Unmanned aerial vehicle low-altitude intelligent traffic dynamic airspace management and control method and system

Abstract

The application provides a UAV low-altitude intelligent traffic dynamic airspace control method and system, relates to the technical field of intelligent control, and comprises the following steps: taking an electronic fence geographic coordinate set as a monitoring reference boundary, fusing ADS-B data, weather information and UAV equipment states, generating a real-time risk heat map and outputting a hierarchical alarm instruction; receiving the real-time risk heat map and the hierarchical alarm instruction, combining wind speed prediction and dynamic airspace occupation data; when the hierarchical alarm instruction is triggered, the following operations are performed: taking a no-fly zone and a high-risk area in the risk heat map as constraint conditions, constructing a route feasible solution space; taking the lowest energy consumption as an optimization target, iteratively evolving a path population through selection, crossover and mutation operations of a genetic algorithm, outputting a globally final obstacle avoidance detour path, and issuing a route update instruction to a UAV flight control system. The application realizes maximum utilization of airspace resources under the premise of ensuring safety.

Description

Technical Field

[0001] This invention relates to the field of intelligent control technology, and in particular to a method and system for dynamic airspace management and control of low-altitude intelligent transportation for unmanned aerial vehicles (UAVs). Background Technology

[0002] With the large-scale application of drones in logistics delivery, agricultural plant protection, and security patrol, low-altitude airspace traffic management faces several challenges. For example, some existing technologies have the following shortcomings:

[0003] Fixed geofences cannot be dynamically adjusted according to the real-time airspace occupancy rate, resulting in less than 40% utilization of idle airspace during off-peak hours (such as the nighttime no-fly period for agricultural plant protection), causing serious waste of airspace resources. Existing monitoring platforms only display the location of drones and lack an active early warning mechanism for potential conflicts (such as no alarm when drones are less than 100 meters away from no-fly zones). Summary of the Invention

[0004] The technical problem to be solved by this invention is to provide a method and system for dynamic airspace management and control of low-altitude intelligent transportation for unmanned aerial vehicles (UAVs), so as to maximize the utilization of airspace resources while ensuring safety.

[0005] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0006] The first aspect is the method for dynamic airspace management of low-altitude intelligent transportation using unmanned aerial vehicles (UAVs), including:

[0007] Step 1: Receive drone flight mission application and generate comprehensive risk value; based on the comprehensive risk value, when the comprehensive risk value is lower than the preset threshold, output the approval permission instruction in seconds;

[0008] Step 2: Using the approval and permission instructions output in Step 1 as the trigger condition, obtain airspace occupancy rate and flight mission priority data in real time; generate electronic fence dynamic adjustment instructions based on airspace occupancy rate and flight mission priority data, and output the updated electronic fence geographic coordinate set.

[0009] Step 3: Use the set of geographic coordinates of the electronic fence output in Step 2 as the monitoring baseline boundary, integrate ADS-B data, meteorological information and drone equipment status, generate a real-time risk heat map and output graded alarm commands.

[0010] Step 4: Receive the real-time risk heatmap and tiered alarm commands output in Step 3, and combine them with wind speed forecasts and dynamic airspace occupancy data; when a tiered alarm command is triggered, perform the following operations:

[0011] Step 41: Construct a feasible solution space for flight routes, using no-fly zones and high-risk areas in the risk heatmap as constraints.

[0012] Step 42: With the goal of minimizing energy consumption, the path population is iteratively evolved through selection, crossover, and mutation operations using a genetic algorithm to output the final global obstacle avoidance and detour path, and then a route update command is sent to the UAV flight control system.

[0013] Secondly, the unmanned aerial vehicle (UAV) low-altitude intelligent traffic dynamic airspace management system includes:

[0014] The receiving module is used to receive drone flight mission applications and generate a comprehensive risk value; based on the comprehensive risk value, when the comprehensive risk value is lower than a preset threshold, it outputs a second-level approval and permission instruction;

[0015] The judgment module is used to obtain airspace occupancy rate and flight mission priority data in real time based on the output approval and permission instructions; it generates electronic fence dynamic adjustment instructions based on the airspace occupancy rate and flight mission priority data, and outputs the updated electronic fence geographic coordinate set.

[0016] The generation module is used to take the output set of geographic coordinates of the electronic fence as the monitoring baseline boundary, integrate ADS-B data, meteorological information and drone equipment status, generate a real-time risk heat map and output graded alarm commands.

[0017] The execution module receives the output real-time risk heat map and graded alarm commands, and combines wind speed prediction with dynamic airspace occupancy data. When a graded alarm command is triggered, it performs the following operations: constructs a feasible solution space for flight routes based on the no-fly zones and high-risk areas in the risk heat map as constraints; it iteratively evolves the path population through selection, crossover, and mutation operations using a genetic algorithm with the goal of minimizing energy consumption, outputs the final global obstacle avoidance and detour path, and issues a flight route update command to the UAV flight control system.

[0018] The above-described solution of the present invention has at least the following beneficial effects:

[0019] The automated decision-making mechanism of the multi-dimensional risk assessment model completely eliminates the delay of manual approval and meets the urgent need for real-time airspace access in emergency missions; while ensuring safety and compliance, the airspace application process is compressed from "hours" to "instant response".

[0020] The electronic fence is dynamically adjusted based on real-time task requirements and airspace load status to solve the resource stagnation problem caused by static fences; idle airspace is released for high-priority tasks, significantly optimizing the time and space utilization of airspace resources.

[0021] Risk heat maps generated by integrating multi-source data enable early warnings of no-fly zone intrusions, weather threats, and equipment failures; a tiered warning mechanism (early warning / mandatory intervention) forms a progressive risk response closed loop, significantly reducing the probability of collision accidents.

[0022] Real-time detour routes are planned under the constraints of risk heat maps to simultaneously avoid dynamic airspace obstacles and weather threats; economical flight routes are generated by combining aircraft performance and energy consumption models to extend the effective operating time of UAVs.

[0023] It deeply integrates with civil aviation regulatory standard interfaces, meets the mandatory requirements of airspace management regulations, and the collaborative mechanism of dynamic fencing and risk assessment forms an unavoidable technical protection network. Attached Figure Description

[0024] Figure 1 This is a schematic diagram of the dynamic airspace management method for low-altitude intelligent transportation provided in an embodiment of the present invention.

