Low-altitude air route risk map construction method and system based on artificial intelligence

Abstract

The invention relates to the technical field of unmanned aerial vehicle route planning, and discloses a low-altitude route risk map construction method and system based on artificial intelligence, and the system comprises a low-altitude environment perception constraint module, a low-altitude route feature extraction module, a dynamic risk constraint judgment module, a low-altitude route map construction module, and a low-altitude route risk analysis module. And the optimal path calibration output module is used for determining a low-altitude air route flight area by acquiring a first constraint condition of low-altitude air route environment perception, extracting key feature parameters from low-altitude air route data, performing second constraint condition analysis on the low-altitude air route, intelligently planning a low-altitude air route route according to an analysis result, and constructing a low-altitude air route map. According to the method, the low-altitude air route is acquired, the constant direction line risk analysis is performed on the low-altitude air route to calibrate the optimal path, the optimal path is output to the user terminal, the path three-dimensional display is performed in the low-altitude air route map, and the execution efficiency and the safety of the flight task are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle route planning, and more particularly to a method and system for constructing a low-altitude route risk map based on artificial intelligence. Background Art

[0002] With the rise of emerging industries such as general aviation, unmanned aerial vehicle logistics, and urban air traffic, low-altitude flight activities are becoming increasingly frequent. As an important passage for these flight activities, the safety and efficiency of low-altitude routes are directly related to the healthy development of the entire low-altitude economy. However, low-altitude routes face many risk factors, such as changes in meteorological conditions, terrain obstacles, air traffic conflicts, etc. Traditional route planning and risk assessment methods are difficult to meet the growing flight demands.

[0003] On the other hand, the development and utilization of low-altitude airspace are becoming increasingly extensive, and the application scenarios of unmanned aerial vehicles and low-altitude aircraft are constantly expanding. How to efficiently and accurately construct a low-altitude route risk map has become an important issue for ensuring flight safety. Traditional technical means such as radar surveillance systems are difficult to effectively capture low-altitude flight targets such as "low, slow, and small" unmanned aerial vehicles, resulting in blind spots in low-altitude airspace management. Through the integration of multi-sensor data and the use of algorithms such as computer vision and machine learning, artificial intelligence technology can achieve real-time and accurate positioning, identification, and tracking of low-altitude flight targets, improving the efficiency and safety of low-altitude traffic management.

[0004] However, existing low-altitude route risk assessment methods mainly rely on static grid division, biological activity analysis, and traditional risk assessment models. However, these methods still have deficiencies in terms of dynamics, intelligence, and global perspective, and are difficult to meet the requirements of the complex and changeable urban low-altitude environment. They may not be able to update risk information in real time, resulting in deviations between the risk map and the actual environment. In some complex low-altitude route scenarios, such as densely populated urban areas and around airports, there are a large number of obstacles and complex air traffic rules. Existing methods may be difficult to accurately assess the risks in these scenarios and cannot provide reasonable route planning suggestions for aircraft. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, the present invention provides a system for constructing a low-altitude route risk map based on artificial intelligence to solve the problems existing in the above-mentioned background art.

[0006] The present invention provides the following technical solutions: A system for constructing a low-altitude route risk map based on artificial intelligence, including: a low-altitude environment perception and constraint module, a low-altitude route feature extraction module, a dynamic risk constraint determination module, a low-altitude route map construction module, a low-altitude route risk analysis module, and an optimal path calibration and output module; The low-altitude environment perception constraint module obtains the first constraint condition for low-altitude route environment perception and determines the flyable area of the low-altitude route; The low-altitude route feature extraction module is used to extract key feature parameters from low-altitude route data, including terrain undulation degree, meteorological change rate, and air traffic density, and convert the parameters into a standardized input format; The dynamic risk constraint determination module analyzes the second constraint condition for the low-altitude route based on the key feature parameters extracted by the low-altitude route feature extraction module, and intelligently plans the low-altitude route according to the analysis results; The low-altitude route map construction module constructs a low-altitude route map based on the low-altitude route intelligently planned by the dynamic risk constraint determination module; The low-altitude route risk analysis module conducts a rhumb line risk analysis on the low-altitude route intelligently planned, and calibrates the optimal path according to the rhumb line risk analysis results; The optimal path calibration and output module outputs the optimal path to the user terminal based on the optimal path calibrated by the low-altitude route risk analysis module, and performs a three-dimensional display of the path on the low-altitude route map.

