Unmanned aerial vehicle wind speed measurement control method, device, equipment, storage medium and product

Abstract

This invention discloses a method, apparatus, device, storage medium, and product for measuring and controlling wind speed in unmanned aerial vehicles (UAVs). The method includes: dividing the area to be measured into multiple initial sub-regions based on wind field information; distributing initial task information corresponding to the initial sub-regions to each UAV in the UAV swarm; reconstructing the wind field information of the area to be measured based on the wind speed information of the initial sub-region fed back by the UAV, obtaining reconstructed wind field information for the area to be measured; and re-dividing the area to be measured into multiple target sub-regions based on the reconstructed wind field information and the status information fed back by the UAVs, determining the target task information for each target sub-region, and sending the target task information to the corresponding UAV. The target task information is used by the sub-agent to adjust the flight path of its UAV. This invention enables efficient control of UAV swarms, thereby achieving accurate measurement of wind speed information in complex scenarios.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to methods, devices, equipment, storage media, and products for measuring and controlling wind speed in unmanned aerial vehicles (UAVs). Background Technology

[0002] In recent years, drones have been used more and more widely in the field of wind speed measurement. For example, drones equipped with wind speed sensors can collect wind speed information, or drone swarms can work together to complete wind speed measurement.

[0003] However, the above methods are still in the early stages of development, and their application scenarios are relatively simple. The control system of the drone swarm is difficult to adapt to complex application scenarios, especially in urban environments where the presence of numerous buildings and the local heat sources generated by the heat island effect place higher demands on the adaptability of the drone swarm. Therefore, there is an urgent need for a drone wind speed measurement and control method with a higher level of intelligence. Summary of the Invention

[0004] This invention provides a method, device, equipment, storage medium, and product for measuring and controlling wind speed in unmanned aerial vehicles (UAVs), to ensure that the control system of a UAV swarm can adapt to more complex application scenarios and efficiently complete the measurement of wind speed information.

[0005] According to one aspect of the present invention, a method for measuring and controlling wind speed in a UAV is provided, characterized in that it is applied to a master intelligent agent, the master intelligent agent being deployed in the central control system of a UAV swarm, the method comprising: Based on the wind field information of the area to be measured, the area to be measured is divided into multiple initial sub-regions, and the initial task information corresponding to the initial sub-regions is distributed to each drone in the drone cluster; wherein, each drone in the drone cluster is deployed with a sub-agent, and the initial task information is used to enable the sub-agent to determine the starting point information of the flight path of its own drone. Based on the wind speed information of the initial sub-region fed back by the UAV, the wind field information of the region to be measured is reconstructed to obtain the reconstructed wind field information of the region to be measured. Based on the reconstructed wind field information and the status information fed back by the UAV, the area to be measured is re-divided into multiple target sub-regions, and the target task information of the target sub-regions is determined. The target task information is then sent to the corresponding UAV, and the target task information is used by the sub-agent to adjust the flight path of its UAV.

[0006] According to another aspect of the present invention, a method for measuring and controlling wind speed in a UAV is provided, characterized in that it is applied to a sub-agent, the sub-agent being deployed in the control system of each UAV in a UAV swarm, the method comprising: Receive task information sent by the main intelligent agent; wherein the main intelligent agent is deployed in the central control system of the UAV cluster, and the task information includes initial task information or target task information determined by any of the UAV wind speed measurement and control methods provided according to the present invention. The flight path of the UAV is adjusted based on the mission information, the UAV's status information, the environmental information of the area where the UAV is located, and the wind field characteristics of the area where the UAV is located.

[0007] According to another aspect of the present invention, a wind speed measurement and control device for unmanned aerial vehicles (UAVs) is provided, characterized in that it is applied to a master intelligent agent, the master intelligent agent being deployed in the central control system of a UAV swarm, the device comprising: The initial task information distribution module is used to divide the area to be measured into multiple initial sub-regions based on the wind field information of the area to be measured, and distribute the initial task information corresponding to the initial sub-regions to each drone in the drone cluster; wherein, each drone in the drone cluster is deployed with a sub-agent, and the initial task information is used to enable the sub-agent to determine the starting point information of the flight path of its own drone. The wind field information reconstruction module is used to reconstruct the wind field information of the area to be measured based on the wind speed information of the initial sub-region fed back by the UAV, so as to obtain the reconstructed wind field information of the area to be measured. The target task information distribution module is used to re-divide the area to be measured into multiple target sub-regions based on the reconstructed wind field information and the status information fed back by the UAV, determine the target task information of the target sub-regions, and send the target task information to the corresponding UAV. The target task information is used by the sub-agent to adjust the flight path of its UAV.

[0008] According to another aspect of the present invention, a wind speed measurement and control device for unmanned aerial vehicles (UAVs) is provided, characterized in that it is applied to a sub-agent, the sub-agent being deployed in the control system of each UAV in a UAV swarm, the device comprising: A task information receiving module is used to receive task information sent by the main intelligent agent; wherein, the main intelligent agent is deployed in the central control system of the UAV cluster, and the task information includes initial task information or target task information determined by the UAV wind speed measurement and control device applied to the main intelligent agent according to the present invention. The flight path adjustment module is used to adjust the flight path of the UAV based on the mission information, the UAV's status information, the environmental information of the area where the UAV is located, and the wind field characteristics of the area where the UAV is located.

[0009] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the UAV wind speed measurement and control method according to any embodiment of the present invention.

[0010] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the UAV wind speed measurement and control method according to any embodiment of the present invention.

[0011] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a processor, implements the UAV wind speed measurement and control method according to any embodiment of the present invention.

[0012] The technical solution of this invention divides the area to be measured into multiple initial sub-regions based on the wind field information of the area to be measured. Compared with a fixed partitioning strategy, this makes the divided initial sub-regions more compatible with the wind field distribution. By distributing the initial task information corresponding to the initial sub-regions to each drone in the drone swarm, the sub-agents in the drones can have more accurate prior knowledge when optimizing the drone's flight path locally. By reconstructing the wind field information of the area to be measured based on the wind speed information of the initial sub-region fed back by the drone, the reconstructed wind field information of the area to be measured is obtained, thus correcting the wind field information. Based on the reconstructed wind field information and the status information fed back by the drone, the area to be measured is re-divided into multiple target sub-regions, and the target task information of the target sub-regions is determined. The target task information is then sent to the corresponding drones, which can further macroscopically adjust the drone's flight path to ensure that the drone's flight path can adapt to the actual wind field distribution. The above steps can be completed by the master agent in the central control system deployed in the drone swarm. Each drone in the swarm is equipped with a sub-agent. Initial task information is used by the sub-agent to determine the starting point of its flight path, and target task information is used by the sub-agent to adjust its flight path. This invention discloses a collaborative control framework between the master and sub-agents, enabling efficient control of the drone swarm. In complex wind field scenarios, through bidirectional information interaction between the master and sub-agents, the drones can adjust their flight paths in real time, improving the flexibility of drone swarm operations and ensuring that the drone swarm can efficiently and accurately measure wind speed information.

