A method for planning a jump flight path of an aircraft and a system thereof

Abstract

The application discloses a kind of flight path planning method of aircraft's jump and system thereof, it is related to path planning technical field.The method includes: data acquisition and generation reference flight path;Establish path planning model and generate predicted flight path;Determine optimal flight path and carry out path test;Risk assessment and determine final actual flight path;Obtain flight path error and carry out path correction;Form path planning database.The application obtains predicted flight path by establishing path planning model and determines optimal flight path by path optimization algorithm, carries out path test and risk assessment to optimal flight path by establishing simulation test environment, and determines final actual flight path, carries out path correction by obtaining real-time flight data and establishes path planning database to ensure the accuracy of path planning, and thus ensures the real-time and accuracy of path planning, and then improves the flight performance of aircraft on jump flight path.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of path planning, and particularly relates to a flight path planning method for a jump flight route of an aircraft and a system thereof. BACKGROUND

[0002] The jump flight route of an aircraft refers to the intentional change in altitude during flight, usually involving sudden jumps from lower altitudes to higher altitudes, or sudden drops from higher altitudes to lower altitudes. Such flight methods can be used to evade enemy radars, counter enemy air defense systems, etc., and therefore, path planning for the jump flight route of an aircraft becomes an important factor in improving the maneuverability of the aircraft.

[0003] Current path planning techniques for the jump flight route of an aircraft include the following forms:

[0004] Heuristic algorithms: such as A* and Dijkstra algorithms, suitable for path planning in fixed environments, the problem is that these algorithms usually deal with static environments, and are not suitable for dynamic changes in obstacles.

[0005] Random sampling methods: such as RRT and PRM algorithms, suitable for high-dimensional space and complex environment, the problem is that the algorithm has high computational complexity, poor real-time performance, and may require a large number of samples to find an effective path.

[0006] Optimization methods: such as genetic algorithms and particle swarm optimization, which can handle complex constraints and multi-objective optimization, the disadvantage is that a large amount of computing resources is required, and the effect is limited when dealing with dynamic changes.

[0007] Therefore, the main problems existing in the current path planning for the jump flight route of an aircraft include:

[0008] Poor adaptability to dynamic environment: during the jump flight, the environment may change, such as the appearance of new obstacles or air currents, which requires the path planning algorithm to update the path in real time, but existing technologies often fail to meet the dual requirements of real-time performance and accuracy.

[0009] High computational complexity: advanced path planning algorithms such as RRT and genetic algorithms may require a large amount of computation, especially in high-dimensional space, which may affect real-time performance.

[0010] Complex modeling of altitude changes: the jump flight characteristics of the aircraft involve significant changes in altitude, and existing technologies may not be able to accurately model the changes in altitude, thereby affecting the feasibility of the path.

[0011] Limited obstacle avoidance capability: although some algorithms can handle static obstacles, existing methods often fall short when dealing with dynamic obstacles, especially in scenarios that require high-speed response.

[0012] System integration is difficult: the path planning system needs to be closely integrated with the control system of the aircraft to ensure the real-time and accuracy of path planning, and the integration and debugging are difficult in actual application.

[0013] Therefore, there is an urgent need for a path planning method that can ensure real-time and accuracy to plan the overall flight path of the aircraft, to improve the flight path planning capability of the aircraft in complex environments. SUMMARY

[0014] The purpose of the present application is to provide a flight path planning method and system for the flight path of an aircraft, which can be realized by the following technical solutions:

[0015] In a first aspect, the present application provides a flight path planning method for the flight path of an aircraft, comprising the following steps:

[0016] Collecting flight environment data and geographic information data in the flight area of the aircraft;

[0017] Determine the starting position and target position of the aircraft and divide the flight area of the aircraft to generate a reference flight path;

[0018] Establish a path planning model according to the geographic information data and the flight environment data, and generate a predicted flight path using the path planning model and the reference flight path;

[0019] Optimize the predicted flight path using a path optimization algorithm to determine the optimal flight path;

[0020] Establish a simulation test environment and perform path testing on the optimal flight path to obtain test results;

[0021] Use a large model to predict risk points in the optimal flight path and perform risk assessment to obtain evaluation results;

[0022] Adjust the path planning strategy based on the test results and the evaluation results and determine the final actual flight path;

[0023] Obtain real-time flight data of the aircraft on the actual flight path and input the real-time flight data into the path planning model to obtain flight path error;

[0024] Use the flight path error to correct the predicted flight path;

[0025] Record the process of each path planning and the generated flight path to form a path planning database.

