Airspace adaptive gridding method and system for flight of unmanned aerial vehicle

Abstract

The invention discloses an airspace adaptive gridding method and system for unmanned aerial vehicle flight, and relates to the technical field of airspace data processing, and the method comprises the steps: obtaining a plurality of groups of maneuverability parameters of various types of unmanned aerial vehicles, and configuring an initial grid size; evaluating the terrain complexity of the to-be-gridding area to obtain a grid size correction coefficient distribution diagram; correcting the initial grid size according to a grid size correction coefficient to obtain a conventional grid size of the unmanned aerial vehicle; historical obstacle avoidance data of the unmanned aerial vehicle in the historical time of the to-be-gridded area is collected, and an obstacle avoidance hot spot area is marked in the to-be-gridded area; if the area where the unmanned aerial vehicle is located is the obstacle avoidance hot spot area, the grid size is reduced, and the final grid size is obtained; and if the area where the unmanned aerial vehicle is located is a non-obstacle avoidance hot spot area, taking the conventional grid size as the final grid size, and carrying out airspace adaptive gridding. The technical problem that in the prior art, an airspace gridding result is poor in adaptability is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of airspace data processing, in particular to an airspace adaptive gridding method and system for unmanned aerial vehicle flight. BACKGROUND

[0002] The current airspace data processing of unmanned aerial vehicles generally adopts a fixed-size static gridding method, which divides the airspace into uniform standard three-dimensional grid cells to standardize the flight path and obstacle avoidance logic. However, this technology has significant defects: first, the fixed grid size cannot adapt to the differences in maneuverability of different models of unmanned aerial vehicles, resulting in excessive restrictions on unmanned aerial vehicles and waste of airspace resources; second, the existing method ignores the dynamic demand of a large amount of data of different terrains for grid fineness, and static division cannot accurately process the division, resulting in poor adaptability of airspace data processing and insufficient accuracy of airspace division. SUMMARY

[0003] The present application provides an airspace adaptive gridding method and system for unmanned aerial vehicle flight, which is used to solve the technical problem of poor adaptability of airspace gridding results in the prior art.

[0004] In view of the above problems, the present application provides an airspace adaptive gridding method and system for unmanned aerial vehicle flight.

[0005] In a first aspect, the present application provides an airspace adaptive gridding method for unmanned aerial vehicle flight, the method comprising: obtaining a plurality of sets of maneuverability parameters of a plurality of models of unmanned aerial vehicles, establishing a mapping relationship between the maneuverability parameters and the initial grid size, and configuring the initial grid size for each of the plurality of models of unmanned aerial vehicles according to the plurality of sets of maneuverability parameters; obtaining a high-precision map of the region to be gridded, evaluating the terrain complexity of the region to be gridded based on the high-precision map, obtaining a terrain complexity distribution map of the region to be gridded, and converting the terrain complexity distribution map to obtain a grid size correction coefficient distribution map; when a specific model of unmanned aerial vehicle enters the region to be gridded, obtaining the initial grid size corresponding to the unmanned aerial vehicle according to the model, calling the grid size correction coefficient distribution map of the region to be gridded, obtaining the grid size correction coefficient according to the real-time position of the unmanned aerial vehicle, correcting the initial grid size according to the grid size correction coefficient, and obtaining the regular grid size of the unmanned aerial vehicle; collecting historical obstacle avoidance data of unmanned aerial vehicles in the region to be gridded within a historical time, and marking an obstacle hotspot region in the region to be gridded according to the historical obstacle avoidance data of the unmanned aerial vehicles; If the region where the UAV is located is an obstacle avoidance hotspot region, then the grid size is reduced on the basis of the regular grid size to obtain a final grid size; if the region where the UAV is located is a non-obstacle avoidance hotspot region, then the regular grid size is taken as the final grid size, and airspace adaptive gridding is performed.

[0006] In a second aspect, the present application provides an airspace adaptive gridding system for UAV flight, comprising: An initial grid size acquisition module is configured to obtain multiple sets of maneuverability parameters of multiple types of UAVs, establish a mapping relationship between the maneuverability parameters and initial grid sizes, and configure initial grid sizes for the multiple types of UAVs one by one according to the multiple sets of maneuverability parameters. A grid size correction module is configured to obtain a high-precision map of a region to be gridded, evaluate the terrain complexity of the region to be gridded on the basis of the high-precision map, obtain a terrain complexity distribution map of the region to be gridded, and convert the terrain complexity distribution map to obtain a grid size correction coefficient distribution map. A regular grid size acquisition module is configured to, when a specific type of UAV enters a region to be gridded, acquire the initial grid size corresponding to the UAV according to the type, call the grid size correction coefficient distribution map of the region to be gridded, acquire the grid size correction coefficient according to the real-time position of the UAV, correct the initial grid size according to the grid size correction coefficient, and obtain the regular grid size of the UAV. A hotspot region marking module is configured to collect historical obstacle avoidance data of UAVs in a historical time of a region to be gridded, and mark obstacle avoidance hotspot regions in the region to be gridded according to the historical obstacle avoidance data of the UAVs. An adaptive gridding module is configured to, if the region where the UAV is located is an obstacle avoidance hotspot region, reduce the grid size on the basis of the regular grid size to obtain a final grid size; and if the region where the UAV is located is a non-obstacle avoidance hotspot region, take the regular grid size as the final grid size, and perform airspace adaptive gridding.

[0007] The one or more technical solutions provided in the present application have at least the following technical effects or advantages: The present application provides an airspace adaptive gridding method and system for UAV flight, which dynamically fuses UAV maneuverability parameters, terrain complexity, and historical obstacle avoidance hotspot region data, significantly improves the adaptability of adaptive allocation of airspace resources and flight safety, and significantly overcomes the problem of rigid utilization of airspace resources caused by static gridding compared with traditional methods, and achieves the technical effect of adaptive gridding of airspace resources according to multiple source parameters. BRIEF DESCRIPTION OF DRAWINGS

[0008] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 This is a flowchart illustrating the airspace adaptive lattice method for UAV flight provided in an embodiment of this application.

[0010] Figure 2 This is a schematic diagram of the airspace adaptive gridding system for UAV flight provided in an embodiment of this application.