[0007] Preferably, the low-altitude environment perception constraint module is used to obtain the first constraint condition for low-altitude route environment perception, and the first constraint condition for low-altitude route environment perception is specifically as follows: By fusing multi-source sensor data, the low-altitude environment is monitored in real time to obtain the environmental perception data of the low-altitude environment. The multi-source sensors include: lidar, weather radar, and infrared imaging equipment; According to the environmental perception data of the low-altitude environment, the boundary conditions for the flyable area of the low-altitude route are defined, and the boundary conditions are the first constraint condition; Based on the first constraint condition, the flyable area range of the low-altitude route is determined.

[0008] Preferably, the low-altitude route feature extraction module is used to extract key feature parameters from low-altitude route data. The key feature parameters are the regional feature parameters of the flyable area of the low-altitude route, including: terrain undulation parameters, meteorological change parameters, and air traffic density parameters; The acquisition content of the terrain undulation parameters is as follows: Using high-resolution digital elevation model data, the slope of the flyable area of the low-altitude route is obtained through GIS software; it is calculated through digital elevation model data and is used to describe the height and low undulation of the terrain along the low-altitude route; using the high-density point cloud data obtained by lidar, the roughness of the flyable area of the low-altitude route is obtained through point cloud processing software; the elevation standard deviation of the flyable area of the low-altitude route is obtained using the elevation model; The content of obtaining the meteorological change parameters is as follows: detecting the actual wind speed of the wind field using the Doppler principle, and combining temperature compensation to obtain the wind speed in the flyable area of the low-altitude airway; establishing the connection between the cloud top temperature and the pixel precipitation points, and using the difference between satellite information and ground rain gauges to obtain the precipitation in the flyable area of the low-altitude airway; obtaining the visibility in the flyable area of the low-altitude airway by observing the brightness contrast between the target object and the background. The content of obtaining the air traffic density parameters is as follows: through radar monitoring and the air traffic management system to count the flight plan data along the low-altitude airway, and obtain the number of aircraft and the distance to the nearest aircraft per unit area in each area within the flyable area of the low-altitude airway and within a preset time window.

[0009] Preferably, the dynamic risk constraint determination module analyzes the second constraint conditions for the low-altitude airway based on the key feature parameters extracted by the low-altitude airway feature extraction module, and intelligently plans the specific content of the low-altitude airway route according to the analysis results as follows: Based on the key feature parameters extracted by the low-altitude airway feature extraction module, analyze the terrain undulation index of the flyable area of the low-altitude airway. The parameters include: the slope, roughness, and elevation standard deviation of the flyable area of the low-altitude airway. Based on the key feature parameters extracted by the low-altitude airway feature extraction module, analyze the meteorological fluctuation index of the flyable area of the low-altitude airway. The key feature parameters include: the wind speed, precipitation, and visibility in the flyable area of the low-altitude airway. Based on the key feature parameters extracted by the low-altitude airway feature extraction module, analyze the air traffic conflict probability index of the flyable area of the low-altitude airway. The key feature parameters include: the number of aircraft per unit area and within a preset time window and the distance to the nearest aircraft.

[0010] Preferably, the specific content of analyzing the second constraint conditions for the low-altitude airway is as follows: Establish a dynamic risk constraint determination model, conduct a non-linear coupling analysis on the terrain undulation index, meteorological fluctuation index, and air traffic conflict probability index of the flyable area of the low-altitude airway, and calculate the comprehensive risk assessment index of the flyable area of the low-altitude airway. Preset the segmentation threshold of the second constraint condition according to the first constraint condition of low-altitude route environment perception. The segmentation threshold includes a maximum segmentation threshold and a minimum segmentation threshold, and the maximum segmentation threshold is greater than the minimum segmentation threshold. Compare the comprehensive risk assessment index of the flyable area of the low-altitude route with the maximum segmentation threshold and the minimum segmentation threshold: when the comprehensive risk assessment index of the flyable area of the low-altitude route is less than or equal to the minimum segmentation threshold, mark the area as a green flyable area; when the comprehensive risk assessment index of the flyable area of the low-altitude route is greater than the minimum segmentation threshold and less than the maximum segmentation threshold, mark the area as a yellow speed-reducing flight area; when the comprehensive risk assessment index of the flyable area of the low-altitude route is greater than or equal to the maximum segmentation threshold, mark the area as a red warning area. According to the constraint result of the second constraint condition, retain the green flyable area and the yellow speed-reducing flight area, and intelligently plan the low-altitude route.