[0026] Preferably, the flight environment data comprises static obstacle data, dynamic obstacle data and weather data; and the geographic information data comprises terrain data, topographic map data and satellite image data.

[0027] Preferably, the flight area of the aircraft is divided to generate the reference flight path, specifically comprising:

[0028] a plurality of basic flight paths are determined according to the starting position and the target position of the aircraft;

[0029] the flight area is divided to determine no-fly zones, danger zones and safe zones;

[0030] flight paths located in the no-fly zones are excluded from the basic flight paths, and the remaining paths are collected in a flight path set;

[0031] a first preset path rule is set, and one or more paths in the flight path set that meet the rule are selected as first preset paths;

[0032] if there is only one first preset path, the first preset path is determined as the reference flight path, and if there are multiple first preset paths, one or more second preset paths are determined from the multiple first preset paths according to a second preset path rule;

[0033] if there is only one second preset path, the second preset path is determined as the reference flight path, and if there are multiple second preset paths, the reference flight path is determined from the multiple second preset paths according to the state index of the aircraft.

[0034] Preferably, the first preset path rule comprises the following contents:

[0035] the flight height corresponding to the flight path is greater than the highest altitude or the highest building in the flight area;

[0036] there is no flight task in the same flight area as the current flight task;

[0037] the noise decibel of the aircraft is lower than the decibel requirement in the flight area;

[0038] the number of flight paths in the danger zone is less than the number of flight paths in the safe zone.

[0039] Preferably, the second preset path rule comprises the following contents:

[0040] the weather environment of the flight path meets the operation requirement for safe operation of the aircraft;

[0041] the task saturation of the aircraft in the flight path is lower than the task saturation threshold;

[0042] The number of aircrafts in the flight path is less than a number saturation threshold.

[0043] Preferably, the state indicator comprises;

[0044] Obtaining power information and flight state information of the aircraft;

[0045] Obtaining path mileage corresponding to the flight path;

[0046] According to the power information, the flight state information and the path mileage, calculating an economic indicator of each flight path in a plurality of second preset paths;

[0047] Taking the flight path corresponding to the minimum indicator in the economic indicator as a reference flight path.

[0048] Preferably, establishing the path planning model comprises the following contents:

[0049] Generating a three-dimensional multi-layer planning map in combination with the geographic information data and the flight environment data;

[0050] Processing the three-dimensional multi-layer planning map by using a convolutional neural network to generate a feature map;

[0051] Constructing a graph structure based on the feature map;

[0052] Processing the graph structure by using a graph neural network to generate the path planning model;

[0053] Wherein, constructing the graph structure specifically comprises:

[0054] According to the feature mapping of the feature map, taking the features in the feature map as node features of the graph structure and defining the connections and weights between nodes.

[0055] Preferably, the path optimization algorithm adopts A* algorithm and particle swarm optimization algorithm.

[0056] Preferably, the predicted flight path is optimized by using a path optimization algorithm, specifically comprising:

[0057] Generating an initial flight path by using A* algorithm;

[0058] Optimizing the initial flight path by using a particle swarm optimization algorithm to output an optimal flight path.

[0059] In a second aspect, the embodiments of the present application provide a flight path planning system for a flight path of a flight vehicle, which is applied to the flight path planning method as described above, and comprises:

[0060] A data acquisition module is configured to acquire flight environment data and geographic information data in a flight area of the flight vehicle;

[0061] An optimal flight path generation module is configured to determine a starting position and a target position of the aircraft and divide a flight area of the aircraft to generate a reference flight path, establish a path planning model according to the geographic information data and the flight environment data, and generate a predicted flight path by using the path planning model and the reference flight path, and optimize the predicted flight path by using a path optimization algorithm to determine an optimal flight path.