[0011] The components represented by each number in the attached diagram are explained below: The module includes: initial grid size acquisition module 100, grid size correction module 200, regular grid size acquisition module 300, hotspot area marking module 400, and adaptive gridding module 500. Detailed Implementation

[0012] This application provides an airspace adaptive lattice method and system for UAV flight, which addresses the technical problem of poor adaptability of airspace lattice results in the prior art.

[0013] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0014] It should be noted that the terms "comprising" and "having" are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or modules that are not explicitly listed or that are inherent to these processes, methods, products, or devices.

[0015] Example 1, as Figure 1 As shown, this application provides an airspace adaptive gridding method for UAV flight, wherein the method includes: S10: Obtain multiple sets of maneuverability parameters for various types of UAVs, establish a mapping relationship between maneuverability parameters and initial grid size, and configure initial grid size for each type of UAV based on the multiple sets of maneuverability parameters.

[0016] The existing static gridding method divides the airspace with a uniform size, which cannot adapt to the mobility differences of different types of UAVs. For example, a UAV with weak mobility cannot avoid obstacles in time in a too large grid due to insufficient capacity, increasing the risk of collision; a UAV with strong mobility is forced to frequently adjust the path in a too dense grid, causing waste of airspace resources and reduction of flight efficiency.

[0017] The step S10 in the method provided by the embodiments of the present application comprises: obtaining a plurality of groups of mobility parameters of a plurality of types of UAVs, wherein one group of mobility parameters comprises a minimum turning radius, a maximum climb rate, and a maximum descent rate; determining a horizontal size of an initial grid size of a specific type of UAV according to the minimum turning radius; determining a height size of the initial grid size of the specific type of UAV according to the maximum climb rate and the maximum descent rate; fusing the horizontal size and the height size of the initial grid size of the specific type of UAV to obtain the initial grid size of the specific type of UAV; configuring the initial grid size for each of the plurality of types of UAVs according to the plurality of groups of mobility parameters.

[0018] In the embodiments of the present application, a plurality of groups of mobility parameters of a plurality of types of UAVs are obtained according to the design parameters of the plurality of types of UAVs, wherein one group of mobility parameters comprises a minimum turning radius in meters, a maximum climb rate in meters per second, and a maximum descent rate in meters per second.

[0019] The horizontal size of the initial grid size of the specific type of UAV is determined according to the minimum turning radius. For example, the horizontal size of the initial grid size = the minimum turning radius of the specific type of UAV x a safety factor. The safety factor is a constant set to prevent accidents caused by too small grid, and for example, the safety factor can be set to 1.5.

[0020] The height size of the initial grid size of the specific type of UAV is determined according to the maximum climb rate and the maximum descent rate. Specifically, the maximum climb rate and the maximum descent rate of the specific type of UAV are compared, and the larger rate is selected for calculation of the height size. For example, if the descent rate is larger than the maximum climb rate, the height size of the initial grid size = the descent rate x a descent unit time, and the descent unit time can be set to 2 seconds to obtain the height size of the initial grid size.

[0021] The initial grid size of the specific type of UAV is obtained by fusing the horizontal size and the height size of the initial grid size of the specific type of UAV, wherein the initial grid size of the specific type of UAV is horizontal size x horizontal size x height size, and the unit is meters.

[0022] According to the multiple sets of maneuverability parameters, initial grid sizes are configured for multiple types of unmanned aerial vehicles one by one.

[0023] By establishing a mapping relationship between the maneuverability parameters and the initial grid sizes, initial grid allocation based on the model capabilities is realized. The horizontal grid size is determined according to the minimum turning radius, and the vertical dimension is set in combination with the climb and descent rates, so that the grid size accurately matches the performance of the unmanned aerial vehicle, and the conflict between the maneuverability and the grid constraint is avoided from the root.

[0024] S20: Obtain a high-precision map of the region to be gridded, evaluate the terrain complexity of the region to be gridded based on the high-precision map, obtain a terrain complexity distribution map of the region to be gridded, and convert the terrain complexity distribution map to obtain a grid size correction coefficient distribution map.

[0025] The traditional method ignores the dynamic demand of complex parameters such as terrain environment on the grid fineness. For example, in a city building dense area, the obstacle distribution is complex, and a small size grid is needed to improve the obstacle avoidance precision; while in an open rural area, using the same grid may cause redundant computing power.

[0026] The step S20 in the method provided by the embodiments of the present application comprises: The region to be gridded is divided into multiple basic grids in advance, and the terrain complexity is calculated in units of basic grids; The ratio of the total floor area of all buildings in each basic grid to the area of the basic grid is calculated to obtain the building area density of each basic grid; The ratio of the total number of buildings in each basic grid to the area of the basic grid is calculated to obtain the building number density of each basic grid; The standard deviation of the height of all buildings in each basic grid is calculated to obtain the building height difference degree of each basic grid; The building area density, building number density, and building height difference degree values corresponding to each basic grid are normalized, and then weighted and summed to obtain the terrain complexity corresponding to each basic grid, wherein the terrain complexity has a value range of greater than 0 and less than or equal to 1; In the high-precision map of the region to be gridded, the range of each basic grid and the corresponding terrain complexity are marked to obtain the terrain complexity distribution map; The terrain complexity corresponding to each basic grid in the terrain complexity distribution map is extracted to obtain a distribution range of multiple terrain complexity values, and a terrain complexity distribution interval is obtained. A grid size correction coefficient range is preset, and a mapping relationship between the terrain complexity distribution interval and the grid size correction coefficient range is established; According to the terrain complexity corresponding to each basic grid, a grid size correction coefficient corresponding to each basic grid is mapped.

[0027] In the embodiments of the present application, a publicly available high-precision map such as OpenStreetMap is acquired, and the area to be gridded is pre-divided into a plurality of basic grids, and the terrain complexity is calculated in units of basic grids. For example, the area to be gridded can be evenly divided into 30m x 30m basic grids.

[0028] The ratio of the total floor area of all buildings in each basic grid to the area of the basic grid is calculated to obtain the building area density of each basic grid, and the building area density of the basic grid = total floor area of buildings in the grid ÷ area of the grid.

[0029] The ratio of the total number of buildings in each basic grid to the area of the basic grid is calculated to obtain the building number density of each basic grid, and the building number density of the basic grid = total number of buildings in the grid ÷ area of the grid, unit: house / m2.