[0025] Figure 2 This is a schematic diagram of a drone-based low-altitude intelligent traffic dynamic airspace management system provided in an embodiment of the present invention. Detailed Implementation

[0026] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0027] like Figure 1 As shown, embodiments of the present invention propose a dynamic airspace management method for low-altitude intelligent transportation using unmanned aerial vehicles (UAVs), comprising:

[0028] Step 1: Receive drone flight mission application and generate comprehensive risk value; based on the comprehensive risk value, when the comprehensive risk value is lower than the preset threshold, output the approval permission instruction in seconds;

[0029] Step 2: Using the approval and permission instructions output in Step 1 as the trigger condition, obtain airspace occupancy rate and flight mission priority data in real time; generate electronic fence dynamic adjustment instructions based on airspace occupancy rate and flight mission priority data, and output the updated electronic fence geographic coordinate set.

[0030] Step 3: Use the set of geographic coordinates of the electronic fence output in Step 2 as the monitoring baseline boundary, integrate ADS-B data, meteorological information and drone equipment status, generate a real-time risk heat map and output graded alarm commands.

[0031] Step 4: Receive the real-time risk heatmap and tiered alarm commands output in Step 3, and combine them with wind speed forecasts and dynamic airspace occupancy data; when a tiered alarm command is triggered, perform the following operations:

[0032] Step 41: Construct a feasible solution space for flight routes, using no-fly zones and high-risk areas in the risk heatmap as constraints.

[0033] Step 42: With the goal of minimizing energy consumption, the path population is iteratively evolved through selection, crossover, and mutation operations using a genetic algorithm to output the final global obstacle avoidance and detour path, and then a route update command is sent to the UAV flight control system.

[0034] In this embodiment of the invention, a comprehensive risk value quantitative assessment (step 1) replaces the traditional manual review mode, enabling automated and rapid approval of drone flight missions. Approval time is reduced to the "second level," significantly shortening mission waiting time, and is particularly suitable for time-sensitive scenarios such as emergency rescue and logistics delivery. The dynamic matching mechanism of risk thresholds can be flexibly adjusted according to airspace management policies to ensure a balance between safety and efficiency. For example, lower risk thresholds can be set for urban core areas, while approval conditions can be relaxed for low-risk areas such as suburbs. Based on real-time monitoring of airspace occupancy and mission priority classification (step 2), the electronic fence can be dynamically expanded or contracted, avoiding the waste of airspace resources caused by static fences. During large-scale events, no-fly zones can be dynamically designated, or priority flight channels can be temporarily opened for medical emergency drones, improving the flexibility and fairness of airspace use. The real-time update mechanism of the geographic coordinate set can seamlessly integrate with the drone navigation system, ensuring that flight paths always comply with current airspace control requirements and reducing the risk of violations due to rule lag.

[0035] By integrating ADS-B data, meteorological information, equipment status, and other multi-dimensional data (step 3), a dynamic risk heat map is constructed to achieve visualized prediction of potential hazards such as collision risks, meteorological disasters, and equipment failures within the airspace. For example, by overlaying wind speed and precipitation data, drones are warned in advance to avoid areas with severe weather. A tiered warning mechanism (such as blue / yellow / orange / red four-color warnings) enables the control system to adopt differentiated response strategies based on risk levels. Low-risk scenarios only require warning prompts, while high-risk scenarios automatically trigger obstacle avoidance path planning, improving the accuracy and efficiency of emergency response. The path optimization model based on genetic algorithms (step 4) aims to minimize energy consumption and, combined with constraints such as no-fly zones and high-risk areas, generates the globally optimal obstacle avoidance path through population iteration. Compared to traditional manual or rule-based obstacle avoidance, this method can reduce detour distance and energy consumption, and is particularly suitable for route optimization of long-endurance logistics drones. Real-time injection of dynamic airspace occupancy data enables path planning to adapt to multi-drone collaborative scenarios within the airspace, avoiding secondary congestion caused by multiple drones simultaneously adjusting their routes, and improving the robustness and coordination of low-altitude traffic.

[0036] In a preferred embodiment of the present invention, step 1, receiving a drone flight mission application and generating a comprehensive risk value, includes:

[0037] Step 11: Obtain the real-time number and distribution coordinates of aircraft in the target airspace;

[0038] Step 12: Calculate the airspace density index based on the real-time number and distribution coordinates of aircraft, as well as the preset aircraft spacing safety threshold.

[0039] Step 13: Receive the airspace density index from Step 12, obtain the corresponding airspace wind speed, precipitation and visibility data, and output the meteorological risk level based on the wind resistance level of the UAV model.

[0040] Step 14: Based on the meteorological risk level, retrieve the electronic identification code of the drone, verify the certification status of the drone's communication module and the battery life threshold, and output the device compliance coefficient.

[0041] Step 15: Generate a comprehensive risk value using a weighted decision matrix based on the airspace density index, meteorological risk level, and equipment compliance coefficient.

[0042] In this embodiment of the invention, the above steps can be implemented through the following specific steps when applied in a specific application:

[0043] In step 11 above, the system scans the target airspace in real time using equipment such as the Automatic Dependent Surveillance-Broadcast (ADS-B) device and airspace monitoring radar. The system receives and records the unique identification code and real-time location coordinates of all aircraft in the target airspace, and counts the number of aircraft to form a list of aircraft distribution in the airspace.

[0044] Step 12 above divides the target airspace into multiple grid regions, mapping the aircraft distribution coordinates obtained in step 11 to each grid. For each grid, the number of aircraft is counted, and the local density of that grid is obtained by dividing the number of aircraft by the area of ​​that grid. The average density value of the entire target airspace is calculated by combining the local densities of all grids. This average density value is then compared with a preset safe threshold for aircraft spacing to obtain the airspace density index. If the actual density is close to or exceeds the safe threshold, the airspace density index is high, indicating that the airspace is relatively crowded; conversely, the index is low.

[0045] Step 13 above involves receiving real-time meteorological data released by the meteorological department, obtaining wind speed, precipitation, and visibility data for the corresponding airspace, and comparing the obtained wind speed data with the wind resistance rating of the drone model applying for flight. If the wind speed is close to or exceeds the drone's wind resistance rating, the wind will have a significant impact on flight. Based on the precipitation intensity and visibility conditions, and according to pre-set meteorological risk assessment rules, the meteorological risk is classified into low, medium, and high levels. For example, if there is heavy precipitation and low visibility, and the wind speed is close to the drone's wind resistance rating, the meteorological risk level is determined to be high.