[0013] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This is a flowchart of a wind speed measurement and control method for a drone according to Embodiment 1 of the present invention; Figure 2 This is a flowchart of a UAV wind speed measurement and control method according to Embodiment 2 of the present invention; Figure 3 This is a flowchart of a wind speed measurement and control method for a drone according to Embodiment 3 of the present invention; Figure 4 This is a schematic diagram of the structure of a UAV wind speed measurement and control device according to Embodiment 4 of the present invention; Figure 5 This is a schematic diagram of the structure of a UAV wind speed measurement and control device according to Embodiment 5 of the present invention; Figure 6 This is a schematic diagram of the structure of an electronic device that implements the UAV wind speed measurement and control method of Embodiment Six of the present invention. Detailed Implementation

[0016] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0017] It should be noted that the terms "first," "second," "initial," and "target," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0018] Example 1 Figure 1 This is a flowchart of a UAV wind speed measurement and control method provided in Embodiment 1 of the present invention. This embodiment is applicable to the control of UAV swarms. The method can be applied to a master agent, which can be deployed in the central control system of the UAV swarm, for example, in the control system of the head drone in a swarm or in a ground station control system. The method can be executed by a UAV wind speed measurement and control device, which can be implemented in hardware and / or software. This device can be configured in an electronic device, which can be the UAV acting as the head drone or a ground station control console. Figure 1 As shown, the method includes: S101. Based on the wind field information of the area to be measured, the area to be measured is divided into multiple initial sub-regions, and the initial task information corresponding to the initial sub-regions is distributed to each drone in the drone cluster. Each drone in the drone cluster is equipped with a sub-agent, and the initial task information is used to help the sub-agent determine the starting point information of the flight path of its own drone.

[0019] In this embodiment, the main agent and the sub-agents can be built based on a general large model. The main agent is deployed in the central control system of the drone swarm, and the sub-agents are deployed in the control systems of each drone in the drone swarm. The main agent and the sub-agents can maintain information interaction through wireless links.

[0020] The area to be measured can be a pre-defined geographic spatial range. The boundary information of the area to be measured can be calibrated using a relevant positioning system, such as determining the boundary coordinates of the area to be measured through the Global Positioning System (GPS) or the BeiDou Navigation Satellite System. Wind field information can be understood as information that reflects the wind field distribution characteristics of the area to be measured, such as wind speed, wind direction, location, and time information. Wind field information can be obtained through meteorological stations or through relevant sensors carried by drones. For example, based on the wind field information of the area to be measured, the meteorological big model integrated within the main intelligent agent clusters areas with similar wind field distributions in the area to be measured, thereby obtaining multiple initial sub-regions. The meteorological big model can be a pre-trained meteorological model or a computational fluid dynamics (CFD) rapid evaluation model.

[0021] The initial task information corresponds one-to-one with the initial sub-region. The initial task information may include the boundary information of the initial sub-region, as well as the initial flight position and flight direction of the UAV in the initial sub-region. The initial task information can provide the starting point information of the UAV's flight path, such as the initial flight position and flight direction. It can also provide the optimization starting point information for the sub-agents in the UAV to perform local optimization of the flight path of their respective UAVs. For example, the boundary information of the initial sub-region carried in the initial task information can be used as the constraint condition of the path optimization algorithm in the sub-agent, and the initial flight position and flight direction of the UAV in the initial sub-region carried in the initial task information can be used as the optimization starting point information of the path optimization algorithm in the sub-agent, so that the sub-agent can perform local optimization of the UAV's flight path.

[0022] Optionally, the initial task information may also include the drone's data collection task information, such as the collection frequency and collection location. For example, the initial task information can be encapsulated into a data packet, and by distributing the data packet to the drone, the sub-agents in the drone can determine their flight path and data collection task based on the initial task information.

[0023] S102. Based on the wind speed information of the initial sub-region fed back by the UAV, the wind field information of the area to be measured is reconstructed to obtain the reconstructed wind field information of the area to be measured.

[0024] In this embodiment, the drone can carry a wind speed sensor to collect wind speed information. The wind speed information may include a timestamp, wind speed, and wind direction, and can be represented in vector form. Reconstructing the wind field information can be understood as reconstructing the wind field information of the area to be measured, resulting in information that reflects the wind field distribution characteristics of that area. For example, the main agent, through its internally integrated meteorological model, adjusts the wind field information of the area to be measured based on the wind speed information of the initial sub-region fed back by the drone, thereby determining the reconstructed wind field information.

[0025] S103. Based on the reconstructed wind field information and the status information fed back by the UAV, the area to be measured is redivided into multiple target sub-regions, and the target task information of the target sub-regions is determined. The target task information is then sent to the corresponding UAV. The target task information is used to allow the sub-agent to adjust the flight path of its UAV.

[0026] In this embodiment, the status information fed back by the UAV may include the UAV's own status information and mission status information. The UAV's own status information may include the UAV's location, attitude, speed, and remaining battery power. The mission status information may include the completion rate of the wind speed collection mission, which can be determined based on the ratio of the collected area to the total collected area.