[0030] The standard deviation of the height of all buildings in each basic grid is calculated to obtain the building height difference degree of each basic grid.

[0031] The building area density, building number density, and building height difference degree corresponding to each basic grid are normalized, and then weighted and summed to obtain the terrain complexity corresponding to each basic grid, wherein the terrain complexity has a value range of greater than 0 and less than or equal to 1. Specifically, the average building area density, average building number density, and average building height difference degree of all basic grids are calculated. The normalized building area density = building density of the basic grid ÷ average building area density; the normalized building number density = building number density of the basic grid ÷ average building number density; and the normalized building height difference degree = height difference degree of the basic grid ÷ average height difference degree. The normalized results are weighted and summed to obtain the terrain complexity, and preferably, the terrain complexity = 0.35 x normalized building area density + 0.35 x normalized building number density + 0.3 x normalized building height difference degree.

[0032] In the high-precision map of the area to be gridded, the range of each basic grid and the corresponding terrain complexity are marked to obtain a terrain complexity distribution map.

[0033] The terrain complexity corresponding to each basic grid in the terrain complexity distribution map is extracted to obtain a distribution range of a plurality of terrain complexity values, and a terrain complexity distribution interval is obtained.

[0034] A preset grid size correction coefficient range is set, and a mapping relationship between a terrain complexity distribution interval and the grid size correction coefficient range is established. For example, the grid size correction coefficient range is set to be between -1 and 1, that is, the range of the grid correction is reduced by one time to one time.

[0035] According to the terrain complexity corresponding to each basic grid, a grid size correction coefficient corresponding to each basic grid is mapped, for example, a terrain complexity is 0.2, and then 0.2 is mapped to the preset grid size correction coefficient range to obtain a grid size correction coefficient = 0.2 ÷ 1 × [1-(-1)] = 0.4.

[0036] In the high-precision map of the region to be gridded, the range of each basic grid and the corresponding grid size correction coefficient are marked to obtain a grid size correction coefficient distribution map.

[0037] By analyzing the high-precision map, a terrain complexity distribution map is generated and converted into a grid correction coefficient, to realize environment-adaptive dynamic scaling of the grid. Based on parameters such as building density and height difference, the terrain complexity is accurately quantified, the grid size is automatically reduced in a complex building area to improve the obstacle recognition accuracy, and the grid is expanded in a flat area to optimize the calculation efficiency.

[0038] S30: When the specific model unmanned aerial vehicle enters the region to be gridded, the initial grid size corresponding to the unmanned aerial vehicle is obtained according to the model, the grid size correction coefficient distribution map of the region to be gridded is called, the grid size correction coefficient is obtained according to the real-time position of the unmanned aerial vehicle, the initial grid size is corrected according to the grid size correction coefficient, and the regular grid size of the unmanned aerial vehicle is obtained.

[0039] In the embodiment of the application, when the specific model unmanned aerial vehicle enters the region to be gridded, the initial grid size corresponding to the unmanned aerial vehicle is obtained according to the model, the grid size correction coefficient distribution map of the region to be gridded is called. According to the real-time position of the unmanned aerial vehicle, the grid size correction coefficient is obtained, and the initial grid size is corrected according to the grid size correction coefficient to obtain the regular grid size of the unmanned aerial vehicle. When the grid size correction coefficient is less than 0, the regular grid size = initial grid size × (1+0.5×grid size correction coefficient); when the grid correction coefficient is equal to 0, the regular grid size = initial grid size; when the grid correction coefficient is greater than 0, the regular grid size = initial grid size × (1+grid correction coefficient). For example, an initial grid size is 30m×30m, and the grid size correction coefficient is -0.4, then the regular grid size = 30×[1+0.5×(-0.4)] = 24, that is, the corrected regular grid size is 24m×24m.

[0040] The initial grid size is fused with a correction coefficient of real-time position to generate a regular grid size that evolves in real time with the terrain. When the UAV enters the area to be gridded, the correction coefficient corresponding to the current position is immediately called to dynamically scale the initial size, thereby improving the adaptability of the gridding process.

[0041] S40: Collect historical UAV obstacle avoidance data in the historical time of the area to be gridded, and mark the obstacle avoidance hotspot areas in the area to be gridded according to the historical UAV obstacle avoidance data.

[0042] The historical obstacle avoidance data contains accident rules, such as high-frequency accident points in densely built-up areas and visual blind areas, which lack of marking, resulting in repeated occurrence of similar obstacle avoidance events.

[0043] The step S40 in the method provided by the embodiment of the present application comprises: According to the flight log of the UAV flying in the area to be gridded in the historical time, historical obstacle avoidance events are extracted, the historical obstacle avoidance events including obstacle avoidance position coordinates when the obstacle avoidance occurs and N historical obstacle avoidance features of N obstacle avoidance at the corresponding obstacle avoidance position, the historical obstacle avoidance features including maneuverability parameter features, flight parameter features, obstacle avoidance time features, and obstacle avoidance weather features of the corresponding UAV, wherein the maneuverability parameter features include minimum turning radius, maximum climb rate, and maximum descent rate; The maneuverability parameter features, flight parameter features, current time features, and weather features of a specific model of UAV are obtained as the comparison features; The clustering algorithm is used to cluster the comparison features and the N historical obstacle avoidance features, to extract a plurality of similar historical obstacle avoidance features similar to the comparison features from the N historical obstacle avoidance features, and to obtain a plurality of obstacle avoidance hotspot coordinates corresponding to the plurality of similar historical obstacle avoidance features; The clustering algorithm is used to cluster the comparison features and the N historical obstacle avoidance features, to extract a plurality of similar historical obstacle avoidance features similar to the comparison features from the N historical obstacle avoidance features, and to obtain a plurality of obstacle avoidance hotspot coordinates corresponding to the plurality of similar historical obstacle avoidance features; The comparison features and the N historical obstacle avoidance features are classified into the same set to obtain a sample obstacle avoidance data set; The K-means clustering algorithm is used to divide the sample obstacle avoidance data set into K clusters, where K is a positive integer greater than or equal to 2, and the Euclidean distance is used as the clustering basis; The cluster where the comparison features are located is extracted, and a plurality of historical obstacle avoidance features classified into the same cluster as the comparison features are obtained as a plurality of similar historical obstacle avoidance features; The basic grid where the plurality of obstacle avoidance hotspot coordinates are located is marked as a plurality of obstacle avoidance hotspot areas; The basic grid where the plurality of obstacle avoidance hotspot coordinates are located is marked as a plurality of obstacle avoidance hotspot areas, comprising: count the number of obstacle-avoiding hot spot coordinates contained in each basic grid; based on the number of obstacle-avoiding hot spot coordinates contained in each basic grid and a preset threshold of the number of obstacle-avoiding hot spot coordinates, mark the grid containing the obstacle-avoiding hot spot coordinates with an obstacle-avoiding hotness identifier, the obstacle-avoiding hotness identifier including a plurality of obstacle-avoiding hotness grades, and take the plurality of basic grids with the obstacle-avoiding hotness identifier as the plurality of obstacle-avoiding hot spot regions.