[0046] Step 14 above, based on the meteorological risk level obtained in step 13, retrieves the electronic identification code of the drone and verifies whether the drone's communication module is certified through the relevant certification system to determine whether its communication function is compliant and usable. Simultaneously, it checks the drone's current battery level and endurance, comparing it with the battery power required for the estimated flight duration to assess whether the battery life meets the mission requirements. Considering both the communication module certification status and battery life, a compliance coefficient is assigned according to certain evaluation standards. A high compliance coefficient indicates a normal communication module certification and sufficient battery life; conversely, a low coefficient indicates a poor compliance coefficient.

[0047] In step 15 above, the airspace density index obtained in step 12, the meteorological risk level obtained in step 13, and the equipment compliance coefficient obtained in step 14 are substituted into a pre-set weighted decision matrix. Based on the different degrees of impact of each factor on flight safety, different weights are assigned to the airspace density index, meteorological risk level, and equipment compliance coefficient. Through weighted calculation, the values ​​of the three factors are combined to finally obtain the comprehensive risk value of the UAV flight mission.

[0048] In this embodiment of the invention, calculations and assessments are performed from multiple dimensions, including airspace density, meteorological conditions, and equipment compliance, avoiding the one-sidedness of assessments based on a single factor. Real-time acquisition of dynamic data such as the number of aircraft and weather conditions enables timely responses to changes in airspace and the environment, making the risk assessment results more realistic and ensuring effective assessment of flight risks in different scenarios. Strict verification of UAV equipment compliance prevents flight accidents caused by equipment problems such as communication failures and insufficient power. Combining meteorological conditions and airspace density assessments proactively avoids risks caused by severe weather and airspace congestion, maximizing UAV flight safety. The automated calculation process quickly generates comprehensive risk values, significantly improving risk assessment efficiency compared to manual assessments, accelerating flight mission approval, and facilitating the efficient operation of UAV services.

[0049] In a preferred embodiment of the present invention, based on a comprehensive risk value, when the comprehensive risk value is lower than a preset threshold, a second-level approval instruction is output, including:

[0050] Step 16: Receive the comprehensive risk value generated in step 15, and compare the comprehensive risk value with the preset airspace safety threshold in real time;

[0051] Step 17: When the overall risk value is lower than the airspace safety threshold, the automatic approval channel is triggered; when the overall risk value is higher than the airspace safety threshold, it is transferred to the manual review queue.

[0052] Step 18: After the automatic approval channel is triggered, extract the spatiotemporal coordinates and device ID of the flight mission application to generate a second-level approval authorization instruction containing an encrypted digital certificate.

[0053] In this embodiment of the invention, the above steps can be implemented through the following specific steps when applied in a specific application:

[0054] Step 16 above receives the comprehensive risk value of the drone flight mission generated in step 15, and simultaneously retrieves the pre-set airspace safety threshold. This threshold is set differently based on different airspace types (such as urban core areas, suburbs, and areas surrounding no-fly zones), flight times (daytime and nighttime), and management policy requirements. The system compares the comprehensive risk value with the corresponding airspace safety threshold in real time, bit by bit, to determine whether the comprehensive risk value is lower than the threshold.

[0055] In step 17 above, based on the comparison results of step 16, if the overall risk value is lower than the airspace safety threshold, the system automatically triggers the automatic approval channel, marking the flight mission application as "low risk" and including it in the fast-track approval process; if the overall risk value is higher than the airspace safety threshold, the flight mission application is transferred to the manual review queue, marked as "high risk," and awaits further evaluation and approval by professionals. This process is executed automatically through the system's built-in conditional judgment logic, requiring no manual intervention and ensuring rapid diversion of the approval path.

[0056] In step 18 above, after the automatic approval channel is triggered, the system immediately extracts key information from the flight mission application, including the planned start and end times of the flight, the coordinates of the specific flight area (longitude, latitude, and altitude range), and the UAV equipment ID. The system uses an encryption algorithm to combine this information with a pre-set digital certificate template to generate a second-level approval authorization instruction containing an encrypted digital certificate. The encrypted digital certificate ensures the security and immutability of the instruction, while also facilitating identity verification and instruction recognition by the UAV equipment and the monitoring system.

[0057] In this embodiment of the invention, automated risk value comparison and approval channel determination enable second-level approval for low-risk flight missions, significantly shortening approval time and meeting the needs of scenarios with extremely high timeliness requirements, such as emergency rescue and express delivery, thereby improving the operational efficiency of drones. Flight missions are automatically diverted according to risk level, with low-risk missions using the automated approval channel and high-risk missions undergoing manual review. This allows limited human resources to focus on high-risk and complex missions, avoiding the waste of resources in manual review and improving overall management efficiency. Pre-set airspace security thresholds and encrypted digital certificate mechanisms ensure both rapid approval of low-risk missions and strict adherence to security standards. Encrypted instructions also ensure the secure transmission of approval information, preventing instructions from being tampered with or misused, thus guaranteeing the standardization and security of drone flight management. The generation of second-level approval permits provides drone operators and users with a convenient and efficient service experience, reducing waiting time and enhancing user trust in the low-altitude traffic management system.

[0058] In a preferred embodiment of the present invention, step 2, using the approval and permission instruction output in step 1 as a trigger condition, involves real-time acquisition of airspace occupancy rate and flight mission priority data, including:

[0059] Step 21: Receive the approval instruction, parse the encrypted digital certificate, verify the certificate validity period and device ID binding status, and output a verification pass signal;

[0060] Step 22: Based on the verification pass signal, locate the target airspace coordinates in the approval and permit instruction, divide the target airspace into 1km×1km spatial grid units, and output the grid index code;

[0061] Step 23, for grid index encoding, perform the following parallel operations:

[0062] Count the number of aircraft in each grid in real time and calculate the airspace occupancy rate;

[0063] Retrieve the flight mission database and output a mission priority queue based on urgency weights.

