Unmanned aerial vehicle airspace scheduling method and device, electronic equipment and storage medium

Abstract

The invention relates to an unmanned aerial vehicle airspace scheduling method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring flight data and environment data of an unmanned aerial vehicle; dividing the airspace into a core area, a buffer area and a free area based on the flight data; on the basis of shift data in the environment data and the flight data, predicting the meteorological condition of the core area in the target time period; when the weather condition is thunderstorm weather, adjusting the flight task of each unmanned aerial vehicle based on the flight data and the weather condition; and performing control scheduling on the unmanned aerial vehicle based on the adjusted flight task. Thus, the core area, the buffer area and the free area are dynamically divided based on the flight data, conflicts caused by disordered passing of multiple unmanned aerial vehicles in the core area are reduced, idle resources in the free area are activated, and the utilization rate of unmanned aerial vehicle resources is increased; moreover, thunderstorm weather is directionally predicted by focusing on the core area instead of whole-airspace generalization prediction, so that the calculation cost is reduced, and resources can be concentrated in the airspace which is most required to be guaranteed.

Description

Technical Field

[0001] This application relates to the field of unmanned aerial vehicle (UAV) technology, and in particular to a UAV airspace scheduling method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the continuous iteration of drone technology and the deep expansion of application scenarios, its penetration rate in fields such as emergency rescue, logistics transportation, power line inspection, and urban governance has significantly increased, making it a key tool for promoting the digital transformation of various industries. However, with the surge in the number of drones and the rapid increase in flight mission density, efficient scheduling in high-density airspace and safe management under complex operating conditions have gradually become the core bottlenecks restricting the large-scale development of the industry, making the technical needs for dynamic airspace management and autonomous obstacle avoidance of drones increasingly urgent.

[0003] Current mainstream UAV flight control systems rely heavily on preset route parameters and static airspace rules for planning and scheduling. When faced with unexpected situations such as neighboring aircraft malfunctions and deviations from the route, or the insertion of temporary emergency tasks, the system struggles to quickly adapt to the temporary reconstruction needs of airspace resources and still relies on manual intervention or fixed process decisions, resulting in a severe lack of response flexibility. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, electronic device, and storage medium for UAV airspace scheduling to address the aforementioned technical problems.

[0005] Firstly, this application provides a method for UAV airspace scheduling, the method comprising: Acquire flight and environmental data from the drone; Based on the flight data, the airspace is divided into a core area, a buffer zone, and a free zone; wherein, the core area represents a flight route congestion level greater than a first target level; the free zone represents a flight route congestion level less than a second target level; the buffer zone represents a flight route congestion level between the second target level and the first target level; and the first target level is greater than the second target level. Based on the environmental data and the flight schedule data, predict the weather conditions of the core area within the target time period; When the weather conditions are thunderstorms, the flight missions of each UAV are adjusted based on the flight data and the weather conditions. The UAV is controlled and scheduled based on the adjusted flight mission.

[0006] In one embodiment, predicting the weather conditions of the core area within a target time period based on the environmental data and flight schedule data includes: The environmental data and the shift data are input into the meteorological prediction model, and a time-series feature vector is obtained through a time-series encoder. The temporal feature vector is concatenated and fused with the corresponding geographic feature vector through a multi-feature fusion layer to obtain a comprehensive feature vector; The comprehensive feature vector is analyzed and reasoned through a probability prediction layer to obtain the target prediction result; wherein, the target prediction result includes the weather conditions and the probability of occurrence.

[0007] In one embodiment, adjusting the flight missions of each UAV based on the flight data and the weather conditions includes: Based on the overlap between the flight schedule data and the warning time periods corresponding to thunderstorm weather, no-fly zones and target drones are determined; wherein, the target drones include the key drone to be adjusted and the secondary drones whose distance from the key drone is within a predetermined range; Using a dynamic safety distance model, the dynamic shortest safety distance between the key UAV and each of the secondary UAVs is determined; Based on the dynamic shortest safe distance, the weather conditions during the warning period, and / or the task priority of the target UAV's real-time flight mission during the warning period, the real-time flight mission is constrained to obtain the adjusted flight mission.

[0008] In one embodiment, the method further includes: When each of the aforementioned UAVs performs the flight mission, it generates a flight message and performs a digital signature to obtain a target message; wherein, the flight message includes a timestamp, an identity identifier, a real-time location, and / or a flight status; Broadcast the target message to the blockchain network; Before determining the dynamic shortest safe distance between the key UAV and each of the secondary UAVs using the dynamic safe distance model, the method further includes: The secondary drone receives the target message from the key drone and determines the digital certificate digest and target hash value of the key drone; The authenticity of the target message is verified based on the digital certificate digest and the blockchain network. The integrity of the target message is verified based on the target hash value.

[0009] In one embodiment, determining the dynamic shortest safe distance between the key UAV and each of the secondary UAVs using a dynamic safe distance model includes: If the authenticity and integrity are both verified, a safety distance benchmark value is determined based on the aircraft type of the key UAV and the secondary UAV. The lateral safety distance is determined based on the real-time speeds of the key UAV and the secondary UAV. Based on the real-time altitude of the key UAV and the secondary UAV, the longitudinal safety distance is determined; The dynamic shortest safety distance is determined based on the lateral safety distance and the longitudinal safety distance.

