Unmanned aerial vehicle path planning method, device, equipment, storage medium and product

Abstract

The invention discloses an unmanned aerial vehicle path planning method, device and equipment, a storage medium and a product, and relates to the technical field of Internet of Things. According to the method, an edge core device obtains flow data and environment data of airspace grids, and a starting point airspace grid and a terminal point airspace grid of an unmanned aerial vehicle; determining the security degree of the airspace grids according to the environmental data, and performing type division to obtain the grid types of the airspace grids; and determining an initial main direction of each airspace grid according to the traffic data of the airspace grids and the grid type, and sending the initial main direction to the cloud platform device, so that the cloud platform device determines a feature main direction of the airspace grid of each edge core device. The edge core device receives the feature main direction and determines a target main direction of each airspace grid according to the initial main direction and the feature main direction; and determining the path of the unmanned aerial vehicle according to the target main directions of the starting point airspace grid, the end point airspace grid and the airspace grids. According to the embodiment of the invention, the safety of the path of the unmanned aerial vehicle is improved.

Description

Technical Field

[0001] This application belongs to the field of Internet of Things (IoT) technology, and in particular relates to a method, apparatus, device, storage medium, and product for drone path planning. Background Technology

[0002] With the development of IoT technology, existing technologies can enable remote control and scheduling of large numbers of drones by establishing a cloud scheduling platform based on the public internet. For example, businesses can receive order information through the cloud platform and remotely schedule drones for package delivery based on their location, status, and task requirements.

[0003] In existing technologies for drone path planning, base stations plan independent paths for each drone individually. This means the base station collects data and calculates the path for each connected drone separately, then sends the calculated path to the drone for remote control and scheduling. Because drone paths are irregular, the increased number of drones leads to an exponential increase in risks such as collision probability, computational power consumption, and airspace congestion. Therefore, existing drone path planning technologies offer relatively low path security. Summary of the Invention

[0004] This application provides a method, apparatus, device, and storage medium for drone path planning to address the problem of low path security in existing drone path planning methods.

[0005] In a first aspect, embodiments of this application provide a method for unmanned aerial vehicle (UAV) path planning, applied to edge core devices, the method comprising: Acquire traffic and environmental data from multiple airspace grids of edge core devices, as well as the starting and ending airspace grids of drones; The security level of each spatial grid is determined based on environmental data, and the spatial grids are classified according to the security level to obtain the grid type of each spatial grid. The initial main direction of each airspace grid is determined based on the traffic data and grid type of the airspace grid, and the initial main direction is sent to the cloud platform device so that the cloud platform device can determine the characteristic main direction of multiple airspace grids of multiple edge core devices based on the initial main direction of multiple airspace grids of multiple edge core devices and the navigation data of the UAV. Receive the feature main direction sent by the cloud platform device, and determine the target main direction of each spatial grid according to the initial main direction and the feature main direction; The path of the UAV is determined based on the target main direction of the UAV's starting airspace grid, ending airspace grid, and multiple airspace grids of the edge core equipment.

[0006] Secondly, embodiments of this application provide a method for unmanned aerial vehicle (UAV) path planning, applied to a cloud platform device, the method comprising: Receive the initial main direction of multiple spatial grids sent by the edge core device; Acquire navigation data of drones within the edge core device, and determine the main navigation direction of the drone within the edge core device based on the navigation data; The characteristic main direction of the spatial grid is determined based on the main navigation direction and the initial main direction of the spatial grid; The characteristic main direction of the airspace grid is sent to the edge core device so that the edge core device can determine the target main direction of each airspace grid based on the initial main direction and the characteristic main direction, and determine the path of the UAV based on the starting airspace grid, the ending airspace grid and the target main directions of multiple airspace grids of the edge core device.

[0007] Thirdly, embodiments of this application provide a device for unmanned aerial vehicle (UAV) path planning, applied to edge core equipment, the device comprising: The acquisition module is used to acquire traffic data and environmental data from multiple airspace grids of the edge core device, as well as the starting airspace grid and ending airspace grid of the drone. The partitioning module is used to determine the safety level of each spatial raster based on environmental data, and to classify the spatial raster into different types based on the safety level, thus obtaining the raster type of each spatial raster. The sending module is used to determine the initial main direction of each airspace grid based on the traffic data and grid type of the airspace grid, and send the initial main direction to the cloud platform device so that the cloud platform device can determine the characteristic main direction of multiple airspace grids of multiple edge core devices based on the initial main direction of multiple airspace grids of multiple edge core devices and the navigation data of the UAV. The receiving module is used to receive the feature main direction sent by the cloud platform device, and determine the target main direction of each spatial grid according to the initial main direction and the feature main direction; The determination module is used to determine the path of the UAV based on the target main direction of the UAV's starting airspace grid, ending airspace grid, and multiple airspace grids of the edge core device.

[0008] Fourthly, embodiments of this application provide an apparatus for unmanned aerial vehicle (UAV) path planning, applied to a cloud platform device, the apparatus comprising: The receiving module is used to receive the initial main directions of multiple spatial grids sent by the edge core device; The acquisition module is used to acquire navigation data of the UAV within the edge core device and determine the main navigation direction of the UAV within the edge core device based on the navigation data. The determination module is used to determine the characteristic main direction of the spatial grid based on the navigation main direction and the initial main direction of the spatial grid; The sending module is used to send the characteristic main direction of the airspace grid to the edge core device, so that the edge core device can determine the target main direction of each airspace grid based on the initial main direction and the characteristic main direction, and determine the path of the UAV based on the starting airspace grid, the ending airspace grid and the target main directions of multiple airspace grids of the edge core device.

[0009] Fifthly, embodiments of this application provide a terminal device, the device including: a processor and a memory storing computer program instructions; the processor executes the computer program instructions to implement a method for UAV path planning as described in the first or second aspect.

[0010] Sixthly, embodiments of this application provide a computer-readable storage medium storing computer program instructions that, when executed by a processor, implement a method for unmanned aerial vehicle path planning as described in the first or second aspect.

[0011] In a seventh aspect, embodiments of this application provide a computer program product in which instructions, when executed by a processor of an electronic device, cause the electronic device to perform a method for unmanned aerial vehicle path planning, as described in the first or second aspect.