[0064] In this embodiment of the invention, the above steps can be implemented through the following specific steps when applied in a specific application:

[0065] In step 21 above, upon receiving the output approval instruction, the encrypted digital certificate in the instruction is first parsed. Using the pre-stored encryption key and verification algorithm, the validity of the digital certificate signature is checked, and the certificate's validity period is verified. Simultaneously, the device ID in the instruction is compared with the drone registration information database to confirm the binding status between the device ID and the actual drone. If the digital certificate is valid and the device ID is correctly bound, a verification pass signal is output; if there are issues such as an expired certificate, invalid signature, or a mismatched device ID, a verification failure signal is output, preventing subsequent processes from executing.

[0066] In step 22 above, after receiving the verification pass signal from step 21, the system extracts the target airspace coordinates (including longitude, latitude, and altitude range) from the approval and permit instruction. Using a standard size of 1km × 1km, the target airspace is divided into grids on a horizontal plane, with each grid assigned a unique index code containing its row and column position information within the airspace. Simultaneously, based on the altitude range of the target airspace, the vertical direction is also divided into layers to ensure that each grid has a clear location marker in three-dimensional space. After the division is complete, the system outputs the index codes of all grids, providing a basis for subsequent data statistics.

[0067] In step 23 above, for each grid index encoding output in step 22, the system performs two operations in parallel.

[0068] Airspace occupancy rate calculation involves using ADS-B equipment, radar, and other monitoring methods to acquire real-time information on the number of aircraft within each grid. The number of aircraft in each grid is compared to the maximum number of aircraft that grid can accommodate (pre-set based on standards such as safety distances) to calculate the airspace occupancy ratio of each grid. The occupancy ratios of all grids are then aggregated, and a weighted average is used to calculate the airspace occupancy rate of the entire target airspace.

[0069] Once task priorities are determined, the system retrieves information from the flight mission database to query detailed information on all approved flight missions within the target airspace. Based on factors such as mission urgency (e.g., high weight for emergency rescue missions, low weight for routine inspection missions) and mission type (e.g., medical supply transport, commercial filming), each mission is assigned a corresponding weight value. The missions are then sorted from highest to lowest weight, generating a task priority queue and clearly defining the priority order of each mission in airspace usage.

[0070] Step 21 of this invention involves strict verification of approval and authorization instructions to ensure that only legal and valid instructions can proceed to subsequent processes. This prevents management chaos and security risks caused by illegal or tampered instructions, thus safeguarding the security and authority of the low-altitude traffic management system. Step 22's grid-based division meticulously segments the target airspace, enabling more precise monitoring and management of airspace usage. Combined with the airspace occupancy rate calculated in Step 23, the system can monitor the real-time airspace resource usage status of each area, avoiding waste or overcrowding and improving airspace resource utilization efficiency. The task priority queue generated in Step 23 provides a clear basis for scheduling UAV flight missions. When airspace resources are scarce, high-priority tasks are prioritized to ensure the smooth completion of critical tasks such as emergency rescue and transportation of important materials, improving the overall coordination and service quality of low-altitude traffic management. The real-time acquired airspace occupancy rate and task priority data provide the management system with rich decision-making data. The system can dynamically adjust electronic fences and optimize flight paths based on this data, achieving intelligent and dynamic management of UAV flights and better adapting to the complex and ever-changing low-altitude traffic environment.

[0071] In a preferred embodiment of the present invention, a dynamic adjustment command for the electronic fence is generated based on airspace occupancy rate and flight mission priority data, and an updated set of geographic coordinates for the electronic fence is output, including:

[0072] Step 24: Receive the airspace occupancy rate and task priority queue. If the occupancy rate is <40% and there is a first-priority task, generate an expansion instruction; if the occupancy rate is >80%, generate a contraction instruction.

[0073] Step 25: Perform differentiated operations based on the types of expansion and contraction instructions:

[0074] Based on the original center of the electronic fence, extend the boundary towards the first occupancy grid, with the extension distance = task priority coefficient × basic expansion radius;

[0075] Remove the mesh cells with the highest idle rate to generate compact polygon boundaries;

[0076] Step 26: Input the compact polygon boundary into the GIS engine to obtain the updated geo coordinate set of the electronic fence, which consists of a sequence of latitude and longitude coordinate points.

[0077] In this embodiment of the invention, the above steps can be implemented through the following specific steps when applied in a specific application:

[0078] Step 24 above receives the airspace occupancy rate and task priority queue data output from step 23. First, the airspace occupancy rate is evaluated and compared to pre-set thresholds (40% and 80%). If the airspace occupancy rate is less than 40%, the task priority queue is further checked for the presence of a first-priority task (such as emergency rescue or medical supply transportation). If a first-priority task exists, an electronic fence expansion command is generated to ensure the smooth execution of high-priority tasks. If the airspace occupancy rate is greater than 80%, it indicates airspace resource scarcity. In this case, an electronic fence contraction command is generated to prevent excessive drone concentration and potential safety hazards.

[0079] In step 25 above, upon receiving an extension command, the system uses the geometric center of the original electronic fence as a reference point to identify the grid cell with the highest occupancy rate in the current airspace (i.e., the first occupancy rate grid) and determines the extension direction of the electronic fence. The task priority coefficient is set according to the urgency of the task (e.g., a coefficient of 3 for the first priority task and 2 for the second priority task), and the basic extension radius is a pre-set fixed distance (e.g., 500 meters). The system multiplies the task priority coefficient by the basic extension radius to obtain the actual extension distance and extends the electronic fence boundary along the direction of the first occupancy rate grid.

[0080] Upon receiving a shrinkage command, the system iterates through all grid cells and calculates the idle rate (i.e., the percentage of time without aircraft) for each cell. The cell with the highest idle rate is selected and removed from the electronic fence's coverage area. By connecting the boundary points of the remaining cells, a compact polygon boundary is reconstructed, thus shrinking the electronic fence.

[0081] In step 26 above, the adjusted compact polygon boundary data from step 25 is input into the Geographic Information System (GIS) engine. The GIS engine performs geographic coordinate transformation on the vertices of the polygon, converting them into a sequence of latitude and longitude coordinate points. Each coordinate point precisely corresponds to a key location on the electronic fence boundary, ultimately generating an updated electronic fence geographic coordinate set consisting of a series of latitude and longitude coordinate points. This coordinate set can be directly used in drone navigation systems and monitoring platforms to achieve real-time updates of the electronic fence.

