Flying-around multipath generation method and device, equipment and storage medium

Abstract

According to the fly-around multipath generation method and device, the equipment and the storage medium provided by the invention, the weather radar echo picture of the target area is processed to obtain the binary matrix for solving the first fly-around path; carrying out clustering processing on the binary matrix to obtain boundaries of different weather blocks in the map, and filling the weather boundaries to obtain a first binary matrix for fly-around path search; according to the first binary matrix, the shortest path of the fly-around starting point and the fly-around end point is determined, the optimal fly-around path is obtained, and a plurality of available paths are obtained by using a path-finding algorithm for multiple times through a method of closing a narrow channel passed by the optimal path. According to the method, the weather radar echo picture of the target area is obtained in real time through the weather radar, the current weather condition can be reflected in real time, so that multiple fly-around paths can be quickly and accurately generated under the complex weather condition, an initial solution set is provided for air traffic flow overall planning under the thunderstorm condition, and the flight operation efficiency is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and particularly to a method, device, equipment and storage medium for generating multiple detour paths. Background Art

[0002] With the wide application of unmanned aerial vehicles, aircraft and other aerial vehicles, the aerial path planning technology has become one of the key technologies to ensure flight safety and improve flight efficiency. Especially in complex environments, such as bad weather, obstacles or other unexpected factors affecting flight, traditional path planning methods often fail to meet the requirements of flexibility and safety. Therefore, how to plan multiple detour paths in an area with obstacles or uncertain weather conditions to meet different flight requirements has become a technical problem to be solved urgently.

[0003] Most of the existing path planning methods rely on fixed routes and usually cannot respond to environmental changes in real time or provide diversified alternative paths. Especially when facing bad weather, complex terrain or sudden changes in the flight area, traditional methods are difficult to provide detour paths efficiently and flexibly. This limitation often leads to the fact that when the aircraft executes tasks, it cannot effectively cope with environmental changes, and may even be in danger or the task cannot be completed smoothly.

[0004] Therefore, how to use advanced computer vision technology and path planning algorithms, combined with the real-time position of the aircraft, weather information and other environmental factors, to dynamically generate multiple detour paths, so as to ensure that the aircraft has multiple path options when encountering obstacles or bad weather, thus ensuring the smooth execution of the flight mission and improving the safety of aerial flight, has become an important research direction in the field of path planning.

[0005] The basic content of this patent does not provide a fast response speed, but rather provides a set of feasible detour paths that are close to actual operation. The set of detour paths is the basis for detour path planning under weather conditions. Only on the basis of reasonable detour paths can a reasonable detour plan that meets the target conditions be planned, and the index calculation under detour conditions can be supported. Most current calculation methods either do not consider the automatic division of detour segments, or only stay at binaryzation in the processing of weather radar images, without the weather clustering and filling operations within the clustering boundary proposed in this patent. The basis of the optimal detour path algorithm is the effective processing of the detour map. Without reasonable map processing, the rationality of the single path obtained is also doubtful. Therefore, there is the weather radar image processing strategy proposed in this patent. Most of the paths generated by the current multi-path generation strategy are "homeomorphic", that is, for two detour paths with the same starting and ending points, there are no weather pixels within the closed curve formed by connecting the head and tail. From the perspective of actual operation, such homeomorphic solutions are not sufficient to support the overall global planning of the detour. Summary of the Invention

[0006] The present invention provides a method, device, equipment and storage medium for generating multiple detour paths, which are used to solve the defects in the prior art, and realize quickly and accurately generating effective detour paths under complex weather conditions, ensuring the safety and stability of flight, and effectively improving the operation efficiency of flights.

[0007] The present invention provides a method for generating multiple detour paths, including:

[0008] By processing the weather radar echo image or weather radar echo intensity data of the target area, a first binary matrix for solving the first detour path is obtained. The target area includes the starting point and the ending point of the planned route. By dividing the planned route, the detour starting points and detour ending points of multiple flight segments are obtained;

[0009] According to the first binary matrix, determine the shortest path between the detour starting point and the detour ending point;

[0010] According to the weather conditions between the connections from the starting point to the path points in the shortest path, optimize the shortest path to obtain the first detour path.

[0011] According to the method for generating multiple detour paths provided by the present invention, after the step of optimizing the shortest path according to the weather conditions between the connections from the starting point to the path points in the shortest path to obtain the first detour path, the method further includes:

[0012] Perform channel closing processing on the weather gaps passed by the first detour path to obtain a new binary matrix;

[0013] Determine a new path for flying around based on the new binary matrix.

[0014] According to a method for generating multiple paths for flying around provided by the present invention, the step of obtaining a first binary matrix for solving the first path for flying around by processing the weather radar echo picture or weather radar echo intensity data of the target area specifically includes:

[0015] Obtain a weather information matrix according to the weather radar echo picture or the radar echo intensity data, where the weather information matrix is used to characterize the weather information of the pixel points on the weather radar echo picture or the radar echo intensity data;

[0016] Perform sparsification processing on the weather information matrix to obtain a subscript matrix representing the weather positions;

[0017] Obtain the Manhattan distance between each pixel point according to the weather subscript matrix;

[0018] Cluster the pixel points according to the weather subscript matrix and the Manhattan distance of the pixel points to obtain a clustering boundary;

[0019] Fill the clustering boundary to obtain a first binary matrix.

[0020] According to a method for generating multiple paths for flying around provided by the present invention, the step of obtaining a weather information matrix according to the weather radar echo picture or the radar echo intensity data, where the weather information matrix is used to characterize the weather information of the pixel points on the weather radar echo picture or the radar echo intensity data specifically includes:

[0021] Determine an RGB picture matrix according to the weather radar echo picture or the radar echo intensity data;

[0022] Initialize the weather information matrix according to the RGB picture matrix, where the RGB picture matrix has the same number of rows and columns as the weather information matrix;

[0023] Determine the weather pixel points in the weather information matrix whose echo intensity is greater than a preset intensity threshold according to the weather radar echo picture or the echo intensity data, and mark them in the weather information matrix to obtain a target weather information matrix.

