, and medium for predicting and correcting the trajectory of an aircraft. Background Technology

[0002] With the rapid development of the low-altitude economy and the increasing maturity of related technologies, low-altitude flight activities are gradually increasing in density and frequency, and new application scenarios are constantly emerging. At the same time, low-altitude flight safety issues are becoming increasingly prominent, with frequent safety hazards. Building an efficient and robust safety system has become an urgent need and prerequisite for the industry's development. This safety system encompasses multiple levels, including flight safety, route safety, operational safety, and social safety. At the operational safety level, its core is to analyze the operational safety of aircraft groups within the same low-altitude airspace, coordinate group flight activities, and predict, detect, avoid, and resolve aerial conflicts. Accurate and efficient aircraft trajectory prediction technology is crucial for this, providing support for conflict early warning, risk reduction, and airspace scheduling optimization.

[0003] Relevant trajectory prediction methods can be mainly divided into two categories: physics model-driven prediction and data-driven prediction. Physics model-driven prediction, such as using physical models to characterize the aircraft's motion state and predict its future position, has two main drawbacks. Firstly, it heavily relies on real-time sensor data and is sensitive to data noise; if sensors fail or data errors increase, the confidence level of the prediction results will significantly decrease. Secondly, related technologies do not fully consider the constraints of flight paths and routes, underutilize environmental factors, and overestimate the aircraft's degrees of freedom in its trajectory, leading to generally large medium- and long-term prediction errors. Data-driven prediction, such as using deep learning models like LSTM (Long Short-Term Memory) and Transformer to learn historical trajectory features and build time-series prediction models, suffers from problems such as reliance on large amounts of labeled data for training and limited model generalization ability. Summary of the Invention

[0004] The embodiments of this application aim to at least partially solve one of the technical problems in the related art. To this end, embodiments of this application propose an aircraft trajectory prediction and correction method, apparatus, electronic device, and medium.

[0005] The embodiments of this application provide a method for predicting and correcting an aircraft trajectory. The method includes: acquiring the planned flight path and current flight data of the aircraft, wherein the current flight data includes the current position of the aircraft; processing the flight data based on a motion model to predict an initial predicted trajectory of the aircraft; and correcting the initial predicted trajectory based on the relative positional relationship between the current position of the aircraft and the planned flight path to obtain a target predicted trajectory.

[0006] In some implementations, the current flight data also includes the current acceleration; based on the relative positional relationship between the aircraft's current position and the planned route, the initial predicted trajectory is corrected to obtain the target predicted trajectory, including: matching the initial predicted trajectory and the planned route based on the relative positional relationship between the aircraft's current position and the planned route to obtain trajectory matching mapping data; determining the degree of deviation of the initial predicted trajectory from the planned route based on the trajectory matching mapping data; and correcting the initial predicted trajectory based on the degree of deviation data and / or the current acceleration to obtain the target predicted trajectory.

[0007] In some implementations, based on the relative positional relationship between the aircraft's current position and the planned route, the initial predicted trajectory and the planned route are matched to obtain trajectory matching mapping data. This includes: discretizing the planned route to obtain multiple planned waypoints; using the planned waypoint closest to the aircraft's current position as the starting point of a sliding window based on the relative positional relationship between the aircraft's current position and the planned route; using the distance between the aircraft's current position and the initial predicted trajectory as the length of the sliding window; matching the planned waypoint corresponding to the end point of the sliding window with the initial predicted trajectory to obtain trajectory matching mapping data; and determining the degree of deviation of the initial predicted trajectory from the planned route based on the trajectory matching mapping data, including: obtaining the distance data between the initial predicted trajectory and the planned waypoints based on the trajectory matching mapping data; and determining the degree of deviation based on the distance data.

[0008] In some implementations, the initial predicted trajectory is corrected based on the deviation data and / or the current acceleration to obtain the target predicted trajectory. This includes: determining gravity data based on the established dynamic gravitational field model, according to the deviation data and / or the current acceleration, wherein the dynamic gravitational field model characterizes the correlation between the deviation data and / or the current acceleration and gravity; and correcting the initial predicted trajectory based on the gravity data to obtain the target predicted trajectory.

[0009] In some implementations, the dynamic gravitational field model includes an objective function that characterizes the relationship between gravity, flight path deviation data, current acceleration, and the gravitational coefficient. Based on the established dynamic gravitational field model, gravity data is determined according to the flight path deviation data and / or current acceleration, including: dynamically adjusting the gravity coefficient based on the flight path deviation data and / or current acceleration; obtaining gravity data based on the adjusted gravity coefficient, flight path deviation data, and current acceleration; wherein, when the flight path deviation data is greater than or equal to a first preset threshold, and / or the acceleration data is greater than or equal to a second preset threshold, the gravity coefficient is increased, thereby increasing the gravity data; when the flight path deviation data is less than the first preset threshold, and / or the acceleration data is less than the second preset threshold, the gravity coefficient is decreased, thereby decreasing the gravity data.