[0044] In the embodiments of the present application, historical obstacle-avoiding events are extracted according to the flight log of the unmanned aerial vehicle in the to-be-gridded region within a historical time. The historical obstacle-avoiding events include the obstacle-avoiding position coordinates at the time of the obstacle-avoiding event and N historical obstacle-avoiding features of N times of obstacle avoidance at the corresponding obstacle-avoiding position. The historical obstacle-avoiding features include maneuverability parameter features, flight parameter features such as flight speed and flight height of the corresponding obstacle-avoiding unmanned aerial vehicle, obstacle-avoiding time features including the time point of the specific obstacle avoidance such as 10 o'clock in the morning, different times leading to different visibility or interference signal strength, and obstacle-avoiding weather features such as sunny day, rainy day, etc. The maneuverability parameter features include minimum turning radius, maximum climb rate, and maximum descent rate.

[0045] The maneuverability parameter features, flight parameter features, current time features, and weather features of the specific model unmanned aerial vehicle are obtained as to-be-contrasted features.

[0046] The to-be-contrasted features and the N historical obstacle-avoiding features are classified into the same set to obtain a sample obstacle-avoiding data set.

[0047] The sample obstacle-avoiding data set is divided into K clusters using a K-means clustering algorithm with Euclidean distance as the clustering basis, wherein K is a positive integer greater than or equal to 2.

[0048] The cluster in which the to-be-contrasted features are located is extracted, and a plurality of historical obstacle-avoiding features classified into the same cluster as the to-be-contrasted features are obtained as a plurality of similar historical obstacle-avoiding features.

[0049] The number of obstacle-avoiding hot spot coordinates contained in each basic grid is counted. The obstacle-avoiding hot spot coordinates are coordinates of the unmanned aerial vehicle triggering the obstacle avoidance multiple times in the to-be-gridded region and similar to the obstacle-avoiding features of the specific model unmanned aerial vehicle within a preset historical time window. For example, the obstacle-avoiding hot spot coordinates can be defined as coordinates of the unmanned aerial vehicle triggering the obstacle avoidance more than 10 times in the to-be-gridded region and similar to the obstacle-avoiding features of the specific model unmanned aerial vehicle within the past 60 days.

[0050] Based on the number of obstacle avoidance hot spot coordinates contained in each basic grid and a preset number threshold of obstacle avoidance hot spot coordinates, the grid containing the obstacle avoidance hot spot coordinates is labeled with an obstacle avoidance heat identifier. The preset number threshold of obstacle avoidance hot spot coordinates refers to a hot spot coordinate number threshold for dividing obstacle avoidance heat levels. The obstacle avoidance heat identifier includes multiple obstacle avoidance heat levels. For example, the obstacle avoidance heat can be divided into three levels: high, medium and low. The number threshold of obstacle avoidance hot spot coordinates corresponding to the high level can be set to 6, that is, the basic grid containing 6 or more obstacle avoidance hot spot coordinates is marked as high obstacle avoidance heat. The number threshold of obstacle avoidance hot spot coordinates corresponding to the medium level can be set to 3-5, that is, the basic grid containing 3 or more and less than or equal to 5 obstacle avoidance hot spot coordinates is marked as medium obstacle avoidance heat. The number threshold of obstacle avoidance hot spot coordinates corresponding to the low level can be set to 2, that is, the basic grid containing 2 or less obstacle avoidance hot spot coordinates is marked as low obstacle avoidance heat. The multiple basic grids with the obstacle avoidance heat identifier are taken as multiple obstacle avoidance hot spot regions.

[0051] By analyzing the spatio-temporal characteristics of historical events, an obstacle avoidance hot spot region prediction model is constructed. The obstacle avoidance position coordinates and associated aircraft model parameters, flight states and other features are extracted, the hot spot regions are clustered and identified on the map, and data support is provided for active optimization of airspace grid.

[0052] S50: If the region where the unmanned aerial vehicle is located is an obstacle avoidance hot spot region, the grid size is reduced on the basis of the conventional grid size to obtain a final grid size; if the region where the unmanned aerial vehicle is located is a non-obstacle avoidance hot spot region, the conventional grid size is taken as the final grid size, and the airspace is adaptively gridded.

[0053] The existing method often uses a conventional grid in a hot spot region, which cannot combine the model accident correlation of the hot spot region, resulting in a lack of pertinence of grid optimization and a lack of adaptability of the optimized grid.

[0054] The step S50 in the method provided by the embodiment of the present application includes: retrieve the maneuverability parameters of the specific model unmanned aerial vehicle; retrieve the maneuverability parameters of multiple obstacle avoidance unmanned aerial vehicles corresponding to multiple obstacle avoidance hot spot coordinates in the basic grid where the specific model unmanned aerial vehicle is located, as a historical obstacle avoidance maneuverability parameter set; According to a predefined comparison rule, the proportion of multiple maneuverability parameters in the historical obstacle avoidance maneuverability parameter set that are superior to the maneuverability parameters of the specific model unmanned aerial vehicle is calculated as a maneuverability risk degree; According to the obstacle avoidance heat identifier, an initial grid size reduction ratio corresponding to each obstacle avoidance heat identifier is set respectively; obtain the obstacle avoidance heat identifier of the obstacle avoidance hot spot region where the specific model unmanned aerial vehicle is located, and the corresponding initial grid size reduction ratio; According to the maneuvering risk degree of the specific model unmanned aerial vehicle in the obstacle avoidance hotspot area corresponding to the maneuvering risk degree, the initial grid size reduction ratio is corrected to obtain a grid size reduction ratio; According to the grid size reduction ratio of the specific model unmanned aerial vehicle entering the obstacle avoidance hotspot area, the conventional grid size is reduced to obtain the final grid size.