[0010] In one embodiment, the step of constraining the real-time flight mission based on the dynamic shortest safe distance, the weather conditions during the warning period, and / or the mission priority of the target UAV's real-time flight mission during the warning period to obtain an adjusted flight mission includes: Based on the dynamic shortest safe distance and the meteorological conditions during the warning period, candidate tasks are generated; Conflicting tasks are identified by comparing the interrelated candidate tasks using a conflict detection algorithm. Based on the task priorities, the conflicting tasks are adjusted. The first task with the highest task priority among the conflicting tasks remains unchanged, while the second tasks with other task priorities are adjusted to obtain the adjusted flight tasks.

[0011] In one embodiment, adjusting the flight missions of each UAV based on the flight data and the weather conditions includes: When the flight mission in the flight data is a rescue mission, the alternative direct flight path of the rescue drone is generated by combining the thunderstorm area boundary, movement speed and impact time in the meteorological conditions, as well as the real-time position, destination position and real-time flight speed in the flight data through a three-dimensional path planning algorithm. Based on the alternative direct flight paths, the safe airspace range of the rescue drone is determined; The flight missions of the UAVs to be evacuated within the safe airspace are adjusted for evacuation.

[0012] Secondly, this application also provides an unmanned aerial vehicle (UAV) airspace scheduling device, the device comprising: The acquisition module is used to acquire the drone's flight data and environmental data; The partitioning module is used to divide the airspace into a core area, a buffer zone, and a free zone based on the flight data; wherein, the core area represents a flight route congestion level greater than a first target level; the free zone represents a flight route congestion level less than a second target level; the buffer zone represents a flight route congestion level between the second target level and the first target level; and the first target level is greater than the second target level. The prediction module is used to predict the weather conditions of the core area within a target time period based on the environmental data and the flight schedule data in the flight data. The adjustment module is used to adjust the flight missions of each UAV based on the flight data and the weather conditions when thunderstorms are present. The scheduling module is used to control and schedule the UAV based on the adjusted flight mission.

[0013] Thirdly, this application also provides an electronic device, including a processor and a memory for storing processor-executable instructions; wherein the processor is configured to, when executing the executable instructions, implement the steps of the method described in any embodiment of this application.

[0014] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the methods described in any embodiment of this application.

[0015] The aforementioned UAV airspace scheduling method, on the one hand, dynamically divides the core area, buffer zone, and free zone based on real-time flight data. This reduces conflicts caused by disorderly passage of multiple UAVs in the core area and revitalizes idle resources in the free zone, improving the utilization rate of UAV resources. On the other hand, it focuses on targeted prediction of thunderstorm weather in the core area, rather than generalized prediction across the entire airspace. This reduces computational costs and concentrates resources on the airspace most in need of protection. By combining UAV flight data and flight schedule information to provide early warnings of risks and by adjusting flight missions in real time based on flight data and weather conditions, it reduces the accident rate while meeting the temporary reconstruction needs of airspace resources, improving response flexibility and mission completion rate. Through data-driven emergency scheduling, it shortens emergency response time and achieves synergistic optimization of safety, efficiency, and emergency response capabilities, providing key support for the large-scale deployment of UAVs in urban low-altitude economy, emergency rescue, smart logistics, and other fields. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating a UAV airspace scheduling method according to an exemplary embodiment; Figure 2 This is a flowchart illustrating a UAV airspace scheduling method according to an exemplary embodiment; Figure 3 This is a structural block diagram of an unmanned aerial vehicle (UAV) airspace scheduling device according to an exemplary embodiment; Figure 4 This is an internal structural diagram of an electronic device according to an exemplary embodiment. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0018] The terms "first," "second," and "third" used in the embodiments of this application are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first," "second," or "third" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0019] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0020] In some embodiments, the UAV airspace scheduling method provided in this application can be applied to an electronic device. The electronic device can be any mobile terminal or fixed terminal. The terminal can be a device that provides voice and / or data connectivity to a user. For example, the terminal can be an Internet of Things (IoT) terminal, such as a sensor device, a mobile phone or so-called "cellular" phone, and a computer with an IoT terminal; for example, it can be a fixed, portable, pocket-sized, handheld, or computer-embedded device.

[0021] In some embodiments, such as Figure 1 As shown, a method for UAV airspace scheduling is provided, the method comprising the following steps: S101 acquires flight data and environmental data of the drone.

[0022] In this embodiment of the application, flight data includes, but is not limited to, positioning data, flight schedule data, and / or flight status data.

[0023] For example, the positioning data may include, but is not limited to, latitude / longitude, real-time altitude, and three-dimensional coordinates in a preset coordinate system.

[0024] For example, shift data may include, but is not limited to, basic task information, route planning information, time parameters, task priority and / or associated resource information.

[0025] For example, flight status data may include, but is not limited to, motion parameters, equipment status, mission execution progress and / or abnormal status information.

[0026] In this embodiment of the application, the environmental data includes temperature data, humidity data, geographic data, meteorological data and / or wind data; wherein, wind data may include wind speed and wind direction.

[0027] S102, based on the flight data, the airspace is divided into a core area, a buffer zone, and a free zone; wherein, the core area represents a flight route congestion level greater than a first target level; the free zone represents a flight route congestion level less than a second target level; the buffer zone represents a flight route congestion level between the second target level and the first target level; the first target level is greater than the second target level.