[0027] For example, the main agent, through its internally integrated meteorological model, re-divides the area to be measured into multiple target sub-regions based on reconstructed wind field information. Combining this with the status information fed back by the UAVs, it uses a task planning model integrated within the main agent to determine whether preset task adjustment conditions have been triggered. If triggered, it redetermines the target task information for the target sub-regions according to the preset task adjustment strategy and sends the target task information to the corresponding UAVs. The task planning model can be constructed based on a global strategy or model optimization algorithm of Multi-Agent Reinforcement Learning (MARL). The preset task adjustment conditions include any one of the following: wind field changes exceeding a threshold (e.g., wind speed changes exceeding a first threshold or wind direction changes exceeding a second threshold), abnormal UAV status (e.g., UAV battery level below a third threshold), and user-issued task adjustment commands. The preset task adjustment strategy includes at least one of the following: minimizing UAV energy consumption and maximizing the overall coverage of the UAV swarm. The above steps can be used to replan the flight path or data collection task of a sub-region (e.g., increase the data collection frequency of the UAV in the preset area, or designate a UAV to take over the data collection task of a malfunctioning UAV), adjust the measurement parameters or behavior patterns of the UAV (e.g., adjust the flight altitude, flight speed, and sensor data collection frequency of the UAV), and optimize the overall coverage of the UAV swarm based on the current wind field information.

[0028] This invention provides a method for controlling wind speed measurement using a drone. By dividing the area to be measured into multiple initial sub-regions based on wind field information, compared to a fixed partitioning strategy, the divided initial sub-regions are more adapted to the wind field distribution. By distributing the initial task information corresponding to the initial sub-regions to each drone in the drone cluster, the sub-agents within the drones can possess more accurate prior knowledge when locally optimizing the drone's flight path. By reconstructing the wind field information of the area to be measured based on the wind speed information of the initial sub-region fed back by the drone, the reconstructed wind field information of the area to be measured is obtained, thus correcting the wind field information. Based on the reconstructed wind field information and the status information fed back by the drone, the area to be measured is re-divided into multiple target sub-regions, and the target task information of the target sub-regions is determined and sent to the corresponding drones. This allows for further macroscopic adjustments to the drone's flight path, ensuring that the drone's flight path adapts to the actual wind field distribution. The above steps can be completed by the master agent in the central control system deployed in the drone swarm. Each drone in the swarm is equipped with a sub-agent. Initial task information is used by the sub-agent to determine the starting point of its flight path, and target task information is used by the sub-agent to adjust its flight path. This invention discloses a collaborative control framework between the master and sub-agents, enabling efficient control of the drone swarm. In complex wind field scenarios, through bidirectional information interaction between the master and sub-agents, the drones can adjust their flight paths in real time, improving the flexibility of drone swarm operations and ensuring that the drone swarm can efficiently and accurately measure wind speed information.

[0029] Example 2 Figure 2 This is a flowchart of a method for measuring wind speed from a drone according to Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiments. Figure 2 As shown, the method includes: S201. Determine the wind field distribution characteristics of the area to be measured based on at least one of the following: three-dimensional geometric information, seasonal information, and weather information.

[0030] In this embodiment, wind field information may include wind field distribution characteristics; three-dimensional geometric information may include terrain information, building distribution information, and building height information of the area to be measured; seasonal information may include seasonal status; weather information may include temperature, wind direction, and wind speed, etc., and wind field distribution characteristics may be feature vectors including the above information.

[0031] S202. Determine the importance parameters of each grid in the three-dimensional grid model corresponding to the area to be measured based on the wind field distribution characteristics.

[0032] In this embodiment, the importance parameter can be used to characterize the importance of each grid, and the priority of the UAV data collection task can be determined based on the importance parameter.

[0033] A 3D mesh model can be constructed using an agent. For example, the agent generates a 3D mesh model of the area to be measured using point cloud segmentation and surface reconstruction algorithms (e.g., Poisson reconstruction or adaptive spatial contour extraction). The 3D mesh model is then divided into multiple cubic meshes according to a preset meshing strategy, and each cubic mesh is labeled with attributes. The preset meshing strategy may include at least one of the following: determining the mesh scale based on a set strategy accuracy and computational resources; or determining the mesh scale based on the building density of the area to be measured. The data for constructing the 3D mesh model can be obtained from a geographic information system database or by scanning the area to be measured using a UAV equipped with a LiDAR. Importance parameters can be recorded in the attribute parameters of each cubic mesh. Optionally, attribute parameters may also include building marker parameters, obstacle marker parameters, and center coordinate parameters. Constructing a 3D mesh model can assist the agent in accurately and efficiently identifying the building distribution and wind field distribution of the area to be measured, providing a basis for determining the UAV's flight path and formulating data acquisition tasks.

[0034] S203. Determine the measurement cost of each grid based on the flight energy consumption of the UAV.

[0035] For example, the drone's flight energy consumption is determined based on the distance between the drone and the grid, and then the measurement cost of the grid is determined based on the flight energy consumption.

[0036] S204. Determine the objective function of the preset optimization algorithm based on the importance parameter and measurement cost.

[0037] In this embodiment, the preset optimization algorithm can be a metaheuristic algorithm, such as a genetic algorithm, particle swarm optimization algorithm, and simulated annealing algorithm, or a more efficient combinatorial optimization algorithm. This invention does not specifically limit the preset optimization algorithm. The preset optimization algorithm is used to determine the combination relationship between the UAV and the grid. The objective function of the preset optimization algorithm can be determined based on the accumulated objective information of each grid, wherein the objective information is determined by weighted summation of the importance parameters and measurement costs of the grid based on preset weights.

[0038] S205. Using a preset optimization algorithm, with the goal of maximizing the value of the objective function, the area to be measured is divided into multiple initial sub-regions based on a three-dimensional mesh model; wherein, the constraints of the preset optimization algorithm include at least one of the following: the coverage constraint of the preset region, the UAV endurance constraint, and the region conflict constraint.

[0039] For example, a binary decision variable can be set. This binary decision variable is determined based on the drone number, grid location, and the correspondence between the drone and the grid. For example, the drone... Responsible for grid The wind speed collection task, then The value is 1, otherwise The value of is 0, where The three-dimensional coordinates represent the mesh. The objective function can be expressed as follows: ; in, This represents the maximum number of initial sub-regions, and its value can be set as a variable. Its final value can be determined based on the solution results of a preset optimization algorithm. In this embodiment, the number of drones and the number of initial sub-regions can be set to the same value. It can represent the number of the current initial sub-region or the number of the current drone; Representing the grid 3D coordinates; Represents the area to be measured; Representing the grid Importance parameters; Represents a binary decision variable; The weights representing the importance parameters; Representing drones With grid Corresponding measurement costs; The weight representing the measurement cost.