[0062] An actual flight path generation module is configured to establish a simulation test environment and perform path testing on the optimal flight path in the simulation test environment to obtain a test result, predict risk points in the optimal flight path by using a large model and perform risk assessment to obtain an assessment result, adjust a path planning strategy based on the test result and the assessment result, and determine a final actual flight path.

[0063] A path planning database generation module is configured to obtain real-time flight data of the aircraft on the actual flight path and input the real-time flight data into the path planning model to obtain a flight path error, perform path correction on the predicted flight path by using the flight path error, and record a process of each path planning and a generated flight path to form a path planning database.

[0064] The present application has the following advantages:

[0065] (1) The present application establishes a path planning model to obtain a predicted flight path and determines an optimal flight path by using a path optimization algorithm, then performs path testing and risk assessment on the optimal flight path by establishing a simulation test environment, and determines a final actual flight path, finally performs path correction by obtaining real-time flight data and establishes a path planning database to ensure the accuracy of path planning, and thus ensures the real-time performance of path planning, and further improves the flight performance of the aircraft on a jump flight route.

[0066] (2) The application adopts the following means, specifically: first, flight environment data and geographic information data of the aircraft in the flight area are collected; then the starting position and target position of the aircraft are determined, the flight area of the aircraft is divided to determine the no-fly area, dangerous area and safe area, and the reference flight path is obtained; then a path planning model is established according to the geographic information data and the flight environment data, and the prediction flight path is generated by using the path planning model based on the reference flight path; then the prediction flight path is optimized by using the path optimization algorithm to determine the optimal flight path; then the simulation test environment is established, and the optimal flight path is tested in the simulation test environment to obtain the test result; then the risk points in the optimal flight path are predicted by using the large model, and the risk points are risk evaluated to obtain the evaluation result; then the path planning strategy is adjusted based on the test result and the evaluation result, and the final actual flight path is determined; then the actual flight path is applied in the actual scene, the real-time flight data of the aircraft on the actual flight path is obtained, and the real-time flight data is input into the path planning model to obtain the flight path error; then the prediction flight path is corrected by using the flight path error; finally, the process of each path planning and the generated flight path are recorded to form a path planning database, which can provide reference data for subsequent path planning, and through recording the path planning process multiple times, the subsequent path planning can be more accurate and perfect. BRIEF DESCRIPTION OF DRAWINGS

[0067] In order to better understand and implement, the technical scheme of the present application is described in detail below in combination with the drawings.

[0068] Figure 1 A step flowchart of a flight path planning method of a flight vehicle provided by an embodiment of the present application is shown in the figure.

[0069] Figure 2 A step flowchart of generating a reference flight path provided by an embodiment of the present application is shown in the figure.

[0070] Figure 3 A step flowchart of establishing a path planning model provided by an embodiment of the present application is shown in the figure.

[0071] Figure 4 A structural schematic diagram of a flight path planning system of a flight vehicle provided by an embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0072] To further clarify the technical means and effects taken by the present application to achieve the predetermined inventive purpose, exemplary embodiments will be described in detail hereinafter with reference to the accompanying drawings. The following description relates to the drawings, unless otherwise indicated, in which like numerals refer to like or similar elements throughout. The implementations described in the following exemplary embodiments are not meant to represent all implementations consistent with the present application. Rather, they are merely examples of methods and systems consistent with some aspects of the present application as detailed in the appended claims.

[0073] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in this application and the appended claims, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that the term "and / or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0074] The specific implementations, features and effects of the embodiments according to the present application are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0075] Embodiment 1

[0076] Please refer to Figure 1 The embodiment of the present application provides a flight path planning method for a flying vehicle, comprising the following steps:

[0077] S1, collecting flight environment data and geographic information data in a flight area of a flying vehicle;

[0078] S2, determining a starting position and a target position of the flying vehicle and dividing the flight area of the flying vehicle to generate a reference flight path;

[0079] S3, establishing a path planning model according to the geographic information data and the flight environment data, and generating a predicted flight path by using the path planning model and the reference flight path;

[0080] S4, optimizing the predicted flight path by using a path optimization algorithm to determine an optimal flight path;