[0055] In the embodiment of the application, the maneuvering parameters of the specific model unmanned aerial vehicle are called, wherein the maneuvering parameters include the minimum turning radius, the maximum climbing rate and the maximum descending rate.

[0056] The maneuvering parameters of the plurality of obstacle avoidance unmanned aerial vehicles corresponding to the plurality of obstacle avoidance hotspot coordinates in the basic grid where the specific model unmanned aerial vehicle is located are called as a historical obstacle avoidance maneuvering parameter set.

[0057] According to the predefined comparison rule, the proportion of the plurality of maneuverability parameters in the historical obstacle avoidance maneuverability parameter set that are superior to the maneuverability parameters of the specific model UAV is calculated as the maneuverability danger degree. Illustratively, the proportions of the maneuverability parameters that are superior to the maneuverability parameters of the specific model UAV are weighted and summed. First, a smaller turning radius, a larger maximum climb rate, and a larger maximum descent rate are defined as superior maneuverability parameters. For example, if the turning radius of the maneuverability parameters of the specific model UAV is 2 meters, the maximum climb rate is 3 meters / second, and the maximum descent rate is 3 meters / second, and if the turning radius of one of the maneuverability parameters in the historical obstacle avoidance maneuverability parameter set is 1 meter, the maximum climb rate is 4 meters / second, and the maximum descent rate is 4 meters / second, then the superior turning ratio = (turning radius of the specific model UAV - turning radius of the historical obstacle avoidance UAV) ÷ turning radius of the specific model UAV = (2 - 1) ÷ 2 = 0.5, the superior maximum climb rate ratio = (maximum climb rate of the historical obstacle avoidance UAV - maximum climb rate of the specific model UAV) ÷ maximum climb rate of the specific model UAV = (4 - 3) ÷ 3 = 0.33, and the superior maximum descent rate ratio = (maximum descent rate of the historical obstacle avoidance UAV - maximum descent rate of the specific model UAV) ÷ maximum descent rate of the specific model UAV = (4 - 3) ÷ 3 = 0.33. The three resulting ratios are weighted and summed to obtain a comprehensive superior maneuverability parameter. Illustratively, the comprehensive superior maneuverability parameter = 0.3 × superior turning ratio + 0.35 × superior maximum climb rate ratio + 0.35 × superior maximum descent rate ratio = 0.3 × 0.5 + 0.35 × 0.33 + 0.35 × 0.33 = 0.38. A maneuverability superior parameter threshold is set, for example, a maneuverability superior comprehensive parameter greater than 0.2 is defined as a maneuverability parameter superior to the maneuverability of the specific model UAV. The maneuverability danger degree = number of historical obstacle avoidance maneuverability parameters with a maneuverability superior comprehensive parameter greater than 0.2 ÷ total number of historical obstacle avoidance maneuverability parameters, for example, if 600 of the 1000 historical obstacle avoidance maneuverability parameters have a maneuverability superior comprehensive parameter greater than 0.2, then the maneuverability danger degree = 600 ÷ 1000 = 0.6, and the greater the maneuverability danger degree, the higher the maneuverability requirement for obstacle avoidance in these obstacle hotspot coordinates.

[0058] According to the obstacle avoidance heat level identifier, the initial grid size reduction ratio corresponding to each obstacle avoidance heat level identifier is set, for example, the size reduction ratio corresponding to high level can be set to 0.8, i.e., the grid size is reduced to 80% of the initial size, the size reduction ratio corresponding to medium level is set to 0.5, and the size reduction ratio corresponding to low level is set to 0.3, to obtain the initial grid size reduction ratio corresponding to each obstacle avoidance heat level identifier.

[0059] The obstacle avoidance heat level identifier of the obstacle hotspot region in which the specific model UAV is located is obtained, as well as the corresponding initial grid size reduction ratio.

[0060] If the region where the UAV is located is an obstacle avoidance hotspot region, the grid size is reduced on the basis of the conventional grid size to obtain a final grid size. Specifically, according to the maneuverability risk degree of the specific model UAV in the obstacle avoidance hotspot region, the initial grid size reduction ratio is corrected to obtain a grid size reduction ratio, that is, grid size reduction ratio = initial grid size reduction ratio × (1-maneuverability risk degree). For example, if the heat level of an obstacle avoidance hotspot region is high, the initial grid size reduction ratio is 0.8, and the maneuverability risk degree is 0.6, then the grid size reduction ratio = 0.8 × (1-0.6) = 0.32, that is, the grid size is reduced to 32% of the initial size.

[0061] According to the grid size reduction ratio of the specific model UAV entering the obstacle avoidance hotspot region, the conventional grid size is reduced to obtain a final grid size. For example, if the conventional grid size is 24m × 24m, the reduced grid size = 24 × 0.32 = 7.68, and the final grid size is 7.68m × 7.68m.

[0062] If the region where the UAV is located is a non-obstacle avoidance hotspot region, the conventional grid size is taken as the final grid size for airspace adaptive gridding.

[0063] Based on the obstacle avoidance hotspot identification and the model characteristics, risk-adaptive grid optimization is realized. When the UAV enters the hotspot region, the conventional grid size is reduced to enhance the path planning fineness, and the reduction ratio is dynamically adjusted in combination with historical data. By binding the hotspot region and the model risk, the hotspot region is actively optimized, and the grid adaptability in complex airspace is significantly improved.