[0040] The coverage constraint of the preset region can be expressed by the following expression: ; in, It can be set to 1; Grid representing a preset area The corresponding wind speed data collection task is covered by at least one drone.

[0041] The drone's endurance constraint can be expressed by the following expression: ; in, Represents the maximum waypoint number. Represents the current waypoint number; Representing drones The One waypoint, Representing drones The One waypoint, Representing waypoints with waypoints The distance; Representing drones The average flight speed; Representing drones The current battery life.

[0042] Regional conflict constraints can include spatial region non-overlapping constraints, for example, that the initial sub-regions do not overlap.

[0043] The above steps can utilize a preset optimization algorithm based on constraints to solve for the objective function, thereby obtaining the combination relationship between the UAV and the mesh. Based on this combination relationship, the meshes corresponding to the same UAV are divided into the same initial sub-region, thus dividing the area to be measured into multiple initial sub-regions.

[0044] S206. Determine the initial task information corresponding to the initial sub-region and distribute the initial task information corresponding to the initial sub-region to each drone in the drone cluster.

[0045] For example, the initial task information corresponding to each initial sub-region in the area to be measured can be determined through the following steps A1 to A3: A1. Determine the boundary information of the initial sub-region based on the position information of each grid in the initial sub-region.

[0046] For example, the coordinates of grids corresponding to the same initial sub-region can be stored in the same set, and the boundary information of the initial sub-region can be determined by filtering the maximum or minimum coordinate values ​​in the set.

[0047] A2. Determine the waypoint sequence of the UAV in the initial sub-region based on the attribute parameters of each grid in the initial sub-region; wherein, the attribute parameters include at least one of building marker parameters, obstacle marker parameters, importance parameters, and center coordinate parameters.

[0048] For example, in the initial sub-region, the grids marked as buildings and obstacles in the attribute parameters are removed. In the remaining grids, each grid is sorted according to the importance parameter. Grids with high importance are listed as candidate waypoints. Based on the center coordinates of the candidate waypoints, a waypoint sequence is generated using a preset algorithm (such as the shortest path algorithm) according to the principle of the shortest distance between adjacent waypoints.

[0049] A3. Based on the boundary information and the waypoint sequence, determine the initial task information corresponding to the initial sub-region.

[0050] For example, boundary information and waypoint sequences can be encapsulated into data packets, and the identification information of the UAVs can be carried in the data packets. This ensures that after the main agent distributes the data packets via broadcast, each UAV can identify the corresponding data packet and decode it to obtain the corresponding initial mission information.

[0051] S207. Based on the wind speed information of the initial sub-region fed back by the UAV, the wind field information of the area to be measured is reconstructed to obtain the reconstructed wind field information of the area to be measured.

[0052] S208. Based on the reconstructed wind field information and the status information fed back by the UAV, the area to be measured is redivided into multiple target sub-regions, and the target task information of the target sub-regions is determined. The target task information is then sent to the corresponding UAV. The target task information is used to allow the sub-agent to adjust the flight path of its UAV.

[0053] This invention, in its embodiments, determines the wind field distribution characteristics of the area to be measured based on at least one of the following: three-dimensional geometric information, seasonal information, and weather information. It then determines the importance parameters of each grid in the corresponding three-dimensional mesh model based on these wind field distribution characteristics. This allows for precise anchoring of grids with high-value measurements. An objective function is constructed by combining the importance parameters and measurement cost. Constraints are established based on coverage, endurance, and anti-collision measures. A preset optimization algorithm is used to solve the problem, aiming to maximize the objective function value, ensuring that the initial sub-region division is more compatible with the UAV swarm. Furthermore, the boundary information of the initial sub-region is determined based on the position information of each grid within the initial sub-region, thereby limiting the spatial range of the UAV data collection task. By determining the waypoint sequence of the UAV in the initial sub-region based on the attribute parameters of each grid in the initial sub-region, wherein the attribute parameters include at least one of building marker parameters, obstacle marker parameters, importance parameters, and center coordinate parameters, the above steps can take into account the importance of buildings, obstacles, and grids when determining the waypoint sequence, thereby ensuring that the obtained waypoint sequence has higher compatibility with the flight environment, and the above strategy can adapt to complex urban scenarios; by determining the initial task information corresponding to the initial sub-region based on the boundary information and the waypoint sequence, and distributing the initial task information corresponding to the initial sub-region to each UAV in the UAV cluster, it can be ensured that the UAV can perform wind speed collection tasks according to the initial task information.

[0054] In some embodiments, reconstructing the wind field information of the area to be measured based on the wind speed information of the initial sub-region fed back by the UAV to obtain the reconstructed wind field information of the area to be measured includes: reconstructing the wind field information of the area to be measured based on a three-dimensional mesh model of the area to be measured, using the wind speed information of the initial sub-region fed back by the UAV, as well as the historical wind speed information and meteorological information of the initial sub-region, to obtain the reconstructed wind field information of the area to be measured. The advantage of this approach is that it allows for dynamic reconstruction of the wind field information based on the wind speed information fed back by the UAV, ensuring the timeliness of the data; and the introduction of historical wind speed and meteorological information during the reconstruction process ensures that the reconstruction results are more consistent with long-term patterns, improving the robustness of the reconstruction model.

[0055] For example, the wind speed information of the initial sub-region fed back by the UAV, the historical wind speed information and meteorological information of the initial sub-region, and the 3D network model are input into the large model integrated inside the main intelligent agent. The output of the large model is the wind speed vector corresponding to each grid in the 3D mesh model (this wind speed vector can be understood as the prediction result of the large model) or the wind speed vector corresponding to the preset query point (which can be a scattered spatial point specified according to user needs). The large model can also output uncertainty, which can be used to characterize the credibility of the prediction result of the large model. The output of the large model can be used as the reconstructed wind field information. The architecture of the large model is based on a pre-trained comprehensive meteorological large model and is implemented by combining Physical Information Neural Networks (PINN) or Graph Neural Networks (GNN) technology. For example, if PINN is combined, the fluid dynamics equations are introduced into the loss function as physical constraints to ensure the physical consistency of the reconstructed wind field; if GNN is combined, each grid of the 3D mesh model can be used as a graph node, and the spatial correlation can be learned using the graph structure to perform wind speed interpolation and reconstruction. Furthermore, the reconstruction process in this step can be carried out dynamically. Based on the wind speed information fed back by the drone, the wind field information is continuously reconstructed to ensure that the wind field information is more accurate.