[0081] S5, establishing a simulation test environment and performing path testing on the optimal flight path in the simulation test environment to obtain a test result;

[0082] S6, predicting risk points in the optimal flight path by using a large model and performing risk assessment to obtain an assessment result;

[0083] S7, adjusting a path planning strategy based on the test result and the assessment result and determining a final actual flight path;

[0084] S8, acquiring real-time flight data of the aircraft on the actual flight path and inputting the real-time flight data into the path planning model to acquire flight path error;

[0085] S9, path correcting the predicted flight path by using the flight path error;

[0086] S10, recording the process of each path planning and the generated flight path to form a path planning database.

[0087] Specifically, since the flight path of the aircraft on the jump flight route will have errors due to dynamic changes in height and environment, affecting the performance of the aircraft and being difficult to meet the requirements of real-time and accuracy of the flight path, in order to ensure the accuracy of the path of the aircraft on the jump flight route, the embodiment adopts the following means, specifically: first, collecting flight environment data and geographic information data of the aircraft in the flight area; then determining the starting position and target position of the aircraft and dividing the flight area of the aircraft to determine the no-fly area, dangerous area and safe area, and acquiring the reference flight path; then establishing a path planning model according to the geographic information data and the flight environment data, and generating a predicted flight path by using the path planning model on the basis of the reference flight path; then optimizing the predicted flight path by using a path optimization algorithm to determine the optimal flight path; then establishing a simulation test environment and testing the optimal flight path in the simulation test environment to acquire a test result; then predicting risk points in the optimal flight path by using a large model and evaluating the risk points to acquire an evaluation result; then adjusting the path planning strategy based on the test result and the evaluation result and determining the final actual flight path; then applying the actual flight path in the actual scene, acquiring real-time flight data of the aircraft on the actual flight path and inputting the real-time flight data into the path planning model to acquire flight path error; then path correcting the predicted flight path by using the flight path error; finally, recording the process of each path planning and the generated flight path to form a path planning database, which can provide reference data for subsequent path planning, and through recording the process of multiple path planning, the subsequent path planning can be more accurate and perfect.

[0088] From the idea, the whole path planning process is divided into three stages: the first stage is to obtain the optimal flight path through various data, the second stage is to simulate and adjust the optimal path in the simulation environment, so as to determine the final actual flight path of the aircraft, the third stage is to actually test the actual flight path in the actual environment, observe the path change of the aircraft in the actual flight process by obtaining the real-time flight data of the aircraft, find out the path error and correct the predicted path according to the error, and finally record the path planning data of each time to establish the path planning database, so as to provide data support and reference for subsequent path planning.

[0089] The embodiment obtains the predicted flight path by establishing the path planning model and determines the optimal flight path through the path optimization algorithm, then tests and evaluates the risk of the optimal flight path by establishing the simulation test environment, and determines the final actual flight path, finally corrects the path by obtaining the real-time flight data and establishes the path planning database to ensure the accuracy of the path planning, and thus ensures the real-time performance of the path planning, and further improves the flight performance of the aircraft on the jump flight route.

[0090] In an embodiment provided in the application, the flight environment data includes static obstacle data, dynamic obstacle data and meteorological data; and the geographic information data includes terrain data, topographic map data and satellite image data.

[0091] Specifically, the embodiment collects flight environment data and geographic information data in the flight area of the aircraft, wherein the static obstacle data in the flight environment data includes information of large, static and aircraft flight-affecting static obstacles such as buildings, communication towers and wind turbines, the dynamic obstacle data includes positions and movement conditions of other aircrafts and birds, and the meteorological data includes wind speed, wind direction, air temperature, precipitation and other meteorological condition-related data; and the geographic information data covers various information related to geographic location, which can be used for subsequent analysis, modeling and decision support, and specifically includes terrain data: describing the elevation, undulation and topographic features of the ground surface, topographic data: indicating detailed information of the ground surface form, such as mountains, plains, rivers, lakes, etc., road network data: including road types (expressway, urban street, etc.), traffic flow data: traffic flow, speed and congestion on the road, and traffic route data: bus routes, railway routes, flight routes, etc.