[0011] Preferably, the low-altitude route map construction module constructs a low-altitude route map based on the low-altitude route intelligently planned by the dynamic risk constraint determination module. The low-altitude route map includes a dynamic three-dimensional display of different routes and gives flight status reminders for areas of different colors: when the moving target enters the yellow speed-reducing flight area from the green flyable area, the low-altitude route map issues a speed-reducing command; when the moving target enters the green flyable area from the yellow speed-reducing flight area, the low-altitude route map issues a speed-up command.

[0012] Preferably, the low-altitude route risk analysis module conducts a rhumb line risk analysis on the low-altitude route intelligently planned, and calibrates the specific content of the optimal path according to the rhumb line risk analysis result as follows: Count the deviation points of the existing m paths to obtain the number of deviation points of the m paths. Connect the deviation points of the m paths in sequence to form a deviation flight segment. The deviation point represents a waypoint where the change range of the flight angle of the moving target exceeds the preset threshold during the process from the starting coordinate to the ending coordinate. According to the starting coordinate and the ending coordinate of the moving target, calculate the rhumb line length of each deviation flight segment in the m paths, and perform an averaging process on the rhumb line lengths to obtain the average rhumb line length of the m paths. Conduct a rhumb line risk analysis on the low-altitude route according to the average rhumb line length of the m paths. The smaller the average rhumb line length, the smaller the flight risk of the corresponding low-altitude route. Calibrate the path corresponding to the minimum value of the average rhumb line length as the optimal path.

[0013] Preferably, the optimal path calibration output module outputs the coordinate information, flight altitude, and estimated flight time of the optimal path to the user terminal based on the optimal path calibrated by the low-altitude route risk analysis module. The user terminal is a drone control platform, which realizes the three-dimensional visualization display of the optimal path in the low-altitude route map and gives flight operation prompts according to the real-time flight situation.

[0014] A method for constructing a low-altitude route risk map based on artificial intelligence includes the following steps: Step S01: Obtain the first constraint condition of low-altitude route environment perception and determine the flyable area of the low-altitude route; Step S02: Extract key feature parameters from the low-altitude route data, including terrain undulation degree, meteorological change rate, and air traffic density; Step S03: Analyze the second constraint condition of the low-altitude route according to the key feature parameters, and intelligently plan the low-altitude route according to the analysis results; Step S04: Construct a low-altitude route map based on the intelligently planned low-altitude route; Step S05: Conduct a rhumb line risk analysis on the intelligently planned low-altitude route and calibrate the optimal path according to the rhumb line risk analysis results; Step S06: Based on the calibrated optimal path, output the optimal path to the user terminal and perform three-dimensional path display in the low-altitude route map.

[0015] The technical effects and advantages of the present invention: The present invention is provided with a low-altitude environment perception constraint module, a low-altitude route feature extraction module, a dynamic risk constraint determination module, a low-altitude route map construction module, a low-altitude route risk analysis module, and an optimal path calibration output module. The first constraint condition is formed by the low-altitude environment perception constraint module, avoiding the limitations of traditional single data sources, and the environmental data is updated in real time to dynamically adjust the constraint conditions to cope with the rapid changes in the low-altitude environment; Nonlinear coupling analysis is carried out on the terrain undulation index, meteorological fluctuation index, and air traffic conflict probability index of the flyable area of the low-altitude route, and the comprehensive risk assessment index of the flyable area of the low-altitude route is calculated. The low-altitude route is intelligently planned and the low-altitude route map is constructed by combining static and dynamic constraints, which can capture the dynamic changes of the low-altitude environment in real time, effectively meet the requirements of the complex and changeable urban low-altitude environment, accurately divide areas with different risk levels, provide reasonable route planning suggestions for aircraft, reduce flight risks, and improve the efficiency and safety of low-altitude traffic management; The rhumb line risk analysis is introduced, and the average rhumb line length of each route is calculated to evaluate the flight risk, so as to determine the optimal path, which combines the actual situation of air traffic and makes the planned route safer and more efficient. Description of the Drawings

[0016] Figure 1 It is a schematic structural diagram of a low-altitude route risk map construction system based on artificial intelligence.

[0017] Figure 2 It is a schematic flow diagram of a method for constructing a low-altitude route risk map based on artificial intelligence. Specific implementation manners

[0018] Next, the technical solutions in the present invention will be clearly and completely described in conjunction with the accompanying drawings in the present invention. In addition, the forms of the respective structures described in the following embodiments are merely examples, and the method and system for constructing a low-altitude route risk map based on artificial intelligence involved in the present invention are not limited to the respective structures described in the following embodiments. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present invention.