[0056] In some embodiments, the step of re-dividing the area to be measured into multiple target sub-regions based on the reconstructed wind field information and the status information fed back by the UAV includes: updating the attribute parameters of each grid in the three-dimensional mesh model of the area to be measured based on the reconstructed wind field information and the status information fed back by the UAV, and re-dividing the area to be measured into multiple target sub-regions based on the update result. The advantage of this setup is that it achieves a closed loop of measured feedback, parameter updates, and area optimization, making the sub-region division more compatible with the wind field information and UAV status, thereby improving the accuracy and safety of the wind speed measurement task.

[0057] For example, the attribute parameters of each grid in the 3D mesh model are updated based on the reconstructed wind field information and the status information fed back by the UAV. For example, the importance parameters of the grids corresponding to the wind field change areas are increased, and the measurement cost parameters of the current acquisition grid and the surrounding grids are increased when the UAV's endurance is insufficient. Based on the updated attribute parameters, the preset optimization algorithm is re-applied to solve the problem with the goal of maximizing the value of the objective function, and the combination relationship between the UAV and the grid is obtained again. Based on the combination relationship, the grids corresponding to the same UAV are divided into the same target sub-region, thereby re-dividing the area to be measured into multiple target sub-regions.

[0058] In some embodiments, after obtaining the reconstructed wind field information of the area to be measured, the method further includes: visualizing the reconstructed wind field information. For example, the visualization method may include two-dimensional wind field slices (e.g., splitting the three-dimensional wind speed information in the reconstructed wind field information into multiple two-dimensional wind speed information based on height information to generate a profile wind vector map or wind speed cloud map), three-dimensional streamline diagrams, and volume rendering diagrams; uncertainties in the reconstructed wind field information may also be superimposed and displayed. Visualizing the reconstructed wind field information can more intuitively reflect wind field changes, facilitating relevant personnel or systems to make relevant decisions.

[0059] Optionally, the method further includes: determining meteorological parameters and statistical characteristics of a preset area based on the reconstructed wind field information, and generating an analysis report based on the meteorological parameters and statistical characteristics. For example, an agent is used to extract information such as average wind speed, prevailing wind direction, and turbulence intensity from the reconstructed wind field information, and presents this information in the form of charts or reports, thereby providing decision support for related applications.

[0060] Example 3 Figure 3 This is a flowchart of a UAV wind speed measurement and control method provided in Embodiment 3 of the present invention. This embodiment is applicable to situations where the flight path of a UAV needs to be adjusted. The method can be applied to a sub-agent, which can be deployed in the control system of each UAV in a UAV swarm. The method can be executed by a UAV wind speed measurement and control device, which can be implemented in hardware and / or software. This device can be configured in an electronic device, which can be a UAV in the UAV swarm. Figure 3 As shown, the method includes: S301, Receive task information sent by the main intelligent agent.

[0061] The main intelligent agent is deployed in the central control system of the UAV swarm, and the task information includes initial task information and / or target task information determined by the UAV wind speed measurement and control method according to any embodiment of the present invention.

[0062] In this embodiment, the master agent deployed in the central control system of the UAV swarm and the sub-agents deployed in each UAV control system can interact in real time via wireless communication links. Therefore, the task information can be initial task information or target task information sent by the master agent. The task information may include boundary information of the sub-regions allocated to the UAVs, such as the boundary information of the initial sub-region or the boundary information of the target sub-region; it may also include waypoint sequences, such as the waypoint sequence of the initial sub-region or the waypoint sequence of the target sub-region.

[0063] S302. Adjust the flight path of the UAV based on mission information, UAV status information, environmental information of the area where the UAV is located, and wind field characteristics of the area where the UAV is located.

[0064] In this embodiment, the drone's status information may include its current position, attitude, speed, and remaining battery power. The environmental information of the area where the drone is located may include obstacle information, such as static and dynamic obstacle information obtained through the drone's onboard sensors (e.g., LiDAR, millimeter-wave radar, and visual sensors) and preset perception algorithms (e.g., target detection and tracking algorithms, and simultaneous localization and mapping algorithms). The wind field characteristics information of the area where the drone is located may include wind speed and wind speed gradient.

[0065] For example, the aforementioned task information, UAV status information, environmental information of the area where the UAV is located, and wind field characteristics of the area where the UAV is located are input into the sub-agent. The sub-agent generates control commands based on an internally integrated path planning model. These control commands are used to adjust the speed, heading, and waypoints of the UAV's flight path to ensure that the UAV's flight path is more adapted to the environment of the area where the UAV is located. The path planning model can be obtained based on a training strategy of reinforcement learning and imitation learning. The reward mechanism of this training strategy can include at least one of the following: encouraging coverage of unmeasured areas, obtaining high-quality data, avoiding obstacles, and saving energy.

[0066] This invention provides a method for controlling wind speed measurement on unmanned aerial vehicles (UAVs). This method is applied to a sub-agent deployed within the control systems of individual UAVs in a UAV swarm. Upon receiving task information from the master agent, the sub-agent adjusts the UAV's flight path based on the task information, UAV status information, environmental information of the UAV's location, and wind field characteristics of that area. This adjustment makes the flight path more adaptable to the environment. Furthermore, the bidirectional decision-making between the master and sub-agents avoids the limitations of single-agent decision-making and the lag of centralized control by the master agent, effectively improving the accuracy of flight path adjustment and ensuring UAV flight safety and successful completion of the data collection task. In this invention, the master and sub-agents have clearly defined roles, share information, and cooperate in a closed-loop control system, jointly improving the control efficiency of the UAV swarm and ensuring that the swarm can adapt to complex and changing scenarios and efficiently complete wind speed data collection tasks.

[0067] In some embodiments, the method further includes: acquiring wind speed data collected by a wind speed sensor in the drone and the drone's flight parameters; fusing the wind speed data and the flight parameters using a preset large model to obtain wind speed information for the area where the drone is located; and feeding the wind speed information back to the main intelligent agent. The advantage of this configuration is that fusing the wind speed data and flight parameters using a preset large model yields more accurate and reliable wind speed information, ensuring that the main intelligent agent can obtain more precise reconstructed wind field information when reconstructing the wind field information of the area to be measured based on the wind speed information fed back by the drone.