[0082] This invention dynamically adjusts the electronic fence based on airspace occupancy and task priority, avoiding resource waste or overcrowding caused by static fences. For example, it expands flight space for high-priority tasks when airspace is idle and shrinks the area to reduce conflict risks when airspace is busy, significantly improving airspace resource utilization. The expansion mechanism for first-priority tasks can temporarily open dedicated flight channels or expand operational areas, ensuring that critical tasks such as emergency rescue and medical transportation are not restricted by airspace, shortening task execution time, and improving public service response efficiency. The shrinkage command promptly reduces the activity range of drones in high-density airspace, lowering the risk of collisions. Removing idle grids avoids invalid area occupation, making the electronic fence more aligned with actual needs and creating a safer and more orderly flight environment. The automated dynamic adjustment of the electronic fence requires no manual intervention and seamlessly integrates with real-time monitoring data and the task priority system.

[0083] In a preferred embodiment of the present invention, step 3, using the electronic fence geographic coordinate set output in step 2 as the monitoring baseline boundary, integrates ADS-B data, meteorological information, and UAV equipment status to generate a real-time risk heat map and output graded alarm commands, including:

[0084] Step 31: Receive the geofence geographic coordinate set output in step 26 and load it into the geographic information system engine; convert the coordinate set into a polygon geofence baseline boundary and output the boundary topology map;

[0085] Step 32: Based on the boundary topology graph, perform the following real-time data mapping:

[0086] The aircraft position in ADS-B data is projected onto the grid within the fence boundary, and the wind speed vector and precipitation intensity layers from meteorological information are overlaid. The drone equipment status is then correlated to obtain fused data.

[0087] Step 33: Perform spatial interpolation calculations on the fused data:

[0088] A static high-risk zone is generated with the no-fly zone as the core, a storm movement high-risk zone is dynamically generated based on meteorological data, and an equipment failure early warning zone is generated by combining equipment status. A real-time risk heat map with all risk layers superimposed is output.

[0089] Step 34, Tiered Alarm Trigger Sub-step:

[0090] When a drone enters an area with a risk value ≥ 0.6 on the heat map, a yellow warning is triggered.

[0091] When the risk value is ≥0.9 or the area enters the static high-risk zone, a red forced return command is triggered.

[0092] In this embodiment of the invention, the above steps can be implemented through the following specific steps when applied in a specific application:

[0093] Step 31 above receives the geofence geographic coordinate set output from step 26 and imports it into the Geographic Information System (GIS) engine. The GIS engine parses the latitude and longitude coordinates in the coordinate set and connects the points sequentially according to the coordinate order to construct a polygonal geofence. During the construction process, the GIS engine automatically identifies and records the connection relationships of each side of the polygon, vertex coordinates, and other information, generating a boundary topology map. This topology map clarifies the shape, extent, and spatial relationship of the geofence with the surrounding geographic area, providing a basic framework for subsequent data mapping and risk analysis.

[0094] In step 32 above, based on the boundary topology map generated in step 31, the system processes the multi-source data acquired in real time. First, the real-time location information of each aircraft recorded in the ADS-B data is projected onto the corresponding grid cells within the geofence boundary according to its latitude and longitude coordinates, achieving spatial positioning of the aircraft. Simultaneously, wind speed vector data and precipitation intensity data from meteorological information are retrieved and overlaid onto the geofence area as layers, visually displaying the spatial distribution of meteorological conditions. Furthermore, the system associates the equipment status data of each drone (such as battery level, communication signal strength, sensor operating status, etc.) with the aircraft location information, binding this data to the aircraft location information. Finally, the three types of data—aircraft location, meteorological information, and equipment status—are integrated to form fused comprehensive data, fully reflecting the real-time situation within the geofence.

[0095] Step 33 above performs spatial interpolation calculations on the data fused in step 32 to estimate the risk value of each area within the electronic fence. First, a static high-risk zone is delineated within a certain range around the no-fly zone, with the highest risk level set, prohibiting drones from entering this area. Next, based on meteorological data such as wind speed, precipitation, and storm movement paths, a storm movement high-risk zone is dynamically generated. The extent and location of this zone are updated in real time as meteorological conditions change. Then, combining drone equipment status data, an equipment failure warning zone is generated for the location and surrounding area of ​​drones with low battery, communication abnormalities, or sensor malfunctions. Finally, the system overlays different types of risk zones, such as the static high-risk zone, the storm movement high-risk zone, and the equipment failure warning zone, and generates a real-time risk heatmap through visualization methods such as color depth and transparency. Darker areas in the heatmap indicate higher risk values, allowing managers to quickly identify high-risk areas.

[0096] Step 34 above involves real-time monitoring of the drone's location on the risk heatmap and the corresponding risk value of the area. When the drone enters an area on the heatmap with a risk value greater than or equal to 0.6, a yellow warning is triggered, sending a warning message to the drone operator via the management platform, reminding them to be aware of flight risks and operate with caution. When the drone enters an area with a risk value greater than or equal to 0.9, or enters a static high-risk zone, a red forced return-to-home command is triggered. The system automatically sends a return-to-home command to the drone's flight control system, controlling the drone to immediately return to a designated safe location to avoid a flight accident.

[0097] This invention integrates ADS-B data, meteorological information, and UAV equipment status to achieve comprehensive monitoring of various risk factors within the electronic fence, avoiding the limitations of a single data source and enabling managers to grasp the complex situation within the airspace in real time. Real-time risk heatmaps display risk distribution in an intuitive and visual way, allowing managers to quickly locate high-risk areas and take preventative measures in advance. Compared to traditional text or data alarms, this significantly improves the efficiency of risk identification and handling. Tiered alarm commands provide differentiated responses based on the severity of the risk: yellow alerts give operators autonomy in decision-making, while red mandatory return-to-home orders ensure UAV safety in high-risk situations, guaranteeing both flight flexibility and a safety baseline in emergencies. The system dynamically generates risk areas based on meteorological conditions and updates warnings in real time according to equipment status, enabling it to adapt to constantly changing flight environments, effectively respond to sudden risks, and improve the intelligence and reliability of low-altitude traffic management. Through early warnings and mandatory return-to-home measures, the system significantly reduces the accident rate of UAVs caused by collisions, meteorological disasters, and equipment failures.

[0098] In a preferred embodiment of the present invention, step 41, using no-fly zones and high-risk areas in the risk heatmap as constraints, constructs a feasible solution space for flight routes, including:

[0099] Step 411: Receive the real-time risk heat map, extract the coordinates of all areas with a risk value ≥ 0.5 to obtain the first risk area; convert the boundary of the first risk area into a set of three-dimensional no-fly cubes.