[0012] This application provides a method, apparatus, device, storage medium, and product for UAV path planning. The method acquires traffic and environmental data from multiple airspace grids of an edge core device, as well as the UAV's starting and ending airspace grids; providing complete foundational data for subsequent safety calculations, direction planning, and path determination. The edge core device determines the safety level of each airspace grid based on the environmental data and classifies the airspace grids according to the safety level, obtaining the grid type for each airspace grid; ensuring that the classified grid types conform to the actual flight scenario. The edge core device determines the initial main direction of each airspace grid based on traffic data and grid type, and sends the initial main direction to the cloud platform device. After obtaining the initial main direction, the cloud platform device acquires the UAV's navigation data from the edge core device, determines the navigation main direction based on the navigation data, and determines the feature main direction based on the navigation main direction and the initial main direction, and sends it to the edge core device. By determining the initial main direction of the corresponding airspace grid, the edge core device ensures directional coordination within its local area, and simultaneously reports the initial direction to the cloud platform device. The cloud platform device coordinates the global directional coordination of multiple edge core devices, avoiding UAV flight direction conflicts. The edge core device receives the feature main direction and determines the target main direction of each airspace grid based on the feature main direction and the initial main direction. By coordinating the feature main direction and the initial main direction to determine the target main direction, the consistency and adaptability of direction planning are ensured while avoiding a disconnect between global and local directions. Finally, the edge core device determines the UAV's path based on the target main direction of each airspace grid, the UAV's starting airspace grid, and the UAV's ending airspace grid. The UAV's flight direction is the same as the target main direction, and the target main direction is determined based on traffic data. The generated path improves the UAV's flight safety while ensuring flight efficiency. Therefore, the embodiments of this application improve the safety of UAV path planning. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a schematic diagram of the structure of the UAV path planning system provided in the embodiments of this application; Figure 2 This is a flowchart illustrating the method for UAV path planning provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of the hexagonal spatial grid provided in the embodiments of this application; Figure 4 This is a schematic diagram illustrating the determination of a baseline according to an embodiment of this application; Figure 5 This is a schematic diagram of the structure of the reference grid provided in the embodiments of this application; Figure 6 This is a schematic diagram of the edge grid wall provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of a vertical waterway provided in an embodiment of this application; Figure 8 This is a flowchart illustrating a method for determining security level provided in an embodiment of this application; Figure 9 This is a schematic diagram of a grid with a defined main direction provided in an embodiment of this application; Figure 10 This is a schematic diagram of a multi-layer early warning structure provided in an embodiment of this application; Figure 11 This is a schematic diagram of the buffering mechanism provided in an embodiment of this application; Figure 12 This is a schematic diagram of the structure of the device for UAV path planning applied to edge core equipment provided in the embodiments of this application; Figure 13 This is a schematic diagram of the structure of the drone path planning device applied to cloud platform equipment provided in the embodiments of this application; Figure 14 This is a schematic diagram of the structure of the terminal device provided in the embodiments of this application. Detailed Implementation

[0015] The features and exemplary embodiments of various aspects of this application will be described in detail below. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit it. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0016] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes the element.

[0017] Existing drone control and scheduling solutions are generally divided into local area and public network scheduling solutions. In small-scale, localized drone applications, direct remote control operation or simple local area network-based scheduling systems are typically used. For example, in a small agricultural plantation, operators can directly control drones for pesticide spraying using remote controls, or use computer software connected to the local area network to perform simple task allocation and flight path planning for several drones. This approach is suitable for situations with a small number of drones, a limited flight range, and relatively simple tasks, but it suffers from limited control range, low scheduling efficiency, and difficulty in handling complex environments. With the development of drone technology and the expansion of application scenarios, public network remote scheduling solutions are gradually being adopted. Some large drone operating companies or organizations have established cloud scheduling platforms based on public networks to achieve remote control and scheduling of a large number of drones. For example, in the logistics and delivery field, companies can receive order information through a cloud platform and remotely schedule drones for package delivery based on the drone's location, status, and task requirements. This approach can overcome the limitations of local areas and achieve large-scale drone scheduling, but it has some problems, such as unstable public network signals that may cause control delays or interruptions, challenges in real-time monitoring and safety management of drones, and difficulty in accurately planning flight paths in complex environments.

[0018] However, regardless of whether it's a local area or public network remote dispatching solution, existing UAV control and dispatching systems suffer from several drawbacks. First, their airspace resource allocation and utilization are relatively simplistic, failing to adequately consider factors such as UAV flight performance and weather conditions. This leads to wasted or improperly allocated airspace resources, impacting UAV flight efficiency and mission execution effectiveness. Second, in terms of UAV flight direction planning, existing dispatching schemes often lack scientific and rational basis, failing to dynamically adjust flight directions based on factors such as UAV destination and traffic flow. This results in irrational flight direction planning, easily causing flight direction confusion, airway congestion, and other problems, reducing UAV flight safety and transportation efficiency. Furthermore, existing UAV control and dispatching schemes have weak perception and response capabilities to local environments, failing to acquire and process local environmental information such as weather changes and obstacle appearances in a timely manner. This impacts UAV flight safety and mission success rates in complex environments. Additionally, in multi-UAV collaborative operations, existing dispatching schemes face difficulties in data alignment and coordination. Inconsistencies in data formats and coordinate systems between different UAVs can hinder data sharing and collaborative work, reducing the overall system's operational efficiency. Finally, existing technologies often rely on direct communication between cluster base stations for scheduling large numbers of aircraft. This connection is unstable in wide-area scenarios and slows response times over long distances. Furthermore, deploying a large amount of core computing power would be wasteful. Therefore, existing technologies for UAV path planning offer relatively low path security.

[0019] To address the problems of existing technologies, embodiments of this application provide a method, apparatus, device, storage medium, and product for UAV path planning. The method acquires traffic and environmental data from multiple airspace grids of an edge core device, as well as the UAV's starting and ending airspace grids; providing complete foundational data for subsequent safety calculations, direction planning, and path determination. The edge core device determines the safety level of each airspace grid based on the environmental data and classifies the airspace grids according to the safety level, obtaining the grid type for each airspace grid; ensuring that the classified grid types conform to the actual flight scenario. The edge core device determines the initial main direction of each airspace grid based on traffic data and grid type, and sends the initial main direction to the cloud platform device. After obtaining the initial main direction, the cloud platform device acquires the UAV's navigation data from the edge core device, determines the navigation main direction based on the navigation data, and determines the feature main direction based on the navigation main direction and the initial main direction, and sends it to the edge core device. By determining the initial main direction of the corresponding airspace grid, the edge core device ensures directional coordination within its local area, and simultaneously reports the initial direction to the cloud platform device. The cloud platform device coordinates the global directional coordination of multiple edge core devices, avoiding UAV flight direction conflicts. The edge core device receives the feature main direction and determines the target main direction of each airspace grid based on the feature main direction and the initial main direction. By coordinating the feature main direction and the initial main direction to determine the target main direction, the consistency and adaptability of direction planning are ensured while avoiding a disconnect between global and local directions. Finally, the edge core device determines the UAV's path based on the target main direction of each airspace grid, the UAV's starting airspace grid, and the UAV's ending airspace grid. The UAV's flight direction is the same as the target main direction, and the target main direction is determined based on traffic data. The generated path improves the UAV's flight safety while ensuring flight efficiency. Therefore, the embodiments of this application improve the safety of UAV path planning.

[0020] The following section first introduces the UAV path planning system provided by the embodiments of this application, which is applied to the method of UAV path planning.