[0068] In this embodiment, wind speed data may include timestamps, wind speed, and wind direction. Flight parameters may include UAV coordinates, ground speed, UAV attitude angles (e.g., rotation angle, pitch angle, and yaw angle), motor speed or output power, three-axis acceleration, and three-axis angular velocity. Wind speed information can be understood as wind speed data output after large-scale model correction and error compensation, based on a preset large model, fusing wind speed data and flight parameters; where wind speed information includes timestamps, wind speed, and wind direction. The preset large model can be constructed based on the encoding and decoding structure of the Transformer model with a self-attention mechanism. The dataset of the preset large model may include simulated wind speed data and simulated flight parameters obtained through simulation models, as well as historical wind speed data and historical flight data collected within a preset historical period.

[0069] For example, the sub-agent obtains wind speed data by reading the output of the wind speed sensor; the sub-agent obtains the UAV's flight parameters at a synchronous or near-synchronous frequency (which can be the same as or a division of the flight control main cycle frequency, such as 50Hz-100Hz) through interfaces with the UAV's built-in flight control system, such as the Micro Air Vehicle Link (MAVLink), the Controller Area Network (CAN bus), and custom interfaces; the flight parameters may include the three-dimensional geographical location (which can be a three-dimensional coordinate system composed of latitude, longitude, and altitude, or a three-dimensional coordinate system in a custom coordinate system) provided by the positioning system, the three-dimensional ground speed vector output by the inertial navigation system, the three-dimensional attitude angles (which may include rotation angle, pitch angle, and yaw angle) provided by the Inertial Measurement Unit (IMU), the rotational speed and / or output power of the UAV's rotor motors, and the three-axis acceleration output by the IMU and the three-axis angular velocity output by the gyroscope, etc.; all of the above data carry timestamp information to ensure that the data can be time-aligned.

[0070] The aforementioned wind speed data and flight parameters are input into a preset large model. The preset large model can correct and compensate for errors in the wind speed data based on preset strategies learned during training, so as to output wind speed information. The preset strategies include at least one of the following: correcting the wind speed data based on the UAV's flight state (e.g., hovering, forward flight, side flight, and takeoff and landing) and the rotational speed and / or output power of the rotor motors; predicting wind speed data based on flight parameters when wind speed data is unavailable (e.g., data missing) or of low quality (e.g., outliers); fusing flight parameters and wind speed data to obtain more accurate wind speed data when wind speed data is available; and smoothing and correcting the current wind speed data based on wind speed data from a past period using the model's sequence processing capabilities.

[0071] Optionally, feeding the wind speed information back to the main intelligent agent includes: encapsulating, encoding, and compressing the wind speed information to obtain a wind speed data packet, and feeding the wind speed data packet back to the main intelligent agent. The advantage of this setup is that it allows the wind speed information to be processed into structured data, reduces data transmission volume and storage requirements, improves communication efficiency, and thus enhances the operational stability of the drone swarm.

[0072] For example, the sub-agent encapsulates wind speed information and its corresponding three-dimensional coordinates, timestamp, and drone identifier into structured data, encodes the structured data using a preset encoding algorithm (e.g., Protocol Buffers encoding algorithm or custom binary encoding algorithm), compresses the encoding result using a compression algorithm to obtain compressed data, encapsulates the compressed data into a wind speed data packet, and feeds the wind speed data packet back to the main agent according to a preset communication protocol negotiated with the main agent.

[0073] Example 4 Figure 4 This is a schematic diagram of a UAV wind speed measurement and control device according to Embodiment 4 of the present invention. This device is applied to a main intelligent agent, which is deployed in the central control system of a UAV swarm. Figure 4 As shown, the device includes: an initial task information distribution module 401, a wind field information reconstruction module 402, and a target task information distribution module 403.

[0074] The initial task information distribution module is used to divide the area to be measured into multiple initial sub-regions based on the wind field information of the area to be measured, and distribute the initial task information corresponding to the initial sub-regions to each drone in the drone cluster; wherein, each drone in the drone cluster is deployed with a sub-agent, and the initial task information is used to enable the sub-agent to determine the starting point information of the flight path of its own drone. The wind field information reconstruction module is used to reconstruct the wind field information of the area to be measured based on the wind speed information of the initial sub-region fed back by the UAV, so as to obtain the reconstructed wind field information of the area to be measured. The target task information distribution module is used to re-divide the area to be measured into multiple target sub-regions based on the reconstructed wind field information and the status information fed back by the UAV, determine the target task information of the target sub-regions, and send the target task information to the corresponding UAV. The target task information is used by the sub-agent to adjust the flight path of its UAV.

[0075] This invention provides a drone wind speed measurement and control device. By dividing the area to be measured into multiple initial sub-regions based on wind field information, compared to a fixed partitioning strategy, the divided initial sub-regions are more adapted to the wind field distribution. By distributing the initial task information corresponding to the initial sub-regions to each drone in the drone cluster, the sub-agents within the drones can possess more accurate prior knowledge when locally optimizing the drone's flight path. By reconstructing the wind field information of the area to be measured based on the wind speed information of the initial sub-region fed back by the drone, the reconstructed wind field information of the area to be measured is obtained, thus correcting the wind field information. Based on the reconstructed wind field information and the status information fed back by the drone, the area to be measured is re-divided into multiple target sub-regions, and the target task information of the target sub-regions is determined and sent to the corresponding drones. This allows for further macroscopic adjustments to the drone's flight path, ensuring that the drone's flight path adapts to the actual wind field distribution. The above steps can be completed by the master agent in the central control system deployed in the drone swarm. Each drone in the swarm is equipped with a sub-agent. Initial task information is used by the sub-agent to determine the starting point of its flight path, and target task information is used by the sub-agent to adjust its flight path. This invention discloses a collaborative control framework between the master and sub-agents, enabling efficient control of the drone swarm. In complex wind field scenarios, through bidirectional information interaction between the master and sub-agents, the drones can adjust their flight paths in real time, improving the flexibility of drone swarm operations and ensuring that the drone swarm can efficiently and accurately measure wind speed information.