[0024] According to a method for generating multiple paths for flying around provided by the present invention, the step of optimizing the shortest path according to the weather conditions between the connections from the starting point to other points in the shortest path to obtain a path planning for flying around specifically includes:

[0025] Determine the starting point of the path according to the shortest path;

[0026] Determine the number of weather pixels in the line connecting the starting point to the i-th point;

[0027] If the number of weather pixels is greater than the preset number threshold, then set the i-th point as the new starting point, where i = 1, 2, 3... k, and k is the K-th point after the i-th starting point on the shortest path;

[0028] Connect all the starting points in sequence to obtain the shortest path.

[0029] According to a method for generating a detour multi-path provided by the present invention, before the step of determining the shortest path between the path-finding starting point and the path-finding ending point according to the first binary matrix, the method further includes:

[0030] Obtain a flight plan route, where the flight plan route includes multiple flight segments;

[0031] Map the flight plan route into the first binary matrix;

[0032] When there are weather pixels in the flight segment, use the starting point of the flight segment as the detour starting point of the segment;

[0033] When the distance between the end point of the flight segment and the weather pixel is greater than the preset distance threshold, use the end point of the flight segment as the detour end point;

[0034] When the distance between the end point of the flight segment and the weather pixel is less than the preset distance threshold, use the end point of the next flight segment whose distance from the weather pixel is greater than the preset distance threshold as the detour end point of the segment.

[0035] According to a method for generating a detour multi-path provided by the present invention, the step of determining the shortest path between the path-finding starting point and the path-finding ending point according to the path-finding binary matrix specifically includes:

[0036] Map the longitude and latitude coordinates of the flight plan route into the path-finding map matrix;

[0037] Determine the path-finding starting point and the path-finding ending point of the detour path according to the situation of the planned route passing through the weather area;

[0038] Determine the distance from each pixel point to the path-finding starting point and the path-finding ending point;

[0039] Based on the A* algorithm, determine the shortest path between the path-finding starting point and the path-finding ending point according to the distance from the path-finding starting point to the path-finding pixel position and the Manhattan distance from the path-finding pixel position to the end point.

[0040] The present invention also provides a device for generating a detour multi-path, including:

[0041] A data acquisition module, configured to obtain an RGB image or echo intensity data of a target area through a weather radar, where the target area includes a pathfinding start point and a pathfinding end point;

[0042] A pathfinding matrix module, configured to determine a pathfinding map matrix according to the RGB image or the echo intensity data;

[0043] A path determination module, configured to determine the shortest path between the pathfinding start point and the pathfinding end point according to the pathfinding map matrix;

[0044] A path optimization module, configured to optimize the shortest path according to the visible distance between adjacent pixel points in the shortest path to obtain a detour path plan.

[0045] The present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the method for generating a detour multi-path as described in any one of the above is implemented.

[0046] The present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method for generating a detour multi-path as described in any one of the above is implemented.

[0047] The present invention further provides a computer program product, including a computer program. When the computer program is executed by a processor, the method for generating a detour multi-path as described in any one of the above is implemented.

[0048] The method, device, equipment, and storage medium for generating a detour multi-path provided by the present invention obtain an RGB image or echo intensity data of a target area through a weather radar, where the target area includes a pathfinding start point and a pathfinding end point; determine a pathfinding map matrix according to the RGB image or the echo intensity data; determine the shortest path between the pathfinding start point and the pathfinding end point according to the pathfinding map matrix; optimize the shortest path according to the visible distance between adjacent pixel points in the shortest path to obtain a detour path plan. By obtaining the RGB image or echo intensity data of the target area in real time through the weather radar, the present invention can reflect the current weather conditions in real time, so as to generate the most suitable detour path according to the real-time data, effectively improving the response speed of the flight path. And by considering the visible distance between adjacent pixel points and optimizing the shortest path, a more reasonable and safe detour path can be obtained, ensuring that the aircraft avoids bad weather areas and improving flight safety. Description of the Drawings

[0049] To more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0050] Figure 1 is a schematic flowchart of the method for generating the fly-around multi-path provided by the present invention;

[0051] Figure 2 is a schematic structural diagram of the device for generating the fly-around multi-path provided by the present invention;

[0052] Figure 3 is a schematic structural diagram of the electronic device provided by the present invention. Detailed implementation manners

[0053] To make the objectives, technical solutions and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0054] To solve the problems in the prior art, the present invention proposes a method for generating a fly-around multi-path to quickly and accurately generate a fly-around path under complex weather conditions, ensure the safety and stability of flight, and effectively improve the operation efficiency of flights. The following describes the method for generating the fly-around multi-path, as Figure 1 shown, including but not limited to the following steps:

[0055] Step 110: Process the weather radar echo image or weather radar echo intensity data of the target area to obtain a first binary matrix for solving the first fly-around path. The target area includes the starting point and the ending point of the planned route. By dividing the planned route, the fly-around starting points and fly-around ending points of multiple flight segments are obtained.

[0056] In this step, the weather radar echo image or weather radar echo intensity data of the target area is obtained. The target area includes the starting point and the ending point of the route, and this route is a part of the planned flight path. The weather radar echo image or intensity data usually exists in the form of a two-dimensional matrix, where each pixel represents the weather condition or radar echo intensity of a specific area.

[0057] These weather radar data need to go through certain preprocessing steps, including but not limited to data denoising, intensity normalization, spatial smoothing of radar images, etc., to improve the accuracy and reliability of the data. Through these processes, a two-dimensional matrix that can reflect the weather conditions in the target area is obtained.

[0058] Obtaining weather radar echo pictures: The weather radar scans the target area and converts it into an RGB image. This image matrix contains color information of different parts of the target area, where each pixel represents a weather area. The color value of each pixel is used to represent the weather conditions in that area, such as sunny, cloudy, thunderstorm, etc.