[0019] As Figure 1 shown, the present invention provides a low-altitude route risk map construction system based on artificial intelligence, including: a low-altitude environment perception constraint module, a low-altitude route feature extraction module, a dynamic risk constraint determination module, a low-altitude route map construction module, a low-altitude route risk analysis module, and an optimal path calibration and output module; The low-altitude environment perception constraint module obtains the first constraint condition for low-altitude route environment perception and determines the flyable area of the low-altitude route; The low-altitude route feature extraction module is used to extract key feature parameters from low-altitude route data, including terrain undulation, meteorological change rate, and air traffic density, and convert the parameters into a standardized input format; The dynamic risk constraint determination module analyzes the second constraint condition for the low-altitude route based on the key feature parameters extracted by the low-altitude route feature extraction module and intelligently plans the low-altitude route according to the analysis results; The low-altitude route map construction module constructs a low-altitude route map based on the low-altitude route intelligently planned by the dynamic risk constraint determination module; The low-altitude route risk analysis module performs rhumb line risk analysis on the low-altitude route intelligently planned and calibrates the optimal path according to the rhumb line risk analysis results; The optimal path calibration and output module outputs the optimal path to the user terminal based on the optimal path calibrated by the low-altitude route risk analysis module and performs three-dimensional display of the path in the low-altitude route map.

[0020] In this embodiment, it should be specifically noted that the low-altitude environment perception constraint module is used to obtain the first constraint condition for low-altitude route environment perception, and the first constraint condition for low-altitude route environment perception is specifically as follows: Real-time monitoring of the low-altitude environment is carried out by fusing multi-source sensor data to obtain environmental perception data of the low-altitude environment. The multi-source sensors include: lidar, weather radar, and infrared imaging equipment; Boundary conditions for delimiting the flyable area of the low-altitude airway are determined based on the environmental perception data of the low-altitude environment. The boundary conditions are the first constraint conditions; Based on the first constraint conditions, the flyable area range of the low-altitude airway is determined; The lidar is used to accurately capture the terrain contour and obstacle distribution. The weather radar provides meteorological parameters such as wind speed, rainfall, and air pressure in the current area. The infrared imaging equipment can identify the heat source distribution to detect potential air traffic conflicts or human activity interferences. After filtering and spatio-temporal alignment of these multi-source data, the first-layer environmental constraint conditions are formed, and the boundary range of the flyable area is determined. For example, in a certain urban area, if there is a high-rise building complex, this area is marked as a high-risk flight area, and at the same time, the airspace beyond a certain height range is also excluded from the flyable area.

[0021] In this embodiment, it should be specifically noted that the low-altitude airway feature extraction module is used to extract key feature parameters from the low-altitude airway data. The key feature parameters are the regional feature parameters of the flyable area of the low-altitude airway, including: terrain undulation parameters, meteorological change parameters, and air traffic density parameters; The content for obtaining the terrain undulation parameters is as follows: Using high-resolution digital elevation model data, the slope of the flyable area of the low-altitude airway is obtained through GIS software; it is calculated from the digital elevation model data and is used to describe the height undulation of the terrain along the low-altitude airway; using the high-density point cloud data obtained by lidar, the roughness of the flyable area of the low-altitude airway is obtained through point cloud processing software; the elevation standard deviation of the flyable area of the low-altitude airway is obtained using the elevation model; The content for obtaining the meteorological change parameters is as follows: Using the Doppler principle to detect the actual wind speed of the wind field, and combining temperature compensation to obtain the wind speed of the flyable area of the low-altitude airway; by establishing the connection between the cloud top temperature and the pixel precipitation points, and using the difference between satellite information and ground rain gauges to obtain the precipitation of the flyable area of the low-altitude airway; the visibility of the flyable area of the low-altitude airway is obtained by observing the brightness contrast between the target object and the background; The content for obtaining the air traffic density parameters is as follows: By monitoring with radar and counting the flight plan data along the low-altitude airway through the air traffic management system, the number of aircraft and the distance to the nearest aircraft within each area unit area and a preset time window in the flyable area of the low-altitude airway are obtained.

