A path planning method and system for low-altitude aircraft navigation guidance

Abstract

The present invention relates to a path planning method and system for low-altitude aircraft navigation guidance. The method calculates probability density values ​​for preprocessed prior flight data based on kernel density estimation, maps the normalized probability density values ​​to a grid map of a rasterized environmental model, generates a flight path safety empirical distribution map, expands obstacle area boundaries based on a safety distance constraint matrix, generates a restricted area matrix, generates an initial path based on a bidirectional A*-KDE algorithm cost function, the flight path safety empirical distribution map, and the restricted area matrix, removes redundant nodes from the initial path, and performs smoothing processing to obtain a flight route. Using prior flight data to obtain a flight route can reduce the deviation between the flight route and the actual navigation path. Furthermore, expanding the obstacle area boundaries based on the safety distance constraint matrix fully considers the obstacle safety distance, thereby reducing the risk of low-altitude aircraft colliding with obstacles.

Description

Technical Field

[0001] The present invention relates to the technical field of low-altitude aircraft flight control, and in particular to a path planning method and system for low-altitude aircraft navigation guidance. Background Art

[0002] Low-altitude aircraft path planning aims to create an optimal or safe path from a starting point to a destination, ensuring the aircraft can complete its mission safely and efficiently. However, existing low-altitude aircraft path planning technologies often exhibit significant deviations from the actual flight path. Furthermore, the planned path can easily approach obstacles, creating the risk of collision. Summary of the Invention

[0003] The present invention provides a path planning method and system for low-altitude aircraft navigation guidance, aiming to solve at least one of the technical problems existing in the prior art.

[0004] The technical solution of the present invention is a path planning method for low-altitude aircraft navigation guidance, comprising:

[0005] Acquiring prior flight data of low-altitude aircraft in a target area and preprocessing the prior flight data;

[0006] Calculating probability density values ​​for the preprocessed priori flight data based on kernel density estimation, normalizing the probability density values, and mapping the normalized probability density values ​​onto a grid map of a gridded environment model to generate a flight route safety empirical distribution map;

[0007] Expand the obstacle area boundary based on the safety distance constraint matrix to generate a restricted area matrix including a safety buffer zone;

[0008] Generate an initial path according to the bidirectional A*-KDE algorithm cost function, the flight route safety experience distribution map and the restricted area matrix;

[0009] The initial path is smoothed by removing redundant nodes and obtaining a flight route.

[0010] According to some embodiments of the present invention, preprocessing the priori flight data includes:

[0011] The priori flight data are cleaned and preprocessed, and missing sampling points are filled by cubic spline interpolation.

[0012] According to some embodiments of the present invention, the step of calculating a probability density value for the preprocessed priori flight data based on kernel density estimation, normalizing the probability density value, and mapping the normalized probability density value to a grid map of the gridded environment model to generate a flight route safety experience distribution map includes:

[0013] Mapping the trajectory points of the pre-processed priori flight data to a three-dimensional block of the rasterized environment model, and calculating the probability density value of the three-dimensional block based on the kernel density estimation;

[0014] The probability density values ​​are normalized, and the normalized probability density values ​​are mapped to the grid map of the gridded environment model to generate the flight route safety experience distribution map.

[0015] According to some embodiments of the present invention, the kernel density estimation is expressed as:

[0016]

[0017] Where p(G) is the probability density value of the prior flight data at the position of the cubic block G, n is the number of trajectory points in the data set of the prior flight data, h is the bandwidth, d is the dimension of the data, K(·) is the kernel function, X i is the i-th trajectory point in the data set of the priori flight data;

[0018] The normalization process is expressed as:

[0019]

[0020] Where, d norm (G) is the probability density value of the prior flight data after normalization at the cubic block G, p max =max(p(G)) is the maximum value of the probability density value.

[0021] According to some embodiments of the present invention, generating the initial path based on the bidirectional A*-KDE algorithm cost function, the flight path safety experience distribution map, and the restricted area matrix includes:

[0022] Generate a path initial node according to the bidirectional A*-KDE algorithm cost function, the flight route safety experience distribution map and the restricted area matrix;

[0023] A bidirectional search mechanism is adopted to simultaneously perform forward and reverse path searches on the initial node of the path, and the initial path is generated when the forward and reverse paths intersect.