[0059] Obtaining the echo intensity matrix: The weather radar also collects echo intensity information to form an echo intensity matrix. The echo intensity represents the intensity of the radar signal reflected from weather targets (such as precipitation cloud clusters, etc.). Strong echoes usually indicate areas with relatively severe weather, while weak echoes indicate relatively stable weather areas.

[0060] Step 120: Determine the shortest path between the waypoint for bypassing and the end point for bypassing according to the first binary matrix.

[0061] In this step, the planned flight route is segmented, and according to the specific requirements of the flight path, multiple flight segments are divided. The starting point and ending point of each segment are the waypoint for bypassing and the end point for bypassing.

[0062] By processing the weather radar echo data of the target area, a first binary matrix is obtained. In this matrix, the matrix element values are divided into two values, "0" or "1", according to the intensity of the radar echo or the weather conditions. Here, "1" represents the existence of severe weather or non - flyable obstacles in that area, while "0" represents relatively good weather or flyable areas. Through the analysis of these data, potential waypoints for bypassing and end points for bypassing within each segment are obtained.

[0063] Step 130: Based on the first binary matrix, use the shortest path algorithm in graph theory (such as Dijkstra's algorithm or A* algorithm) to calculate the shortest path between the waypoint for bypassing and the end point for bypassing. This shortest path is the shortest feasible path calculated considering the weather conditions in the target area, flight restrictions, and other geographical and meteorological factors.

[0064] During this process, the selection of the path not only depends on the shortest distance, but also comprehensively considers the flight safety of each segment. If the area corresponding to a certain flight path in the radar echo matrix is "1", that is, there is severe weather or other obstacles, this path will not be considered as part of the shortest path.

[0065] Once the initial shortest path is obtained, it is necessary to optimize it according to the weather conditions between each path point in the path. Specifically, the optimization process includes:

[0066] Evaluate the weather conditions between the starting point and each path point in the shortest path, such as precipitation intensity, wind speed, thunderstorm activity, etc.;

[0067] If the weather condition of a certain path segment is relatively bad (such as large-scale precipitation or thunderstorm), then re-select an alternative path that is parallel to the current path and can avoid the bad weather;

[0068] After considering factors such as the safety, distance, and time of the bypass path, determine an optimal bypass path.

[0069] Finally, the obtained first bypass path not only meets the requirement of the shortest flight distance, but also avoids the bad weather area, ensuring flight safety.

[0070] The purpose of this application is not to provide a fast response speed, but to provide a set of bypass paths that are close to the actual operation and have a relatively high feasibility. The set of bypass paths is the basis for bypass path planning under weather conditions. Only on the basis of reasonable bypass paths can a reasonable bypass plan that meets the target conditions be planned, and the index calculation under bypass conditions can be supported. Most of the current calculation methods, first, do not consider the automatic division of the bypass flight segments, and second, the processing of weather radar images only stays at binarization, without the weather clustering and filling operations within the clustering boundary proposed in this patent. And the basis of the optimal bypass path algorithm is the effective processing of the bypass map. If there is no reasonable map processing, then the rationality of the single path obtained is also doubtful. Therefore, there is the weather radar image processing strategy proposed in this patent. Most of the paths generated by the current multi-path generation strategy are "homeomorphic", that is, for two bypass paths with the same starting and ending points, there are no weather pixels within the closed curve formed by connecting the beginning and the end. From the perspective of actual operation, such homeomorphic solutions are not sufficient to support the overall planning of the entire bypass.

[0071] As a further optional embodiment, after the step of optimizing the shortest path according to the weather conditions between the starting point and the path point in the shortest path to obtain the first bypass path, the method further includes:

[0072] Step 140: Perform channel closing processing on the weather gaps passed by the first bypass path to obtain a new binary matrix;

[0073] Step 150: Determine a new bypass path according to the new binary matrix.

[0074] In this further embodiment, in addition to path optimization, in order to obtain as many available air routes as possible, some narrow weather channels passed by the above optimal path are closed, and A* pathfinding is performed multiple times to obtain new air routes, thereby obtaining a set of planned air routes. This embodiment introduces steps for judging and processing the "channel width". For the optimal path obtained from the first pathfinding, by judging the width of the weather channel passed through, if it is less than the threshold, this channel is filled with weather pixels using the pixel filling method, thereby obtaining a new bypass binary map, so that the new bypass algorithm cannot pass through the current channel, and then a new bypass path will be obtained.

[0075] After the closing process, it is necessary to recalculate the flight path. That is, based on the closed path map and the new weather data, the shortest path of the aircraft from the starting point to the ending point is recalculated. This recalculation process can use the A* algorithm or other path planning algorithms to ensure that the aircraft can avoid areas that are not suitable for passing through and find a new and safer channel.

[0076] Specifically, assume that the preliminary bypass path is [p1 - p2 - p3 - p4… - pn]; select any segment [Pi - Pi+1] in the path; obtain the perpendicular line segment at point Pi of the corresponding flight segment, set the length of the perpendicular line segment to 2L (L on both sides of the foot of the perpendicular), assume the feet of the perpendicular are PPil and PPir respectively, and find the number of pixels passed by the first weather pixel from Pi to PPil and from Pi to PPir respectively, denoted as Nl and Nr, and record TDL = Nl + Nr; the pixel width of the channel, define the width threshold TDL_limit of the channel. If the calculated channel width is less than TDL_limit, then mark [PPi - PPi+1] as a channel TDi, and Pi is recorded as the reference point of the channel. By calculating all the waypoints Pi, a channel set can be obtained. By sequentially closing (the closing operation is to set all the pixels passed by the perpendicular line segment to weather pixels - the corresponding pixel position value is 0) a channel and performing A* pathfinding, multiple paths can be obtained.