[0010] In some implementations, the motion model includes a uniform motion model, and the flight data includes latitude and longitude data, altitude data, flight time data, time step, and three-dimensional flight velocity data. The flight data is processed based on the motion model to predict the initial predicted trajectory of the aircraft. This includes: updating the flight time data based on the time step to obtain real-time updated flight time data; obtaining three-dimensional flight displacement data based on the time step and three-dimensional flight velocity data; updating the latitude and longitude data and altitude data based on the real-time updated flight time data and three-dimensional flight displacement data to obtain updated latitude and longitude data and updated altitude data; and obtaining the initial predicted trajectory of the aircraft based on the updated latitude and longitude data and updated altitude data. Alternatively, the motion model includes a uniformly accelerated motion model, and the flight data includes latitude and longitude data, altitude data, flight time data, and time step. The system analyzes flight data, including time step size, three-dimensional flight velocity data, and three-dimensional motion acceleration data. Based on a motion model, the flight data is processed to predict the initial predicted trajectory of the aircraft. This includes: updating flight time data based on the time step size to obtain updated flight time data; obtaining three-dimensional flight displacement data based on the time step size, three-dimensional flight velocity data, and three-dimensional motion acceleration data; updating latitude, longitude, and altitude data based on the updated flight time data and three-dimensional flight displacement data; updating three-dimensional flight velocity data based on the updated flight time data, time step size, and three-dimensional motion acceleration data to obtain updated three-dimensional flight velocity data; and obtaining the initial predicted trajectory of the aircraft based on the updated latitude, longitude, altitude, and three-dimensional flight velocity data.

[0011] In some implementations, the method further includes: acquiring the actual trajectory of the aircraft; and verifying the target predicted trajectory based on error data between the target predicted trajectory and the actual trajectory.

[0012] The embodiments of this application provide an aircraft trajectory prediction and correction device, the device comprising: an acquisition module for acquiring the planned flight path and current flight data of the aircraft, wherein the current flight data includes the current position of the aircraft; a prediction module for processing the flight data based on a motion model to predict an initial predicted trajectory of the aircraft; and a correction module for correcting the initial predicted trajectory based on the relative positional relationship between the current position of the aircraft and the planned flight path to obtain a target predicted trajectory.

[0013] An embodiment of this application provides an electronic device, which includes: a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by one or more processors, which are executed by one or more processors to cause the one or more processors to implement the steps of the method of any of the above embodiments.

[0014] Embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method of any of the above embodiments.

[0015] The embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the steps of the method according to any of the above embodiments.

[0016] In the embodiments provided in this application, a collaborative architecture of a phased prediction mechanism and a dynamic correction system is proposed. This scheme corrects the predicted trajectory by integrating and utilizing the aircraft's planned route information, taking into account the constraints of environmental factors such as planned routes on the aircraft's trajectory degrees of freedom. This effectively reduces the error between the predicted trajectory and the actual trajectory, and improves the smoothness of the predicted trajectory. Simultaneously, through a dynamic adaptive adjustment mechanism of weight parameters, the motion model can adapt to different flight states, such as steady-state and unsteady-state, thereby improving the trajectory prediction accuracy in various scenarios and ensuring the operational safety of the aircraft flying in low-altitude airspace. Attached Figure Description

[0017] Figure 1 A flowchart illustrating an aircraft trajectory prediction and correction method provided in this application embodiment;

[0018] Figure 2 A schematic diagram of RMSE (Piecework Planned Path) at different prediction times with and without correction, according to an embodiment of this application;

[0019] Figure 3 A schematic diagram of the RMSE (Polylinear Planned Path) of the target predicted track and the actual track at a typical prediction time provided in an embodiment of this application;

[0020] Figure 4A schematic diagram of RMSE (Circular Path Layout) at different prediction times for both uncorrected and corrected paths according to an embodiment of this application;

[0021] Figure 5 A schematic diagram of the RMSE (Circular Path Result) of the target predicted track and the actual track at a typical prediction time provided in an embodiment of this application;

[0022] Figure 6 A schematic flowchart of an aircraft trajectory prediction and correction method provided in an embodiment of this application;

[0023] Figure 7 A schematic diagram of an aircraft trajectory prediction and correction device provided in this application;

[0024] Figure 8 A block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0025] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0026] With the rapid development of the low-altitude economy and the increasing maturity of related technologies, the density and frequency of low-altitude flight activities continue to grow, and new application scenarios are constantly emerging. This has led to increasingly prominent low-altitude flight safety issues and frequent safety hazards, making the construction of an efficient and robust safety system an urgent need and prerequisite for the industry's development.

[0027] This safety system encompasses multiple levels, including flight safety, route safety, operational safety, and social safety. At the operational safety level, its core function is to analyze the operational safety of a group of aircraft within the same low-altitude airspace, coordinate group flight activities, and predict, detect, avoid, and resolve aerial conflicts. Accurate and efficient aircraft trajectory prediction technology is crucial for this, providing support for conflict early warning, risk reduction, and airspace scheduling optimization.

[0028] Relevant trajectory prediction methods can be mainly divided into two categories: prediction based on physical models and prediction based on data. Physical model-driven prediction, such as using models like Constant Velocity (CV) or Constant Acceleration (CA) to characterize the aircraft's motion state and predict its future position, suffers from several drawbacks. Firstly, it heavily relies on real-time sensor data and is sensitive to data noise; if sensors fail or data errors increase, the confidence level of the prediction results will significantly decrease. Secondly, these technologies do not fully consider the constraints of flight paths and routes, underutilize environmental factors, and overestimate the aircraft's degrees of freedom in its trajectory, leading to generally large medium- and long-term prediction errors. Data-driven prediction, such as using deep learning models like Long Short-Term Memory (LSTM) or Transformer (Deep Self-Attention Transformer) to learn historical trajectory features and construct time-series prediction models, suffers from problems such as reliance on large amounts of labeled data for training and limited model generalization ability.

[0029] The relevant technologies mainly include physics-driven models and data-driven models. Neither currently considers environmental constraints such as flight paths and routes, thus overestimating the flight path's degrees of freedom. Physics-driven models heavily rely on real-time sensor data, are significantly affected by data noise, and experience error accumulation over time, supporting only short-term predictions with large errors in the medium to long term. Meanwhile, data-driven models require supervised training based on historical data, using time-series models to fit inherent nonlinear relationships, resulting in weak interpretability, requiring large amounts of high-quality labeled data, and limited model generalization ability.