[0092] It should be noted that the above risk point refers to a point in the flight path that may cause danger to the flight of the aircraft.

[0093] For example, the flight environment data includes static obstacle data, dynamic obstacle data and meteorological data. Figure 2As shown, in an embodiment provided by the present application, the flight area of the aircraft is divided to generate the reference flight path, specifically including:

[0094] A plurality of basic flight paths are determined according to the starting position and the target position of the aircraft;

[0095] The flight area is divided to determine the no-fly area, the dangerous area and the safe area;

[0096] The flight paths located in the no-fly area are excluded from the basic flight paths, and the remaining paths are collected in a flight path set;

[0097] A first preset path rule is set, and one or more paths conforming to the rule are selected from the flight path set as the first preset path;

[0098] If there is only one first preset path, the first preset path is determined as the reference flight path, and if there are a plurality of first preset paths, one or more second preset paths are determined from the plurality of first preset paths according to a second preset path rule set;

[0099] If there is only one second preset path, the second preset path is determined as the reference flight path, and if there are a plurality of second preset paths, the reference flight path is determined from the plurality of second preset paths according to the state index of the aircraft.

[0100] In an embodiment provided by the present application, the first preset path rule includes the following contents:

[0101] The flight height corresponding to the flight path is greater than the highest altitude or the highest building in the flight area;

[0102] There is no same flight task as the current flight task in the same flight area;

[0103] The noise decibel of the aircraft is lower than the decibel requirement in the flight area;

[0104] The number of flight paths in the dangerous area is less than the number of flight paths in the safe area;

[0105] The second preset path rule includes the following contents:

[0106] The meteorological environment of the flight path meets the operation requirement of the safe operation of the aircraft;

[0107] The task saturation of the aircraft in the flight path is lower than the task saturation threshold;

[0108] The number of aircrafts in the flight path is less than the number saturation threshold;

[0109] The state index includes:

[0110] acquire power information and flight state information of the aircraft;

[0111] acquire path mileage corresponding to the flight path;

[0112] calculate economic indicators of each flight path in the plurality of second preset paths according to the power information, the flight state information and the path mileage;

[0113] take the flight path corresponding to the minimum indicator in the economic indicators as the reference flight path.

[0114] Specifically, the embodiment divides a flight area of the aircraft into a no-fly area, a dangerous area and a safe area, collects flight paths of the dangerous area and the safe area in a set after excluding the no-fly area, selects flight paths meeting preset path rules through setting the preset path rules, and takes the selected flight paths as the reference flight path. The reference flight path can provide data support and reference for subsequent acquisition of predicted flight paths, and improves accuracy and comprehensiveness of the flight paths.

[0115] As shown in Figure 3 In an embodiment provided by the present application, establishing the path planning model includes the following contents:

[0116] generate a three-dimensional multi-layer planning map in combination with the geographic information data and the flight environment data;

[0117] process the three-dimensional multi-layer planning map by using a convolutional neural network to generate a feature map;

[0118] construct a graph structure based on the feature map;

[0119] process the graph structure by using a graph neural network to generate the path planning model;

[0120] Specifically, constructing the graph structure includes:

[0121] perform feature mapping according to the feature map, take features in the feature map as node features of the graph structure, and define connections between nodes and weights thereof.

[0122] Specifically, the embodiment adopts a combination of a convolutional neural network (CNN) and a graph neural network (GNN) to construct a path planning model. By simultaneously utilizing the spatial features of image data and the relationship information of graph structure data, the spatial features and graph structure information of environmental data can be effectively integrated, thereby improving the accuracy and practicality of the path planning model. In the convolutional neural network, processing includes: performing convolution on a three-dimensional multi-layer planning map image in a convolution layer to extract local features; using a nonlinear function to activate the local features; performing a pooling operation in a pooling layer to reduce the size of the feature map; generating a plurality of feature maps through multi-layer convolution and pooling operations; in the graph neural network, processing includes: generating an embedding vector for each node; the embedding vector represents the features of the node and its context information in the graph structure; generating features of edges and describing the relationship and connection strength between nodes; performing message passing and updating node features in a graph convolution layer. The GNN can effectively process graph structure data and capture the relationship between nodes and the overall structure of the graph.