[0028] In one embodiment, the electronic device calculates the real-time number of drones in a unit airspace using positioning data from flight data and sets a hierarchical threshold to divide the airspace into a core area, a buffer zone, and a free zone.

[0029] In one embodiment, the electronic device calculates the real-time number of drones in a unit airspace using positioning data from flight data and sets hierarchical quantity thresholds; it then adjusts the quantity thresholds by weighting them based on task priority, task type, etc., from the flight data; and finally divides the airspace into a core area, a buffer zone, and a free zone based on the quantity thresholds.

[0030] For example, a 10km×10km planar area combined with a +20m altitude layer can be used as the smallest airspace unit. If the number of real-time UAVs in the first airspace unit is greater than or equal to N and the duration is long enough, it can be initially identified as a candidate core area. If the number of real-time UAVs in the second airspace unit is between P and N, it can be identified as a candidate buffer zone. If the number of real-time UAVs in the third airspace unit is less than P, it can be identified as a candidate free zone. Based on the flight data, shift data, such as high-priority tasks like emergency rescue and medical transportation, are assigned higher density weights. For example, one high-priority UAV is equivalent to two regular-priority UAVs. Based on the density weights, the density distribution of UAVs in each area is determined, and the final core area, buffer zone, and free zone are determined.

[0031] S103, based on the environmental data and the flight schedule data, predict the weather conditions of the core area within the target time period.

[0032] In some embodiments, such as Figure 2 As shown, predicting the meteorological conditions of the core area within a target time period based on the environmental data and the flight schedule data includes: S1031, The environmental data and the shift data are input into the meteorological prediction model, and the time-series feature vector is obtained by the time-series encoder; S1032, The temporal feature vector is concatenated and fused with the corresponding geographic feature vector through a multi-feature fusion layer to obtain a comprehensive feature vector; S1033, the comprehensive feature vector is analyzed and reasoned through the probability prediction layer to obtain the target prediction result; wherein, the target prediction result includes the weather conditions and the probability of occurrence.

[0033] In one embodiment, the electronic device can collect multi-source historical data to train a weather forecasting model (e.g., the ST-Transformer model), and the multi-source historical data may include historical weather data and historical flight data. For example, it can acquire archived meteorological data from the meteorological bureau within a predetermined historical time range (such as temperature, humidity, air pressure, wind speed, and / or precipitation intensity observed by ground stations), meteorological satellite cloud image data (such as cloud top temperature and cloud cover density), and radar echo data (reflecting vertical atmospheric motion and allowing extraction of strong echo information characteristic of thunderstorms); or, it can acquire flight schedule dynamics (such as takeoff / landing time, flight path deviation records, altitude adjustment logs, and delay duration) and density data (such as the number of drones per hour in a specific airspace) during the thunderstorm-affected period; and perform spatiotemporal alignment of historical meteorological data and historical flight schedule data. For example, within a certain spatiotemporal grid (30°-30°10′N, 120°-120°10′E, 14:00-14:15 on July 10, 2023), it must simultaneously include the radar echo intensity, cloud top temperature, and records of the altitude, speed, and whether the flight path was adjusted due to thunderstorms for the three drones flying within that grid.

[0034] In one embodiment, the electronic device can perform data cleaning and anomaly processing on multi-source historical data. For missing time periods in historical meteorological data, the missing values ​​can be filled by weighted calculation based on normal data from adjacent airspace units and adjacent time periods. Data that obviously does not conform to physical logic and non-meteorological anomaly data in historical flight data, such as anomaly data caused by mechanical failure of drones or sensors, are removed to obtain preprocessed sample data. The meteorological prediction model is trained and validated based on the sample data to obtain the trained meteorological prediction model.

[0035] In one embodiment, the meteorological prediction model architecture includes a temporal encoder, a multi-feature fusion layer, and a probabilistic prediction layer. Environmental data and flight schedule data are input into the temporal encoder. Each time step includes a meteorological feature set (such as numerical features like temperature, humidity, wind speed, and radar echo intensity) and a flight schedule feature set (such as the number of drones, flight altitude, and number of flight adjustments within the spatiotemporal grid). The temporal encoder calculates the correlation weights between different time steps and different features through a self-attention layer. The multi-feature fusion layer concatenates the temporal feature vector output by the temporal encoder with the corresponding geographic feature vector, ensuring that the meteorological prediction model considers the impact of geographic factors on meteorological conditions. For example, mountainous areas are prone to orographic rain that triggers thunderstorms. The geographic feature vector is determined by the positioning data from the drone's flight data. The probabilistic prediction layer uses a Softmax activation function to output the target prediction result, which may include the probability of thunderstorm occurrence, the corresponding intensity prediction, and the specific occurrence time within the target occurrence segment.

[0036] In this embodiment, on the one hand, the combination of multi-source data fusion and time-series coding significantly improves the comprehensiveness and dynamic adaptability of predictions: compared with traditional static predictions that rely solely on environmental data, by combining environmental data with flight schedule data from flight data, it not only covers the basic influencing factors of meteorology itself, but also incorporates the related variable of UAV activity intensity in the core area; at the same time, by capturing the evolution of data over time through time-series encoders, it can more accurately match the actual scenario of dynamic coupling between meteorological conditions and flight conditions in the core area.