[0021] Figure 1 A schematic diagram of the structure of a drone path planning system according to an embodiment of this application is shown. Figure 1As shown, the system may include: a sensor layer 101, an edge core layer 102, and a cloud platform layer 103. The sensor layer 101 includes a sensor environment data acquisition module 1011. The edge core layer 102 includes an edge core navigation data acquisition module 1021, an edge core route map generation module 1022, and an edge core raster map generation module 1023. The cloud platform layer 103 includes a cloud platform navigation data acquisition module 1031, a cloud platform feature main direction extraction module 1032, a cloud platform feature main direction distribution module 1033, a basin scene processing module 1034, an emergency handling module 1035, and a main direction generation algorithm module 1036.

[0022] Specifically, the sensor environment data acquisition module 1011 is used to collect multi-dimensional raw environmental data of the airspace grid. The edge core navigation data acquisition module 1021 is used to collect navigation-related data of UAVs within the jurisdiction; the edge core route map generation module 1022 is used to generate a route distribution map of the jurisdictional airspace based on local data, clarifying the priority flight direction and route attributes of each grid; and the edge core grid map generation module 1023 is used to generate a three-dimensional grid attribute map of the jurisdictional airspace. The cloud platform navigation data acquisition module 1031 is used to aggregate navigation data from multiple edge cores; the cloud platform feature main direction extraction module 1032 is used to calculate the feature main direction of each edge core based on global navigation requirements and local initial main directions; the cloud platform feature main direction distribution module 1033 is used to distribute the calculated feature main direction to the corresponding edge core; the basin scene processing module 1034 is used to develop path planning strategies for the special environment of basin terrain; the emergency handling module 1035 is used to handle emergencies at the global level, dynamically adjust system strategies, and ensure system stability; and the main direction generation algorithm module 1036 is used to provide the core logic support for feature main direction calculation.

[0023] The method for UAV path planning provided in the embodiments of this application is described below.

[0024] Figure 2 This illustration shows a flowchart of a method for unmanned aerial vehicle (UAV) path planning according to one embodiment of this application. Figure 2 As shown, the method may include the following steps: S201 to S205.

[0025] S201, the edge core device acquires traffic data and environmental data from multiple airspace grids of the edge core device, as well as the starting airspace grid and ending airspace grid of the UAV.

[0026] Among them, the edge core device is a terminal device that integrates communication, environmental perception and computing power processing functions; the airspace grid is a three-dimensional spatial unit that divides the airspace according to a preset size; the traffic data is the passage data of UAVs within the airspace grid; the environmental data is the external environmental information data that affects the flight safety of UAVs in the airspace grid; the starting airspace grid and the ending airspace grid are the airspace grids where UAVs depart and arrive, respectively.

[0027] In some embodiments, the edge core device collects environmental data through associated sensing devices, obtains traffic data of UAVs passing through the airspace grid through wireless communication links with UAVs or historical stored data, and receives the starting airspace grid and ending airspace grid sent by UAVs. Finally, it organizes the data into a structured dataset according to the grid number.

[0028] In some embodiments, the edge core device may include at least a communication base station, an environmental observation group, and a meteorological observation group. The communication base station is used for network coverage, the environmental observation group is used for measuring air hazards, and the meteorological observation group is used for measuring air hazard such as air currents and cyclones. Each part needs to cover the area covered by the grid.

[0029] This application embodiment acquires traffic data, environmental data, and the starting and ending airspace grids of the UAV from the airspace grid. The acquired data covers all dimensions of airspace status (traffic data), safety risks (environmental data), and flight targets (starting and ending airspace grids), providing a precise and complete data foundation for subsequent steps.

[0030] In some embodiments, such as Figure 3 As shown, the spatial grid can be a hexagonal prism grid, and the spatial grid is a rectangular grid that is wider horizontally (i.e., in the x, y coordinate direction) than vertically (i.e., in the z-axis coordinate direction).

[0031] The embodiments of this application use hexagonal prism grids, which, compared with the square grids commonly used in existing UAV path planning methods, shorten the path length by an average of about 12.5% ​​in terms of spatial continuity, reduce the diffusion simulation error of meteorological parameters to 1 / √3 times that of square grids, and improve the parameter transfer efficiency by 22%-35% due to the uniformity of the hexagonal neighborhood system in terms of safety calculation efficiency.

[0032] S202, the edge core device determines the security level of each spatial grid based on environmental data, and classifies the spatial grids according to the security level to obtain the grid type of each spatial grid.

[0033] Among them, the safety level of the airspace grid is an indicator that quantifies the flight safety of the empty grid; the grid type of the airspace grid is a flight permit type classified according to the safety level.

[0034] In some embodiments, the grid type may include a flyable grid, a changeable-layer grid, and a no-fly grid; wherein, a flyable grid is an airspace grid that allows drones to fly horizontally, a changeable-layer grid is an airspace grid that allows drones to change course vertically, and a no-fly grid is an airspace grid that prohibits drones from flying.

[0035] In one example, airspace grids with a safety score below 0.3 are designated as no-fly grids. A safety score below 0.3 indicates poor safety for these grids, posing a higher risk to drones flying within them; therefore, they are designated as no-fly grids. Airspace grids with a safety score above 0.6 are designated as layer-changeable grids. When drones perform vertical lane changes, they need to switch between different altitude layers, requiring a higher level of airspace safety. Therefore, airspace grids with a safety score above 0.6 are designated as layer-changeable grids. Airspace grids with a safety score between 0.3 and 0.6 are designated as flyable grids. When drones fly horizontally, the safety requirement is lower than for vertical lane changes but higher than for no-fly zones; therefore, airspace grids with a safety score between 0.3 and 0.6 are designated as flyable grids.

[0036] This application embodiment divides the airspace grid into grid types according to the level of safety, which can adapt to the safety requirements of different flight scenarios of UAVs and ensure that the flight activities of UAVs match the airspace risk situation.

[0037] S203, the edge core device determines the initial main direction of each spatial grid based on the traffic data and grid type of the spatial grid, and sends the initial main direction to the cloud platform device.

[0038] The initial main direction is the initial grid flight direction determined based on the local flow data of the airspace grid and the grid type.

[0039] In some embodiments, for each airspace grid, multiple flight directions that allow UAVs to fly are determined according to the grid type of the airspace grid, and multiple flight directions are selected according to traffic data to determine the flight direction with the highest traffic volume as the initial main direction of each airspace grid.

[0040] This application embodiment determines the initial main direction of the airspace grid based on the traffic data and grid type of the airspace grid. The traffic data ensures that the determined initial main direction meets the passage requirements of the UAV in the airspace grid, and the grid type limits the initial main direction to ensure that the initial main direction meets the safety requirements.

[0041] S204, the cloud platform device receives the initial main direction of multiple spatial grids sent by the edge core device.

[0042] Among them, the cloud platform device is the core device responsible for the global scheduling of multiple edge core devices; the initial main direction of multiple spatial grids sent by the edge core devices received by the cloud platform is the initial main direction of the spatial grids under the jurisdiction of the edge core devices in different regions.