[0123] In an embodiment provided in the application, the path optimization algorithm adopts an A* algorithm and a particle swarm optimization algorithm; the predicted flight path is optimized by using the path optimization algorithm, specifically including:

[0124] generating an initial flight path by using the A* algorithm;

[0125] optimizing the initial flight path by using the particle swarm optimization algorithm, and outputting an optimal flight path.

[0126] Specifically, the embodiment combines the A* algorithm and the particle swarm optimization algorithm (PSO) to optimize the flight path. The A* algorithm is used to preliminarily determine a relatively reasonable initial flight path. While considering heuristic information, the A* algorithm can effectively find a relatively optimal path from the starting point to the ending point. Then, the particle swarm optimization algorithm (PSO) is used to refine and optimize the path generated by the A* algorithm, improve the smoothness and overall efficiency of the path, and further improve the path quality by simulating the flight of particles in the solution space to handle possible local optimal problems. This combination method can utilize the efficient search of the A* algorithm and the global optimization characteristics of the PSO, and achieve better flight path planning effect.

[0127] On the other hand, the embodiment adopts a combination of the A* algorithm and the particle swarm optimization algorithm to optimize the path. While being able to handle complex constraints and multi-objective optimization, the combination can also handle significant height changes in the path, and better solve the problem of dynamic environmental changes on the jump flight route.

[0128] Embodiment 2

[0129] Referring to Figure 4 The embodiment of the application provides a flight path planning system for a flight path planning method as described above, comprising:

[0130] a data acquisition module configured to acquire flight environment data and geographic information data in a flight area of the aircraft;

[0131] an optimal flight path generation module configured to determine a starting position and a target position of the aircraft, divide the flight area of the aircraft, and generate a reference flight path; establish a path planning model according to the geographic information data and the flight environment data, and generate a predicted flight path using the path planning model and the reference flight path; and optimize the predicted flight path using a path optimization algorithm to determine an optimal flight path;

[0132] an actual flight path generation module configured to establish a simulation test environment, perform path testing on the optimal flight path in the simulation test environment to obtain a test result, use a large model to predict a risk point in the optimal flight path and perform risk assessment to obtain an assessment result, adjust a path planning strategy based on the test result and the assessment result, and determine a final actual flight path;

[0133] a path planning database generation module configured to acquire real-time flight data of the aircraft on the actual flight path, input the real-time flight data into the path planning model to obtain a flight path error, perform path correction on the predicted flight path using the flight path error, and record a process of each path planning and a generated flight path to form a path planning database.

[0134] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0135] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above functional units and modules is taken as an example, and in actual application, the above functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software functional unit. In addition, the specific names of each functional unit and module are only for convenient distinction, and do not limit the protection scope of the application. The specific working process of the units and modules in the system can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0136] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0137] The above is only a preferred embodiment of the present application, and is not intended to limit the present application in any form. Although the present application has been disclosed as the above preferred embodiment, it is not intended to limit the present application. Any person skilled in the art can make slight changes or modifications to the above disclosed technical content to obtain equivalent embodiments with equivalent changes, without departing from the scope of the technical solution of the present application. Any brief modification, equivalent change and modification of the above embodiments made according to the technical essence of the present application still belongs to the scope of the technical solution of the present application.

Claims

1. A method for planning a jump flight trajectory path of an aircraft, characterized in that: The method comprises the following steps: Collecting flight environment data and geographic information data in the flight area of the aircraft; Determining the starting position and target position of the aircraft and dividing the flight area of the aircraft to generate a reference flight path; Building a path planning model according to the geographic information data and the flight environment data, and generating a predicted flight path by using the path planning model and the reference flight path; Optimizing the predicted flight path by using a path optimization algorithm to determine an optimal flight path; Building a simulation test environment and performing path testing on the optimal flight path in the simulation test environment to obtain a test result; Using a large model to predict risk points in the optimal flight path and performing risk assessment to obtain an assessment result; Adjusting the path planning strategy based on the test result and the assessment result and determining a final actual flight path; Obtaining real-time flight data of the aircraft on the actual flight path and inputting the real-time flight data into the path planning model to obtain a flight path error; Correcting the predicted flight path by using the flight path error; Recording the process of each path planning and the generated flight path to form a path planning database.