[0022] In this embodiment, it should be specifically noted that the dynamic risk constraint determination module analyzes the second constraint conditions for the low-altitude airway based on the key feature parameters extracted by the low-altitude airway feature extraction module, and the specific content of the intelligent planning of the low-altitude airway route based on the analysis results is as follows: Based on the key feature parameters extracted by the low-altitude airway feature extraction module, analyze the terrain undulation index of the flyable area of the low-altitude airway. The parameters include: the slope, roughness, and elevation standard deviation of the flyable area of the low-altitude airway. The calculation formula for the terrain undulation index of the flyable area of the low-altitude airway is: , where represents the terrain undulation index of the flyable area of the low-altitude airway, represents the average slope of each flyable area, represents the maximum measured slope in each flyable area, represents the roughness of each flyable area, represents the maximum measured roughness in each flyable area, represents the elevation standard deviation of each flyable area, represents the maximum measured elevation standard deviation in each flyable area, , and respectively represent the weight coefficients, and their sum is 1. i represents the serial number of each area in the flyable area of the low-altitude airway, i = 1, 2, 3,..., n, and n represents the total number of flyable areas of the low-altitude airway under the first constraint condition; Based on the key feature parameters extracted by the low-altitude airway feature extraction module, analyze the meteorological fluctuation index of the flyable area of the low-altitude airway. The key feature parameters include: the wind speed, precipitation, and visibility of the flyable area of the low-altitude airway. The calculation formula for the meteorological fluctuation index of the flyable area of the low-altitude airway is: , where represents the meteorological fluctuation index of the flyable area of the low-altitude airway, represents the difference between the maximum and minimum wind speeds in each flyable area during the data collection period, represents the time length of the data collection period for each flyable area, represents the precipitation in each flyable area during the data collection period, represents the maximum visibility in each flyable area during the data collection period, , and respectively represent the weight coefficients; Based on the key feature parameters extracted by the low-altitude route feature extraction module, analyze the air traffic conflict probability index of the flyable area of the low-altitude route. The key feature parameters include: the regional unit area, the number of aircraft within a preset time window, and the distance to the nearest aircraft. The calculation formula for the air traffic conflict probability index of the flyable area of the low-altitude route is: , where represents the air traffic conflict probability index of the flyable area of the low-altitude route, represents the number of aircraft in each flyable area within the regional unit area and the preset time window, represents the regional unit area of each flyable area, represents the preset time window, represents the distance from the central measurement point in each flyable area to the nearest aircraft, represents the preset safety distance.

[0023] In this embodiment, it should be specifically noted that the specific content of the second constraint condition analysis for the low-altitude route is as follows: Establish a dynamic risk constraint judgment model, conduct non-linear coupling analysis on the terrain undulation index, meteorological fluctuation index, and air traffic conflict probability index of the flyable area of the low-altitude route, and calculate the comprehensive risk assessment index of the flyable area of the low-altitude route. The calculation formula is: , where represents the comprehensive risk assessment index of the flyable area of the low-altitude route; According to the first constraint condition of the low-altitude route environment perception, preset the segmentation threshold of the second constraint condition. The segmentation threshold includes the maximum segmentation threshold and the minimum segmentation threshold, and the maximum segmentation threshold is greater than the minimum segmentation threshold. Compare the comprehensive risk assessment index of the flyable area of the low-altitude route with the maximum segmentation threshold and the minimum segmentation threshold: when the comprehensive risk assessment index of the flyable area of the low-altitude route is less than or equal to the minimum segmentation threshold, mark the area as a green flyable area; when the comprehensive risk assessment index of the flyable area of the low-altitude route is greater than the minimum segmentation threshold and less than the maximum segmentation threshold, mark the area as a yellow speed-reducing flight area; when the comprehensive risk assessment index of the flyable area of the low-altitude route is greater than or equal to the maximum segmentation threshold, mark the area as a red warning area; According to the constraint result of the second constraint condition, retain the green flyable area and the yellow speed-reducing flight area, and intelligently plan the low-altitude route.

[0024] In this embodiment, it should be specifically noted that the low-altitude route map construction module constructs a low-altitude route map based on the low-altitude route constructed by the dynamic risk constraint determination module. The low-altitude route map includes a dynamic three-dimensional display of different routes and reminds the flight status of different colored areas: when the moving target enters the yellow deceleration flight area from the green flyable area, the low-altitude route map issues a deceleration command; when the moving target enters the green flyable area from the yellow deceleration flight area, the low-altitude route map issues an acceleration command.