[0043] A single edge device can only grasp the directional situation of a local area. The cloud platform device in this application embodiment receives the initial main direction of multiple airspace grids sent by the edge core device, and unifies and converges the local directions of multiple edge core devices to achieve the unification of global direction data, thereby avoiding cross-regional flight conflicts caused by isolated direction planning in different areas.

[0044] In some embodiments, the cloud platform device receives the initial master direction of the edge grid located at the intersection of multiple edge core devices, for use in subsequently determining the global feature master direction of the edge grid of the edge core device based on the initial master direction and navigation master direction of each edge grid.

[0045] This application embodiment only performs global unified processing on the edge grids at the boundary line between the edge core and the edge core, and does not intervene in all airspace grids. It focuses on the high-incidence area of ​​conflict in the boundary edge grids of cross regions. The internal grids of the edge core are still determined by the edge core equipment based on the edge grids. This eliminates the confusion of flight direction across regions and avoids the management redundancy caused by global processing of all airspaces.

[0046] S205, the cloud platform device acquires the navigation data of the drone in the edge core device, and determines the main navigation direction of the drone in each edge core device based on the navigation data.

[0047] Among them, the navigation data of the UAV is the flight data of the UAV passing through the edge core equipment area; the main navigation direction is the main direction determined based on the overall flight direction of the UAV's navigation data.

[0048] In some embodiments, determining the main navigation direction of the UAV within the edge core device based on navigation data may include: determining the starting coordinates and ending coordinates of all UAVs based on the UAVs' navigation data, determining the flight direction of the UAVs based on the direction from the starting coordinates to the ending coordinates, and selecting the flight direction with the most occurrences as the main navigation direction of the corresponding edge core device.

[0049] The embodiments of this application determine the main navigation direction of the UAV within the edge core device based on the UAV's navigation data. The main navigation direction can reflect the global flight requirements, avoiding the problem that the main direction determined by the local traffic data of the airspace grid deviates from the global flight direction requirements of the UAV.

[0050] S206, the cloud platform device determines the characteristic main direction of the spatial grid of the edge core device based on the navigation main direction of each edge core device and the initial main direction of multiple spatial grids.

[0051] Among them, the feature principal direction is the global principal direction of the spatial grid obtained by the cloud platform device based on the coordination of the global navigation principal direction and the local initial principal direction.

[0052] In some embodiments, the cloud platform device compares the navigation main direction of each edge core device with the initial main direction of all spatial grids reported by the device one by one, and determines the feature main direction of each spatial grid corresponding to each edge core device based on the navigation main direction and the initial main direction.

[0053] This application embodiment determines the feature main direction by combining the navigation main direction and the initial main direction, and then determines the global feature main direction by combining the local initial main direction of the edge core device, making the global feature main direction more scenario-specific and improving the global coordination of the generated feature main direction.

[0054] S207, the cloud platform device sends the main direction of the spatial grid features to the edge core device.

[0055] In this embodiment, the cloud platform device sends the main feature direction of each generated spatial grid to the corresponding edge core device, ensuring that the edge core device obtains the main feature direction of each spatial grid in a timely manner, so as to adjust the main direction of the spatial grid according to the global coordination direction and ensure the global coordination effect.

[0056] S208, the edge core device receives the feature main direction sent by the cloud platform device, and determines the target main direction of each spatial grid according to the initial main direction and the feature main direction.

[0057] Among them, the target main direction is the grid flight direction finally determined by fusing the initial main direction and the feature main direction.

[0058] In some embodiments, the direction difference between the initial principal direction and the characteristic principal direction can be calculated, and the final target principal direction can be determined based on the initial principal direction, the characteristic principal direction, and the direction difference.

[0059] This application embodiment determines the target main direction by combining the initial main direction and the feature main direction, making the direction planning more in line with the local dynamic scene, ensuring the uniformity of the global direction, and flexibly adapting to local dynamic changes.

[0060] S209, the edge core device determines the path of the UAV based on the starting airspace grid, the ending airspace grid, and the target main direction of multiple airspace grids of the edge core device.

[0061] In some embodiments, the starting airspace grid of the UAV can be used as the flight starting point, and a continuous path to the ending airspace grid of the UAV can be selected sequentially according to the target main direction of multiple airspace grids to obtain the path of the UAV.

[0062] The target main direction in this embodiment is set based on the safety level of the airspace grid. The path of the UAV is determined according to the starting airspace grid, the ending airspace grid and the target main direction. This ensures that the obtained path has a high degree of fit with the required flight direction of the UAV, while also ensuring that the flight path of the UAV complies with the safety level restrictions of different airspace grids, thereby improving the safety of the generated UAV path.

[0063] In some embodiments, before the edge core device acquires traffic data and environmental data from multiple airspace grids of the edge core device, as well as the originating airspace grid and the destination airspace grid of the UAV, the method may further include: Obtain the average altitude of the area corresponding to the edge core device, and determine the baseline of the reference grid in the spatial grid based on the average altitude; The intersecting grids at the baseline height, located on the boundary line of the edge core device, are selected as the reference grids of the edge core device. Based on the reference grids, they are numbered sequentially according to the top and bottom and the six horizontal directions of the hexagon, and the grids are aligned to obtain the encoding information of all spatial grids.

[0064] In some embodiments, such as Figure 4 As shown, the baseline can be the height obtained by adding the average altitude to the preset altitude.

[0065] In some embodiments, the encoding information may include: Raster coordinates = longitude (12 bits) + latitude (12 bits) + altitude (8 bits); Direction code = Angle quantization value (4 bits, accuracy ±5°) + Channel ID (2 bits); Grid ID = Base station ID (8 bits) + neighboring base station (16 bits) + altitude level (2 bits) + six-way level number.

[0066] In one example, the encoding method using six-way direction vectors is as follows: Figure 5 As shown, the grid with the code (00,0,0,0,0,0,0) is the reference grid, the grid with the code (00,0,1,0,0,0,0) is the grid in the second direction of the reference grid, and the grid with the code (00,0,0,0,1,0,0) is the grid in the fourth direction of the reference grid.

[0067] In one example, the numbering method using up and down and six directions is as follows: Figure 6As shown, the reference corner grid on the baseline serves as the reference. Reference grids and ordinary grids are sequentially extended and numbered in six horizontal directions. Edge grids are defined in the vertical direction, ultimately constructing an edge grid wall between adjacent grids of the base station. Reference corner grid A is numbered (Base Station Number, Layer 0, 0,0,0,0,0,0). Reference grid A is the grid of the reference corner grid in the third direction, hence its numbering is (Base Station Number, Layer 0, 0,0,1,0,0,0). Ordinary grid A is the grid of the reference corner grid in the fourth direction, hence its numbering is (Base Station Number, Layer 0, 0,0,0,1,0,0). Reference grid B is the grid of the reference corner grid in the fifth direction, hence its numbering is (Base Station Number, Layer 0, 0,0,0,0,1,0). The grid below reference grid B is edge grid A, which, being located one layer below the reference corner grid, is numbered (Base Station Number, Layer 1, 0,0,0,0,0,0), and so on.