[0100] Step 412: Based on the equipment failure warning zone data in the heat map, retrieve the current maximum climb rate and minimum turning radius of the UAV to output the UAV maneuverability parameter set;

[0101] Step 413: Integrate the no-fly cube set and the maneuverability parameter set, take the line connecting the start point and the end point as the reference axis, expand the safety buffer zone along both sides of the axis, eliminate invalid spaces that overlap with the no-fly cube, and output the route feasible solution space network topology diagram composed of the remaining spaces.

[0102] In this embodiment of the invention, the above steps can be implemented through the following specific steps when applied in a specific application:

[0103] In step 411 above, the system receives the real-time risk heatmap generated in step 33, filters out all areas with a risk value greater than or equal to 0.5, marks these areas as the first risk area, and extracts their boundary coordinates. Since UAV flight is a three-dimensional activity, the system extends the first risk area vertically, converting the two-dimensional planar boundary into multiple three-dimensional no-fly cubes based on the actual flight altitude range. Each no-fly cube clearly defines the spatial range within a specific altitude interval where UAVs are prohibited from entering, forming a complete set of three-dimensional no-fly cubes, providing clear spatial constraints for subsequent flight path planning.

[0104] In step 412 above, based on the equipment failure warning zone data in the risk heatmap, the drones in the warning state are located. For these drones, parameters such as the maximum climb rate (i.e., the maximum height the drone can reach per unit time) and minimum turning radius (the minimum spatial radius required for the drone to complete a turning maneuver) recorded in their registration information are retrieved. Simultaneously, these parameters are dynamically corrected based on the drone's current flight status (such as speed and attitude) to ensure accuracy. Ultimately, a parameter set reflecting the drone's current actual maneuverability is formed, which will be used to evaluate the drone's flightability in different spaces.

[0105] Step 413 integrates the no-fly zone cube set generated in step 411 with the UAV maneuverability parameter set obtained in step 412. First, using the line connecting the start and end points of the UAV flight mission as the baseline axis, a three-dimensional safety buffer zone is extended on both sides of the axis according to the UAV's minimum turning radius and safe distance requirements. This buffer zone represents the space range within which the UAV can fly under ideal conditions. Next, the safety buffer zone is spatially compared with the no-fly zone cube set, eliminating all invalid spatial portions overlapping with the no-fly zone cubes. After processing, the remaining spatial regions constitute the feasible solution space for flight paths. The system connects these feasible spatial regions and performs topology analysis to generate a network topology diagram of the feasible solution space for flight paths. The diagram clearly shows the connection relationships and path directions between each feasible space, providing a basic framework for subsequent path optimization.

[0106] This invention transforms high-risk areas in a risk heatmap into three-dimensional no-fly zones, comprehensively covering the risk space that UAVs may encounter during flight and avoiding the risk of three-dimensional collisions caused by two-dimensional planning. By combining the UAV's own maneuverability parameters such as maximum climb rate and minimum turning radius to construct a feasible solution space, it ensures that the planned flight path conforms to the actual controllability of the UAV, avoiding flight control failures due to exceeding its capabilities and improving flight reliability. The network topology of the feasible solution space provides a clear search space for subsequent path optimization algorithms, reducing the exploration of invalid paths and significantly improving path planning efficiency. Simultaneously, the connectivity in the topology helps to quickly generate multiple alternative flight paths. This construction method can dynamically adjust the feasible solution space according to different risk heatmaps and UAV models, quickly generating feasible flight spaces that meet safety requirements, whether in complex urban airspace or remote mountainous areas.

[0107] In a preferred embodiment of the present invention, step 42, with the goal of minimizing energy consumption, iteratively evolves the path population through selection, crossover, and mutation operations using a genetic algorithm to output the final global obstacle avoidance path, and issues a route update command to the UAV flight control system, including:

[0108] Step 421: In the feasible solution space network topology graph of the route, randomly generate N initial paths connecting the origin and destination; each path is represented by a sequence of waypoints, where the distance between points is greater than or equal to the minimum turning radius;

[0109] Step 422, execute for each path:

[0110] Extract the average real-time risk heat map value of the area traversed by the path, calculate the total path length and wind speed vector projection resistance, and integrate the risk value and energy consumption factor to generate a fitness score.

[0111] Execute the loop until convergence:

[0112] Choose and retain the top 30% of paths in terms of fitness score as the parent generation;

[0113] Crossover involves exchanging and recombining fragments of the parent's path waypoints;

[0114] Mutation, randomly adjusting 5% of waypoint positions;

[0115] When the number of iterations reaches the upper limit, the corresponding path in the current population is extracted, the waypoints are smoothed and the data volume is compressed, and the route update command is sent to the flight control system through the air-to-ground communication link.

[0116] In this embodiment of the invention, the above steps can be implemented through the following specific steps when applied in a specific application:

[0117] In step 421 above, based on the feasible solution space network topology graph of the flight path output in step 413, N initial paths are randomly generated between the origin and destination. When generating paths, the system strictly adheres to the minimum turning radius constraint of the UAV, ensuring that the distance between adjacent waypoints is greater than or equal to the minimum turning radius, so as to guarantee that the UAV can safely and smoothly complete turning maneuvers. Each path consists of a series of ordered waypoint sequences, each waypoint containing precise latitude and longitude coordinates and altitude information. These initial paths constitute the initial path population used for subsequent optimization.

[0118] In step 422 above, for each path in the initial path population, the system performs the following operations: First, it extracts the risk value of the area traversed by the path from the real-time risk heatmap and calculates the average risk of that area to quantify the safety risk faced by the path. Next, it calculates the total length of the path and, combined with wind speed vector data from meteorological information, analyzes the angle between the path direction and the wind speed direction to calculate the projected drag of the wind speed in the path direction, thereby assessing the energy consumed by the path's flight. Finally, it integrates the risk value and energy consumption factor according to pre-set weights to generate a fitness score for each path. A higher score indicates a better overall performance in terms of safety and energy consumption.

[0119] The path population is sorted according to fitness scores, and the top 30% of paths are retained as parent paths, while the rest are eliminated. This operation simulates the "survival of the fittest" law in nature, ensuring that excellent path characteristics can be passed on to the next generation.