[0030] Therefore, this application proposes a method for predicting and correcting aircraft tracks, which can effectively solve the above problems.

[0031] Figure 1 This is a flowchart illustrating an aircraft trajectory prediction and correction method provided in an embodiment of this application.

[0032] like Figure 1 As shown, the aircraft trajectory prediction and correction method 100 provided in this application embodiment includes steps S110-S130.

[0033] Step S110: Obtain the planned flight path and current flight data of the aircraft, wherein the current flight data includes the current position of the aircraft.

[0034] For example, the current flight data of the aircraft can be preprocessed data. Specifically, data preprocessing can involve performing field integrity checks, numerical validity verification, and data model transformation on the acquired current flight data, and using it to construct a standardized input dataset to ensure that the data received by subsequent methods can be used correctly.

[0035] Step S120: Process the flight data based on the motion model to predict the initial predicted trajectory of the aircraft.

[0036] For example, since the motion of an aircraft in three-dimensional space is approximately the motion of a spatial point mass, without considering external interference, a motion model can be used to characterize the aircraft's motion, and then the possible trajectory over a future period can be extrapolated. For example, the motion model can be a uniform motion model (CV) or a uniformly accelerated motion model (CA). The geographic coordinates of the aircraft's motion in three-dimensional space can be in the northeast-northeast coordinate system.

[0037] Step S130: Based on the relative positional relationship between the current position of the aircraft and the planned route, the initial predicted trajectory is corrected to obtain the target predicted trajectory.

[0038] The proposed solution integrates a phased prediction mechanism with a dynamic correction system. This approach modifies the predicted trajectory by fusing and utilizing planned flight path information, taking into account environmental constraints such as planned flight paths on the aircraft's trajectory degrees of freedom. This effectively reduces the error between the predicted and actual trajectories, improving the smoothness of the predicted trajectory. Furthermore, through a dynamic adaptive adjustment mechanism for weight parameters, the motion model can adapt to different flight states, including steady-state and unsteady-state conditions, thereby improving trajectory prediction accuracy in various scenarios and ensuring the operational safety of the aircraft in low-altitude airspace.

[0039] In one embodiment, the motion model includes a uniform motion model, and the flight data includes latitude and longitude data, altitude data, flight time data, time step, and three-dimensional flight velocity data; the flight data is processed based on the motion model to predict the initial predicted trajectory of the aircraft; including:

[0040] Based on the time step, the flight time data is updated to obtain real-time flight time update data; based on the time step and the three-dimensional flight velocity data, the three-dimensional flight displacement data is obtained; based on the real-time flight time update data and the three-dimensional flight displacement data, the latitude, longitude and altitude data are updated to obtain latitude, longitude and altitude update data; based on the latitude, longitude and altitude update data, the initial predicted trajectory of the aircraft is obtained.

[0041] For example, the initial predicted trajectory of the aircraft is predicted using a uniform motion model, and the following explanation is provided.

[0042] Specifically, the flight data of the aircraft is determined, which may include the aircraft's flight state variables. For example, the flight state variable is a certain time t. k The latitude (unit: °), longitude (unit: °), and altitude (unit: m) are defined as follows:

[0043] t k ,lat(t),lon(t),alt(t)

[0044] Based on the time step, the flight time data is updated to obtain real-time flight time update data:

[0045] t k+1 =t k +Δt

[0046] Where Δt is the time step (in seconds), t k This is the current timestamp.

[0047] Based on the time step and three-dimensional flight velocity data, the three-dimensional flight displacement data is obtained. Based on the uniform motion model, the three-dimensional flight displacement data is the product of velocity and time.

[0048]

[0049] Where, Δ N Δ E Δ D These represent the northward displacement data (unit: m), eastward displacement data (unit: m), and groundward displacement data (unit: m) from the three-dimensional flight displacement data. N v E v D These are the northward flight speed data (unit: m / s), eastward flight speed data (unit: m / s), and groundward flight speed data (unit: m / s) in the three-dimensional flight speed data.

[0050] Based on real-time flight time data and three-dimensional flight displacement data, latitude, longitude, and altitude data are updated to obtain updated latitude, longitude, and altitude data. Based on these updated data, the initial predicted flight path of the aircraft is obtained.

[0051] Converting three-dimensional flight displacement data in meters into latitude, longitude, and altitude update data allows for updating of geographic coordinates using geographic tools or small-scale approximation methods. The following is a formula for the small-scale approximation method, which has the advantage of requiring no iterative solution and having a small computational load.

[0052]

[0053] Where R Earth It is the Earth's radius (unit: meter).

[0054] In another example, the motion model includes a uniformly accelerated motion model, and the flight data includes latitude and longitude data, altitude data, flight time data, time step, three-dimensional flight velocity data, and three-dimensional motion acceleration data. Based on the motion model, the flight data is processed to predict the initial predicted trajectory of the aircraft. This includes: updating the flight time data based on the time step to obtain updated flight time data; obtaining three-dimensional flight displacement data based on the time step, three-dimensional flight velocity data, and three-dimensional motion acceleration data; updating the latitude and longitude data and altitude data based on the updated flight time data and three-dimensional flight displacement data to obtain updated latitude and longitude data and updated altitude data; updating the three-dimensional flight velocity data based on the updated flight time data, time step, and three-dimensional motion acceleration data to obtain updated three-dimensional flight velocity data; and obtaining the initial predicted trajectory of the aircraft based on the updated latitude and longitude data, updated altitude data, and updated three-dimensional flight velocity data.

[0055] For example, the initial predicted trajectory of the aircraft is predicted using a uniform acceleration motion model, and the following explanation is provided.