[0024] According to some embodiments of the present invention, removing redundant nodes and performing smoothing on the initial path to obtain a flight route includes:

[0025] removing the redundant nodes from the initial path using a sight line detection algorithm;

[0026] The initial path after removing the redundant nodes is smoothed using a Bezier curve to obtain the flight route.

[0027] According to some embodiments of the present invention, removing the redundant nodes from the initial path using a line-of-sight detection algorithm includes:

[0028] Extracting nodes from the initial path based on a sight line detection algorithm;

[0029] Starting from the first node, traverse each node to determine whether the line of sight between the current node and the subsequent node is blocked by an obstacle or a dangerous node that does not satisfy the safety distance constraint matrix;

[0030] If the line of sight between the current node and the subsequent node is unobstructed, then

[0031] Connecting the current node and the subsequent node to obtain a connecting line;

[0032] Calculate the vertical distance from the intermediate original node between the current node and the subsequent node to the connecting line to obtain an offset distance;

[0033] Determining whether the offset distance exceeds a deviation threshold;

[0034] If the offset distance does not exceed the deviation threshold, the intermediate original node is used as the redundant node, the current node and the subsequent node are connected, and the redundant node is removed; otherwise, the connection between the current node and the subsequent node is abandoned, and the intermediate original node is retained.

[0035] According to some embodiments of the present invention, if the offset distance does not exceed the deviation threshold, it is expressed as:

[0036]

[0037] Wherein, δ is the deviation threshold.

[0038] According to some embodiments of the present invention, the cost function of the bidirectional A*-KDE algorithm is expressed as:

[0039]

[0040] Where g(n) is the actual cost of the path, h(n) is the heuristic cost, P(n) is the kernel density potential field cost, F(neighbor(n)) is the cost function of the bidirectional A*-KDE algorithm, and α is the weight parameter of the kernel density potential field cost.

[0041] The technical solution of the present invention also relates to an electronic device, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the path planning method for low-altitude aircraft navigation guidance as described above.

[0042] The technical solution of the present invention also relates to a computer system, which includes a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, it implements the path planning method for low-altitude aircraft navigation guidance as described above.

[0043] The beneficial effects of the present invention include: obtaining prior flight data of low-altitude aircraft in a target area, preprocessing the prior flight data, then calculating a probability density value for the preprocessed prior flight data based on kernel density estimation, normalizing the probability density value, mapping the normalized probability density value to a grid map of a rasterized environment model, generating a flight route safety experience distribution map, expanding the obstacle area boundary based on a safety distance constraint matrix, generating a restricted area matrix including a safety buffer zone, generating an initial path based on a bidirectional A*-KDE algorithm cost function, the flight route safety experience distribution map, and the restricted area matrix, removing redundant nodes from the initial path and performing smoothing to obtain a flight route. Using the prior flight data of the low-altitude aircraft to obtain the flight route can reduce the deviation between the flight route and the actual navigation path, and expanding the obstacle area boundary based on the safety distance constraint matrix fully considers the obstacle safety distance, thereby reducing the risk of the low-altitude aircraft colliding with obstacles.

[0044] In addition, additional aspects and advantages of the present invention will be set forth in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is an optional flow chart of a path planning method for low-altitude aircraft navigation guidance in an embodiment of the present invention.

[0046] Figure 2 This is an optional flow chart for generating a flight route safety experience distribution map based on kernel density estimation in an embodiment of the present invention.

[0047] Figure 3This is an optional flow chart for obtaining a flight route based on an initial path in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of this application can be combined with each other unless there is a conflict.

[0049] It should be noted that, unless otherwise specified, when a feature is referred to as being "fixed" or "connected" to another feature, it may be directly fixed or connected to the other feature or indirectly fixed or connected to the other feature. Furthermore, terms such as "upper," "lower," "left," "right," "top," and "bottom" used in this disclosure are intended solely to describe the relative positions of the components of the disclosure as shown in the accompanying drawings.

[0050] In addition, unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art. The terms used in this specification are only for describing specific embodiments and are not intended to limit the present invention. The term "and / or" as used herein includes any combination of one or more of the related listed items.