[0025] In this embodiment, it should be specifically noted that the low-altitude route risk analysis module performs a rhumb line risk analysis on the low-altitude route intelligently planned, and calibrates the specific content of the optimal path according to the rhumb line risk analysis result as follows: Statistical analysis is performed on the deflection points of the existing m paths to obtain the number of deflection points of the m paths. The deflection points of the m paths are connected in sequence to form a deflection section. The deflection point represents a waypoint where the change range of the flight angle of the moving target exceeds a preset threshold during the process from the starting coordinate to the ending coordinate. According to the starting coordinate and the ending coordinate of the moving target, calculate the rhumb line length of each deflection section in the m paths, and perform an averaging process on the rhumb line lengths to obtain the average rhumb line length of the m paths. The expression of the rhumb line length of each deflection section in the m paths is: , where represents the rhumb line length of each deflection section in the m paths, represents the meridian arc length of the starting point of each deflection section in the m paths, represents the meridian arc length of the ending point of each deflection section in the m paths, represents the course angle of each deflection section in the m paths, a represents the semi-major axis of the earth ellipsoid, e represents the eccentricity of the ellipsoid, represents the current latitude of each deflection section in the m paths, represents the longitude of the starting point of each deflection section in the m paths, represents the longitude of the ending point of each deflection section in the m paths; When the change in latitude is not equal to 0, the rhumb line length is proportional to the change in latitude. The closer the course angle is to the north-south direction the larger it is, the shorter the path; Perform a rhumb line risk analysis on the low-altitude route according to the average rhumb line length of the m paths. The smaller the average rhumb line length, the lower the flight risk of the corresponding low-altitude route. The path corresponding to the minimum value of the average rhumb line length is calibrated as the optimal path.

[0026] In this embodiment, it should be specifically noted that the optimal path calibration and output module outputs the coordinate information, flight altitude, and estimated flight time of the optimal path to the user terminal based on the optimal path calibrated by the low-altitude route risk analysis module. The user terminal is a drone control platform, which realizes the three-dimensional visualization display of the optimal path in the low-altitude route map and gives flight operation prompts according to the real-time flight situation.

[0027] As Figure 2 shown, in this embodiment, it should be specifically noted that the method for constructing a low-altitude route risk map based on artificial intelligence includes the following steps: Step S01: Obtain the first constraint condition for low-altitude route environment perception and determine the flyable area of the low-altitude route; Step S02: Extract key feature parameters from the low-altitude route data, including terrain undulation, meteorological change rate, and air traffic density; Step S03: Analyze the second constraint condition for the low-altitude route based on the key feature parameters and intelligently plan the low-altitude route according to the analysis results; Step S04: Construct a low-altitude route map based on the intelligently planned low-altitude route; Step S05: Conduct a rhumb line risk analysis on the intelligently planned low-altitude route and calibrate the optimal path according to the rhumb line risk analysis results; Step S06: Based on the calibrated optimal path, output the optimal path to the user terminal and perform a three-dimensional display of the path in the low-altitude route map.

[0028] In this embodiment, it should be specifically noted that the main difference between this embodiment and the prior art is that this embodiment is provided with a low-altitude environment perception constraint module, a low-altitude route feature extraction module, a dynamic risk constraint determination module, a low-altitude route map construction module, a low-altitude route risk analysis module, and an optimal path calibration and output module. The first constraint condition is formed through the low-altitude environment perception constraint module to avoid the limitations of traditional single data sources, and the environmental data is updated in real time to dynamically adjust the constraint conditions to cope with the rapid changes in the low-altitude environment; Nonlinear coupling analysis is performed on the terrain undulation index, meteorological fluctuation index, and air traffic conflict probability index of the flyable area of the low-altitude airway. The comprehensive risk assessment index of the flyable area of the low-altitude airway is calculated. Combining static and dynamic constraints, the low-altitude airway route is intelligently planned and the low-altitude airway map is constructed. It can capture the dynamic changes of the low-altitude environment in real time, effectively respond to the complex and changeable requirements of the urban low-altitude environment, accurately divide areas with different risk levels, provide reasonable airway planning suggestions for aircraft, reduce flight risks, and improve the efficiency and safety of low-altitude traffic management; the rhumb line risk analysis is introduced. By calculating the average rhumb line length of each route, the flight risk is evaluated, and thus the optimal path is determined. Combining the actual situation of air traffic makes the planned route safer and more efficient.

[0029] Finally: The above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

[0030] As described above, this is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or replacements, which should all be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claimed rights.