[0077] As a further optional embodiment, the step of obtaining the first binary matrix for solving the first bypass path by processing the weather radar echo picture or the weather radar echo intensity data of the target area specifically includes:

[0078] According to the weather radar echo picture or the radar echo intensity data, a weather information matrix is obtained, and the weather information matrix is used to characterize the weather information of the pixel points on the weather radar echo picture or the radar echo intensity data;

[0079] The weather information matrix is sparsified to obtain a subscript matrix representing the weather position;

[0080] Based on the weather icon matrix, obtain the Manhattan distance between each pixel point;

[0081] Based on the weather icon matrix and the Manhattan distance of the pixel points, cluster the pixel points to obtain a clustering boundary;

[0082] Fill the clustering boundary to obtain a first binary matrix.

[0083] In this embodiment, first, use the weather radar echo image of the target area obtained by the weather radar as the input. The weather radar echo image represents the optical reflection information of the target area at different wavelengths and is used to characterize the meteorological conditions of the area.

[0084] Combine with the echo intensity matrix, which represents the intensity of the radar echo and can reflect the density of the weather area and the strength of the weather system. The echo intensity matrix is usually generated by scanning the target area by the radar and reflects the distribution of the meteorological system in space.

[0085] By combining the RGB image or echo intensity data, construct a weather information matrix. The weather information of each pixel point will be comprehensively obtained based on its corresponding RGB value and echo intensity value, and can accurately describe the meteorological conditions (such as cloud density, precipitation intensity, etc.) of the area. Each element in this matrix represents the weather information of a pixel point, for example, representing the intensity of meteorological data or other meteorological attributes.

[0086] In order to improve the processing efficiency and reduce data redundancy, perform sparsification processing on the weather information matrix. The purpose of the sparsification processing is to remove unnecessary information and retain important meteorological features, for example, areas with significant radar echo intensity (such as storm cloud clusters) or areas with large meteorological changes (such as sudden precipitation areas).

[0087] The sparsification processing can adopt the method of threshold setting. Set a threshold for the echo intensity or RGB feature. Pixel points below this threshold can be ignored, and pixel points above the threshold are retained. These retained pixel points form a sparsified weather icon matrix, where each icon represents an area with important meteorological features.

[0088] The weather icon matrix can be used to quickly locate and judge areas with special meteorological features in the subsequent path planning process. This matrix indicates the distribution of weather systems or meteorological phenomena in the form of icons, thus providing important weather information references for path finding.

[0089] The Manhattan distance refers to the sum of the distances between two points along the horizontal and vertical directions on a plane. Different from the Euclidean distance, the Manhattan distance only considers the distances in the horizontal and vertical directions. Therefore, the Manhattan distance is usually used to calculate the distance between two points in the grid-based path finding process.

[0090] Based on the index information of each pixel in the weather index matrix, calculate the Manhattan distance from each pixel to other pixels. This distance reflects the approximate flight distance between the aircraft from a certain point to the target point. Based on this calculation, it can help determine the shortest path.

[0091] The Manhattan distance provides a basis for path planning. Especially in complex weather environments, the aircraft needs to adjust the path according to the degree of weather influence. By calculating the Manhattan distance between each pixel, a more accurate path can be selected.

[0092] According to the Manhattan distance and the weather index matrix, use a clustering algorithm to group the pixels to form several meteorological regions or weather clusters. Each cluster represents a region with similar weather characteristics, which can be a dense cloud area, a precipitation area, etc.

[0093] Common clustering algorithms include the K-means algorithm, the DBSCAN algorithm, etc. In this embodiment, according to the similarity of the weather index matrix and the Manhattan distance, the pixels are divided into several meteorological regions. The clustered regions can be composite regions containing multiple meteorological features or independent weather phenomenon regions.

[0094] The result after clustering will define the boundaries of each cluster and mark the edges of each meteorological region. The clustering boundary provides a clear reference for subsequent path planning and helps determine whether the aircraft needs to avoid certain specific meteorological regions.

[0095] By considering the region inside the clustering boundary as a homogeneous region, fill these clustered regions. The boundary region of the cluster may contain information on different meteorological characteristics, so the filled region can represent different flight conditions.

[0096] The filled clustered regions form a complete pathfinding map matrix. This matrix not only contains the geographical information of the target region but also the meteorological information of the target region. The pathfinding map matrix provides the aircraft with global meteorological information and geographical information to help the aircraft plan a detour path according to the weather conditions.

[0097] Specifically, the computer reads the RGB image matrix img_mtx of the weather radar and the radar echo intensity pixel library matrix radar_desity_mtx, and defines the log_img_mtx (a two-dimensional matrix with the same number of rows and columns as img_mtx) matrix as the binary matrix of the pathfinding map. For each vector pixel_vct composed of pixel rgb values in img_mtx, pixel_vct is compared with radar_desity_mtx, and then the intensity level threshold D is defined. When the intensity of Pixel_vct is greater than D, the element value of the corresponding position in log_img_mtx is assigned 0 (indicating there is weather), otherwise the element value of the corresponding position in log_img_mtx is assigned 1 (indicating no weather). After traversing the entire img_mtx, the binary matrix log_img_mtx after intensity screening is obtained as the subsequent pathfinding map.

[0098] The sparse processing of the weather radar map yields the subscript matrix parse_log_img_mtx at the 0 positions in log_img_mtx, whose dimension is N*2, where N is the number of weather pixel points. Denote the clustering distance threshold as D_limit. Record the Manhattan distance between the subscripts of any two weather pixel points pi and pj as

[0099] Manhuttan_dis = abs(parse_log_img_mtx(i,1) - parse_log_img_mtx(j,1)) + abs(parse_log_img_mtx(i,2) - parse_log_img_mtx(j,2))

[0100] Select the first point in parse_log_img_mtx as the clustering core core_group, and the remaining points as the target set target_group to start the clustering calculation. The set of points in target_group whose Manhattan distance to core_group is less than D_limit is obtained as the new added set add_group. Add the points in add_group to core_group and remove the points in add_group from target_group.