[0051] It should be understood that although the terms first, second, third, etc. may be used to describe various elements in the present invention, these elements should not be limited to these terms. These terms are only used to distinguish elements of the same type from each other. For example, a first element may also be referred to as a second element, and similarly, a second element may also be referred to as a first element without departing from the scope of the present invention.

[0052] Reference Figures 1 to 3 In some embodiments, the technical solution of the present invention is a path planning method for low-altitude aircraft navigation guidance, including but not limited to steps 101 to 105. Each step is introduced in turn below.

[0053] Step 101: Acquire prior flight data of low-altitude aircraft in the target area and pre-process the prior flight data.

[0054] In a specific embodiment, the low-altitude aircraft is a UAV. Priori flight data of the UAV in the target area is obtained and pre-processed.

[0055] In some embodiments, prior flight data of low-altitude aircraft in the target area is obtained. Before preprocessing the prior flight data, the path planning method for low-altitude aircraft navigation guidance also includes rasterizing spatial modeling of the target area to obtain a rasterized environment model.

[0056] Specifically, for rasterized spatial modeling, rasterization involves dividing the target area into 100×100 grids, where 100 can be any positive integer other than 100. The specific value is selected based on actual conditions and is not specifically limited in this invention. Spatial rasterization involves dividing the target area into multiple 3D blocks.

[0057] In a specific embodiment, before performing rasterized spatial modeling on the target area and obtaining the rasterized environment model, the path planning method for low-altitude aircraft navigation guidance further includes confirming the target area based on the starting point and end point of the low-altitude aircraft flight.

[0058] In a specific embodiment, a gridded space model is performed on the target area using a cubic block partitioning method to obtain a gridded environment model.

[0059] In a specific embodiment, actual map data of the target area is obtained, and the actual map data of the target area is processed using grayscale image processing technology to generate a grayscale processed map, and then the grayscale processed map is rasterized, and the obstacle information in the rasterized map is mapped to the rasterized environment model.

[0060] Specifically, in the rasterized environment model, black cubes represent the location and size of obstacles, and white cubes represent areas where low-altitude aircraft can pass. Prior flight data is historical flight data.

[0061] In some embodiments, preprocessing the prior flight data includes cleaning and preprocessing the prior flight data, and filling in missing sampling points using cubic spline interpolation. It is understood that cleaning and preprocessing the prior flight data optimizes the quality of the prior flight data and improves the accuracy of the flight route.

[0062] In a specific embodiment, data cleaning and data preprocessing of the prior flight data include: formatting the timestamp, latitude and longitude, speed and heading fields of the prior flight data; removing abnormal position information, and removing abnormal speed and heading data points.

[0063] Step 102: Based on kernel density estimation, calculate the probability density value of the preprocessed prior flight data, normalize the probability density value, and map the normalized probability density value to the grid map of the rasterized environment model to generate a flight route safety experience distribution map.

[0064] Specifically, Kernel Density Estimation (KDE) is a nonparametric probability density function estimation method. It should be noted that the normalized probability density values ​​are mapped to each cubic block in the grid map of the rasterized environment model. The probability density values ​​represent safety experience; larger values ​​indicate greater safety. The grid map contains the probability density values, forming a flight path safety experience distribution map.

[0065] Reference Figure 2 In some embodiments, based on kernel density estimation, probability density values ​​are calculated for the preprocessed prior flight data, the probability density values ​​are normalized, and the normalized probability density values ​​are mapped to a grid map of a rasterized environment model to generate a flight route safety experience distribution map, including but not limited to the following steps 201 to 202.

[0066] Step 201: Mapping the trajectory points of the pre-processed priori flight data to the three-dimensional blocks of the rasterized environment model, and calculating the probability density value of the three-dimensional blocks based on kernel density estimation.

[0067] Step 202: normalize the probability density values, map the normalized probability density values ​​to a grid map of the gridded environment model, and generate a flight path safety experience distribution map.

