Rotary-wing UAV attitude control methods and systems

Abstract

This invention relates to the field of unmanned aerial vehicle (UAV) technology, specifically disclosing a method and system for attitude control of rotary-wing UAVs. This invention involves selecting a direct-operation UAV and an auxiliary monitoring UAV; performing basic flight control; performing in-situ flight control; acquiring the workspace position of the direct-operation UAV in real time; adjusting the monitoring attitude of the auxiliary monitoring UAV accordingly; analyzing the follow-up monitoring data; and adjusting the working attitude of the direct-operation UAV accordingly. This allows for the follow-up adjustment of the auxiliary monitoring UAV's monitoring attitude based on the workspace position of the direct-operation UAV, and, based on the follow-up monitoring of the direct-operation UAV by the auxiliary monitoring UAV, the direct-operation UAV adjusts its working attitude accordingly. This solves the problem of monitoring blind spots in complex firefighting environments, making timely and effective attitude adjustment and control of rotary-wing UAVs difficult, thus improving the efficiency and effectiveness of firefighting missions.

Description

Technical Field

[0001] This invention belongs to the field of unmanned aerial vehicle (UAV) technology, and particularly relates to a method and system for attitude control of rotary-wing UAVs. Background Technology

[0002] Rotary-wing drones are a type of unmanned aerial vehicle (UAV) that generates lift by rotating rotors to achieve flight and perform various tasks. They typically rely on electric motors to drive the rotors to generate power and mainly consist of a rotor system, fuselage, power system, flight control system, and sensor system. They are widely used in fields such as aerial photography, geographic surveying, agricultural planting, logistics distribution, and emergency rescue.

[0003] In existing technologies, the attitude adjustment of rotary-wing drones mainly relies on data monitored and acquired by various sensors onboard the drone. Based on the analysis results, corresponding adjustment and control operations are implemented. For rotary-wing drones used in firefighting operations, the working environment is extremely complex. Firefighting sites are often filled with large amounts of dense smoke, which not only severely obstructs visibility but also interferes with the normal operation of sensors. At the same time, high temperatures can affect the performance of the drone's electronic components and sensors, reducing the accuracy and reliability of its monitoring. In addition, various obstacles that may exist at the scene, such as collapsed buildings and burning debris, will further increase the difficulty and risk of flight. In such a complex environment, rotary-wing drones are prone to monitoring blind spots and cannot make timely and effective attitude adjustment and control based on the limited and potentially inaccurate data they acquire, thus affecting the efficiency and effectiveness of firefighting missions. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for attitude control of rotary-wing unmanned aerial vehicles (UAVs), aiming to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions: A method for attitude control of a rotary-wing unmanned aerial vehicle, the method specifically includes the following steps: Receive firefighting work requirements, plan target firefighting routes, and select direct-operation drones and auxiliary monitoring drones from multiple rotary-wing drones; According to the target firefighting route, perform basic flight control on the direct-operation drone and the auxiliary monitoring drone, and receive basic environmental data transmitted by the auxiliary monitoring drone; The basic environmental data is analyzed to plan the direct working area and auxiliary monitoring location, and the direct working UAV and the auxiliary monitoring UAV are controlled in place for flight. The system acquires the workspace position of the direct-working UAV in real time, adjusts the monitoring attitude of the auxiliary monitoring UAV accordingly, and acquires the follow-up monitoring data of the auxiliary monitoring UAV in real time. The motion monitoring data is analyzed to generate work adjustment data, and the working attitude of the direct-working UAV is adjusted accordingly based on the work adjustment data.

[0006] A rotary-wing unmanned aerial vehicle (UAV) attitude control system, comprising a fire-fighting UAV selection unit, a basic flight control unit, a positioning flight control unit, a monitoring and servo adjustment unit, and a work-corresponding adjustment unit, wherein: The firefighting drone selection unit is used to receive firefighting work requirements, plan target firefighting routes, and select direct-operation drones and auxiliary monitoring drones from multiple rotary-wing drones. The basic flight control unit is used to perform basic flight control on the direct-operation UAV and the auxiliary monitoring UAV according to the target fire-fighting route, and to receive basic environmental data transmitted by the auxiliary monitoring UAV. The in-situ flight control unit is used to analyze the basic environmental data, plan the direct working area and auxiliary monitoring position, and perform in-situ flight control on the direct working UAV and the auxiliary monitoring UAV. The monitoring and follow-up adjustment unit is used to acquire the workspace position of the direct working UAV in real time, perform follow-up adjustment of the monitoring attitude of the auxiliary monitoring UAV, and acquire the follow-up monitoring data of the auxiliary monitoring UAV in real time. The work-corresponding adjustment unit is used to analyze the follow-up monitoring data, plan and generate work adjustment data, and adjust the working attitude of the direct-working UAV according to the work adjustment data.