[0068] In some embodiments, the vertical flight path of the airspace grid is as follows: Figure 7 As shown, the grid cells labeled with the main direction vector on the upper layer are interchangeable grid cells. The main direction vector is the horizontal flight direction of the interchangeable grid cells. The main direction of the grid cells within the same flight path is continuous, meaning that the main direction of the grid cells below the interchangeable grid cells is the same in the horizontal direction, thus avoiding the directional conflict problem that the UAV needs to make sharp turns.

[0069] In some embodiments, the density of the airspace grid is allowed to decrease from top to bottom. Because there are fewer aerial obstructions in urban scenarios when dividing airways, but more likely obstructions near the ground, safety and road continuity are correspondingly reduced. Therefore, the density of available grid cells in the vertical direction is planned to decrease. For example, the upper layer (50m-30m) is the high-capacity main airway with more airspace grid cells, the middle layer (30m-15m) is the transition layer, and the bottom layer (below 15m) is the terminal connection layer with fewer airspace grid cells.

[0070] In some embodiments, such as Figure 8 As shown, the environmental data includes the number of real-time devices, three-dimensional wind field vector values, obstacle threat coefficients, communication signal quality, and meteorological parameters. The security level of each airspace grid is determined based on the environmental data, which may include: S801 to S803.

[0071] S801, the edge core device determines the remaining load value of the device based on the real-time number of devices and the preset maximum number of devices of the edge core device.

[0072] Among them, the real-time device count is the number of drones currently flying within the airspace grid; the device remaining load value is the drone carrying capacity of the airspace grid.

[0073] In some embodiments, the formula for calculating the remaining load value of the device can be summarized as follows: in, This represents the remaining load value of the equipment. This represents the number of devices in real time. Set the maximum number of devices to preset.

[0074] S802, the edge core device determines the wind field stability value based on the three-dimensional wind field vector value and the set threshold.

[0075] Among them, the three-dimensional wind field vector value is a physical quantity that describes the three-dimensional motion state of the wind within the grid; the wind field stability value is a value of wind field stability obtained by comparing the three-dimensional wind field vector value with a set threshold.

[0076] In some embodiments, the formula for calculating the wind field stability value can be: in, Here, w represents the stable wind field value, and w represents the three-dimensional wind field vector value. To set a threshold.

[0077] S803, the edge core equipment determines the security level of the corresponding airspace grid by multiplying at least one of the following: equipment remaining load value, wind field stability value, obstacle threat coefficient, communication signal quality, and meteorological parameters, by a preset weighting coefficient.

[0078] Among them, the obstacle threat coefficient is a quantitative value of the degree of impact of obstacles within the airspace grid on flight safety; the communication signal quality is the quality value of the communication link between the UAV and the edge core equipment; and the meteorological parameters are the meteorological parameter values ​​that affect the flight of the UAV.

[0079] This application embodiment quantifies the security level by weighting multidimensional environmental data, thereby achieving an accurate assessment of the security level of the spatial raster.

[0080] In some embodiments, when the obstacle threat factor exceeds a set threshold—that is, when the sensor detects a clear danger, such as airflow speed exceeding a safety threshold or identifying a large obstacle—a no-fly mechanism is directly triggered and transmitted to the edge core device via a high-privilege interrupt. The edge core device immediately generates a no-fly instruction and sends it to all drones within the relevant grid via a high-speed communication link, ensuring they quickly stop flying or avoid the danger zone. In other words, in the dynamic airspace matrix, the corresponding grid is set as a no-fly zone.

[0081] In some embodiments, when the change in the obstacle threat coefficient exceeds a set threshold, a high-privilege interrupt is triggered and transmitted to the edge core device. The edge core device performs a security degree calculation and prioritizes the relevant grids. The edge core marks these grids as high priority, recalculates their security degree, and generates corresponding instructions based on the calculation results.

[0082] In some embodiments, the grid types include flyable grids, interchangeable grids, and no-fly grids. The main direction of flyable grids is horizontal, and the main direction of interchangeable grids is vertical. Determining the initial main direction of each airspace grid based on the airspace grid's traffic data and grid type may include: When the airspace grid is a flyable grid, the edge core equipment determines the horizontal direction with the highest traffic frequency as the initial main direction of the airspace grid based on the traffic data of the airspace grid in the horizontal direction. When the spatial grid is a replaceable grid, the edge core device determines the vertical direction with the highest traffic frequency as the initial main direction of the spatial grid based on the vertical traffic data of the spatial grid.

[0083] This application's embodiments divide the airspace into grids based on safety levels and limit the main direction of different airspace grid types, avoiding conflicts between the horizontal flight and vertical lane-changing functions of the airspace grids and improving the rationality of airspace utilization. Furthermore, determining the main direction based on traffic frequency meets the traffic needs of UAVs and can improve airspace traffic efficiency.

[0084] In one example, for flyable grids, the frequency of passage in the horizontal direction (east, south, west, north, northeast, southeast, northwest, southwest) is counted, and the direction with the highest frequency is selected as the initial main direction; for grids with interchangeable layers, the frequency of passage in the vertical direction (up and down) is counted, and the direction with the highest frequency is selected as the initial main direction.

[0085] In some embodiments, determining the target main direction of each spatial grid cell based on the initial main direction and the feature main direction may include: If the directional deviation between the initial main direction and the feature main direction of the spatial grid does not exceed a set threshold, the edge core device determines the feature main direction as the target main direction of the spatial grid. When the directional deviation between the initial principal direction and the characteristic principal direction of the spatial grid exceeds a set threshold, the edge core device determines the target principal direction of the spatial grid based on the initial principal direction, the characteristic principal direction, and the preset weight parameters.

[0086] In this embodiment, the initial principal direction and the feature principal direction are differentiated based on the direction deviation value. When the deviation value is relatively small, the feature principal direction is selected to ensure global coordination. When the deviation is large, the feature principal direction and the initial principal direction are combined for weighted fusion, so that the target principal direction achieves a balance between the global feature principal direction and the local initial principal direction.

[0087] In some embodiments, such as Figure 9As shown, the target main direction of each spatial grid needs to meet the direction constraint requirements, that is, the main direction of the next spatial grid that the current spatial grid points to can only be forward, left-forward, and right-forward, while backward, left-backward, and right-backward directions are prohibited directions.

[0088] In some embodiments, determining the path of the UAV based on the target main direction of the UAV's starting airspace grid, ending airspace grid, and multiple airspace grids of the edge core device may include: The edge core equipment determines multiple candidate paths based on the starting point airspace grid and the ending point airspace grid, where all the passing airspace grids are of a preset grid type. Among them, the candidate paths are all feasible routes from the starting point grid to the ending point grid, passing through grids that are either flyable or can be changed in layer. For each candidate path, the edge core device determines the matching degree between the candidate path and the UAV based on the target main direction of the airspace grid in the candidate path and the UAV's heading; where the matching degree is the degree of fit between the target main direction of each grid in the candidate path and the UAV's heading. The edge core device selects the candidate path with the highest sum of matching degree of all airspace grids and the shortest path length as the path of the UAV; where the path length is the number of airspace grids in the candidate path.