Claims

1. An artificial intelligence-based low-altitude airway risk map construction system, characterized in that: Including: Low-altitude environment perception constraint module, low-altitude route feature extraction module, dynamic risk constraint determination module, low-altitude route map construction module, low-altitude route risk analysis module, and optimal path calibration and output module; The low-altitude environment perception constraint module obtains the first constraint condition for low-altitude route environment perception and determines the flyable area of the low-altitude route; The low-altitude route feature extraction module is used to extract key feature parameters from low-altitude route data, including terrain undulation degree, meteorological change rate, and air traffic density, and convert the parameters into a standardized input format; The dynamic risk constraint determination module analyzes the second constraint condition for the low-altitude route based on the key feature parameters extracted by the low-altitude route feature extraction module and intelligently plans the low-altitude route according to the analysis results; The low-altitude route map construction module constructs a low-altitude route map based on the low-altitude route intelligently planned by the dynamic risk constraint determination module; The low-altitude route risk analysis module conducts a rhumb line risk analysis on the low-altitude route intelligently planned and calibrates the optimal path according to the rhumb line risk analysis results; The optimal path calibration and output module outputs the optimal path to the user terminal based on the optimal path calibrated by the low-altitude route risk analysis module and performs a three-dimensional display of the path on the low-altitude route map.

2. The system for constructing a low-altitude airway risk map based on artificial intelligence according to claim 1, wherein: The low-altitude environment perception constraint module is used to obtain the first constraint condition for low-altitude route environment perception. The specific content of the first constraint condition for low-altitude route environment perception is as follows: Real-time monitoring of the low-altitude environment is carried out by fusing multi-source sensor data to obtain the environmental perception data of the low-altitude environment. The multi-source sensors include: lidar, weather radar, and infrared imaging equipment; The boundary conditions for the flyable area of the low-altitude route are delimited based on the environmental perception data of the low-altitude environment. The boundary conditions are the first constraint condition; The flyable area range of the low-altitude route is determined based on the first constraint condition.

3. The system for constructing a low-altitude route risk map based on artificial intelligence according to claim 1, characterized in that: The low-altitude route feature extraction module is used to extract key feature parameters from low-altitude route data. The key feature parameters are the regional feature parameters of the flyable area of the low-altitude route, including: terrain undulation parameters, meteorological change parameters, and air traffic density parameters; The content of obtaining the terrain undulation parameters is as follows: Using high-resolution digital elevation model data, the slope of the flyable area of the low-altitude route is obtained through GIS software; Calculated from the digital elevation model data, it is used to describe the height and low undulation of the terrain along the low-altitude route; Using the high-density point cloud data obtained by lidar, the roughness of the flyable area of the low-altitude route is obtained through point cloud processing software; The elevation standard deviation of the flyable area of the low-altitude route is obtained using the elevation model; The content of obtaining the meteorological change parameters is as follows: The actual wind speed of the wind field is detected using the Doppler principle, and the wind speed of the flyable area of the low-altitude route is obtained by combining temperature compensation; By establishing the connection between the cloud top temperature and the pixel precipitation point, the precipitation of the flyable area of the low-altitude route is obtained using the difference between satellite information and ground rain gauges; The visibility of the flyable area of the low-altitude route is obtained by observing the brightness contrast between the target and the background; The content for obtaining the air traffic density parameter is as follows: By monitoring with radar and counting the flight plan data along the low-altitude route through the air traffic management system, the number of aircraft and the distance to the nearest aircraft within each unit area of the flyable area of the low-altitude route and within a preset time window are obtained.

4. The system for constructing a low-altitude route risk map based on artificial intelligence according to claim 1, wherein: The specific content of the dynamic risk constraint determination module for performing a second constraint condition analysis on the low-altitude route based on the key feature parameters extracted by the low-altitude route feature extraction module and for intelligently planning the low-altitude route is as follows: Based on the key feature parameters extracted by the low-altitude route feature extraction module, analyze the terrain undulation index of the flyable area of the low-altitude route. The parameters include: the slope, roughness, and elevation standard deviation of the flyable area of the low-altitude route. Based on the key feature parameters extracted by the low-altitude route feature extraction module, analyze the meteorological fluctuation index of the flyable area of the low-altitude route. The key feature parameters include: the wind speed, precipitation, and visibility of the flyable area of the low-altitude route. Based on the key feature parameters extracted by the low-altitude route feature extraction module, analyze the air traffic conflict probability index of the flyable area of the low-altitude route. The key feature parameters include: the number of aircraft within the unit area of the region and within a preset time window and the distance to the nearest aircraft.