[0037] S104, when the weather conditions are thunderstorms, adjust the flight missions of each UAV based on the flight data and the weather conditions.

[0038] In some embodiments, adjusting the flight missions of each UAV based on the flight data and the weather conditions includes: Based on the overlap between the flight schedule data and the warning time periods corresponding to thunderstorm weather, no-fly zones and target drones are determined; wherein, the target drones include the key drone to be adjusted and the secondary drones whose distance from the key drone is within a predetermined range; Using a dynamic safety distance model, the dynamic shortest safety distance between the key UAV and each of the secondary UAVs is determined; Based on the dynamic shortest safe distance, the weather conditions during the warning period, and / or the task priority of the target UAV's real-time flight mission during the warning period, the real-time flight mission is constrained to obtain the adjusted flight mission.

[0039] For example, the predetermined range can be 5 kilometers, 10 kilometers, etc., and the specific value can be determined according to the actual application.

[0040] For example, the electronic device determines the core area as location A to location C, with location B located between location A and location C. The flight data includes information for the first flight: "2024-07-02, 14:00-16:10, the third UAV flew from point A to point B." The core area experiencing thunderstorms is from point A to point D. Point D is located in the area where the thunderstorm warning period is "2024-07-02, 13:00-15:25," which overlaps with the first flight information. Therefore, the no-fly zone can be confirmed as the area from point A to point D during the "2024-07-02, 13:00-15:25" period. Alternatively, by combining ionospheric detection results, the no-fly zone can be determined as the target altitude layer within the "2024-07-02, 13:00-15:25" period, where the target altitude layer indicates the altitude range where thunderstorms are present in the airspace. The key UAV is identified as the third UAV, and based on the key UAV, a secondary UAV within a predetermined distance from the key UAV is determined.

[0041] In some embodiments, constraining the real-time flight mission based on the dynamic shortest safe distance, the weather conditions during the warning period, and / or the mission priority of the target UAV's real-time flight mission during the warning period to obtain an adjusted flight mission includes: Based on the dynamic shortest safe distance and the meteorological conditions during the warning period, candidate tasks are generated; Conflicting tasks are identified by comparing the interrelated candidate tasks using a conflict detection algorithm. Based on the task priorities, the conflicting tasks are adjusted. The first task with the highest task priority among the conflicting tasks remains unchanged, while the second tasks with other task priorities are adjusted to obtain the adjusted flight tasks.

[0042] In some embodiments, the electronic device may refer to the area where thunderstorms occur during the warning period to ensure that the detour path in the candidate task is at a certain distance from the thunderstorm boundary in order to reserve safety redundancy; and / or, follow the safety distance constraint to ensure that the distance between the key UAV and the secondary UAV in the candidate task is not less than the dynamic shortest safety distance.

[0043] For example, based on the conflict detection algorithm, all candidate tasks are compared to find and mark conflicting candidate tasks. For example, if the climb task B of UAV B is to climb from 800 meters to 1000 meters, and the climb task C of UAV C is to climb from 900 meters to 1000 meters, the heights overlap and the lateral distance is less than 1 kilometer, the climb tasks B / C can be marked as conflicting tasks.

[0044] In one embodiment, for conflicting tasks, the task priorities recorded on the blockchain can be combined (e.g., aircraft B undertaking emergency rescue tasks has the highest priority, while aircraft C performing logistics transportation tasks has a medium priority) to prioritize the adjustment method that minimizes the delay to its own task. For example, aircraft B with the highest priority will tend to adjust its climb altitude rather than change its flight path because it has less impact on the timeliness of rescue. At the same time, each adjusted flight task must include the adjustment direction (e.g., southward shift, climb), adjustment range (e.g., shift 3 kilometers, climb 200 meters), time to complete the adjustment (e.g., within 30 seconds), and the adjusted waypoint (specific latitude, longitude, and altitude) to ensure that the task information is complete and can be directly used for subsequent collaborative negotiations.

[0045] S105, based on the adjusted flight mission, control and schedule the UAV.

[0046] The aforementioned UAV airspace scheduling method, on the one hand, dynamically divides the core area, buffer zone, and free zone based on real-time flight data. This reduces conflicts caused by disorderly passage of multiple UAVs in the core area and revitalizes idle resources in the free zone, improving the utilization rate of UAV resources. On the other hand, it focuses on targeted prediction of thunderstorm weather in the core area, rather than generalized prediction across the entire airspace. This reduces computational costs and concentrates resources on the airspace most in need of protection. By combining UAV flight data and flight schedule information to provide early warnings of risks and by adjusting flight missions in real time based on flight data and weather conditions, it reduces the accident rate while meeting the temporary reconstruction needs of airspace resources, improving response flexibility and mission completion rate. Through data-driven emergency scheduling, it shortens emergency response time and achieves synergistic optimization of safety, efficiency, and emergency response capabilities, providing key support for the large-scale deployment of UAVs in urban low-altitude economy, emergency rescue, smart logistics, and other fields.