2. The method of claim 1, wherein: The flight environment data includes static obstacle data, dynamic obstacle data and meteorological data; the geographic information data includes terrain data, topographic map data and satellite image data.

3. The method of claim 1, wherein: The flight area of the aircraft is divided to generate a reference flight path, specifically comprising: Determining a plurality of basic flight paths according to the starting position and target position of the aircraft; Dividing the flight area to determine no-fly areas, dangerous areas and safe areas; Excluding flight paths located in the no-fly areas from the basic flight paths, and collecting the remaining paths in a flight path set; Setting a first preset path rule and selecting one or more paths that meet the rule in the flight path set as a first preset path; If there is only one first preset path, the first preset path is determined as the reference flight path; if there are multiple first preset paths, one or more second preset paths are determined from the multiple first preset paths according to a second preset path rule; If there is only one second preset path, the second preset path is determined as the reference flight path; if there are multiple second preset paths, the reference flight path is determined from the multiple second preset paths according to a state index of the aircraft.

4. The method of claim 3, wherein: The first preset path rule comprises the following contents: The flight height corresponding to the flight path is greater than the highest altitude or the highest building in the flight area; There is no same flight task as the current flight task in the same flight area; The noise decibel of the aircraft is lower than the decibel requirement in the flight area; The number of flight paths in the dangerous area is less than the number of flight paths in the safe area.

5. The method of claim 3, wherein: The second preset path rule comprises the following contents: The meteorological environment of the flight path meets the operation requirement of the safe operation of the aircraft; The task saturation of the aircraft in the flight path is lower than the task saturation threshold; The number of aircrafts in the flight path is less than the number threshold.

6. The method of claim 3, wherein: The state index comprises: Obtaining the power information and flight state information of the aircraft; Obtaining the path mileage corresponding to the flight path; According to the electric quantity information, the flight state information and the path mileage, an economic index of each flight path in a plurality of second preset paths is calculated; The flight path corresponding to the minimum index in the economic index is taken as a reference flight path.

7. The method of claim 1, wherein: The path planning model is established, including the following contents: A three-dimensional multi-layer planning map is generated in combination with the geographic information data and the flight environment data; A convolutional neural network is used to process the three-dimensional multi-layer planning map to generate a feature map; A graph structure is constructed based on the feature map; A graph neural network is used to process the graph structure to generate the path planning model; The graph structure is constructed as follows: According to the feature mapping of the feature map, the features in the feature map are taken as node features of the graph structure, and the connections and weights between nodes are defined.

8. The method of claim 1, wherein: The path optimization algorithm uses A* algorithm and particle swarm optimization algorithm.

9. The method of claim 8, wherein: The path optimization algorithm is used to optimize the predicted flight path, specifically including: An initial flight path is generated using A* algorithm; The initial flight path is optimized using particle swarm optimization algorithm to output an optimal flight path.

10. A skip flight path planning system for an aircraft, applied to the skip flight path planning method according to any one of claims 1-9, characterized in that: The data acquisition module is used to acquire flight environment data and geographic information data in the flight area of the aircraft. The optimal flight path generation module is used to determine the starting position and target position of the aircraft and divide the flight area of the aircraft to generate a reference flight path; a path planning model is established according to the geographic information data and the flight environment data, and a predicted flight path is generated using the path planning model and the reference flight path; the path optimization algorithm is used to optimize the predicted flight path to determine the optimal flight path. The actual flight path generation module is used to establish a simulation test environment and perform path testing on the optimal flight path in the simulation test environment to obtain a test result. A large model is used to predict risk points in the optimal flight path and perform risk assessment to obtain an evaluation result; based on the test result and the evaluation result, the path planning strategy is adjusted and a final actual flight path is determined. The path planning database generation module is used to acquire real-time flight data of the aircraft on the actual flight path and input the real-time flight data into the path planning model to obtain a flight path error; the flight path error is used to correct the predicted flight path; the process of each path planning and the generated flight path are recorded to form a path planning database. ​

Images