[0068] Specifically, the coordinates of the prior flight data are three-dimensional. Using cubes as basic units, the probability density of low-altitude aircraft routes is statistically analyzed. If the cubes are clustered with trajectory points, the probability density of the cubes is high. If the cubes are relatively small or the cubes are far from the trajectory points, the probability density of the cubes is low.

[0069] In some embodiments, the kernel density estimate is expressed as:

[0070]

[0071] Where p(G) is the probability density value of the prior flight data at the position of the cubic block G, n is the number of trajectory points in the dataset of the prior flight data, h is the bandwidth, d is the dimension of the data, K(·) is the kernel function, X i is the i-th trajectory point in the dataset of prior flight data;

[0072] The normalization process is expressed as:

[0073]

[0074] Where, d norm (G) is the probability density value of the normalized prior flight data at the cubic block G, p max=max(p(G)) is the maximum value of the probability density value.

[0075] Specifically, X is the currently observed trajectory point, which is the point where the density needs to be estimated. K(·) is the kernel function, and a Gaussian kernel can also be used. The kernel density estimation after using the Gaussian kernel function is expressed as:

[0076]

[0077] Where σ is the potential field diffusion coefficient, exp(·) is the exponential function, for example, exp(m) represents the base of the natural logarithm e to the power of m. T represents the transposition operation, (XX i ) T Is the vector (XX i ), which converts a column vector into a row vector.

[0078] Step 103: Expand the obstacle area boundary based on the safety distance constraint matrix to generate a restricted area matrix including a safety buffer zone.

[0079] In a specific embodiment, the safety distance constraint matrix A nn It is a matrix of size n×n, which aims to expand the obstacle area in the route to form a restricted area matrix including a safety buffer zone. Specifically, by the preset safety distance d safe Adjust the safety distance constraint matrix A nn The size of the safety distance constraint matrix A is used to ensure that during the node expansion process, only nodes that maintain a preset safety distance from obstacles are selected for expansion. nn and the preset safety distance d safe The relationship is expressed as:

[0080] A nn ,n=2·d safe +1,

[0081] When d safe When the value is 1, the grid units around the obstacle will not meet the safety distance constraint.

[0082] Specifically, after the target area is rasterized, multiple cubes are formed. Obstacles will not be selected as path extensions. safe When the value is 1, a cube close to an obstacle will not be used as a node for path selection, so that the generated path and the obstacle have a certain distance.

[0083] Step 104: Generate an initial path based on the bidirectional A*-KDE algorithm cost function, the flight path safety experience distribution map, and the restricted area matrix.

[0084] In one specific embodiment, a bidirectional A*-KDE algorithm cost function is designed to integrate the actual path cost, heuristic cost, and kernel density potential field cost, guiding the path to prioritize high-safety density areas for path search. Specifically, the bidirectional A*-KDE algorithm is a combination of the A* algorithm and the KDE algorithm.

[0085] In some embodiments, generating an initial path based on a bidirectional A*-KDE algorithm cost function, a flight path safety experience distribution map, and a restricted area matrix includes:

[0086] Generate the initial nodes of the path based on the cost function of the bidirectional A*-KDE algorithm, the flight line safety experience distribution map and the restricted area matrix;

[0087] A bidirectional search mechanism is used to simultaneously search the forward and reverse paths of the initial node of the path, and the initial path is generated when the forward and reverse paths intersect.

[0088] Specifically, when the forward and reverse paths intersect, a path backtracking algorithm is used to generate the initial path and record the coordinates and index information of the intersection node. This bidirectional search mechanism significantly shortens the calculation time of path planning.

[0089] Step 105: Remove redundant nodes from the initial path and perform smoothing to obtain a flight route.

[0090] Reference Figure 3 In some embodiments, redundant nodes are removed from the initial path and smoothing is performed to obtain a flight route, including but not limited to the following steps 301 to 302.

[0091] Step 301: Use a sight line detection algorithm to remove redundant nodes from the initial path.

[0092] Step 302: Use a Bezier curve to smooth the initial path after removing redundant nodes to obtain a flight route.

[0093] In a specific embodiment, the path curvature continuity of the initial path after removing redundant nodes is optimized by Bezier curve smoothing.