[0047] In some embodiments, the method further includes: When each of the aforementioned UAVs performs the flight mission, it generates a flight message and performs a digital signature to obtain a target message; wherein, the flight message includes a timestamp, an identity identifier, a real-time location, and / or a flight status; Broadcast the target message to the blockchain network; Before determining the dynamic shortest safe distance between the key UAV and each of the secondary UAVs using the dynamic safe distance model, the method further includes: The secondary drone receives the target message from the key drone and determines the digital certificate digest and target hash value of the key drone; The authenticity of the target message is verified based on the digital certificate digest and the blockchain network. The integrity of the target message is verified based on the target hash value.

[0048] In this embodiment, the timestamp indicates the precise time when the flight message was generated. For example, the timestamp could be the message generation time 2024-05-20 14:30:00, valid for 5 minutes.

[0049] In this embodiment, the identity identifier indicates the unique digital identity of the drone. The identity identifier may include, but is not limited to, a registration number, a public key hash, a blockchain node identifier, and / or a digital certificate digest.

[0050] In this embodiment, the real-time location indicates the current geographic coordinates of the drone. For example, the real-time location can be latitude and longitude plus altitude.

[0051] In this embodiment, the flight status indicates the current operating status of the UAV. The flight status may include, but is not limited to, at least one of the following: flight mode (such as cruise, landing, etc.), flight speed, flight heading, remaining battery life, and fault codes.

[0052] In one embodiment, the secondary drone extracts the node identifier (ID) and digital certificate digest of the key drone from the target message, queries the blockchain ledger for the current identity status of the key drone, such as whether it is a legitimate node or whether there are any malicious behavior records; at the same time, it uses the public key of the key drone to verify the SM2 signature in the target message to confirm that the target message has not been forged, thus ensuring the authenticity of the target message.

[0053] In one embodiment, the secondary drone calculates the SM3 hash value based on the target message, compares the SM3 hash value with the original hash value in the target message, and if they match, it can be determined that the target message has not been tampered with during transmission, thus ensuring the integrity of the target message.

[0054] In one embodiment, the secondary drone can also verify the timeliness of the target message. By reading the timestamp of the target message, it can determine whether the difference between the current time and the message generation time exceeds the validity period. If it does, it can be marked as invalid information and the key drone can be requested to resend the latest target message.

[0055] In one embodiment, if any verification of the integrity, authenticity, and / or timeliness of the target message fails, a suspicious message is reported to the blockchain endorsing node and the airspace scheduling / obstacle avoidance operation based on the message is refused.

[0056] In this embodiment, on the one hand, authenticity verification based on digital certificate digests and blockchain can accurately confirm the credibility of the message source. At the same time, the immutability of blockchain ensures that the verification basis cannot be maliciously tampered with, reducing the risk of questionable messages misleading obstacle avoidance decisions. On the other hand, verifying the integrity of message content through target hash values ​​can prevent flight messages from being tampered with during transmission, ensuring that the key drone information obtained by the secondary drone is consistent with the actual situation. Finally, calculating the dynamic shortest safe distance based on real and complete message data can provide a reliable data foundation for subsequent multi-drone collaborative obstacle avoidance and airspace scheduling, significantly reducing the risk of aerial collisions caused by falsified or distorted messages. Meanwhile, the broadcasting and evidence storage characteristics of blockchain also make the message flow process traceable, facilitating subsequent accident investigation and responsibility determination, further improving the safety and collaborative reliability of drone flights in high-density airspace.

[0057] In some embodiments, determining the dynamic shortest safe distance between the key UAV and each of the secondary UAVs using a dynamic safe distance model includes: If the authenticity and integrity are both verified, a safety distance benchmark value is determined based on the aircraft type of the key UAV and the secondary UAV. The lateral safety distance is determined based on the real-time speeds of the key UAV and the secondary UAV. Based on the real-time altitude of the key UAV and the secondary UAV, the longitudinal safety distance is determined; The dynamic shortest safety distance is determined based on the lateral safety distance and the longitudinal safety distance.

[0058] For example, the aircraft type of a drone may include, but is not limited to, lightweight, mid-range, and high-end / industrial grade.

[0059] For example, at the same altitude level in the airspace, the safe distance reference values ​​for different types of drones are different; for instance, the safe distance reference value between large drones can be 5km, the safe distance reference value between large and small drones can be 3km, and the safe distance reference value between small drones can be 1km.

[0060] In some embodiments, the faster the flight speed, the greater the required safety distance between the drones; the lateral safety distance can be determined by multiplying the safety distance reference value by the real-time speed.

[0061] In some embodiments, if the critical UAV and the secondary UAV are located at different altitude levels, the altitude difference is determined as the longitudinal safety distance.

[0062] In some embodiments, when the longitudinal safety distance is large, such as greater than 300 meters, it can be determined that there is no risk of collision between the key UAV and the secondary UAV in the vertical direction. In this case, the lateral safety distance can be reduced by a first preset ratio to obtain the dynamic shortest safety distance, and the risk level can be marked as low. When the longitudinal safety distance is small, such as less than 100 meters, it can be determined that there is a risk of collision between the key UAV and the secondary UAV in the vertical direction. In this case, the lateral safety distance can be increased by a second preset ratio to obtain the dynamic shortest safety distance, and the risk level can be marked as high.

[0063] For example, if the lateral safety distance is 2.5 kilometers and the longitudinal safety distance is 350 meters, which is greater than the safety threshold of 280 meters, then the lateral safety distance can be shortened by 30% to 1.75 kilometers as the dynamic minimum safety distance.