[0089] This application embodiment selects the candidate path with the highest sum of airspace grid matching degree and the shortest path length from multiple candidate paths. A high sum of matching degree indicates that the candidate path matches the flight direction of the UAV, avoiding flight conflicts between UAVs and thus ensuring the safety of the generated UAV path.

[0090] In some embodiments, the formula for selecting the candidate path with the highest sum of matching degrees can be: Where i represents the main direction of the current grid, j represents the grid coordinates, W(i) is the flow weight in that direction, and a is a special weight.

[0091] In some embodiments, the method may further include: The edge core device obtains the computing load value of the edge core device; where the computing load value is the current computing resource utilization rate of the edge core device. When the computing load value of the edge core device exceeds the set threshold, it sends an early warning message to the cloud platform device. The early warning message includes the computing load value that exceeds the set threshold. The cloud platform equipment receives early warning information sent by the edge core equipment; The cloud platform device obtains the computing power redundancy edge core devices adjacent to the edge core device, and allocates the computing power load value exceeding the set threshold to the computing power redundancy edge core devices; wherein, the computing power redundancy edge core device is the edge device whose current computing power load value is lower than the set redundancy threshold.

[0092] Edge core devices have limited computing power. If the number of drones surges or the complexity of tasks increases, it can easily lead to overload and response delays. This application embodiment coordinates adjacent redundant devices through a cloud platform to share the load, ensuring the stable operation of edge core devices and making full use of the redundant computing power of adjacent devices to avoid wasting computing power.

[0093] In some embodiments, the formula for calculating the computing load value of the edge core device can be: in, The computing power requirement for a single computing core is given by H, where H is the spatial height, R is the horizontal coverage radius of the base station, and d is the grid side length. The directional coding efficiency factor is determined by the degree of discretization optimization of the hexagonal main directional coding, and its value ranges from 0.8 to 1.2. The directional weights are dynamically adjusted based on airway traffic statistics to ensure that the sum of the weights of all facets is 0. It has a unidirectional encoding complexity; For safety redundancy coefficient, To update the frequency in real time.

[0094] In some embodiments, the formula for calculating the directional coding efficiency factor can be: in, This represents the maximum angular deviation between adjacent principal directions.

[0095] In some embodiments, the formula for calculating the complexity of unidirectional coding can be: Among them, BW k Q represents the spectral bandwidth in that direction. mod R is the modulation order. error This is the bit error rate threshold.

[0096] In some embodiments, the formula for calculating the safety redundancy factor can be: in, V represents the number of obstacles per unit volume. wind This refers to wind speed.

[0097] In some embodiments, the cloud platform device may also identify the main direction of the reported computing power core and provide connection warnings for cores surrounding the reported core and multi-level cores connected along the main direction, such as... Figure 10 As shown, there are 11 airspace grids in total, extending two levels down from the core and main direction of the surrounding area.

[0098] In wide-area UAV flight path planning, there are basin scenarios, such as city squares, depressions, residential areas, and urban building clusters, where there are height differences around large open areas. Directly using shortest path or ant colony algorithms for UAV route planning may lead to underutilization of airspace resources and localized congestion within the basin. Introducing dynamic traffic detection for path planning could result in a large number of devices accumulating within the basin and being unable to leave for extended periods, creating potential field traps and posing significant safety hazards. Furthermore, introducing dynamic parameter tuning and frame-based scheduling platforms would require substantial computing resources on the edge side.

[0099] In some embodiments, the method may further include: When the area where the airspace grid is located is a preset area, the edge core device determines the safety threshold of the airspace grid based on the traffic data of the airspace grid in the preset area; where the preset area is a preset special terrain area; the safety threshold is a safety threshold value customized for the preset area and divided into grid types.

[0100] When the security level of the spatial grid in a preset area is greater than the security threshold, the edge core device determines the grid type of the spatial grid as the first grid type; wherein, the first grid type is the preset grid type when the security level in the preset area exceeds the security threshold.

[0101] In some embodiments, when the edge core device is located in a preset area within a spatial grid, determining the security threshold of the spatial grid based on the traffic data of the spatial grid in the preset area requires determining whether the area where the spatial grid is located is a preset area. Specifically, this may include: After generating a spatial raster from a real-world scan of a fixed building, a depth-first traversal of the horizontal planes of each layer is performed on the generated raster in the vertical direction for regional connectivity analysis. Within each layer, starting with a regular raster covered by a single base station, the horizontal connectivity of adjacent rasteres is recursively traversed. All interconnected raster clusters are marked. Independent clusters that cannot be connected to edge raster walls via horizontal movement, or congested clusters where the connection path occupies too small a proportion of the cluster's raster area, are marked as preset areas, i.e., dead-end areas. Clusters at critical values ​​are marked as key areas and prioritized for traversal during real-time calculations.

[0102] In one example, the scheduling settings for the dead end area are shown in Table 1.

[0103] Table 1. Scheduling Settings for the Head-Cutting Scheme In some embodiments, the security threshold of the spatial raster is determined based on the traffic data of the spatial raster in a preset area, and the formula can be: In one example, the preset area is the decapitation area, such as... Figure 11 As shown, during low flow, real-time monitoring of existing replaceable grids is activated, and the device connectivity weight in the S-safety calculation mentioned above is reduced, allowing more devices to exist in the replaceable grid. Then, the speed and heading angle deviation tolerances of aircraft within the grid are forcibly limited. During medium flow, the safety threshold is reduced in the dead zone, and a three-layer buffer zone centered on the replaceable grid is established. The speed density threshold within the third layer is increased, the heading within the second layer is locked to a certain angle range of the replaceable direction, and the speed is forcibly limited in the core layer. During high flow, the safety threshold is reduced in the dead zone, the replaceable grid is modified to a forced replaceable grid, and its vertical projection layer corresponding to the grid's main direction is forcibly set to the vertical axis. The offset tolerance is reduced, and speed is limited throughout the entire area. The three-layer buffer mechanism remains unchanged during medium flow. The second layer is set as a normal replaceable grid, and the speed limits of the second and third layers are further reduced. Since the main direction of the replaceable grid is fixed, the contact speed is limited.