[0056] Specifically, the flight data of the aircraft is determined, which may include the aircraft's flight state variables. For example, the flight state variable is a certain time t. k The latitude (unit: °), longitude (unit: °), altitude (unit: m), northward velocity (unit: m / s), eastward velocity (unit: m / s), and groundward velocity (unit: m / s) are defined as follows:

[0057] t k ,lat(t),lon(t),alt(t),v N ,v E ,v D

[0058] Based on the time step, the flight time data is updated to obtain real-time flight time update data:

[0059] t k+1 =t k +Δt

[0060] Where Δt is the time step (in seconds), t k This is the current timestamp.

[0061] Based on the time step, three-dimensional flight velocity data, and three-dimensional motion acceleration data, the three-dimensional flight displacement data is obtained:

[0062]

[0063] Where, Δ N Δ E Δ D These represent the northward displacement data (unit: m), eastward displacement data (unit: m), and groundward displacement data (unit: m) from the three-dimensional flight displacement data. N v E v D These represent the northward flight speed data (unit: m / s), eastward flight speed data (unit: m / s), and groundward flight speed data (unit: m / s) in the three-dimensional flight speed data, respectively. N a E a D These are the northward movement acceleration data from the three-dimensional movement acceleration data (unit: m / s²). 2 Eastward acceleration data (unit: m / s²) 2 Ground-to-ground acceleration data (unit: m / s²) 2 ).

[0064] Based on the flight time update data and the three-dimensional flight displacement data, the latitude and longitude data and altitude data are updated to obtain the latitude and longitude update data and altitude update data.

[0065] Converting three-dimensional flight displacement data in meters into latitude, longitude, and altitude update data allows for updating of the geographic coordinates using geographic tools or small-scale approximation methods. The following is a formula for the small-scale approximation method, which has the advantage of requiring no iterative solution and involving minimal computation:

[0066]

[0067] Where R Earth It is the Earth's radius (unit: meter).

[0068] Based on the flight time update data, time step, and three-dimensional directional motion acceleration data, the three-dimensional directional flight velocity data is updated to obtain the three-dimensional directional flight velocity update data:

[0069]

[0070] Based on latitude and longitude update data, altitude update data, and three-dimensional flight speed update data, the initial predicted trajectory of the aircraft is obtained.

[0071] According to the embodiments provided in this application, an initial predicted trajectory can be generated by using aircraft flight data and updating flight time data, three-dimensional flight displacement data, latitude and longitude data, and altitude data step by step based on a uniform motion model or a uniform acceleration motion model (for a uniform acceleration model, three-dimensional flight velocity update data also needs to be updated). Furthermore, by introducing a dynamic adaptive adjustment mechanism for weight parameters, the motion model can be optimized in real time according to the dynamic changes in flight state. This significantly improves the trajectory prediction accuracy of the motion model in complex low-altitude scenarios, thereby enhancing the reliability of the prediction results and providing more reliable technical support for effectively avoiding flight conflicts and ensuring the operational safety of aircraft in low-altitude airspace.

[0072] In another embodiment, the current flight data also includes the current acceleration; based on the relative positional relationship between the current position of the aircraft and the planned route, the initial predicted trajectory is corrected to obtain the target predicted trajectory, including: matching the initial predicted trajectory and the planned route based on the relative positional relationship between the current position of the aircraft and the planned route to obtain trajectory matching mapping data; determining the route deviation data of the initial predicted trajectory relative to the planned route based on the trajectory matching mapping data; and correcting the initial predicted trajectory based on the route deviation data and / or the current acceleration to obtain the target predicted trajectory.

[0073] For example, a sliding window can be used to determine planned waypoints that match the initial predicted track one by one. The set of all planned waypoints constitutes the planned route, thereby establishing track matching mapping data between the initial predicted track and the planned route. Then, based on the track matching mapping data, the deviation of the initial predicted track from the planned route is determined. Based on the deviation data and / or the current acceleration, the initial predicted track is corrected to obtain the target predicted track.

[0074] In another embodiment, based on the relative positional relationship between the aircraft's current position and the planned route, the initial predicted trajectory and the planned route are matched to obtain trajectory matching mapping data. This includes: discretizing the planned route to obtain multiple planned waypoints; using the planned waypoint closest to the aircraft's current position as the starting point of a sliding window based on the relative positional relationship between the aircraft's current position and the planned route; using the distance between the aircraft's current position and the initial predicted trajectory as the length of the sliding window; matching the planned waypoint corresponding to the end point of the sliding window with the initial predicted trajectory to obtain trajectory matching mapping data; and determining the deviation of the initial predicted trajectory from the planned route based on the trajectory matching mapping data. This includes: obtaining the distance data between the initial predicted trajectory and the planned waypoints based on the trajectory matching mapping data; and determining the deviation data based on the distance data.

[0075] For example, a mapping relationship between the initial predicted trajectory and the planned route can be established based on the idea of ​​a sliding window. The main process includes discretizing the reference route, searching for the nearest matching waypoint at the current position of the aircraft, and establishing the mapping relationship between the initial predicted trajectory and the planned route based on the sliding window.

[0076] First, the entire planned route can be discretized based on a fixed distance interval, and interpolation can be performed on the low-density planned waypoints to obtain a high-density waypoint list. A KD-Tree (K-Dimensional Tree) can then be built to improve the efficiency of subsequent nearest neighbor searches.

[0077] Then, the starting and ending points of the sliding window are determined, which is the current position of the aircraft. The nearest neighbor search method is used to retrieve the waypoint on the planned route that is closest to the current position of the aircraft, which is used as the starting point of the sliding window. The length of the sliding window is determined by the distance between the initial predicted track and the current position of the aircraft. The sliding window is then mapped on the planned route to determine the ending point of the sliding window.