[0064] In this embodiment, a safety distance benchmark is set based on the aircraft types of the key UAV and the secondary UAV. This allows for the matching of appropriate basic safety thresholds to different models (such as large logistics UAVs and small inspection UAVs) based on their physical size and anti-interference capabilities. This reduces the risk of collisions due to insufficient spacing between large UAVs or the waste of airspace due to excessive spacing between small UAVs caused by a uniform benchmark. Secondly, the lateral safety distance is dynamically adjusted based on the real-time speed of both UAVs to ensure that the collision risk is controllable during high-speed flight and that airspace resources are not idle during low-speed operations. At the same time, the longitudinal safety distance is determined based on the real-time altitude, and the vertical spacing can be flexibly optimized according to the height difference (such as appropriately reducing the longitudinal distance when the height difference is large and strengthening the spacing when the height difference is small) to adapt to the actual risk distribution of the three-dimensional airspace. Finally, the dynamic shortest safety distance obtained by integrating the lateral and longitudinal safety distances not only comprehensively covers the three-dimensional spatial risks of UAV flight, but also maximizes the utilization rate of high-density airspace while ensuring extremely low collision risks. This provides a scientific safety basis that fits the actual flight scenario for subsequent multi-UAV collaborative obstacle avoidance and path adjustment, effectively balancing flight safety and scheduling efficiency.

[0065] In some embodiments, adjusting the flight missions of each UAV based on the flight data and the weather conditions includes: When the flight mission in the flight data is a rescue mission, the alternative direct flight path of the rescue drone is generated by combining the thunderstorm area boundary, movement speed and impact time in the meteorological conditions, as well as the real-time position, destination position and real-time flight speed in the flight data through a three-dimensional path planning algorithm. Based on the alternative direct flight paths, the safe airspace range of the rescue drone is determined; The flight missions of the UAVs to be evacuated within the safe airspace are adjusted for evacuation.

[0066] In some embodiments, the rescue drone is automatically identified through a blockchain identity management contract: First, the node ID and digital certificate digest uploaded by the drone's onboard blockchain client are read. The contract verifies its identity information (whether it is registered as an "emergency rescue dedicated aircraft"), mission qualifications (the mission type is marked as "life rescue / emergency material transportation" in the flight data) and historical reputation (no record of illegal flight). After verification, it is immediately marked as the highest priority in the core area, and the priority result is broadcast to all airspace nodes (including other aircraft and air traffic control edge nodes) to ensure that the priority right of passage is recognized throughout the entire chain.

[0067] In some embodiments, the thunderstorm area boundary, movement speed (e.g., 20 km / h northeastward), and impact duration (e.g., 40 minutes) output by the meteorological forecast model are called. Combined with the real-time location, destination location, and real-time flight speed of the rescue drone, a three-dimensional path planning algorithm is used to generate one or more alternative direct flight paths based on path selection criteria. Through dynamic comparison with real-time meteorological data, the option that moves away from the thunderstorm path is prioritized (e.g., if the thunderstorm moves northeastward, the southwest detour path is prioritized), and the key waypoints of the path (e.g., a node every 4 km, latitude, longitude + altitude) are uploaded to the blockchain for evidence storage.

[0068] For example, route selection criteria may include detour distance ≤ 10% of the original route (to ensure timeliness), distance between the route and the boundary of the thunderstorm area ≥ 3km (to reserve safety redundancy), and avoiding fixed obstacles such as high-voltage cables / no-fly zones.

[0069] In this embodiment, the safe airspace range includes a horizontal range and a vertical range. For example, the horizontal range can be radiating horizontally for 5km from the center of the rescue drone, and the vertical range can be radiating vertically for 500m from the center of the rescue drone.

[0070] In one embodiment, an airspace clearance instruction is sent via blockchain to all non-priority aircraft (such as conventional logistics drones and inspection drones) within the safe airspace. For example, the clearance instruction could be "must evacuate to outside the safe area within 3 minutes," along with suggested evacuation directions. After completing the evacuation, the non-priority aircraft must upload their new location to the blockchain, and electronic devices will verify in real time whether they have left the safe airspace of the rescue drone. If they fail to evacuate within the specified time, air traffic control nodes will intervene to force adjustments and ensure that the rescue drone's path is free from interference during its rescue mission.

[0071] In this embodiment, by combining key thunderstorm parameters with real-time flight data of rescue drones, a three-dimensional path planning algorithm is used to generate alternative direct flight paths. This ensures that the paths avoid thunderstorm threats while minimizing detour distances by focusing on direct flight, thus saving valuable time for the rescue mission. Determining a safe airspace based on the alternative paths allocates a dedicated, interference-free flight space for the rescue drones, mitigating the risk of collisions with other drones from the outset and ensuring safety throughout the rescue flight. Adjusting the flight paths of drones awaiting evacuation within the safe airspace not only proactively clears the rescue path and prevents them from interfering with the rescue process, but also ensures that the drones themselves avoid both thunderstorm and rescue path risks through targeted adjustments. Ultimately, this achieves multiple objectives: efficient progress of the rescue mission, safe flight of the rescue drones, and orderly avoidance of other drones within the airspace, maximizing the landing efficiency of emergency rescue and overall airspace safety in thunderstorm scenarios.