[0064] Embodiment two, as shown in Figure 2 Based on the same inventive concept as the airspace adaptive gridding method for UAV flight provided in embodiment one, the present embodiment also provides an airspace adaptive gridding system for UAV flight, which comprises: An initial grid size acquisition module 100 is configured to obtain multiple sets of maneuverability parameters of multiple models of UAVs, establish a mapping relationship between the maneuverability parameters and the initial grid size, and configure the initial grid size for each of the multiple models of UAVs according to the multiple sets of maneuverability parameters; A grid size correction module 200 is configured to obtain a high-precision map of a region to be gridded, evaluate the terrain complexity of the region to be gridded on the basis of the high-precision map, obtain a terrain complexity distribution map of the region to be gridded, and convert the terrain complexity distribution map to obtain a grid size correction coefficient distribution map; The conventional grid size obtaining module 300 is configured to obtain an initial grid size corresponding to the unmanned aerial vehicle according to the model when the unmanned aerial vehicle of the specific model enters the area to be gridded, call a grid size correction coefficient distribution map of the area to be gridded, obtain a grid size correction coefficient according to the real-time position of the unmanned aerial vehicle, correct the initial grid size according to the grid size correction coefficient, and obtain the conventional grid size of the unmanned aerial vehicle. The hotspot area marking module 400 is configured to collect historical obstacle avoidance data of unmanned aerial vehicles in the area to be gridded in a historical time, and mark an obstacle avoidance hotspot area in the area to be gridded according to the historical obstacle avoidance data of the unmanned aerial vehicles. The adaptive gridding module 500 is configured to, if the area where the unmanned aerial vehicle is located is the obstacle avoidance hotspot area, reduce the grid size on the basis of the conventional grid size to obtain a final grid size; and if the area where the unmanned aerial vehicle is located is not the obstacle avoidance hotspot area, take the conventional grid size as the final grid size to perform adaptive gridding of the airspace.

[0065] In one embodiment, the initial grid size obtaining module 100 is further configured to: obtain a plurality of sets of maneuverability parameters of a plurality of models of unmanned aerial vehicles, wherein one set of maneuverability parameters includes a minimum turning radius, a maximum climb rate, and a maximum descent rate; determine a horizontal dimension of the initial grid size of the unmanned aerial vehicle of the specific model according to the minimum turning radius; determine a height dimension of the initial grid size of the unmanned aerial vehicle of the specific model according to the maximum climb rate and the maximum descent rate; fuse the horizontal dimension and the height dimension of the initial grid size of the unmanned aerial vehicle of the specific model to obtain the initial grid size of the unmanned aerial vehicle of the specific model; configure the initial grid size for the plurality of models of unmanned aerial vehicles one by one according to the plurality of sets of maneuverability parameters.

[0066] In one embodiment, the grid size correction module 200 is further configured to: pre-divide the area to be gridded into a plurality of basic grids, and calculate the terrain complexity in units of the basic grids; calculate a ratio of a total floor area of all buildings in each basic grid to an area of the basic grid to obtain a building area density of each basic grid; calculate a ratio of a total number of buildings in each basic grid to the area of the basic grid to obtain a building number density of each basic grid; calculate a standard deviation of heights of all buildings in each basic grid to obtain a building height difference degree of each basic grid; The building area density, the building number density, and the building height difference value corresponding to each base grid are normalized, and then weighted summation is performed to obtain the terrain complexity corresponding to each base grid, wherein the terrain complexity has a value range greater than 0 and less than or equal to 1; In the high-precision map of the to-be-gridded area, the range of each base grid and the terrain complexity corresponding thereto are labeled to obtain the terrain complexity distribution map; The terrain complexity corresponding to each base grid in the terrain complexity distribution map is extracted to obtain a distribution range of a plurality of terrain complexity values, and a terrain complexity distribution interval is obtained. A preset grating size correction coefficient range is set, and a mapping relationship between the terrain complexity distribution interval and the grating size correction coefficient range is established. According to the terrain complexity corresponding to each base grid, a grating size correction coefficient corresponding to each base grid is obtained.

[0067] In one embodiment, the hotspot area marking module 400 is further configured to: According to the flight log of the unmanned aerial vehicle in the to-be-gridded area within a historical time, a historical obstacle avoidance event is extracted, the historical obstacle avoidance event including an obstacle avoidance position coordinate at the time of obstacle avoidance and N historical obstacle avoidance features of N times of obstacle avoidance at the corresponding obstacle avoidance position, the historical obstacle avoidance features including maneuverability parameter features, flight parameter features, obstacle avoidance time features, and obstacle avoidance weather features of the corresponding unmanned aerial vehicle, wherein the maneuverability parameter features include a minimum turning radius, a maximum climb rate, and a maximum descent rate. The maneuverability parameter features, the flight parameter features, the current time features, and the weather features of the specific model unmanned aerial vehicle are obtained as to-be-contrasted features. The to-be-contrasted features and the N historical obstacle avoidance features are clustered using a clustering algorithm, a plurality of similar historical obstacle avoidance features similar to the to-be-contrasted features are extracted from the N historical obstacle avoidance features, and a plurality of obstacle avoidance hotspot coordinates corresponding to the plurality of similar historical obstacle avoidance features are obtained. The to-be-contrasted features and the N historical obstacle avoidance features are clustered using a clustering algorithm, a plurality of similar historical obstacle avoidance features similar to the to-be-contrasted features are extracted from the N historical obstacle avoidance features, and a plurality of obstacle avoidance hotspot coordinates corresponding to the plurality of similar historical obstacle avoidance features are obtained. The to-be-contrasted features and the N historical obstacle avoidance features are classified into the same set to obtain a sample obstacle avoidance dataset; The sample obstacle avoidance dataset is divided into K clusters using a K-means clustering algorithm, wherein K is a positive integer greater than or equal to 2. The cluster in which the to-be-contrasted features are located is extracted, and a plurality of historical obstacle avoidance features classified into the same cluster as the to-be-contrasted features are obtained as a plurality of similar historical obstacle avoidance features. Mark the basic grid where the plurality of obstacle avoidance hotspot coordinates are located as a plurality of obstacle avoidance hotspot areas; The marking of the basic grid where the plurality of obstacle avoidance hotspot coordinates are located as a plurality of obstacle avoidance hotspot areas comprises: Count the number of obstacle avoidance hotspot coordinates contained in each basic grid; Based on the number of obstacle avoidance hotspot coordinates contained in each basic grid and a preset threshold of the number of obstacle avoidance hotspot coordinates, mark the grid containing the obstacle avoidance hotspot coordinates with an obstacle avoidance heat identification, the obstacle avoidance heat identification containing a plurality of obstacle avoidance heat grades, and take the plurality of basic grids with the obstacle avoidance heat identification as the plurality of obstacle avoidance hotspot areas.