[0101] Then, calculate each point in add_group and make a judgment with the new target_group to obtain a new add_group, and then update core_group and target_group and repeat the calculation until add_group is empty, at which point the clustering of the current core ends and a weather class is obtained.

[0102] Repeat the above steps until target_group is empty to complete all clustering.

[0103] The weather point set wx_group obtained through the above clustering. Each clustering result is a subscript matrix of weather points with a dimension of Ni*2. Then, the boundaries of each clustering are obtained using existing algorithms. By re-filling the clustering boundaries, the final binary map matrix can be obtained, thus solving the problem of discrete weather pixels in the weather map.

[0104] As a further optional embodiment, the step of obtaining a weather information matrix according to the weather radar echo picture or the radar echo intensity data, where the weather information matrix is used to characterize the weather information of pixel points on the weather radar echo picture or the radar echo intensity data, specifically includes:

[0105] Determine an RGB picture matrix according to the weather radar echo picture or the radar echo intensity data;

[0106] Initialize a weather information matrix according to the RGB picture matrix, where the RGB picture matrix and the weather information matrix have the same number of rows and columns;

[0107] Determine the weather pixel points in the weather information matrix where the echo intensity is greater than a preset intensity threshold according to the weather radar echo picture or the echo intensity data, and mark them in the weather information matrix to obtain a target weather information matrix.

[0108] As a further optional embodiment, the step of optimizing the shortest path according to the weather conditions between the connections from the starting point to other points in the shortest path to obtain a flight-around path plan specifically includes:

[0109] Determine the path starting point according to the shortest path;

[0110] Determine the number of weather pixel points in the connection from the starting point to the i-th point;

[0111] If the number of weather pixel points is greater than a preset number threshold, then set the i-th point as the new starting point, where i = 1, 2, 3... k, and k is the K-th point after the i-th starting point on the shortest path;

[0112] Connect all the starting points in sequence to obtain the shortest path.

[0113] In this embodiment, the starting point of the shortest path is usually determined by the current position of the aircraft or the planned departure location. In this embodiment, the path starting point can be determined according to the current position of the aircraft or the starting point set in the flight path planning (such as the departure airport or mission point). The starting point of the path will directly affect the direction and length of the entire path planning. Therefore, ensuring the accuracy of the starting point is crucial in the path planning process. Through effective positioning technology, the starting point position can be accurately determined and used as the starting point for the shortest path calculation.

[0114] The target point of the shortest path is usually the final destination of the aircraft or the mission completion location. In this embodiment, the target point can be set in advance by the flight mission or the navigation system. The target point is not necessarily a fixed geographical coordinate, but may be a variable area affected by weather conditions.

[0115] In the path segment from the path starting point to the first target point, calculate the number of weather pixels passed by these path pixels. Weather pixels represent areas with higher radar echo intensity or specific meteorological conditions (such as storms, thunderstorms, etc.), and these areas may affect flight safety and path feasibility.

[0116] According to the pre-set weather index matrix, check the position of each pixel point in the shortest path one by one, and count the number of weather pixels included in the area passed by the path. The larger the number of weather pixels, the more complex the meteorological conditions passed by the path segment, which may lead to the need for detouring or avoidance.

[0117] To avoid the aircraft passing through dangerous weather areas, set a predetermined quantity threshold (such as 20 weather pixels). When the number of weather pixels in the path exceeds this threshold, it means that the aircraft may enter a severe weather area, such as a heavy precipitation area, a thunderstorm area, etc., which may pose a threat to flight safety.

[0118] If the number of weather pixels passed by the path exceeds the set threshold, it means that the weather in the area where the first target point is located is relatively complex, and the aircraft needs to detour. Therefore, it is possible to choose to replace the original first target point.

[0119] The method of replacing the target point can be based on a heuristic search algorithm (such as the A* algorithm) or based on meteorological information analysis to select a more suitable target point with better weather conditions. The new target point should ensure that the path can avoid areas with complex weather and continue to maintain the optimization principle of the shortest path.

[0120] Once the first target point is replaced with a new target point, the new path will be recalculated. The shortest path from the starting point to the new target point can be recalculated again through a standard shortest path algorithm (such as the A* algorithm).

[0121] The new shortest path will consider the distribution of weather pixels, optimize the path, enable the aircraft to avoid possible severe weather areas, and ensure flight safety. The finally obtained path is the detour path.

[0122] As a further optional embodiment, when the number of weather pixels is greater than a preset number threshold, the step of replacing the target point specifically includes:

[0123] Determine the priority of each pixel near the starting point according to the heuristic function;

[0124] Determine a new target point according to the priority;

[0125] Replace the first target point with the new target point.

[0126] The heuristic function is a function used to evaluate the potential cost of the path from the starting point to the target point. In this embodiment, the heuristic function can determine the priority according to factors such as weather conditions, distance, obstacles, etc. Specifically, the heuristic function can calculate the priority of each pixel according to the following factors:

[0127] Weather conditions: If the weather conditions in the area corresponding to a certain pixel are good (for example, there are no severe meteorological phenomena), the priority of this point is higher; if the weather conditions in the area corresponding to a certain pixel are poor (for example, thunderstorms, heavy precipitation), the priority of this point is lower.

[0128] Distance to the target point: The closer the pixel is to the target point from the starting point, the higher its priority should be. Common distance metrics (such as Manhattan distance, Euclidean distance, etc.) can be used for calculation.

[0129] Path connectivity: Whether the pixel forms an effective connected path with the starting point and other pixels can also affect the priority.

[0130] Through the heuristic function, according to the meteorological information, distance information and connectivity of each pixel, calculate the priority of each pixel. A pixel with a high priority indicates that this point has a higher priority in path planning, meaning that the aircraft is more inclined to select these points as part of the detour path.