[0072] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0073] Based on the same inventive concept, this application also provides a UAV airspace scheduling device for implementing the UAV airspace scheduling method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more UAV airspace scheduling device embodiments provided below can be found in the limitations of the UAV airspace scheduling method described above, and will not be repeated here.

[0074] In one embodiment, such as Figure 3 As shown, a drone airspace scheduling device is provided, the device comprising: Acquisition module 10 is used to acquire flight data and environmental data of the UAV; The partitioning module 20 is used to divide the airspace into a core area, a buffer zone, and a free zone based on the flight data; wherein, the core area represents a flight congestion level greater than a first target level; the free zone represents a flight congestion level less than a second target level; the buffer zone represents a flight congestion level between the second target level and the first target level; and the first target level is greater than the second target level. Prediction module 30 is used to predict the weather conditions of the core area within a target time period based on the environmental data and the flight schedule data in the flight data; The adjustment module 40 is used to adjust the flight missions of each UAV based on the flight data and the weather conditions when there is thunderstorm weather. The scheduling module 50 is used to control and schedule the UAV based on the adjusted flight mission.

[0075] In one embodiment, the prediction module 30 is configured to perform the following steps: The environmental data and the shift data are input into the meteorological prediction model, and a time-series feature vector is obtained through a time-series encoder. The temporal feature vector is concatenated and fused with the corresponding geographic feature vector through a multi-feature fusion layer to obtain a comprehensive feature vector; The comprehensive feature vector is analyzed and reasoned through a probability prediction layer to obtain the target prediction result; wherein, the target prediction result includes the weather conditions and the probability of occurrence.

[0076] In one embodiment, the adjustment module 40 includes: The filtering unit is used to determine no-fly zones and target drones based on the overlap between the flight data and the warning time periods corresponding to thunderstorm weather; wherein, the target drones include key drones to be adjusted and secondary drones whose distance from the key drones is within a predetermined range; The determining unit is used to determine the dynamic shortest safe distance between the key UAV and each of the secondary UAVs using a dynamic safe distance model; The adjustment unit is used to constrain the real-time flight mission based on the dynamic shortest safe distance, the weather conditions during the warning period, and / or the mission priority of the target UAV's real-time flight mission during the warning period, so as to obtain the adjusted flight mission.

[0077] In one embodiment, the apparatus further includes: The generation module is used to generate flight messages and digitally sign them when each of the UAVs performs the flight mission to obtain target messages; wherein, the flight messages include timestamps, identification identifiers, real-time locations and / or flight status; The transmission module is used to broadcast the target message to the blockchain network; Before determining the dynamic shortest safe distance between the key UAV and each of the secondary UAVs using the dynamic safe distance model, the device further includes: The determination module is used for the secondary drone to receive the target message from the key drone and determine the digital certificate digest and target hash value of the key drone; The verification module is used to verify the authenticity of the target message based on the digital certificate digest and in conjunction with the blockchain network; The verification module is used to verify the integrity of the target message based on the target hash value.

[0078] In one embodiment, the determining unit is configured to perform the following steps: If the authenticity and integrity are both verified, a safety distance benchmark value is determined based on the aircraft type of the key UAV and the secondary UAV. The lateral safety distance is determined based on the real-time speeds of the key UAV and the secondary UAV. Based on the real-time altitude of the key UAV and the secondary UAV, the longitudinal safety distance is determined; The dynamic shortest safety distance is determined based on the lateral safety distance and the longitudinal safety distance.

[0079] In one embodiment, the adjustment unit is configured to perform the following steps: Based on the dynamic shortest safe distance and the meteorological conditions during the warning period, candidate tasks are generated; Conflicting tasks are identified by comparing the interrelated candidate tasks using a conflict detection algorithm. Based on the task priorities, the conflicting tasks are adjusted. The first task with the highest task priority among the conflicting tasks remains unchanged, while the second tasks with other task priorities are adjusted to obtain the adjusted flight tasks.

[0080] In one embodiment, the adjustment module 40 is configured to perform the following steps: When the flight mission in the flight data is a rescue mission, the alternative direct flight path of the rescue drone is generated by combining the thunderstorm area boundary, movement speed and impact time in the meteorological conditions, as well as the real-time position, destination position and real-time flight speed in the flight data through a three-dimensional path planning algorithm. Based on the alternative direct flight paths, the safe airspace range of the rescue drone is determined; The flight missions of the UAVs to be evacuated within the safe airspace are adjusted for evacuation.

[0081] Each module in the aforementioned UAV airspace scheduling device can be implemented entirely or partially through software, hardware, or a combination thereof. Each module can be embedded in the processor of the electronic device in hardware form or independent of the processor, or it can be stored in the memory of the electronic device in software form, so that the processor can call and execute the corresponding operations of each module.

[0082] In one embodiment, an electronic device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 4 As shown, the electronic device includes a processor, memory, communication interface, display unit, and input device connected via a method bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores operating methods and computer programs. The internal memory provides an environment for the operation of the operating methods and computer programs stored in the non-volatile storage medium. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a UAV airspace scheduling method. The display screen can be an LCD screen or an e-ink display screen. The input device can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the device's casing, or an external keyboard, touchpad, or mouse.