[0076] Optionally, the wind field information includes wind field distribution characteristics; the initial task information distribution module includes: The wind field distribution characteristic determination unit is used to determine the wind field distribution characteristics of the area to be measured based on at least one of the three-dimensional geometric information, seasonal information, and weather information of the area to be measured. The importance parameter determination unit is used to determine the importance parameters of each grid in the three-dimensional grid model corresponding to the area to be measured based on the wind field distribution characteristics. A measurement cost determination unit is used to determine the measurement cost of each grid based on the flight energy consumption of the UAV; The objective function determination unit is used to determine the objective function of the preset optimization algorithm based on the importance parameter and the measurement cost; An initial sub-region division unit is used to divide the area to be measured into multiple initial sub-regions based on the three-dimensional mesh model by employing the preset optimization algorithm to maximize the value of the objective function; wherein, the constraints of the preset optimization algorithm include at least one of the following: a preset region coverage constraint, a UAV endurance constraint, and a region conflict constraint. The information distribution unit is used to distribute the initial task information corresponding to the initial sub-region to each drone in the drone cluster.

[0077] Optionally, the device further includes: The boundary information determination module is used to determine the boundary information of the initial sub-regions based on the position information of each grid in the initial sub-regions after dividing the area to be measured into multiple initial sub-regions according to the wind field information of the area to be measured. The waypoint sequence determination module is used to determine the waypoint sequence of the UAV in the initial sub-regions after dividing the area to be measured into multiple initial sub-regions based on the wind field information of the area to be measured; wherein, the attribute parameters include at least one of building marker parameters, obstacle marker parameters, importance parameters, and center coordinate parameters; The initial task information determination module is used to determine the initial task information corresponding to the initial sub-regions based on the boundary information and the waypoint sequence after dividing the area to be measured into multiple initial sub-regions according to the wind field information of the area to be measured.

[0078] Optionally, the wind field information reconstruction module is specifically used for: Based on the wind speed information of the initial sub-region fed back by the UAV, as well as the historical wind speed information and meteorological information of the initial sub-region, the wind field information of the region to be measured is reconstructed based on the three-dimensional mesh model of the region to be measured, so as to obtain the reconstructed wind field information of the region to be measured.

[0079] Optionally, the target task information distribution module includes: The target sub-region division unit is used to update the attribute parameters of each grid in the three-dimensional mesh model of the area to be measured according to the reconstructed wind field information and the status information fed back by the UAV, and to re-divide the area to be measured into multiple target sub-regions according to the update results; The target task information distribution unit is used to determine the target task information of the target sub-region and send the target task information to the corresponding UAV. The target task information is used by the sub-agent to adjust the flight path of its UAV.

[0080] The UAV wind speed measurement and control device provided in this embodiment of the invention can execute the UAV wind speed measurement and control method for the main intelligent agent provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0081] Example 5 Figure 5 This is a schematic diagram of a UAV wind speed measurement and control device according to Embodiment 5 of the present invention. This device is applied to a sub-agent, which is deployed in the control system of each UAV in a UAV swarm. Figure 5 As shown, the device includes a mission information receiving module 501 and a flight path adjustment module 502.

[0082] The task information receiving module is used to receive task information sent by the main intelligent agent; wherein, the main intelligent agent is deployed in the central control system of the UAV cluster, and the task information includes the initial task information or target task information determined by the UAV wind speed measurement and control device applied to the main intelligent agent according to the present invention. The flight path adjustment module is used to adjust the flight path of the UAV based on the mission information, the UAV's status information, the environmental information of the area where the UAV is located, and the wind field characteristics of the area where the UAV is located.

[0083] This invention provides a wind speed measurement and control device for unmanned aerial vehicles (UAVs). This device is applied to a sub-agent, which is deployed within the control system of each UAV in a UAV swarm. Upon receiving task information from the master agent, the sub-agent adjusts the UAV's flight path based on the task information, UAV status information, environmental information of the UAV's location, and wind field characteristics of that area. This adjusts the flight path to better adapt to the environment. Furthermore, the bidirectional decision-making between the master and sub-agents avoids the limitations of single-agent decision-making and the lag of centralized control by the master agent, effectively improving the accuracy of flight path adjustment and ensuring UAV flight safety and successful completion of the data collection task. The master and sub-agents in this invention have clearly defined roles, share information, and cooperate in a closed-loop control system, jointly improving the control efficiency of the UAV swarm and ensuring that the swarm can adapt to complex and changing scenarios and efficiently complete wind speed data collection tasks.

[0084] Optionally, the device further includes: The data acquisition module is used to acquire wind speed data collected by the wind speed sensor in the drone, as well as the drone's flight parameters; The wind speed information determination module is used to fuse the wind speed data and the flight parameters through a preset large model to obtain the wind speed information of the area where the UAV is located; The information feedback module is used to feed back the wind speed information to the main intelligent agent.

[0085] The UAV wind speed measurement and control device provided in this embodiment of the invention can execute the UAV wind speed measurement and control method for sub-intelligent agents provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0086] Example 6 Figure 6 A schematic diagram of an electronic device 600 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0087] like Figure 6As shown, the electronic device 600 includes at least one processor 601 and a memory, such as a read-only memory (ROM) 602 or a random access memory (RAM) 603, communicatively connected to the at least one processor 601. The memory stores computer programs executable by the at least one processor. The processor 601 can perform various appropriate actions and processes based on the computer program stored in the ROM 602 or loaded into the RAM 603 from storage unit 608. The RAM 603 may also store various programs and data required for the operation of the electronic device 600. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0088] Multiple components in electronic device 600 are connected to I / O interface 605, including: input unit 606, such as keyboard, mouse, etc.; output unit 607, such as various types of displays, speakers, etc.; storage unit 608, such as disk, optical disk, etc.; and communication unit 609, such as network card, modem, wireless transceiver, etc. Communication unit 609 allows electronic device 600 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0089] Processor 601 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 601 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 601 performs the various methods and processes described above, such as the unmanned aerial vehicle (UAV) wind speed measurement and control method.

[0090] In some embodiments, the UAV wind speed measurement and control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 608. In some embodiments, part or all of the computer program may be loaded into and / or installed on electronic device 600 via ROM 602 and / or communication unit 609. When the computer program is loaded into RAM 603 and executed by processor 6011, one or more steps of the UAV wind speed measurement and control method described above may be performed. Alternatively, in other embodiments, processor 601 may be configured to perform the UAV wind speed measurement and control method by any other suitable means (e.g., by means of firmware).