[0131] After determining the priority of each pixel, the aircraft will select a pixel with a higher priority as the new target point (i.e., the new target point). The selection criterion can be to start from the starting point and gradually search along the pixel with the highest priority until a feasible target point is found.

[0132] The selection of the new target point should consider the following factors:

[0133] Shortest path principle: The new target point should be as close as possible to the starting point while avoiding a large number of weather pixels.

[0134] Paths with high priority: Prioritize areas with better meteorological conditions and lower flight difficulty.

[0135] Safety: The new target point should ensure that the aircraft can avoid severe weather areas and maintain flight safety.

[0136] Based on the priority calculated by the heuristic function, gradually explore the surrounding pixels starting from the starting point, and select a target point that meets the conditions as the new target point. This target point should avoid severe weather areas in the current path to ensure the safety of the aircraft.

[0137] Once the new target point is determined, the flight path planning system will replace the original first target point with the new target point. The new target point should have better meteorological conditions, and its path should be more suitable for the safety and efficiency of the aircraft.

[0138] After replacing the target point, the system needs to recalculate the shortest path from the starting point to the new target point. This can use path planning algorithms such as the A* algorithm, combined with the new target point and the heuristic function, to calculate the new shortest path.

[0139] The planning of the new path should take into account the new target point and the need to avoid severe weather areas to ensure the optimal and safe path.

[0140] When the target point is replaced, the flight path will be recalculated. The new path will be re-planned for the shortest path based on the new target point and the original starting point. At this time, the new path should avoid the previously discovered severe weather areas while still maintaining the goal of the shortest flight path.

[0141] During the calculation of the new shortest path, the system will consider meteorological factors again to optimize the path to ensure that the aircraft can safely bypass bad weather areas and reduce potential risks during flight.

[0142] As a further optional embodiment, the step of determining the shortest path between the pathfinding start point and the pathfinding end point according to the pathfinding map matrix specifically includes:

[0143] Map the longitude and latitude coordinates of the flight plan route to the pathfinding map matrix to determine the distances from each pixel point to the pathfinding start point and the pathfinding end point;

[0144] Based on the distances from each pixel point to the pathfinding start point and the pathfinding end point, determine the shortest path between the pathfinding start point and the pathfinding end point based on the A* algorithm.

[0145] In this embodiment, the latitude and longitude coordinates of the flight plan route provide the geographical locations of the starting point and the ending point. These coordinates need to be converted into the pixel positions in the pathfinding map matrix. Specifically, the starting point and ending point coordinates of the aircraft will be converted into the corresponding pixel coordinates in the pathfinding map matrix.

[0146] The mapping process can be carried out in the following way:

[0147] Coordinate normalization: Normalize the latitude and longitude coordinates of the flight plan according to the size of the map matrix. For example, convert the longitude and latitude values into row and column coordinates in the matrix according to a ratio.

[0148] Map resolution matching: Determine the matrix position corresponding to each latitude and longitude coordinate according to the resolution of the map and the accuracy of the latitude and longitude. Usually, the resolution of the map will be adjusted according to the application requirements to ensure that each pixel accurately represents the flight area.

[0149] Once the latitude and longitude coordinates are successfully mapped into the pathfinding map matrix, the specific positions of the pathfinding starting point and the pathfinding ending point in the matrix can be determined. These positions will be used as the starting point and the ending point for subsequent path planning.

[0150] The distance from each pixel to the starting point and the ending point can be calculated by various methods. The most common way is based on the Manhattan distance or the Euclidean distance:

[0151] Manhattan distance: Applicable to calculating the distance between pixel points in a grid-like grid in the horizontal and vertical directions. Usually, the formula is:

[0152] D Manhattan =|x 1 -x 2 |+|y 1 -y 2 |

[0153] where (x1, y1) and (x2, y2) are the coordinates of two pixel points respectively.

[0154] For path planning, first, it is necessary to calculate the distances from each pixel point in the entire pathfinding map matrix to the pathfinding starting point and the ending point. These distance values will form two distance matrices: one representing the distance from each pixel point to the pathfinding starting point, and the other representing the distance from each pixel point to the pathfinding ending point.

[0155] Path calculation of the A* algorithm:

[0156] Initialization: Starting from the pathfinding starting point, initialize the g value of the starting point to 0, the h value to the estimated distance from the starting point to the ending point, and calculate its f value (f(n) = g(n) + h(n)).

[0157] Search process: The system traverses all possible path points and calculates the g, h, and f values for each point. It preferentially selects the point with the smallest f value for expansion.

[0158] Path update: Whenever a better path is found, update the path information of the current node (including the parent node, g value, h value, etc.).

[0159] Path termination: When the node at the end point is expanded, it indicates that the shortest path from the start point to the end point has been found, and the algorithm terminates.

[0160] Once the A* algorithm completes the path search, a shortest path from the start point to the end point will be obtained. This path is formed by connecting multiple pixel points, and the aircraft can fly according to this path.

[0161] As a further optional embodiment, before the step of determining the shortest path between the path finding start point and the path finding end point according to the first binary matrix, the method further includes:

[0162] Obtain a flight plan route, where the flight plan route includes multiple flight segments;

[0163] Map the flight plan route to the first binary matrix;

[0164] When there is a weather pixel point in the flight segment, use the starting point of the flight segment as the detour starting point of the segment;

[0165] When the distance between the end point of the flight segment and the weather pixel point is greater than a preset distance threshold, use the end point of the flight segment as the detour end point;

[0166] When the distance between the end point of the flight segment and the weather pixel point is less than the preset distance threshold, use the end point of the next flight segment whose distance from the weather pixel point is greater than the preset distance threshold as the detour end point of this segment.