[0104] Figure 12 This application illustrates a drone path planning device 1200, applied to an edge core device. The device may include: The acquisition module 1201 is used to acquire traffic data and environmental data of multiple airspace grids of the edge core device, as well as the starting airspace grid and ending airspace grid of the UAV. The partitioning module 1202 is used to determine the safety level of each spatial grid based on environmental data, and to partition the spatial grid according to the safety level to obtain the grid type of each spatial grid. The sending module 1203 is used to determine the initial main direction of each airspace grid according to the traffic data and grid type of the airspace grid, and send the initial main direction to the cloud platform device, so that the cloud platform device can determine the characteristic main direction of multiple airspace grids of multiple edge core devices according to the initial main direction of multiple airspace grids of multiple edge core devices and the navigation data of UAV. The receiving module 1204 is used to receive the feature main direction sent by the cloud platform device, and determine the target main direction of each spatial grid according to the initial main direction and the feature main direction; The determination module 1205 is used to determine the path of the UAV based on the target main direction of the UAV's starting airspace grid, ending airspace grid, and multiple airspace grids of the edge core device.

[0105] In some embodiments, the determining module 1205 is further configured to determine the remaining load value of the device based on the real-time number of devices and the preset maximum number of devices of the edge core device; The determination module 1205 is also used to determine the wind field stability value based on the three-dimensional wind field vector value and the set threshold. The determination module 1205 is also used to determine the safety level of the corresponding airspace grid by multiplying at least one of the equipment remaining load value, wind field stability value, obstacle threat coefficient, communication signal quality and meteorological parameters and a preset weighting coefficient.

[0106] In some embodiments, the determining module 1205 is further configured to determine the horizontal direction with the highest traffic frequency as the initial main direction of the airspace grid when the airspace grid is a flyable grid. The determination module 1205 is also used to determine the initial main direction of the spatial grid as the vertical direction with the highest traffic frequency based on the vertical traffic data of the spatial grid when the spatial grid is a replaceable layer grid.

[0107] In some embodiments, the determining module 1205 is further configured to determine the feature main direction as the target main direction of the spatial grid if the directional deviation between the initial main direction and the feature main direction of the spatial grid does not exceed a set threshold. The determination module 1205 is also used to determine the target main direction of the spatial grid based on the initial main direction, the feature main direction, and the preset weight parameters when the directional deviation between the initial main direction and the feature main direction of the spatial grid exceeds a set threshold.

[0108] In some embodiments, the drone path planning apparatus 1200 may further include: The determination module 1205 is also used to determine multiple candidate paths whose path spatial grids are all preset grid types, based on the starting point spatial grid and the ending point spatial grid. The determination module 1205 is also used to determine the matching degree between the candidate path and the UAV for each candidate path based on the target main direction of the airspace grid in the candidate path and the UAV's heading. The selection module is used to select the candidate path with the highest sum of matching degrees among all airspace grids and the shortest path length as the path for the UAV.

[0109] In some embodiments, the acquisition module 1201 is further configured to acquire the computing load value of the edge core device; The sending module 1203 is also used to send a warning message to the cloud platform device when the computing load value exceeds a set threshold. The warning message includes the computing load value exceeding the set threshold, so that the cloud platform device can allocate the computing load value of the edge core device exceeding the set threshold to the computing power redundant edge core device adjacent to the edge core device.

[0110] In some embodiments, the determining module 1205 is further configured to determine the safety threshold of the spatial grid based on the traffic data of the spatial grid in the preset area when the area where the spatial grid is located is a preset area. The determining module 1205 is also used to determine the grid type of the spatial grid as the first grid type when the security level of the spatial grid in the preset area is greater than the security threshold.

[0111] Figure 12 The various modules in the illustrated device can achieve Figure 2 The various steps involved, and the corresponding technical effects achieved, will not be elaborated upon here for the sake of brevity.

[0112] Figure 13 This application illustrates an embodiment of a drone path planning device 1300, applied to a cloud platform device. The device may include: The receiving module 1301 is used to receive the initial main direction of multiple spatial grids sent by the edge core device; The acquisition module 1302 is used to acquire navigation data of the UAV within the edge core device and determine the main navigation direction of the UAV within the edge core device based on the navigation data. The determination module 1303 is used to determine the characteristic main direction of the airspace grid based on the main navigation direction and the initial main direction of the airspace grid; The sending module 1304 is used to send the characteristic main direction of the airspace grid to the edge core device, so that the edge core device can determine the target main direction of each airspace grid according to the initial main direction and the characteristic main direction, and determine the path of the UAV according to the starting airspace grid, the ending airspace grid and the target main directions of multiple airspace grids of the edge core device.

[0113] In some embodiments, the receiving module 1301 is further configured to receive warning information sent by the edge core device, the warning information including a computing load value exceeding a set threshold; The acquisition module 1302 is also used to acquire the computing power redundant edge core devices adjacent to the edge core devices, and to allocate computing power load values ​​exceeding a set threshold to the computing power redundant edge core devices.

[0114] Figure 13 The various modules in the device shown can achieve Figure 2 The various steps involved, and the corresponding technical effects achieved, will not be elaborated upon here for the sake of brevity.

[0115] Figure 14 A schematic diagram of the hardware structure of the terminal device provided in an embodiment of this application is shown.

[0116] The terminal device may include a processor 1401 and a memory 1402 storing computer program instructions.

[0117] Specifically, the processor 1401 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0118] Memory 1402 may include mass storage for data or instructions. For example, and not limitingly, memory 1402 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. In one instance, memory 1402 may include removable or non-removable (or fixed) media, or memory 1402 may be non-volatile solid-state memory. Memory 1402 may be internal or external to the integrated gateway disaster recovery device.

[0119] In one example, memory 1402 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Thus, typically, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform operations described with reference to the method of UAV path planning according to this disclosure.

[0120] Processor 1401 reads and executes computer program instructions stored in memory 1402 to achieve... Figure 2 The method for drone path planning in the illustrated embodiment.

[0121] In one example, the terminal device may also include a communication interface 1403 and a bus 1404. For example, Figure 14 As shown, the processor 1401, memory 1402, and communication interface 1403 are connected through bus 1404 and complete communication with each other.

[0122] The communication interface 1403 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0123] Bus 1404 includes hardware, software, or both, that couples components of an end device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 1404 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, this application contemplates any suitable bus or interconnect.

[0124] Furthermore, in conjunction with the UAV path planning method in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the UAV path planning methods in the above embodiments.

[0125] This application also provides a computer program product, including a computer program that, when executed, implements any of the UAV path planning methods described in the above embodiments.

[0126] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0127] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or text segments used to perform the required tasks. Programs or text segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, read-only memory (ROM), flash memory, erasable read-only memory (EROM), floppy disks, compact disc read-only memory (CD-ROM), optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Text segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0128] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0129] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0130] The above are merely specific embodiments of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method for unmanned aerial vehicle (UAV) path planning, characterized in that, Applied to edge core devices, the method includes: Acquire traffic and environmental data from multiple airspace grids of the edge core device, as well as the starting and ending airspace grids of the UAV. The security level of each spatial grid is determined based on the environmental data, and the spatial grid is classified according to the security level to obtain the grid type of each spatial grid. The initial main direction of each airspace grid is determined based on the traffic data and grid type of the airspace grid, and the initial main direction is sent to the cloud platform device so that the cloud platform device can determine the characteristic main direction of the airspace grid of each edge core device based on the initial main directions of multiple airspace grids of multiple edge core devices and the navigation data of the UAV. Receive the feature main direction sent by the cloud platform device, and determine the target main direction of each spatial grid according to the initial main direction and the feature main direction; The path of the UAV is determined based on the target main direction of the UAV's starting airspace grid, ending airspace grid, and multiple airspace grids of the edge core device.