[0120] Crossover operations involve randomly selecting and recombining waypoint segments from the selected parent paths. For example, combining the first half of a parent path with the second half of another parent path generates a new child path. Crossover operations help integrate the advantages of different paths, resulting in better path combinations.

[0121] The mutation operation randomly adjusts waypoints in the offspring path, selecting approximately 5% of waypoints each time and fine-tuning their positions while satisfying the minimum turning radius and feasible solution space constraints. The mutation operation introduces new path characteristics, preventing the algorithm from getting trapped in local optima and increasing population diversity.

[0122] After iteration termination and command issuance, the system continuously performs selection, crossover, and mutation operations in a loop until the preset maximum number of iterations is reached or the population fitness score stabilizes (i.e., convergence). When the iteration ends, the path with the highest fitness score is selected from the current population. Waypoints on this path are smoothed, redundant points are removed, and data volume is compressed to reduce communication transmission burden. Finally, the optimized flight path update command is sent to the UAV flight control system via the air-to-ground communication link to guide the UAV to execute the new flight path.

[0123] The above method, by integrating risk values ​​and energy consumption factors to calculate fitness scores, balances flight safety and energy consumption during path planning. It avoids risky traversal of high-risk areas in pursuit of low energy consumption, or excessive risk avoidance leading to a significant increase in energy consumption, thus ensuring efficient and safe drone flight. The iterative optimization mechanism of the genetic algorithm can quickly search for globally optimal solutions in a complex feasible solution space. Compared to traditional path planning methods, it significantly reduces the time required for path planning, while generating more reasonable and efficient paths, especially suitable for dynamically changing low-altitude environments. Crossover and mutation operations enable the algorithm to continuously explore new path combinations, adapting to different airspace environments, weather conditions, and drone models. Even if airspace risks or weather conditions change during flight, a suitable path can be quickly replanned, improving the drone's ability to cope with complex scenarios. Smoothing and data compression of the optimized path reduce the amount of data in route update commands, lower the transmission pressure on the air-to-ground communication link, and reduce the computational burden on the drone flight control system, improving the overall system's operational efficiency and stability.

[0124] like Figure 2 As shown, the UAV low-altitude intelligent traffic dynamic airspace management system includes:

[0125] The receiving module is used to receive drone flight mission applications and generate a comprehensive risk value; based on the comprehensive risk value, when the comprehensive risk value is lower than a preset threshold, it outputs a second-level approval and permission instruction;

[0126] The judgment module is used to obtain airspace occupancy rate and flight mission priority data in real time based on the output approval and permission instructions; it generates electronic fence dynamic adjustment instructions based on the airspace occupancy rate and flight mission priority data, and outputs the updated electronic fence geographic coordinate set.

[0127] The generation module is used to take the output set of geographic coordinates of the electronic fence as the monitoring baseline boundary, integrate ADS-B data, meteorological information and drone equipment status, generate a real-time risk heat map and output graded alarm commands.

[0128] The execution module receives the output real-time risk heat map and graded alarm commands, and combines wind speed prediction with dynamic airspace occupancy data. When a graded alarm command is triggered, it performs the following operations: constructs a feasible solution space for flight routes based on the no-fly zones and high-risk areas in the risk heat map as constraints; it iteratively evolves the path population through selection, crossover, and mutation operations using a genetic algorithm with the goal of minimizing energy consumption, outputs the final global obstacle avoidance and detour path, and issues a flight route update command to the UAV flight control system.

[0129] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A method for dynamic airspace management and control of low-altitude intelligent transportation using unmanned aerial vehicles (UAVs), characterized in that: The method includes: Step 1: Receive drone flight mission application and generate a comprehensive risk value. Based on the comprehensive risk value, when the comprehensive risk value is lower than a preset threshold, output a second-level approval authorization instruction, including: Step 11: Obtain the real-time number and distribution coordinates of aircraft in the target airspace; Step 12: Calculate the airspace density index based on the real-time number and distribution coordinates of aircraft and a preset aircraft spacing safety threshold; Step 13: Receive the airspace density index from Step 12, correlate and obtain the corresponding airspace wind speed, precipitation, and visibility data, and output the meteorological risk level based on the drone model's wind resistance level; Step 14: Retrieve the electronic identification code of the applying drone, verify the drone's communication module authentication status and battery endurance threshold, and output the equipment compliance coefficient; Step 15: Generate a comprehensive risk value through a weighted decision matrix based on the airspace density index, meteorological risk level, and equipment compliance coefficient. Step 2: Using the approval and permission instructions output in Step 1 as the trigger condition, obtain airspace occupancy rate and flight mission priority data in real time; generate electronic fence dynamic adjustment instructions based on airspace occupancy rate and flight mission priority data, and output the updated electronic fence geographic coordinate set. Step 3: Use the set of geographic coordinates of the electronic fence output in Step 2 as the monitoring baseline boundary, integrate ADS-B data, meteorological information and drone equipment status to generate a real-time risk heat map and output graded alarm commands. Step 4: Receive the real-time risk heatmap and graded alarm commands output in Step 3. When a graded alarm command is triggered, perform the following operations: Step 41: Construct a feasible solution space for flight routes, using no-fly zones and high-risk areas in the risk heatmap as constraints. Step 42: With the goal of minimizing energy consumption, the path population is iteratively evolved through selection, crossover, and mutation operations using a genetic algorithm to output the final global obstacle avoidance and detour path, and then a route update command is sent to the UAV flight control system.

2. The method for dynamic airspace management of low-altitude intelligent transportation by unmanned aerial vehicles according to claim 1, characterized in that, Based on the comprehensive risk value, when the comprehensive risk value is lower than a preset threshold, a second-level approval instruction is output, including: Step 16: Receive the comprehensive risk value generated in step 15, and compare the comprehensive risk value with the preset airspace safety threshold in real time; Step 17: When the overall risk value is lower than the airspace safety threshold, the automatic approval channel is triggered; when the overall risk value is higher than the airspace safety threshold, it is transferred to the manual review queue. Step 18: After the automatic approval channel is triggered, extract the spatiotemporal coordinates and device ID of the flight mission application to generate a second-level approval authorization instruction containing an encrypted digital certificate.