[0078] Finally, by repeating this step, planned waypoints corresponding one-to-one with the initial predicted track can be identified. The set of all planned waypoints constitutes the planned route, and a mapping list between the initial predicted track and the planned route can be established. Based on this mapping list, track matching mapping data can be obtained, thereby determining the degree of deviation of the initial predicted track from the planned route.

[0079] In the embodiments of this application, the sliding window length is dynamically adjusted to adapt to the real-time changes in the predicted trajectory. At the same time, the nearest neighbor search is efficiently performed using the KD-Tree data structure, which significantly improves the accuracy and processing efficiency of trajectory matching in complex flight path scenarios. Finally, quantified flight path deviation data is output, providing key input parameters for the dynamic gravitational field model and effectively supporting the optimization and safe operation of the aircraft's subsequent flight trajectory.

[0080] In another embodiment, the initial predicted trajectory is corrected based on the deviation data and / or the current acceleration to obtain the target predicted trajectory. This includes: determining gravity data based on the established dynamic gravitational field model, according to the deviation data and / or the current acceleration, wherein the dynamic gravitational field model characterizes the correlation between the deviation data and / or the current acceleration and gravity; and correcting the initial predicted trajectory based on the gravity data to obtain the target predicted trajectory.

[0081] In another embodiment, the dynamic gravitational field model includes an objective function that characterizes the relationship between gravity, flight path deviation data, current acceleration, and gravitational coefficient. Based on the established dynamic gravitational field model, gravitational data is determined according to the flight path deviation data and / or current acceleration, including: dynamically adjusting the gravitational coefficient based on the flight path deviation data and / or current acceleration; obtaining gravitational data based on the adjusted gravitational coefficient, flight path deviation data, and current acceleration; wherein, when the flight path deviation data is greater than or equal to a first preset threshold, and / or the acceleration data is greater than or equal to a second preset threshold, the gravitational coefficient is increased, thereby increasing the gravitational data; when the flight path deviation data is less than the first preset threshold, and / or the acceleration data is less than the second preset threshold, the gravitational coefficient is decreased, thereby decreasing the gravitational data.

[0082] For example, considering the deviation data and / or current acceleration, the gravitational force of the planned flight path can be determined. The greater the deviation data, i.e., the further the spacecraft deviates from the planned flight path, the weaker the gravitational force of the planned flight path is considered; similarly, the greater the current acceleration of the spacecraft, the weaker the gravitational force of the planned flight path is considered. Based on this, and using the adjusted gravitational coefficient, the deviation data, and the current acceleration, gravitational data is obtained, and a dynamic gravitational model is established. The specific formula is as follows:

[0083]

[0084] Where K0 represents the gravitational coefficient, d0 is the effective radius of gravitational influence of the flight path, and α is the maneuver sensitivity factor. k Let be the acceleration modulus at the current moment.

[0085] The initial predicted trajectory is corrected based on gravity data to obtain the target predicted trajectory. Specifically, this step is based on an adaptive weight adjustment strategy, which can adjust the overall system of the dynamic gravity model according to factors such as the spacecraft's current position, whether it is in a stable state, and whether it follows the planned route.

[0086] For example, when the flight path deviation data is greater than or equal to a first preset threshold, such as when the flight path deviation data is more than twice the planned flight path (d0), it is considered that the aircraft is not flying according to the planned flight path, and the coefficient K0 is automatically decreased. When the flight path deviation data is less than the first preset threshold, such as when the flight path deviation data is less than twice the planned flight path (d0), it is considered that the aircraft is flying according to the planned flight path, and the coefficient K0 is automatically increased. And / or, when the acceleration data is greater than or equal to a second preset threshold, it is considered that the aircraft is about to perform a maneuver, and K0 is appropriately decreased; otherwise, K0 is increased. For example, when the aircraft follows the planned flight path for a long time, the coefficient K0 is automatically increased; otherwise, K0 is decreased.

[0087] After calculating the final gravitational force, the initial predicted trajectory is corrected according to the following formula:

[0088]

[0089] in, This indicates the latitude, longitude, and altitude of the target's predicted trajectory; The initial predicted trajectory represents the latitude, longitude, and altitude. airline lon airline alt airline The latitude, longitude, and altitude of the planned route point that matches the target predicted trajectory are represented, and F is the modulus of dynamic gravity.

[0090] Therefore, in the embodiments of this application, the planned flight path is used as a reference line in the prediction process, and the "gravitational field" model is used to correct the predicted trajectory of the target. Specifically, by establishing a dynamic gravitational field model and dynamically and adaptively adjusting the weight parameters, the prediction accuracy of the model can be improved in different flight states, such as steady state (flying according to the planned flight path) and unsteady state (flying outside the planned flight path). Taking into account the constraints of environmental factors such as flight paths on the degree of freedom of the aircraft's trajectory, the error between the predicted trajectory and the actual trajectory can be effectively reduced, and the smoothness of the predicted trajectory can be improved, thereby ensuring the operational safety of the aircraft flying in low-altitude airspace.

[0091] In another embodiment, the method further includes: acquiring the actual trajectory of the aircraft; and verifying the target predicted trajectory based on error data between the target predicted trajectory and the actual trajectory.

[0092] For example, after obtaining the corrected target prediction track, field integrity verification and numerical validity verification are performed to verify whether the latitude, longitude and altitude of the target prediction track are within a reasonable range, so as to ensure the rationality of the output target prediction track.