[0091] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0092] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0093] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0094] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0095] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0096] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0097] This disclosure provides a computer program product, including a computer program that, when executed by a processor, implements the UAV wind speed measurement and control method provided in the above embodiments.

[0098] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0099] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for measuring and controlling wind speed in a drone, characterized in that, Applied to a master intelligent agent deployed in the central control system of a drone swarm, the method includes: Based on the wind field information of the area to be measured, the area to be measured is divided into multiple initial sub-regions, and the initial task information corresponding to the initial sub-regions is distributed to each drone in the drone cluster; wherein, each drone in the drone cluster is deployed with a sub-agent, and the initial task information is used to enable the sub-agent to determine the starting point information of the flight path of its own drone. Based on the wind speed information of the initial sub-region fed back by the UAV, the wind field information of the region to be measured is reconstructed to obtain the reconstructed wind field information of the region to be measured. Based on the reconstructed wind field information and the status information fed back by the UAV, the area to be measured is re-divided into multiple target sub-regions, and the target task information of the target sub-regions is determined. The target task information is then sent to the corresponding UAV, and the target task information is used by the sub-agent to adjust the flight path of its UAV.

2. The UAV wind speed measurement and control method according to claim 1, characterized in that, The wind field information includes wind field distribution characteristics; The step of dividing the area to be measured into multiple initial sub-regions based on the wind field information of the area to be measured includes: The wind field distribution characteristics of the area to be measured are determined based on at least one of the three-dimensional geometric information, seasonal information, and weather information of the area to be measured. Based on the wind field distribution characteristics, determine the importance parameters of each grid in the three-dimensional grid model corresponding to the area to be measured; The measurement cost of each grid is determined based on the flight energy consumption of the UAV; The objective function of the preset optimization algorithm is determined based on the importance parameter and the measurement cost; The preset optimization algorithm is used to maximize the value of the objective function. Based on the three-dimensional mesh model, the area to be measured is divided into multiple initial sub-regions. The constraints of the preset optimization algorithm include at least one of the following: a preset area coverage constraint, a UAV endurance constraint, and a region conflict constraint.

3. The UAV wind speed measurement and control method according to claim 2, characterized in that, After dividing the area to be measured into multiple initial sub-regions based on the wind field information of the area to be measured, the method further includes: The boundary information of the initial sub-region is determined based on the position information of each grid in the initial sub-region; Based on the attribute parameters of each grid in the initial sub-region, the waypoint sequence of the UAV in the initial sub-region is determined; wherein, the attribute parameters include at least one of building marker parameters, obstacle marker parameters, importance parameters, and center coordinate parameters; Based on the boundary information and the waypoint sequence, the initial task information corresponding to the initial sub-region is determined.

4. The UAV wind speed measurement and control method according to claim 1, characterized in that, The step of reconstructing the wind field information of the area to be measured based on the wind speed information of the initial sub-region fed back by the UAV, to obtain the reconstructed wind field information of the area to be measured, includes: Based on the wind speed information of the initial sub-region fed back by the UAV, as well as the historical wind speed information and meteorological information of the initial sub-region, the wind field information of the region to be measured is reconstructed based on the three-dimensional mesh model of the region to be measured, so as to obtain the reconstructed wind field information of the region to be measured.

5. The UAV wind speed measurement and control method according to claim 1, characterized in that, The method involves re-dividing the area to be measured into multiple target sub-regions based on the reconstructed wind field information and the status information fed back by the UAV, including: Based on the reconstructed wind field information and the status information fed back by the UAV, the attribute parameters of each grid in the three-dimensional mesh model of the area to be measured are updated, and the area to be measured is re-divided into multiple target sub-regions based on the update results.

6. A method for measuring and controlling wind speed in a drone, characterized in that, The method, applied to sub-agents deployed in the control systems of individual drones within a drone swarm, includes: Receive task information sent by the main intelligent agent; wherein the main intelligent agent is deployed in the central control system of the UAV cluster, and the task information includes initial task information or target task information determined by the UAV wind speed measurement and control method according to any one of claims 1-5; The flight path of the UAV is adjusted based on the mission information, the UAV's status information, the environmental information of the area where the UAV is located, and the wind field characteristics of the area where the UAV is located.

7. The UAV wind speed measurement and control method according to claim 6, characterized in that, The method further includes: Acquire wind speed data collected by the wind speed sensor in the drone, as well as the drone's flight parameters; By fusing the wind speed data and flight parameters using a pre-set large model, the wind speed information of the area where the UAV is located can be obtained; The wind speed information is fed back to the main intelligent agent.

8. A wind speed measurement and control device for unmanned aerial vehicles (UAVs), characterized in that, Applied to a primary intelligent agent deployed in the central control system of a drone swarm, the device includes: The initial task information distribution module is used to divide the area to be measured into multiple initial sub-regions based on the wind field information of the area to be measured, and distribute the initial task information corresponding to the initial sub-regions to each drone in the drone cluster; wherein, each drone in the drone cluster is deployed with a sub-agent, and the initial task information is used to enable the sub-agent to determine the starting point information of the flight path of its own drone. The wind field information reconstruction module is used to reconstruct the wind field information of the area to be measured based on the wind speed information of the initial sub-region fed back by the UAV, so as to obtain the reconstructed wind field information of the area to be measured. The target task information distribution module is used to re-divide the area to be measured into multiple target sub-regions based on the reconstructed wind field information and the status information fed back by the UAV, determine the target task information of the target sub-regions, and send the target task information to the corresponding UAV. The target task information is used by the sub-agent to adjust the flight path of its UAV.

9. A wind speed measurement and control device for unmanned aerial vehicles (UAVs), characterized in that, An application to sub-agents, wherein the sub-agents are deployed in the control systems of individual drones in a drone swarm, the device includes: A task information receiving module is used to receive task information sent by the main intelligent agent; wherein, the main intelligent agent is deployed in the central control system of the UAV cluster, and the task information includes initial task information or target task information determined by the UAV wind speed measurement and control device according to claim 8. The flight path adjustment module is used to adjust the flight path of the UAV based on the mission information, the UAV's status information, the environmental information of the area where the UAV is located, and the wind field characteristics of the area where the UAV is located.

10. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the UAV wind speed measurement and control method according to any one of claims 1-7.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute the UAV wind speed measurement and control method according to any one of claims 1-7.

12. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the UAV wind speed measurement and control method according to any one of claims 1-7.

Images