2. The method for UAV path planning according to claim 1, characterized in that, The environmental data includes the number of real-time devices, three-dimensional wind field vector values, obstacle threat coefficients, communication signal quality, and meteorological parameters. Determining the security level of each airspace grid based on the environmental data includes: The remaining load value of the devices is determined based on the real-time number of devices and the preset maximum number of devices in the edge core devices. The wind field stability value is determined based on the three-dimensional wind field vector value and the set threshold. The safety level of the corresponding airspace grid is determined by multiplying at least one of the following: the remaining load value of the equipment, the wind field stability value, the obstacle threat coefficient, the communication signal quality, and the meteorological parameters, by a preset weighting coefficient.

3. The method for UAV path planning according to claim 1, characterized in that, The grid types include flyable grids, interchangeable-layer grids, and no-fly grids. The main direction of the flyable grid is horizontal, and the main direction of the interchangeable-layer grid is vertical. Determining the initial main direction of each airspace grid based on the airspace grid's traffic data and grid type includes: When the airspace grid is a flyable grid, the horizontal direction with the highest traffic frequency is determined as the initial main direction of the airspace grid based on the traffic flow data of the airspace grid in the horizontal direction. When the spatial grid is a replaceable layer grid, the vertical direction with the highest traffic frequency is determined as the initial main direction of the spatial grid based on the traffic data of the spatial grid in the vertical direction.

4. The method for UAV path planning according to claim 1, characterized in that, The step of determining the target main direction of each spatial grid cell based on the initial main direction and the feature main direction includes: If the directional deviation between the initial principal direction and the characteristic principal direction of the spatial grid does not exceed a set threshold, the characteristic principal direction is determined as the target principal direction of the spatial grid. If the directional deviation between the initial principal direction and the characteristic principal direction of the spatial grid exceeds a set threshold, the target principal direction of the spatial grid is determined based on the initial principal direction, the characteristic principal direction, and the preset weight parameters.

5. The method for UAV path planning according to claim 1, characterized in that, The process of determining the path of the UAV based on the starting airspace grid, ending airspace grid, and multiple airspace grids of the edge core device includes: Based on the starting point spatial grid and the ending point spatial grid, multiple candidate paths are determined, all of which are preset grid types in the path spatial grid. For each candidate path, the matching degree between the candidate path and the UAV is determined based on the target main direction of the airspace grid in the candidate path and the UAV's heading. The candidate path with the highest sum of matching degrees among all airspace grids and the shortest path length is selected as the path for the UAV.

6. The method for UAV path planning according to claim 1, characterized in that, The method further includes: Obtain the computing load value of edge core devices; When the computing load value exceeds a set threshold, an early warning message is sent to the cloud platform device. The early warning message includes the computing load value exceeding the set threshold, so that the cloud platform device can allocate the computing load value of the edge core device exceeding the set threshold to a computing power redundant edge core device adjacent to the edge core device.

7. The method for UAV path planning according to claim 1, characterized in that, The method further includes: When the area where the airspace grid is located is a preset area, the safety threshold of the airspace grid is determined based on the traffic data of the airspace grid in the preset area. If the security level of the spatial grid in the preset area is greater than the security threshold, the grid type of the spatial grid is determined to be the first grid type.

8. A method for unmanned aerial vehicle (UAV) path planning, characterized in that, Applied to cloud platform devices, the method includes: Receive the initial main direction of multiple spatial grids sent by multiple edge core devices; The navigation data of the UAVs in the multiple edge core devices are acquired, and the main navigation direction of the UAVs in each edge core device is determined based on the navigation data. The characteristic main direction of the spatial grid of the edge core device is determined based on the navigation main direction of each edge core device and the initial main direction of multiple spatial grids; The edge core device sends the characteristic main direction of the airspace grid to the edge core device so that the edge core device can determine the target main direction of each airspace grid based on the initial main direction and the characteristic main direction, and determine the path of the UAV based on the starting airspace grid, the ending airspace grid and the target main directions of multiple airspace grids of the edge core device.

9. The method for UAV path planning according to claim 8, characterized in that, The method further includes: Receive early warning information sent by the edge core device, the early warning information including a computing load value exceeding a set threshold; Obtain the adjacent redundant edge core devices of the edge core device, and allocate the computing load value exceeding the set threshold to the redundant edge core device.

10. A device for unmanned aerial vehicle (UAV) path planning, characterized in that, Applied to edge core devices, the device includes: The acquisition module is used to acquire traffic data and environmental data of multiple airspace grids of the edge core device, as well as the starting airspace grid and ending airspace grid of the UAV. The partitioning module is used to determine the safety level of each spatial grid based on the environmental data, and to partition the spatial grid according to the safety level to obtain the grid type of each spatial grid. The sending module is used to determine the initial main direction of each airspace grid based on the traffic data and grid type of the airspace grid, and send the initial main direction to the cloud platform device, so that the cloud platform device can determine the characteristic main direction of multiple airspace grids of multiple edge core devices based on the initial main directions of multiple airspace grids of multiple edge core devices and the navigation data of the UAV. The receiving module is used to receive the feature main direction sent by the cloud platform device, and determine the target main direction of each spatial grid according to the initial main direction and the feature main direction; The determination module is used to determine the path of the UAV based on the starting airspace grid, the ending airspace grid, and the target main direction of multiple airspace grids of the edge core device.

11. A device for unmanned aerial vehicle (UAV) path planning, characterized in that, Applied to cloud platform devices, the device includes: The receiving module is used to receive the initial main directions of multiple spatial grids sent by the edge core device; The acquisition module is used to acquire navigation data of the UAV within the edge core device and determine the main navigation direction of the UAV within the edge core device based on the navigation data. The determination module is used to determine the characteristic main direction of the spatial grid based on the navigation main direction and the initial main direction of the spatial grid; The sending module is used to send the characteristic main direction of the airspace grid to the edge core device, so that the edge core device can determine the target main direction of each airspace grid according to the initial main direction and the characteristic main direction, and determine the path of the UAV according to the starting airspace grid, the ending airspace grid and the target main directions of multiple airspace grids of the edge core device.

12. A terminal device, characterized in that, The device includes: a processor and a memory storing computer program instructions; the processor executes the computer program instructions to implement the UAV path planning method as described in any one of claims 1-9.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, implement the UAV path planning method as described in any one of claims 1-9.

14. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device causes the electronic device to perform the unmanned aerial vehicle path planning method as described in any one of claims 1-9.

Images