[0068] In an embodiment, the adaptive gridding module 500 is further configured to: retrieve the maneuverability parameters of the specific model of UAV; retrieve the maneuverability parameters of the plurality of obstacle avoidance UAVs corresponding to the plurality of obstacle avoidance hotspot coordinates in the basic grid where the specific model of UAV is located as a set of historical obstacle avoidance maneuverability parameters; According to the predefined comparison rule, calculate the proportion of the plurality of maneuverability parameters in the set of historical obstacle avoidance maneuverability parameters that are superior to the maneuverability parameters of the specific model of UAV as a maneuverability risk degree; According to the obstacle avoidance heat identification, set the initial gridding size reduction ratio corresponding to each obstacle avoidance heat identification respectively; Obtain the obstacle avoidance heat identification of the obstacle avoidance hotspot area where the specific model of UAV is located and the corresponding initial gridding size reduction ratio; According to the maneuverability risk degree of the specific model of UAV in the obstacle avoidance hotspot area, correct the initial gridding size reduction ratio to obtain the gridding size reduction ratio; According to the gridding size reduction ratio of the specific model of UAV entering the obstacle avoidance hotspot area, reduce the regular gridding size to obtain the final gridding size.

[0069] In summary, the embodiments of the present application have at least the following technical effects: The application provides a method and system for airspace adaptive gridding for unmanned aerial vehicle flight. By dynamically fusing unmanned aerial vehicle maneuverability parameters, terrain complexity and historical obstacle avoidance hotspot area data, the adaptability of airspace resource allocation and flight safety are significantly improved. First, based on the initial gridding configuration of the maneuverability difference of multiple unmanned aerial vehicle models, the motion ability of different models is fundamentally adapted, preventing maneuverability advantage models from being limited by dense grids and wasting airspace resources. Second, relying on the terrain complexity dynamic correction mechanism of high-precision maps, the grid size is automatically reduced in high-risk environments such as building-intensive areas and complex terrain to improve obstacle avoidance accuracy, and the grid size is appropriately expanded in open areas to optimize path planning efficiency, achieving a balance between safety and airspace utilization. Finally, by mining historical obstacle avoidance event features to identify hotspots, the grid is fine-tuned in hotspots to block the repeated occurrence of historical obstacle avoidance risks. Compared with traditional methods, the technical solution provided by the application significantly overcomes the problem of rigid airspace utilization caused by static gridding, achieving the technical effect of adaptive gridding of airspace resources according to multiple parameters.

[0070] It should be noted that the above sequence of the embodiments of the application is only for description, and does not represent the advantages and disadvantages of the embodiments. Moreover, the above describes specific embodiments of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are possible or can be advantageous.

[0071] The above only describes the preferred embodiments of the application and does not limit the application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the application shall be included in the protection scope of the application.

[0072] The present application and the drawings are only exemplary descriptions of the application, and are considered to cover any and all modifications, changes, combinations or equivalents within the scope of the application. Obviously, those skilled in the art can make various modifications and changes to the application without departing from the scope of the application. Thus, if these modifications and changes of the application belong to the scope of the application and its equivalent technology, the application intends to include these modifications and changes.

Claims

1. A method for airspace adaptive gridding for drone flight, characterized in that, The method includes: Multiple sets of maneuverability parameters for various types of UAVs are obtained, a mapping relationship between maneuverability parameters and initial grid size is established, and initial grid size is configured for each type of UAV based on the multiple sets of maneuverability parameters. Obtain a high-precision map of the area to be gridded, assess the terrain complexity of the area based on the high-precision map, obtain a terrain complexity distribution map of the area to be gridded, and calculate the grid size correction coefficient distribution map based on the terrain complexity distribution map. When a specific model of drone enters the area to be gridded, the initial grid size corresponding to the drone is obtained according to the model, the grid size correction coefficient distribution map of the area to be gridded is retrieved, the grid size correction coefficient is obtained according to the real-time position of the drone, and the initial grid size is corrected according to the grid size correction coefficient to obtain the conventional grid size of the drone. Collect historical obstacle avoidance data of UAVs in the area to be gridded over a historical period, and mark obstacle avoidance hotspots in the area to be gridded based on the historical obstacle avoidance data of UAVs. If the area where the drone is located is an obstacle avoidance hotspot, the grid size is reduced based on the regular grid size to obtain the final grid size; if the area where the drone is located is not an obstacle avoidance hotspot, the regular grid size is used as the final grid size, and airspace adaptive gridding is performed.

2. The drone flight oriented airspace adaptive gridding method of claim 1, wherein, Multiple sets of maneuverability parameters for various UAV models are obtained, and a mapping relationship between these maneuverability parameters and initial grid sizes is established. Based on these multiple sets of maneuverability parameters, initial grid sizes are configured for each UAV model, including: Multiple sets of maneuverability parameters for various UAV models were obtained, including minimum turning radius, maximum rate of climb, and maximum rate of descent. Based on the minimum turning radius, determine the horizontal dimension of the initial grille size for a specific model of UAV; The height dimension of the initial grille size for a specific model of UAV is determined based on the maximum climb rate and maximum descent rate. By combining the horizontal and vertical dimensions of the initial grille size for a specific drone model, the initial grille size for that drone model can be obtained. Based on the aforementioned multiple sets of mobility parameters, initial grid sizes are configured for each type of UAV.

3. The drone flight oriented airspace adaptive gridding method of claim 1, wherein, Based on a high-precision map, the terrain complexity of the area to be gridded is assessed, and a terrain complexity distribution map of the area to be gridded is obtained, including: The area to be gridded is pre-divided into multiple basic grids, and the terrain complexity is calculated in units of the basic grids. Calculate the ratio of the total floor area of ​​all buildings in each basic grid to the area of ​​the basic grid to obtain the building area density of each basic grid; Calculate the ratio of the total number of buildings in each basic grid to the area of ​​the basic grid to obtain the building density of each basic grid; Calculate the standard deviation of the height of all buildings within each base grid to obtain the building height difference of each base grid; The building area density, building number density, and building height difference values ​​corresponding to each basic grid are normalized and then weighted and summed to obtain the terrain complexity corresponding to each basic grid. The terrain complexity value ranges from greater than 0 to less than or equal to 1. In the high-precision map of the region to be gridded, the range of each basic grid and its corresponding terrain complexity are marked to obtain the terrain complexity distribution map.