[0094] Specifically, the basic idea behind the Line of Sight (LOS) algorithm is to determine whether there is an unobstructed straight path between an observation point and a target point. This algorithm calculates a virtual line between the current position and the target path, as well as the angular deviation between this virtual line and the forward direction, to guide the system in adjusting its heading and speed to maintain the intended path. A Bezier curve is used to smooth and optimize the initial path after removing redundant nodes, improving the continuity, stability, and safety of the flight path.

[0095] In some embodiments, using a sight line detection algorithm to remove redundant nodes from the initial path includes:

[0096] Extract nodes from the initial path based on the line of sight detection algorithm;

[0097] Starting from the first node, traverse each node to determine whether the line of sight between the current node and the subsequent nodes is blocked by obstacles or dangerous nodes that do not meet the safety distance constraint matrix;

[0098] If the line of sight between the current node and the subsequent node is unobstructed, then

[0099] Connect the current node and the subsequent node to obtain a connecting line;

[0100] Calculate the vertical distance from the middle original node to the connecting line between the current node and the subsequent node to obtain the offset distance;

[0101] Determine whether the offset distance exceeds the deviation threshold;

[0102] If the offset distance does not exceed the deviation threshold, the middle original node is used as a redundant node, the current node and the subsequent node are connected, and the redundant node is removed; otherwise, the connection between the current node and the subsequent node is abandoned, and the middle original node is retained.

[0103] In a specific embodiment, if the line of sight between the current node and the subsequent node is blocked, further connections between the current node and the subsequent node are impossible, and the redundant node removal operation is terminated. At this point, based on the actual situation, the next smoothing operation can be performed, or the previous step can be returned to and the initial path can be generated again based on the cost function of the bidirectional A*-KDE algorithm, the flight path safety experience distribution map, and the restricted area matrix.

[0104] In a specific embodiment, when the traversal reaches the last node, the redundant node removal operation is terminated.

[0105] Specifically, a dangerous node that does not satisfy the safety distance constraint matrix is ​​one where the distance between the dangerous node and the obstacle does not satisfy the safety distance constraint matrix, making it impossible to expand the obstacle area boundary to include the node in the safety buffer zone. It can be understood that removing redundant nodes from the initial path optimizes the flight path length.

[0106] In some embodiments, if the offset distance does not exceed the deviation threshold, it is expressed as:

[0107]

[0108] Where δ is the deviation threshold, E, F, and C are the three-dimensional normal vectors of the initial path after removing redundant nodes, D is a constant, and x i 、y i 、z iare the x, y, and z coordinates of the original intermediate node, respectively. Specifically, this formula is a constraint formula that limits the maximum offset distance between the path optimized by the LOS algorithm and the initial path.

[0109] In some embodiments, the cost function of the bidirectional A*-KDE algorithm is expressed as:

[0110]

[0111] Where g(n) is the actual cost of the path, h(n) is the heuristic cost, P(n) is the kernel density potential field cost, F(neighbor(n)) is the cost function of the bidirectional A*-KDE algorithm, α is the weight parameter of the kernel density potential field cost, and d safe is the preset safety distance, and neighbor(n) represents the neighboring node of the current node n.

[0112] Specifically, the actual path cost represents the path length from the starting point to the current node, the heuristic cost represents the estimated cost from the current node to the target node, the kernel density potential field cost represents the potential field cost generated by the kernel density estimation, and the weight parameter of the kernel density potential field cost is used to adjust the balance between path length and safety.

[0113] In a specific embodiment, the actual path cost g(n) is expressed as:

[0114]

[0115] Where, pos x (n), pos y (n) and pos z (n) are the x, y, and z coordinates of the current node n, and parent(n) represents the parent node of the current node n.

[0116] In a specific embodiment, the heuristic cost h(n) is used to estimate the shortest path cost from the current node to the target node, which is expressed as follows:

[0117]

[0118] Where, dx = |pos x (goal)-pos x (n)|,dy=|pos y (goal)-pos y (n)|, dz=|pos z (goal)-pos z (n)|, goal represents the location of the target node.