[0093] Specifically, two classic scenarios can be set up to validate the predicted target trajectory: a polyline planned route and a circular planned route. Euclidean distance can be used to measure the error between the predicted and actual target trajectories. For example, RMSE (Root Mean Square Error) can be used as a practical indicator, as shown in the following formula:

[0094]

[0095] Figure 2 This is a schematic diagram of the RMSE (Piecework Planned Path) at different prediction times for both uncorrected and corrected paths, according to an embodiment of this application.

[0096] Figure 3This is a schematic diagram of the RMSE (Rectangular Planned Path) of the target predicted track and the actual track at a typical predicted time, provided in an embodiment of this application.

[0097] The following explanation uses a zigzag flight path as a verification scenario. For example, based on its starting position, the aircraft first flies approximately 500 meters north, then approximately 1000 meters east, and then approximately 500 meters south. All segments involve accelerating from 0, reaching maximum speed, maintaining a constant speed, and then decelerating to 0 speed just before reaching the planned waypoint.

[0098] The aircraft's performance parameters are as follows:

[0099] Maximum level flight speed: 10 m / s; acceleration during level flight: 2 m / s² 2

[0100] Maximum ascent speed: 3 m / s; acceleration during ascent: 1 m / s² 2

[0101] Maximum descent speed: 3 m / s; acceleration during descent: 1 m / s² 2

[0102] The analog sensor noise parameters are:

[0103] Location noise: 1 meter

[0104] Velocity noise: 0.1 m / s

[0105] Acceleration noise: 0.1 m / s² 2

[0106] Algorithm parameters:

[0107] Table 1 Algorithm Parameter Table (Example 1)

[0108] <![CDATA[K0]]> 1.0 Motion Sensitivity Factor α 0.2 <![CDATA[Effective gravitational action radius d0]]> 50m Kinematic model CV route discretization density 1m Time interval 1s

[0109] Based on the above parameters, a planned flight path and the actual flight path of the aircraft are generated. The method proposed in this application is called in real time to obtain the predicted flight path. The RMSE (Root Mean Square Error) at different prediction times is calculated, and a line graph and RMSE index are plotted as follows: Figure 2 and Figure 3 As shown, compared to the uncorrected approach, considering the constraints of the planned route on the aircraft's degree of freedom, the target predicted trajectory RMSE is significantly reduced after the correction, especially in medium- to long-term (over 60 seconds) predictions.

[0110] Figure 4 This is a schematic diagram of the RMSE (Circular Path Sequence) at different prediction times for both uncorrected and corrected paths, according to an embodiment of this application.

[0111] Figure 5 This is a schematic diagram of the RMSE (Circular Path Result) of the target predicted track and the actual track at a typical prediction time, provided in an embodiment of this application.

[0112] The following explanation uses a circular planned flight path as a verification scenario. For example, if an aircraft is moving in a uniform circular motion and then has a vertically upward velocity added to it, the overall flight path will be a spiral ascent.

[0113] The planned route parameters are as follows:

[0114] Circular route radius: 1000 meters

[0115] Center position: lat:29.3730015, lon:106.0252575, alt:1000.0

[0116] Angular velocity: 6° / s

[0117] Vertical ascent speed: 2m / s

[0118] Total duration: 120s

[0119] Time interval: 1s

[0120] The planned trajectory parameters are:

[0121] Location noise: 1 meter

[0122] Velocity noise: 0.1 m / s

[0123] Acceleration noise: 0.1 m / s² 2

[0124] The algorithm parameters are:

[0125] Table 2 Algorithm Parameter Table (Example 2)

[0126] <![CDATA[K0]]> 1.0 Motion Sensitivity Factor α 0.2 <![CDATA[Effective gravitational action radius d0]]> 50m Kinematic model CA route discretization density 1m Time interval 1s

[0127] Based on the above parameters, a planned flight path and the actual flight path of the aircraft are generated. The method proposed in this application is called in real time to obtain the target predicted flight path. The RMSE at different prediction times is calculated, and line graphs and RMSE indices are plotted as follows. Figure 4 , Figure 5 As shown, compared to the uncorrected route, the predicted trajectory RMSE is significantly reduced after the fusion plan route is corrected, especially in the medium to long term (60s and above).

[0128] Therefore, according to the solution provided in this application, the field integrity and numerical validity of the target predicted track can be verified in two classic scenarios: broken line planned route and circular planned route. By verifying whether the latitude, longitude and altitude of the target predicted track are within a reasonable range, the rationality of the output target predicted track can be guaranteed.

[0129] Figure 6 This is a flowchart illustrating an embodiment of the aircraft trajectory prediction and correction method provided in this application.

[0130] like Figure 6 As shown, the aircraft trajectory prediction and correction method 600 includes:

[0131] The data preprocessing module 610 is used to construct a standardized input dataset through field integrity verification, numerical validity verification, and data model transformation. Specifically, the data preprocessing module 610 implements its function through steps S611-S613.

[0132] Step S611: Field integrity check. If the field integrity check passes, proceed to step S612; if the field integrity check fails, the process will be flagged as an exception and terminate.

[0133] Step S612: Numerical validity check. If the numerical validity check passes, proceed to step S613; if the numerical validity check fails, the process will be flagged as an error and terminate.

[0134] Step S613, data model transformation.

[0135] The prediction module 620 is used to extrapolate the state of the kinematic model. The state suppression module 622 constrains and truncates the position, velocity, acceleration, and other state variables in the initial predicted trajectory to ensure that the prediction result does not exceed the aircraft's performance boundaries, thus generating a preliminary predicted trajectory. Specifically, the data preprocessing module 610 implements its function through the variable acceleration motion model 621 and the state suppression module 622.