[0083] Those skilled in the art will understand that Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0084] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0085] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps performed by the processor of the electronic device of any of the above.

[0086] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0087] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, compilable logic units, quantum computing-based data processing logic units, etc., and are not limited to these.

[0088] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0089] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for UAV airspace scheduling, characterized in that, The method comprises: acquiring flight data and environment data of a UAV; based on the flight data, dividing airspace into a core area, a buffer area and a free area; wherein the core area represents a flight route congestion degree greater than a first target degree; the free area represents a flight route congestion degree less than a second target degree; the buffer area represents a flight route congestion degree between the second target degree and the first target degree; the first target degree is greater than the second target degree; based on the environment data and shift data in the flight data, predicting a weather condition of the core area in a target time period; in the case that the weather condition is thunderstorm weather, adjusting a flight task of each UAV based on the flight data and the weather condition; controlling and scheduling the UAV based on the adjusted flight task.

2. The method of claim 1, wherein, The method further comprises: inputting the environment data and the shift data into a weather prediction model to obtain a time sequence feature vector through a time sequence encoder; splicing and fusing the time sequence feature vector with a corresponding geographical feature vector through a multi-feature fusion layer to obtain a comprehensive feature vector; analyzing and reasoning the comprehensive feature vector through a probability prediction layer to obtain a target prediction result; wherein the target prediction result includes the weather condition and a probability of occurrence.

3. The method of claim 1, wherein, The method further comprises: based on a coincidence of a warning time period corresponding to thunderstorm weather in the shift data, determining a no-fly area and a target UAV; wherein the target UAV includes a key UAV to be adjusted and a secondary UAV within a predetermined range from the key UAV; determining a dynamic shortest safety distance between the key UAV and each secondary UAV using a dynamic safety distance model; based on the dynamic shortest safety distance, the weather condition of the warning time period and / or a task priority of a real-time flight task of the target UAV in the warning time period, constraining the real-time flight task to obtain an adjusted flight task.

4. The method of claim 3, wherein, The method further comprises: when each UAV executes the flight task, generating a flight message and digitally signing the flight message to obtain a target message; wherein the flight message includes a timestamp, an identity, a real-time position and / or a flight state; broadcasting the target message to a blockchain network; Before determining the dynamic shortest safety distance between the key UAV and each secondary UAV using the dynamic safety distance model, the method further comprises: the secondary UAV receives the target message of the key UAV and determines a digital certificate digest and a target hash value of the key UAV; based on the digital certificate digest, verifying the authenticity of the target message in combination with the blockchain network; based on the target hash value, verifying the integrity of the target message.

5. The method of claim 4, wherein, The method further comprises: In the case that the authenticity and the integrity are both verified, a safe distance benchmark value is determined based on the aircraft types of the key unmanned aerial vehicle and the secondary unmanned aerial vehicle; A lateral safe distance is determined based on the real-time speeds of the key unmanned aerial vehicle and the secondary unmanned aerial vehicle; A longitudinal safe distance is determined based on the real-time altitudes of the key unmanned aerial vehicle and the secondary unmanned aerial vehicle; The dynamic shortest safe distance is determined based on the lateral safe distance and the longitudinal safe distance.

6. The method of claim 3, wherein, The real-time flight task is constrained based on the dynamic shortest safe distance, the weather condition of the warning time period and / or the task priority of the real-time flight task of the target unmanned aerial vehicle within the warning time period, to obtain an adjusted flight task, including: A candidate task is generated based on the dynamic shortest safe distance and the weather condition of the warning time period; The candidate tasks are compared with each other by using a conflict detection algorithm to determine conflict tasks; The conflict tasks are adjusted based on the task priority, the first task with the highest task priority in the conflict tasks is kept unchanged, and the second task with other task priorities is adjusted to obtain the adjusted flight task.

7. The method of claim 1, wherein, The flight tasks of each unmanned aerial vehicle are adjusted based on the flight data and the weather condition, including: In the case that the flight task in the flight data is a rescue task, the thunderstorm area boundary, the moving speed and the influence time limit in the weather condition are combined with the real-time position, the destination position and the real-time flight speed in the flight data to generate a candidate direct flight path of a rescue unmanned aerial vehicle by using a three-dimensional path planning algorithm; The safe airspace range of the rescue unmanned aerial vehicle is determined based on the candidate direct flight path; The flight task of a to-be-evacuated unmanned aerial vehicle located in the safe airspace range is adjusted for evacuation.

8. An unmanned aircraft airspace scheduling apparatus, characterized by, The device includes: An acquisition module configured to acquire flight data and environmental data of an unmanned aerial vehicle; A division module configured to divide airspace into a core area, a buffer area and a free area based on the flight data; wherein the core area represents a flight route congestion degree greater than a first target degree; the free area represents a flight route congestion degree less than a second target degree; the buffer area represents a flight route congestion degree between the second target degree and the first target degree; and the first target degree is greater than the second target degree; A prediction module configured to predict a weather condition of the core area in a target time period based on the environmental data and shift data in the flight data; An adjustment module configured to adjust flight tasks of each unmanned aerial vehicle based on the flight data and the weather condition in the case that the weather condition is thunderstorm weather; A scheduling module configured to control and schedule the unmanned aerial vehicles based on the adjusted flight tasks.

9. An electronic device, comprising: The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 7.

Images