[0119] In a specific embodiment, the kernel density potential field cost P(n) guides the path to avoid low-density areas through the normalized probability density value of the kernel density estimate. The exponential form of the Gaussian distribution can achieve rapid density decay, effectively amplify the advantages of high-density areas, suppress the path selection risk in low-density areas, and at the same time avoid excessive fluctuations in values, which helps to stabilize the path planning. The controllable parameters A and σ enable the path planning method for low-altitude aircraft navigation guidance to flexibly adapt to different navigation scenarios. The design of the potential field cost function adopts the Gaussian distribution form, which is expressed as:

[0120]

[0121] Where exp(·) is an exponential function, A is the potential field strength coefficient, which controls the degree of influence of the density field on the path. In high-risk scenarios, increasing A can enhance the penalty effect of low-density areas. σ is the potential field diffusion coefficient, which determines the range of the density field's influence. A smaller σ limits the influence of high density and emphasizes localization, while a larger σ expands the range of density influence and is suitable for more global path search needs. d(n) is the normalized probability density value at location n, calculated using KDE.

[0122] In a specific embodiment, the Bezier curve can smoothly transition the path by adjusting the control points, which is expressed as:

[0123]

[0124] Where B(t) is the Bezier curve, and t represents a parameter value on the Bezier curve, which is used to control the position of the Bezier curve. The expression of the Bezier curve uses this parameter t to interpolate within the interval [0,1] of the Bezier curve.

[0125] Specifically, n is the highest degree of the Bezier curve, which is equal to the number of control points minus 1. For example, if a Bezier curve has 4 control points, then n = 3, which is called a cubic Bezier curve. In, P i is the i-th control point; is the binomial coefficient, which is a mathematical calculation, namely

[0126]

[0127] It should be noted that a Bézier curve is a vector curve defined by control points.

[0128] Among them, control points: In a Bezier curve, control points are the points that define the shape of the Bezier curve. The Bezier curve does not pass directly through these control points, but they control the curvature and path of the Bezier curve. The start control point and the end control point are the endpoints of the Bezier curve. The Bezier curve will start from the start control point and eventually reach the end control point. The intermediate control points (for quadratic or higher-order Bezier curves) determine the degree and direction of the curvature of the Bezier curve. By adjusting the position of these control points, the shape of the Bezier curve can be changed. For example, for a quadratic Bezier curve, there are three control points: a start point, an end point, and an intermediate control point. For a cubic Bezier curve, there are four control points: a start point, an end point, and two intermediate control points.

[0129] In a specific embodiment, the initial path after removing redundant nodes is segmented to obtain segmented paths. A minimum safety distance check is then performed to ensure that the segmented paths meet the minimum safety distance requirement. The order of the Bezier curve is determined based on the number of turning points in the segmented path. If the segmented path passes through obstacles or dangerous nodes, control points of the Bezier curve are added. The segmented paths are then smoothed and optimized using the Bezier curve, and the smoothed and optimized segmented paths are connected to obtain the flight path. The minimum safety distance is a deviation threshold δ.

[0130] In a specific embodiment, generating the path initial node according to the bidirectional A*-KDE algorithm cost function, the flight route safety experience distribution map and the restricted area matrix includes:

[0131] By traversing each node, the bidirectional A*-KDE algorithm cost function comprehensively considers the actual path cost, heuristic distance, and potential impact of the density field. The actual path cost, heuristic cost, and kernel density potential field cost are integrated to guide the priority selection of high safety density areas in the flight route safety experience distribution map for path search. The expansion direction of the path points is strictly restricted by the restricted area matrix to limit the selection of dangerous nodes that do not meet the safety distance constraint matrix. Finally, the initial node of the path is obtained, ensuring the safety and rationality of the path search.

[0132] It can be understood that the flight route safety experience distribution map is generated by using kernel density estimation, and the bidirectional A*-KDE algorithm cost function is used to guide the priority selection of high safety density areas of the flight route safety experience distribution map for path search, which narrows the path search range, reduces the computational complexity, and can avoid potential risk areas.

[0133] In one possible implementation, the path planning method for low-altitude aircraft navigation guidance is applied to the main control unit of the low-altitude aircraft, and works in conjunction with the flight control system to achieve precise control of the low-altitude aircraft's flight status and efficient execution of tasks.