[0167] This step proposes a detour division strategy for the entire planned route to effectively deal with weather obstacles in the route and provide multiple detour path options for the aircraft. The specific implementation method is as follows:

[0168] First, for each segment in the entire planned route, perform weather judgment. If there is a weather obstacle (e.g., thunderstorm, cloud layer, or other adverse weather) in a segment, set the starting point of the segment as the detour starting point.

[0169] For the determined detour starting point, continue to judge whether the end point of the segment is affected by the weather. The specific determination method is: according to the pixel distance between the weather obstacle and the end point, if the distance is greater than the preset threshold, set the end point of the segment as the detour end point and end the detour planning for this segment.

[0170] If the distance to the weather obstacle at the end point is less than the preset threshold, continue to judge the weather condition of the next flight segment.

[0171] When judging the next flight segment, if the segment does not contain a weather obstacle and the distance between its end point and the end point of the previous segment is greater than the given threshold, use the end point of the next flight segment as the detour end point and continue with the next step of the route judgment. If this condition is not met, continue to judge the next flight segment.

[0172] Repeat the above process until the end point of the detour plan is found or the last point of the entire route is judged. If the detour end point is found, record and mark this point, and at the same time continue to search for a new detour start point and end point from the next flight segment until the last point of the route.

[0173] Through this strategy, the entire planned route can be segmented section by section to obtain multiple detour sections. Each detour section is calculated separately to obtain an optimized path for each detour section. Finally, by integrating the paths of all detour sections, the final detour plan for the entire route is obtained.

[0174] After obtaining the path of each detour section, it can be optimized by combining a shortest path algorithm (such as the A* algorithm) to ensure that each detour section minimizes the flight distance, saves fuel, and improves flight efficiency while meeting safety requirements. In addition, the threshold can be dynamically adjusted during actual operation to adapt to different flight environments and emergencies.

[0175] In summary, the beneficial effects of this method are as follows:

[0176] The beneficial effects of this patent can be highlighted from the following aspects:

[0177] Automatic segmentation of detour flight segments: The present invention optimizes the flight path planning by automatically segmenting detour flight segments. This strategy can effectively divide the flight segments into more reasonable flight areas, reduce the risk of collision between the aircraft and adverse weather or obstacles, thereby improving flight safety and efficiency. The automatic segmentation process significantly reduces the possibility of manual intervention and human error, and enhances the flexibility and intelligence level of flight scheduling and management.

[0178] Binary processing of radar weather maps: By performing binary processing on radar weather maps, the present invention can quickly extract weather information and simplify the subsequent analysis and decision-making processes. This binary technology can effectively improve the accuracy and real-time performance of weather monitoring, enabling pilots or flight managers to obtain key information in a short time, make flight decisions quickly, and greatly improve the response speed of flight safety and route optimization.

[0179] Cluster the weather first and then find the boundary using FCA convex hull: The present invention uses advanced clustering techniques to preprocess weather data. By clustering analysis, similar weather conditions are grouped into one category, and further, the FCA (Finite Reachability Operator) convex hull algorithm is used to accurately determine the weather boundary. This method can effectively predict and avoid the risks brought by bad weather through accurate boundary recognition, and can avoid the influence of adverse weather in route planning, improving the overall safety and flight quality of flights.

[0180] The lane closure strategy makes multiple paths non-homeomorphic: By applying the lane closure strategy, the present invention effectively provides multiple feasible options for flight paths. The application of this strategy can effectively cope with complex weather conditions and emergencies, flexibly adjust flight paths, and optimize resource allocation, thus ensuring flight stability and flight punctuality.

[0181] The following describes the device for generating detour multiple paths provided by the present invention. As Figure 2 shown, the device for generating detour multiple paths described below can be correspondingly referred to the method for generating detour multiple paths described above.

[0182] A device for generating detour multiple paths includes:

[0183] A matrix determination module 210, configured to process the weather radar echo picture or weather radar echo intensity data of the target area to obtain a first binary matrix for solving the first detour path. The target area includes the starting point and the ending point of the planned route. By dividing the planned route, the detour starting point and the detour ending point of multiple flight segments are obtained;

[0184] A path determination module 220, configured to determine the shortest path between the detour starting point and the detour ending point according to the first binary matrix;

[0185] A path optimization module 230, configured to optimize the shortest path according to the weather conditions between the connection lines from the starting point to the path points in the shortest path to obtain the first detour path.

[0186] As an optional embodiment, a device for generating detour multiple paths further includes:

[0187] A channel closure module 240, configured to perform channel closure processing on the weather gaps passed by the first detour path to obtain a new binary matrix;

[0188] A detour path module 250, configured to determine a new detour path according to the new binary matrix.

[0189] Figure 3 Illustrates a schematic diagram of the physical structure of an electronic device. As Figure 3As shown in the figure, the electronic device may include: a processor 310, a communications interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communications interface 320, and the memory 330 communicate with each other through the communication bus 340. The processor 310 may call the logical instructions in the memory 330 to execute the method for generating a circumvention multi-path, and this method includes:

[0190] By processing the weather radar echo picture or weather radar echo intensity data of the target area, a first binary matrix for solving the first circumvention path is obtained. The target area includes the starting point and the ending point of the planned route. By dividing the planned route, the circumvention starting points and circumvention ending points of multiple flight segments are obtained;

[0191] According to the first binary matrix, determine the shortest path between the circumvention starting point and the circumvention ending point;

[0192] According to the weather conditions between the connections from the starting point to the path points in the shortest path, optimize the shortest path to obtain the first circumvention path.

[0193] In addition, when the logical instructions in the above-mentioned memory 330 are implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. And the aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical disks, etc., which can store program codes.

[0194] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the method for generating a circumvention multi-path provided by the above-mentioned various methods. This method includes:

[0195] By processing weather radar echo pictures or weather radar echo intensity data of a target area, a first binary matrix for solving a first bypass path is obtained. The target area includes the starting point and the ending point of a planned route. By segmenting the planned route, bypass starting points and bypass ending points of multiple flight segments are obtained;

[0196] According to the first binary matrix, determine the shortest path between the bypass starting point and the bypass ending point;

[0197] According to the weather conditions between the connecting lines from the starting point to the path points in the shortest path, optimize the shortest path to obtain a first bypass path.