5. The system for constructing a low-altitude route risk map based on artificial intelligence according to claim 4, wherein: The specific content of performing a second constraint condition analysis on the low-altitude route is as follows: Establish a dynamic risk constraint determination model, perform a non-linear coupling analysis on the terrain undulation index, meteorological fluctuation index, and air traffic conflict probability index of the flyable area of the low-altitude route, and calculate the comprehensive risk assessment index of the flyable area of the low-altitude route. According to the first constraint condition of the low-altitude route environment perception, preset the segmentation thresholds of the second constraint condition. The segmentation thresholds include the maximum segmentation threshold and the minimum segmentation threshold, and the maximum segmentation threshold is greater than the minimum segmentation threshold. Compare the comprehensive risk assessment index of the flyable area of the low-altitude route with the maximum segmentation threshold and the minimum segmentation threshold: When the comprehensive risk assessment index of the flyable area of the low-altitude route is less than or equal to the minimum segmentation threshold, mark the area as a green flyable area; when the comprehensive risk assessment index of the flyable area of the low-altitude route is greater than the minimum segmentation threshold and less than the maximum segmentation threshold, mark the area as a yellow speed reduction flight area; when the comprehensive risk assessment index of the flyable area of the low-altitude route is greater than or equal to the maximum segmentation threshold, mark the area as a red warning area. According to the constraint results of the second constraint condition, retain the green flyable area and the yellow speed reduction flight area, and intelligently plan the low-altitude route.

6. The system for constructing a low-altitude airway risk map based on artificial intelligence according to claim 1, characterized in that: The low-altitude route map construction module constructs a low-altitude route map based on the low-altitude route intelligently planned by the dynamic risk constraint determination module. The low-altitude route map includes a dynamic three-dimensional display of different routes and gives flight status reminders for areas of different colors: When the moving target enters the yellow speed reduction flight area from the green flyable area, the low-altitude route map issues a speed reduction command; when the moving target enters the green flyable area from the yellow speed reduction flight area, the low-altitude route map issues a speed increase command.

7. The system for constructing a low-altitude route risk map based on artificial intelligence according to claim 1, characterized in that: The low-altitude route risk analysis module conducts rhumb line risk analysis on the intelligently planned low-altitude route and calibrates the optimal path based on the rhumb line risk analysis results. The specific content is as follows: Statistically analyze the deviation points of the existing m paths, obtain the number of deviation points of the m paths, and connect the deviation points of the m paths in sequence to form a deviation flight segment. The deviation point represents a waypoint where the change range of the flight angle of the moving target exceeds a preset threshold during the process from the starting coordinate to the ending coordinate; Calculate the rhumb line lengths of each deviation flight segment in the m paths based on the starting coordinate and ending coordinate of the moving target, perform mean processing on the rhumb line lengths, and obtain the average rhumb line length of the m paths; Conduct rhumb line risk analysis on the low-altitude route based on the average rhumb line lengths of the m paths. The smaller the average rhumb line length, the lower the flight risk of the corresponding low-altitude route. Calibrate the path corresponding to the minimum value of the average rhumb line length as the optimal path.

8. The system for constructing a low-altitude route risk map based on artificial intelligence according to claim 1, characterized in that: The optimal path calibration and output module outputs the coordinate information, flight altitude, and estimated flight time of the optimal path to the user terminal based on the optimal path calibrated by the low-altitude route risk analysis module. The user terminal is a drone control platform, which realizes three-dimensional visualization display of the optimal path in the low-altitude route map and gives flight operation prompts according to the real-time flight situation.

9. A method for constructing a low-altitude route risk map based on artificial intelligence, which is used for the low-altitude route risk map construction system based on artificial intelligence according to any one of claims 1-8 above, characterized in that: It includes the following steps: Step S01: Obtain the first constraint condition of low-altitude route environment perception and determine the flyable area of the low-altitude route; Step S02: Extract key characteristic parameters from the low-altitude route data, including terrain undulation degree, meteorological change rate, and air traffic density; Step S03: Conduct second constraint condition analysis on the low-altitude route based on the key characteristic parameters and intelligently plan the low-altitude route according to the analysis results; Step S04: Construct a low-altitude route map based on the intelligently planned low-altitude route; Step S05: Conduct rhumb line risk analysis on the intelligently planned low-altitude route and calibrate the optimal path based on the rhumb line risk analysis results; Step S06: Based on the calibrated optimal path, output the optimal path to the user terminal and perform three-dimensional path display in the low-altitude route map.

Images