[0136] The correction module 630 is used to discretize the planned flight path and establish a nearest neighbor retrieval data structure. It obtains a dynamic mapping between the initial predicted trajectory and the planned flight path using a sliding window matching method. Then, based on a "gravitational field model" (integrating parameters such as the aircraft's instantaneous acceleration and flight path deviation data), it quantifies the correction force vector and combines it with a dynamic weight allocation strategy (adaptively adjusting the ratio of flight path constraint weights to real-time state weights) to complete the accurate correction of the predicted trajectory. Specifically, the correction module 630 implements its function through steps S631-S635.

[0137] Step S631: Discretize the planned route.

[0138] Step S632: Establish the nearest neighbor retrieval data structure and obtain the dynamic mapping between the initial predicted trajectory and the planned route through the sliding window matching method.

[0139] Step S633: Quantify the correction force vector based on the "gravitational field model" (which integrates parameters such as instantaneous acceleration of the aircraft and deviation distance from the flight path).

[0140] Step S634 involves combining a dynamic weight allocation strategy.

[0141] Step S635, trajectory correction output.

[0142] The data post-processing module 640 is used to perform secondary verification and output format conversion on the correction results to ensure the integrity and rationality of the target predicted trajectory. Specifically, the data post-processing module 640 implements its function through steps S641-S643.

[0143] Step S641: Field integrity verification. If the field integrity verification passes, proceed to step S642; if the field integrity verification fails, the process will be flagged as an exception and terminate.

[0144] Step S642: Numerical validity check. If the numerical validity check passes, proceed to step S643; if the numerical validity check fails, the process will be flagged as an error and terminate.

[0145] Step S643, data model transformation.

[0146] The proposed solution divides trajectory prediction into two stages: prediction and correction. The prediction stage uses kinematic models (CV, CA, etc.) to make a preliminary prediction of the aircraft's trajectory. The correction stage establishes a mapping between the predicted trajectory and the planned route using a sliding window, employs a nearest neighbor search algorithm to locate waypoints matching the current position, and combines segment distance reasoning to obtain an accurate mapping between the predicted trajectory and the planned route (i.e., the reference line). Based on the assumption that the route exerts a "gravitational pull" on the predicted trajectory, a "gravitational field" correction model is constructed. Using the route as the reference line, considering factors such as the aircraft's real-time acceleration and route deviation, the model adaptively quantifies the magnitude and direction of the route's gravitational pull to correct the predicted trajectory, finally outputting the corrected predicted trajectory.

[0147] This application aims to address the problems of significant cumulative effects of medium- and long-term prediction errors, insufficient resistance to noise interference, and poor adaptability to multiple scenarios in existing aircraft trajectory prediction technologies. It proposes a method for aircraft trajectory prediction and correction. The scheme of this application embodies a collaborative architecture of a phased prediction mechanism and a dynamic correction system. By utilizing aircraft flight path information, the initial predicted trajectory is corrected, reducing the error between the predicted and actual trajectories and improving the smoothness of the predicted trajectory. Through a dynamic adaptive adjustment method of weights, accurate trajectory prediction is achieved under both steady-state and unsteady-state conditions.

[0148] Figure 7 A schematic diagram of an aircraft trajectory prediction and correction device provided in this application.

[0149] like Figure 7 As shown, the aircraft trajectory prediction and correction device 700 includes:

[0150] The acquisition module 710 is used to acquire the planned flight path and current flight data of the aircraft, wherein the current flight data includes the current position of the aircraft.

[0151] The prediction module 720 is used to process flight data based on the motion model and predict the initial predicted trajectory of the aircraft.

[0152] The correction module 730 corrects the initial predicted trajectory based on the relative positional relationship between the aircraft's current position and the planned route, thereby obtaining the target predicted trajectory.

[0153] It is understood that for a detailed description of the aircraft trajectory prediction and correction device 700, please refer to the description of the aircraft trajectory prediction and correction method 100 above.

[0154] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the method in any of the above embodiments.

[0155] This application provides a computer program product that includes instructions that, when executed by a processor of a computer device, enable the computer device to perform the steps of the method described in any of the above embodiments.

[0156] Figure 8 A block diagram of an electronic device provided in an embodiment of this application.

[0157] This application provides an electronic device, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method in any of the above embodiments.

[0158] like Figure 8As shown, for ease of understanding, embodiments of this application illustrate a specific electronic device 800.

[0159] Electronic device 800 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0160] like Figure 8 As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of electronic device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0161] Multiple components in electronic device 800 are connected to I / O interface 805. These components include: input unit 806, such as a keyboard or mouse; output unit 807, such as various types of displays or speakers; storage unit 808, such as a disk or optical disk; and communication unit 809, such as a network interface card (NIC), modem, or wireless transceiver. Communication unit 809 allows electronic device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0162] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods described above. For example, in some embodiments, any one or more of the methods described above can be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of any one or more of the methods described above can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform any one or more of the methods described above by any other suitable means (e.g., by means of firmware).

[0163] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequential list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this application, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0164] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0165] In the description of this application, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this application, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0166] In the description of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0167] Furthermore, the terms "first," "second," etc., used in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying relative importance, or implicitly specifying the number of technical features indicated in this embodiment. Therefore, features defined with terms such as "first" and "second" in the embodiments of this application can explicitly or implicitly indicate that the embodiment includes at least one of those features. In the description of this application, the word "multiple" means at least two or more, such as two, three, four, etc., unless otherwise explicitly and specifically defined in the embodiments.

[0168] In this application, unless otherwise explicitly specified or limited in the embodiments, the terms "installation," "connection," "joining," and "fixing" appearing in the embodiments should be interpreted broadly. For example, a connection can be a fixed connection, a detachable connection, or an integral part; it can also be a mechanical connection, an electrical connection, etc. Of course, it can also be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication between two components, or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific implementation.