[0198] On the other hand, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is used to execute the method for generating multiple bypass paths provided by the above-mentioned various methods. The method includes:

[0199] By processing weather radar echo pictures or weather radar echo intensity data of a target area, a first binary matrix for solving a first bypass path is obtained. The target area includes the starting point and the ending point of a planned route. By segmenting the planned route, bypass starting points and bypass ending points of multiple flight segments are obtained;

[0200] According to the first binary matrix, determine the shortest path between the bypass starting point and the bypass ending point;

[0201] According to the weather conditions between the connecting lines from the starting point to the path points in the shortest path, optimize the shortest path to obtain a first bypass path.

[0202] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative labor.

[0203] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0204] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for generating fly-around multipaths, characterized in that: include: A first binary matrix for solving a first detour path is obtained by processing a weather radar echo image or weather radar echo intensity data of a target area, wherein the target area includes a starting point and an end point of a planned route, and detour starting points and detour end points of a plurality of flight segments are obtained by segmenting the planned route; Determine the shortest path between the circumvention starting point and the circumvention end point according to the first binary matrix; According to the weather conditions between the line connecting the starting point and the path point in the shortest path, the shortest path is optimized to obtain a first detour path.

2. The method for generating fly-around multi-paths according to claim 1, characterized in that: After the step of optimizing the shortest path according to the weather conditions between the line connecting the starting point and the path point in the shortest path to obtain the first detour path, the method further includes: The weather gaps passed by the first detour path are sequentially closed to obtain a new binary matrix; A new detour path is determined according to the new binary matrix.

3. The method for generating fly-around multi-paths according to claim 1, characterized in that: The step of obtaining a first binary matrix for solving a first circumvention path by processing a weather radar echo image or weather radar echo intensity data of a target area specifically includes: According to the weather radar echo picture or the radar echo intensity data, a weather information matrix is ​​obtained, where the weather information matrix is ​​used to characterize the weather information of the pixel points on the weather radar echo picture or the radar echo intensity data; The weather information matrix is ​​subjected to sparse processing to obtain a subscript matrix representing the weather position; According to the weather index matrix, the Manhattan distance between each pixel point is obtained; Clustering the pixels according to the weather index matrix and the Manhattan distance of the pixels to obtain cluster boundaries; The cluster boundaries are filled to obtain a first binary matrix.

4. The method for generating fly-around multi-paths according to claim 3, characterized in that: The step of obtaining a weather information matrix according to the weather radar echo picture or the radar echo intensity data, wherein the weather information matrix is ​​used to characterize the weather information of the pixel points on the weather radar echo picture or the radar echo intensity data, specifically includes: Determine an RGB picture matrix according to the weather radar echo picture or the radar echo intensity data; Initialize a weather information matrix according to the RGB picture matrix, wherein the RGB picture matrix and the weather information matrix have the same dimensions in rows and columns; According to the weather radar echo picture or echo intensity data, weather pixel points whose echo intensity is greater than a preset intensity threshold in the weather information matrix are determined and marked in the weather information matrix to obtain a target weather information matrix.

5. The method for generating fly-around multi-paths according to claim 3, characterized in that: The step of optimizing the shortest path according to the weather conditions between the lines connecting the starting point and other points in the shortest path to obtain the detour route planning specifically includes: Determine a path starting point according to the shortest path; Determine the number of weather pixels in the line from the starting point to the i-th point; If the number of weather pixel points is greater than a preset number threshold, the i-th point is set as a new starting point, where i=1, 2, 3...k, and k is the K-th point after the i-th starting point on the shortest path; All starting points are connected in sequence to obtain the shortest path.

6. The method for generating fly-around multi-paths according to claim 1, characterized in that: Before the step of determining the shortest path between the circumvention starting point and the circumvention end point according to the first binary matrix, the method further includes: Acquire a flight plan route, where the flight plan route includes multiple flight segments; Mapping the flight plan route into the first binary matrix; When there is a weather pixel point in the flight segment, the starting point of the flight segment is used as the detour starting point of the flight segment; When the distance between the end point of the flight segment and the weather pixel point is greater than a preset distance threshold, the end point of the flight segment is used as the detour end point; When the distance between the end point of the flight segment and the weather pixel point is less than a preset distance threshold, the end point of the next flight segment whose distance to the weather pixel point is greater than the preset distance threshold is used as the detour end point of the segment.

7. The method for generating fly-around multi-paths according to claim 1, characterized in that: The step of determining the shortest path between the circumvention starting point and the circumvention end point according to the first binary matrix specifically includes: Mapping the latitude and longitude coordinates of the flight plan route into the pathfinding map matrix; Determine the starting point and end point of the detour route based on the weather conditions of the planned route across the weather area; According to the distance traveled from the path finding starting point to the path finding pixel position and the Manhattan distance from the path finding pixel position to the end point, the shortest path between the path finding starting point and the path finding end point is determined based on the A star algorithm.

8. A device for generating fly-around multi-paths, characterized in that: include: A data acquisition module is used to obtain a first binary matrix for solving a first circumvention path by processing a weather radar echo image or weather radar echo intensity data of a target area, wherein the target area includes a starting point and an end point of a planned route, and obtains circumvention starting points and circumvention end points of a plurality of flight segments by segmenting the planned route; A path determination module, used to determine the shortest path between the detour starting point and the detour end point according to the first binary matrix; The path optimization module is used to optimize the shortest path according to the weather conditions between the line connecting the starting point and the path point in the shortest path to obtain a first detour path.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, it implements the method for generating fly-by multi-paths as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for generating fly-by multi-paths as described in any one of claims 1 to 7 is implemented.

Images