3. The method for dynamic airspace management of low-altitude intelligent transportation by unmanned aerial vehicles according to claim 2, characterized in that, Step 2: Using the approval and permission instructions output in Step 1 as the trigger condition, obtain real-time airspace occupancy rate and flight mission priority data, including: Step 21: Receive the approval instruction, parse the encrypted digital certificate, verify the certificate validity period and device ID binding status, and output a verification pass signal; Step 22: Based on the verification pass signal, locate the target airspace coordinates in the approval and permit instruction, divide the target airspace into 1km×1km spatial grid units, and output the grid index code; Step 23, for grid index encoding, perform the following parallel operations: Count the number of aircraft in each grid in real time and calculate the airspace occupancy rate; Retrieve the flight mission database and output a mission priority queue based on urgency weights.

4. The method for dynamic airspace management of low-altitude intelligent transportation by unmanned aerial vehicles according to claim 3, characterized in that, Based on airspace occupancy rate and flight mission priority data, dynamic adjustment instructions for the electronic fence are generated, and the updated set of geographic coordinates for the electronic fence is output, including: Step 24: Receive the airspace occupancy rate and task priority queue. If the occupancy rate is <40% and there is a first-priority task, generate an expansion instruction; if the occupancy rate is >80%, generate a contraction instruction. Step 25: Perform differentiated operations based on the types of expansion and contraction instructions: Based on the original center of the electronic fence, extend the boundary towards the first occupancy grid, with the extension distance = task priority coefficient × basic expansion radius; Remove the mesh cells with the highest idle rate to generate compact polygon boundaries; Step 26: Input the compact polygon boundary into the GIS engine to obtain the updated geo coordinate set of the electronic fence, which consists of a sequence of latitude and longitude coordinate points.

5. The method for dynamic airspace management of low-altitude intelligent transportation by unmanned aerial vehicles according to claim 4, characterized in that, Step 3: Using the geolocation set of the electronic fence output in Step 2 as the monitoring baseline boundary, integrate ADS-B data, meteorological information, and drone equipment status to generate a real-time risk heat map and output tiered alarm commands, including: Step 31: Receive the geofence geographic coordinate set output in step 26 and load it into the geographic information system engine; convert the coordinate set into a polygon geofence baseline boundary and output the boundary topology map. Step 32: Based on the boundary topology graph, perform the following real-time data mapping: The aircraft position in the ADS-B data is projected onto the grid inside the fence boundary, and the wind speed vector and precipitation intensity layer from the meteorological information are overlaid. The drone equipment status is then correlated to obtain the fused data. Step 33: Perform spatial interpolation calculations on the fused data: A static high-risk zone is generated with the no-fly zone as the core, a storm movement high-risk zone is dynamically generated based on meteorological data, and an equipment failure early warning zone is generated by combining equipment status. A real-time risk heat map with all risk layers superimposed is output. Step 34, Tiered Alarm Trigger Sub-step: When a drone enters an area with a risk value ≥ 0.6 on the heat map, a yellow warning is triggered. When the risk value is ≥0.9 or the area enters the static high-risk zone, a red forced return command is triggered.

6. The method for dynamic airspace management of low-altitude intelligent transportation by unmanned aerial vehicles according to claim 5, characterized in that, Step 41: Using the no-fly zones and high-risk areas in the risk heatmap as constraints, construct the route feasibility solution space, including: Step 411: Receive the real-time risk heat map, extract the coordinates of all areas with risk values ​​≥ 0.5 to obtain the first risk area; convert the boundary of the first risk area into a set of three-dimensional no-fly cubes. Step 412: Based on the equipment failure warning zone data in the heat map, retrieve the current maximum climb rate and minimum turning radius of the UAV to output the UAV maneuverability parameter set; Step 413: Integrate the no-fly cube set and the maneuverability parameter set, take the line connecting the start point and the end point as the reference axis, expand the safety buffer zone along both sides of the axis, eliminate invalid spaces that overlap with the no-fly cube, and output the route feasible solution space network topology diagram composed of the remaining spaces.

7. The method for dynamic airspace management of low-altitude intelligent transportation by unmanned aerial vehicles according to claim 6, characterized in that, Step 42: With minimum energy consumption as the optimization objective, the path population is iteratively evolved through selection, crossover, and mutation operations using a genetic algorithm to output the final global obstacle avoidance path. A flight path update command is then issued to the UAV flight control system, including: Step 421: In the feasible solution space network topology graph of the route, randomly generate N initial paths connecting the origin and destination; each path is represented by a sequence of waypoints, where the distance between points is greater than or equal to the minimum turning radius; Step 422, execute for each path: Extract the average real-time risk heat map value of the area traversed by the path, calculate the total path length and wind speed vector projection resistance, and integrate the risk value and energy consumption factor to generate a fitness score. Execute the loop until convergence: Choose and retain the top 30% of paths in terms of fitness score as the parent generation; Crossover involves exchanging and recombining fragments of the parent's path waypoints; Mutation, randomly adjusting 5% of waypoint positions; When the number of iterations reaches the upper limit, the corresponding path in the current population is extracted, the waypoints are smoothed and the data volume is compressed, and the route update command is sent to the flight control system through the air-to-ground communication link.

8. A low-altitude intelligent traffic dynamic airspace management system for unmanned aerial vehicles (UAVs), characterized in that: The system is used to perform the method as described in any one of claims 1 to 7, comprising: The receiving module is used to receive drone flight mission applications and generate a comprehensive risk value; based on the comprehensive risk value, when the comprehensive risk value is lower than a preset threshold, it outputs a second-level approval and permission instruction; The judgment module is used to obtain airspace occupancy rate and flight mission priority data in real time based on the output approval and permission instructions; it generates electronic fence dynamic adjustment instructions based on the airspace occupancy rate and flight mission priority data, and outputs the updated electronic fence geographic coordinate set. The generation module is used to take the output set of geographic coordinates of the electronic fence as the monitoring baseline boundary, integrate ADS-B data, meteorological information and drone equipment status, generate a real-time risk heat map and output graded alarm commands. The execution module receives the output real-time risk heat map and graded alarm instructions. When a graded alarm instruction is triggered, it performs the following operations: constructs a feasible solution space for flight routes based on the no-fly zones and high-risk areas in the risk heat map as constraints; iteratively evolves the path population through selection, crossover, and mutation operations of a genetic algorithm with the goal of minimizing energy consumption, outputs the final global obstacle avoidance and detour path, and issues a flight route update instruction to the UAV flight control system.

Images