[0169] In this application, unless otherwise expressly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "on top of," and "over" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

Claims

1. A method for predicting and correcting aircraft trajectories, characterized in that, The method includes: The planned flight path and current flight data of the aircraft are obtained, wherein the current flight data includes the current position of the aircraft; The flight data is processed based on the motion model to predict the initial predicted trajectory of the aircraft. Based on the relative positional relationship between the current position of the aircraft and the planned route, the initial predicted trajectory is corrected to obtain the target predicted trajectory.

2. The method according to claim 1, characterized in that, The current flight data also includes the current acceleration; the process of correcting the initial predicted trajectory based on the relative positional relationship between the current position of the aircraft and the planned route to obtain the target predicted trajectory includes: Based on the relative positional relationship between the current position of the aircraft and the planned route, the initial predicted trajectory and the planned route are matched to obtain trajectory matching mapping data; Based on the track matching mapping data, determine the deviation of the initial predicted track from the planned route. Based on the deviation data of the flight path and / or the current acceleration, the initial predicted flight path is corrected to obtain the target predicted flight path.

3. The method according to claim 2, characterized in that, The process involves matching the initial predicted trajectory with the planned trajectory based on the relative positional relationship between the current position of the aircraft and the planned route, to obtain trajectory matching mapping data, including: The planned route is discretized to obtain multiple planned waypoints; Based on the relative positional relationship between the current position of the aircraft and the planned route, the planned waypoint that is closest to the current position of the aircraft is used as the starting point of the sliding window; The distance between the current position of the aircraft and the initial predicted trajectory is used as the length of the sliding window; The planned waypoint corresponding to the end point of the sliding window is matched with the initial predicted trajectory to obtain trajectory matching mapping data; The step of determining the deviation of the initial predicted trajectory from the planned route based on the trajectory matching mapping data includes: Based on the track matching mapping data, the distance data between the initial predicted track and the planned waypoint is obtained; Based on the distance data, the deviation of the flight path is determined.

4. The method according to claim 2, characterized in that, The step of correcting the initial predicted trajectory based on the route deviation data and / or the current acceleration to obtain the target predicted trajectory includes: Based on the established dynamic gravitational field model, gravitational data is determined according to the flight path deviation data and / or the current acceleration, wherein the dynamic gravitational field model characterizes the correlation between the flight path deviation data and / or the current acceleration and gravity; The initial predicted trajectory is corrected based on the gravity data to obtain the target predicted trajectory.

5. The method according to claim 4, characterized in that, The dynamic gravitational field model includes an objective function, which characterizes the relationship between gravity, the course deviation data, the current acceleration, and the gravitational coefficient. The established dynamic gravitational field model determines gravitational data based on the flight path deviation data and / or the current acceleration, including: The gravity coefficient is dynamically adjusted based on the flight path deviation data and / or the current acceleration. The gravity data is obtained based on the adjusted gravity coefficient, the deviation data of the flight path, and the current acceleration; Specifically, when the flight path deviation data is greater than or equal to a first preset threshold, and / or when the acceleration data is greater than or equal to a second preset threshold, the gravity coefficient is increased, thereby increasing the gravity data; When the deviation from the flight path is less than a first preset threshold, and / or when the acceleration is less than a second preset threshold, the gravitational coefficient is reduced, thereby reducing the gravitational data.

6. The method according to claim 1, characterized in that, The motion model includes a uniform motion model, and the flight data includes latitude and longitude data, altitude data, flight time data, time step, and three-dimensional flight velocity data; the process of processing the flight data based on the motion model to predict the initial predicted trajectory of the aircraft includes: Based on the time step, the flight time data is updated to obtain real-time flight time update data; Based on the time step and the three-dimensional flight velocity data, the three-dimensional flight displacement data is obtained. Based on the real-time flight time update data and the three-dimensional flight displacement data, the latitude and longitude data and the altitude data are updated to obtain the latitude and longitude update data and the altitude update data. Based on the latitude and longitude update data and the altitude update data, the initial predicted trajectory of the aircraft is obtained; or, The motion model includes a uniformly accelerated motion model, and the flight data includes latitude and longitude data, altitude data, flight time data, time step, three-dimensional flight velocity data, and three-dimensional motion acceleration data; the process of processing the flight data based on the motion model to predict the initial predicted trajectory of the aircraft includes: Based on the time step, the flight time data is updated to obtain flight time update data; Based on the time step, the three-dimensional flight velocity data, and the three-dimensional movement acceleration data, the three-dimensional flight displacement data is obtained. Based on the flight time update data and the three-dimensional flight displacement data, the latitude and longitude data and the altitude data are updated to obtain the latitude and longitude update data and the altitude update data; Based on the flight time update data, the time step, and the three-dimensional direction movement acceleration data, the three-dimensional direction flight velocity data is updated to obtain the three-dimensional direction flight velocity update data. Based on the latitude and longitude update data, the altitude update data, and the three-dimensional flight speed update data, the initial predicted trajectory of the aircraft is obtained.

7. The method according to claim 1, characterized in that, The method further includes: Obtain the actual flight path of the aircraft; The predicted target trajectory is verified based on the error data between the predicted target trajectory and the actual trajectory.

8. An aircraft trajectory prediction and correction device, characterized in that, The device includes: The acquisition module is used to acquire the planned flight path and current flight data of the aircraft, wherein the current flight data includes the current position of the aircraft; The prediction module is used to process the flight data based on the motion model and predict the initial predicted trajectory of the aircraft. The correction module corrects the initial predicted trajectory based on the relative positional relationship between the current position of the aircraft and the planned route to obtain the target predicted trajectory.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1-7.

Images