[0134] In a specific implementation, the path planning method for low-altitude aircraft navigation guidance is applied to the main control unit of the UAV, working in conjunction with the flight control system to achieve precise control of the UAV's flight status and efficient execution of tasks.

[0135] As can be seen, gridded spatial modeling of the target area is performed to obtain a gridded environmental model. Prior flight data of low-altitude aircraft in the target area is obtained, preprocessed, and probability density values ​​are calculated for the preprocessed prior flight data based on kernel density estimation. These probability density values ​​are normalized and mapped to the grid map of the gridded environmental model. A flight path safety empirical distribution map is generated, the obstacle area boundary is expanded based on the safety distance constraint matrix, and a restricted area matrix containing a safety buffer zone is generated. An initial path is generated based on the cost function of the bidirectional A*-KDE algorithm, the flight path safety empirical distribution map, and the restricted area matrix. Redundant nodes are removed from the initial path and smoothed to obtain the flight route. Using prior flight data of low-altitude aircraft to obtain the flight route can reduce the deviation between the flight route and the actual navigation path. Furthermore, expanding the obstacle area boundary based on the safety distance constraint matrix fully considers the obstacle safety distance, thereby reducing the risk of low-altitude aircraft colliding with obstacles.

[0136] An embodiment of the present invention further provides an electronic device comprising a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the aforementioned path planning method for low-altitude aircraft navigation guidance. The electronic device can be any intelligent terminal, such as a computer.

[0137] An embodiment of the present invention further provides a computer system, which includes a storage medium storing a computer program. When the computer program is executed by a processor, the computer system implements the above-mentioned path planning method for low-altitude aircraft navigation guidance.

[0138] It should be appreciated that the method steps in the embodiments of the present invention can be implemented or executed by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory. The method can use standard programming techniques. Each program can be implemented in a high-level procedural or object-oriented programming language to communicate with the computer system. However, if desired, the program can be implemented in assembly or machine language. In any case, the language can be a compiled or interpreted language. In addition, for this purpose, the program can be run on a programmed application-specific integrated circuit.

[0139] Furthermore, the operations of the processes described herein may be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by the context. The processes described herein (or variations and / or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that is executed collectively on one or more processors, by hardware, or a combination thereof. The computer program includes a plurality of instructions that can be executed by one or more processors.

[0140] Further, the methods can be implemented in any type of computing platform that is operably connected to a suitable computer, including but not limited to a personal computer, a minicomputer, a mainframe, a workstation, a network or distributed computing environment, a separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, etc. Various aspects of the present invention can be implemented as machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, an optical read and / or write storage medium, RAM, ROM, etc., so that it can be read by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the processes described herein. In addition, the machine-readable code, or portions thereof, can be transmitted over a wired or wireless network. When such media includes instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor, the invention described herein includes these and other different types of non-transitory computer-readable storage media. When programmed according to the methods and techniques of the present invention, the present invention can also include the computer itself.

[0141] The computer program can be applied to input data to perform the functions described herein, thereby converting the input data to generate output data that is stored in a non-volatile memory. The output information can also be applied to one or more output devices such as a display. In a preferred embodiment of the present invention, the converted data represents a physical and tangible object, including a specific visual depiction of the physical and tangible object produced on the display.

[0142] The above description is merely a preferred embodiment of the present invention. The present invention is not limited to the aforementioned embodiments. As long as the technical effects of the present invention are achieved by the same means, any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention. Within the scope of protection of the present invention, various modifications and variations of the technical solutions and / or implementation methods are possible.