4. The drone flight oriented airspace adaptive gridding method of claim 3, wherein, According to the terrain complexity distribution map, a gridding size correction coefficient distribution map is converted, including: Extracting the terrain complexity corresponding to each basic grid in the terrain complexity distribution map, obtaining the distribution range of a plurality of terrain complexity values, and obtaining a terrain complexity distribution interval; A preset gridding size correction coefficient range is established, and a mapping relationship between the terrain complexity distribution interval and the gridding size correction coefficient range is established; According to the terrain complexity corresponding to each basic grid, the gridding size correction coefficient corresponding to each basic grid is mapped.

5. The drone flight oriented airspace adaptive gridding method of claim 1, wherein, Collecting historical UAV obstacle avoidance data of the region to be gridded within a historical time, and marking an obstacle avoidance hotspot region in the region to be gridded according to the historical UAV obstacle avoidance data, including: According to the flight log of the UAV in the region to be gridded within the historical time, a historical obstacle avoidance event is extracted, the historical obstacle avoidance event includes an obstacle avoidance position coordinate when the obstacle avoidance event occurs and N historical obstacle avoidance features of N obstacle avoidance events at the corresponding obstacle avoidance position, the historical obstacle avoidance features include maneuverability parameter features, flight parameter features, obstacle avoidance time features, and obstacle avoidance weather features of the corresponding UAV, wherein the maneuverability parameter features include a minimum turning radius, a maximum climb rate, and a maximum descent rate; Obtaining the maneuverability parameter features, flight parameter features, current time features, and weather features of a specific type of UAV as comparison features; Using a clustering algorithm to cluster the comparison features and N historical obstacle avoidance features, extracting a plurality of similar historical obstacle avoidance features similar to the comparison features from the N historical obstacle avoidance features, and obtaining a plurality of obstacle avoidance hotspot coordinates corresponding to the plurality of similar historical obstacle avoidance features; Marking the basic grid where the plurality of obstacle avoidance hotspot coordinates are located as a plurality of obstacle avoidance hotspot regions.

6. The drone flight oriented airspace adaptive gridding method of claim 5, wherein, Using a clustering algorithm to cluster the comparison features and N historical obstacle avoidance features, extracting a plurality of similar historical obstacle avoidance features similar to the comparison features from the N historical obstacle avoidance features, including: Grouping the comparison features and the N historical obstacle avoidance features into the same set to obtain a sample obstacle avoidance data set; Using a K-means clustering algorithm to divide the sample obstacle avoidance data set into K clusters based on Euclidean distance as the clustering basis, wherein K is a positive integer greater than or equal to 2; Extracting the cluster where the comparison features are located, and obtaining a plurality of historical obstacle avoidance features grouped into the same cluster as the comparison features as a plurality of similar historical obstacle avoidance features.

7. The drone flight oriented airspace adaptive gridding method of claim 6, wherein, Marking the basic grid where the plurality of obstacle avoidance hotspot coordinates are located as a plurality of obstacle avoidance hotspot regions, including: Counting the number of obstacle avoidance hotspot coordinates contained in each basic grid; Based on the number of obstacle avoidance hotspot coordinates contained in each basic grid and a preset threshold of the number of obstacle avoidance hotspot coordinates, marking the grid containing the obstacle avoidance hotspot coordinates with an obstacle avoidance heat identifier, the obstacle avoidance heat identifier includes a plurality of obstacle avoidance heat grades, and the plurality of basic grids with the obstacle avoidance heat identifier are taken as the plurality of obstacle avoidance hotspot regions.

8. The drone flight oriented airspace adaptive gridding method of claim 7, wherein, if the region where the UAV is located is an obstacle avoidance hotspot region, then the grid size is reduced on the basis of the regular grid size to obtain a final grid size, including: obtaining the maneuverability parameters of the specific model UAV; obtaining the maneuverability parameters of a plurality of obstacle avoidance UAVs corresponding to a plurality of obstacle avoidance hotspot coordinates in the basic grid where the specific model UAV is located, as a historical obstacle avoidance maneuverability parameter set; calculating, according to a predefined comparison rule, a proportion of the plurality of maneuverability parameters in the historical obstacle avoidance maneuverability parameter set that are superior to the maneuverability parameters of the specific model UAV, as a maneuverability risk degree; respectively setting an initial grid size reduction ratio corresponding to each obstacle avoidance heat degree identifier according to the obstacle avoidance heat degree identifier; obtaining the obstacle avoidance heat degree identifier of the obstacle avoidance hotspot region where the specific model UAV is located, and the corresponding initial grid size reduction ratio; correcting the initial grid size reduction ratio according to the maneuverability risk degree of the specific model UAV in the obstacle avoidance hotspot region to obtain a grid size reduction ratio; reducing the regular grid size of the specific model UAV entering the obstacle avoidance hotspot region according to the grid size reduction ratio to obtain the final grid size.

9. A drone flight oriented airspace adaptive gridding system, characterized by, A system for implementing the airspace adaptive gridding method for UAV flight according to any one of claims 1 to 8, the system comprising: an initial grid size acquisition module, configured to obtain a plurality of sets of maneuverability parameters of a plurality of models of UAVs, establish a mapping relationship between the maneuverability parameters and the initial grid size, and configure the initial grid size for each of the plurality of models of UAVs according to the plurality of sets of maneuverability parameters; a grid size correction module, configured to obtain a high-precision map of a region to be gridded, evaluate the terrain complexity of the region to be gridded on the basis of the high-precision map, obtain a terrain complexity distribution map of the region to be gridded, and convert the terrain complexity distribution map to obtain a grid size correction coefficient distribution map; a regular grid size acquisition module, configured to, when a specific model UAV enters the region to be gridded, obtain the initial grid size corresponding to the model of the UAV, retrieve the grid size correction coefficient distribution map of the region to be gridded, obtain the grid size correction coefficient according to the real-time position of the UAV, correct the initial grid size according to the grid size correction coefficient, and obtain the regular grid size of the UAV; a hotspot region marking module, configured to collect historical obstacle avoidance data of UAVs in the region to be gridded in a historical time, and mark an obstacle avoidance hotspot region in the region to be gridded according to the historical obstacle avoidance data of the UAVs; an adaptive gridding module, configured to, if the region where the UAV is located is an obstacle avoidance hotspot region, reduce the grid size on the basis of the regular grid size to obtain a final grid size, and if the region where the UAV is located is not an obstacle avoidance hotspot region, take the regular grid size as the final grid size to perform airspace adaptive gridding.

Images