Claims

1. A path planning method for low-altitude aircraft navigation guidance, characterized in that: include: Acquiring prior flight data of low-altitude aircraft in a target area and preprocessing the prior flight data; Calculating probability density values ​​for the preprocessed priori flight data based on kernel density estimation, normalizing the probability density values, and mapping the normalized probability density values ​​onto a grid map of a gridded environment model to generate a flight route safety empirical distribution map; Expand the obstacle area boundary based on the safety distance constraint matrix to generate a restricted area matrix including a safety buffer zone; Generate an initial path according to the bidirectional A*-KDE algorithm cost function, the flight route safety experience distribution map and the restricted area matrix; Removing redundant nodes from the initial path and performing smoothing processing to obtain a flight route; The method of calculating a probability density value for the preprocessed priori flight data based on kernel density estimation, normalizing the probability density value, and mapping the normalized probability density value to a grid map of the gridded environment model to generate a flight route safety experience distribution map includes: Mapping the trajectory points of the pre-processed priori flight data to a three-dimensional block of the rasterized environment model, and calculating the probability density value of the three-dimensional block based on the kernel density estimation; Normalizing the probability density values, and mapping the normalized probability density values ​​to the grid map of the gridded environment model to generate the flight path safety experience distribution map; The kernel density estimate is expressed as: Where p(G) is the probability density value of the prior flight data at the position of the cubic block G, n is the number of trajectory points in the data set of the prior flight data, h is the bandwidth, d is the dimension of the data, K(·) is the kernel function, X i is the i-th trajectory point in the data set of the priori flight data; The normalization process is expressed as: Where, d norm (G) is the probability density value of the prior flight data after normalization at the cubic block G, p max =max(p(G)) is the maximum value of the probability density value.

2. A path planning method for low-altitude aircraft navigation guidance according to claim 1, characterized in that: Preprocessing the priori flight data includes: The priori flight data are cleaned and preprocessed, and missing sampling points are filled by cubic spline interpolation.

3. A path planning method for low-altitude aircraft navigation guidance according to claim 1, characterized in that: The generating of the initial path according to the bidirectional A*-KDE algorithm cost function, the flight route safety experience distribution map and the restricted area matrix includes: Generate a path initial node according to the bidirectional A*-KDE algorithm cost function, the flight route safety experience distribution map and the restricted area matrix; A bidirectional search mechanism is adopted to simultaneously perform forward and reverse path searches on the initial node of the path, and the initial path is generated when the forward and reverse paths intersect.

4. A path planning method for low-altitude aircraft navigation guidance according to claim 1, characterized in that: The initial path is subjected to a smoothing process by removing redundant nodes and obtaining a flight route, including: removing the redundant nodes from the initial path using a sight line detection algorithm; The initial path after removing the redundant nodes is smoothed using a Bezier curve to obtain the flight route.

5. A path planning method for low-altitude aircraft navigation guidance according to claim 4, characterized in that: The removing of the redundant nodes from the initial path by using a sight line detection algorithm includes: Extracting nodes from the initial path based on a sight line detection algorithm; Starting from the first node, traverse each node to determine whether the line of sight between the current node and the subsequent node is blocked by an obstacle or a dangerous node that does not satisfy the safety distance constraint matrix; If the line of sight between the current node and the subsequent node is unobstructed, then Connecting the current node and the subsequent node to obtain a connecting line; Calculate the vertical distance from the intermediate original node between the current node and the subsequent node to the connecting line to obtain an offset distance; Determining whether the offset distance exceeds a deviation threshold; If the offset distance does not exceed the deviation threshold, the intermediate original node is used as the redundant node, the current node and the subsequent node are connected, and the redundant node is removed; otherwise, the connection between the current node and the subsequent node is abandoned, and the intermediate original node is retained.

6. A path planning method for low-altitude aircraft navigation guidance according to claim 5, characterized in that: If the offset distance does not exceed the deviation threshold, it is expressed as: Where δ is the deviation threshold, E, F, and C are the three-dimensional normal vectors of the initial path after removing redundant nodes, D is a constant, and x i 、y i 、z i are the x, y, and z coordinates of the middle original node respectively.

7. A path planning method for low-altitude aircraft navigation guidance according to claim 1, characterized in that: The cost function of the bidirectional A*-KDE algorithm is expressed as: Where g(n) is the actual cost of the path, h(n) is the heuristic cost, P(n) is the kernel density potential field cost, F(neighbor(n)) is the cost function of the bidirectional A*-KDE algorithm, α is the weight parameter of the kernel density potential field cost, and d safe is the preset safety distance, and neighbor(n) represents the neighboring node of the current node n.

8. A computer system comprising a storage medium storing a computer program, wherein: When the computer program is executed by a processor, the path planning method for low-altitude aircraft navigation guidance according to any one of claims 1 to 7 is implemented.

Images