[0007] Compared with the prior art, the beneficial effects of the present invention are: This invention, through the selection of a direct-operation UAV and an auxiliary monitoring UAV, performs basic flight control, in-situ flight control, real-time acquisition of the workspace position of the direct-operation UAV, and adjusts the monitoring attitude of the auxiliary monitoring UAV accordingly. It analyzes the follow-up monitoring data and adjusts the working attitude of the direct-operation UAV accordingly. This allows for the follow-up adjustment of the auxiliary monitoring UAV's monitoring attitude based on the workspace position of the direct-operation UAV, and the corresponding adjustment of the direct-operation UAV's working attitude based on the follow-up monitoring data from the auxiliary monitoring UAV. This solves the problem of monitoring blind spots and difficulty in timely and effective attitude adjustment control of rotary-wing UAVs in complex firefighting environments, thereby improving the efficiency and effectiveness of firefighting missions. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention.

[0009] Figure 1 A flowchart of the method provided by an embodiment of the present invention is shown.

[0010] Figure 2 A flowchart illustrating the selection of a direct-operation drone and an auxiliary monitoring drone in the method provided by an embodiment of the present invention is shown.

[0011] Figure 3 A flowchart illustrating basic flight control in the method provided by an embodiment of the present invention is shown.

[0012] Figure 4 A flowchart illustrating in-situ flight control is shown in the method provided by an embodiment of the present invention.

[0013] Figure 5 A flowchart illustrating the follow-up adjustment of attitude monitoring in the method provided by an embodiment of the present invention is shown.

[0014] Figure 6 A flowchart illustrating the corresponding adjustment of the working posture in the method provided by an embodiment of the present invention is shown.

[0015] Figure 7 An application architecture diagram of the system provided in an embodiment of the present invention is shown.

[0016] Figure 8 The diagram shows a structural block diagram of the fire-fighting drone selection unit in the system provided by an embodiment of the present invention.

[0017] Figure 9 A structural block diagram of the in-situ flight control unit in the system provided by an embodiment of the present invention is shown.

[0018] Figure 10 A structural block diagram of the monitoring and follow-up adjustment unit in the system provided by an embodiment of the present invention is shown. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0020] Understandably, in existing technologies, the attitude adjustment of rotary-wing drones mainly relies on data monitored and acquired by various sensors onboard the drone. Based on the analysis results, corresponding adjustment and control operations are implemented. For rotary-wing drones used in firefighting operations, the working environment is extremely complex. Firefighting sites are often filled with large amounts of dense smoke, which not only severely obstructs visibility but also interferes with the normal operation of sensors. At the same time, high temperatures can affect the performance of the drone's electronic components and sensors, reducing the accuracy and reliability of its monitoring. In addition, various obstacles that may exist at the scene, such as collapsed buildings and burning debris, will further increase the difficulty and risk of flight. In such a complex environment, rotary-wing drones are prone to monitoring blind spots and cannot make timely and effective attitude adjustment and control based on the limited and potentially inaccurate data they acquire, thus affecting the efficiency and effectiveness of firefighting missions.

[0021] To address the aforementioned problems, this invention receives firefighting work requirements, plans target firefighting routes, and selects a direct-operation drone and an auxiliary monitoring drone from multiple rotorcraft drones. Following the target firefighting route, it performs basic flight control on both the direct-operation and auxiliary monitoring drones and receives basic environmental data transmitted by the auxiliary monitoring drone. It analyzes the basic environmental data, plans the direct-operation area and auxiliary monitoring position, and performs in-situ flight control on both drones. It acquires the workspace position of the direct-operation drone in real time, adjusts the monitoring attitude of the auxiliary monitoring drone accordingly, and acquires the follow-up monitoring data from the auxiliary monitoring drone in real time. It analyzes the follow-up monitoring data, generates work adjustment data, and adjusts the working attitude of the direct-operation drone accordingly. This allows for the follow-up adjustment of the auxiliary monitoring drone's monitoring attitude based on the workspace position of the direct-operation drone, and the corresponding adjustment of the direct-operation drone's working attitude based on the follow-up monitoring of the direct-operation drone by the auxiliary monitoring drone. This solves the problem of monitoring blind spots for rotorcraft drones in complex firefighting environments, making timely and effective attitude adjustment control difficult, thus improving the efficiency and effectiveness of firefighting missions.

[0022] Figure 1 A flowchart of the method provided by an embodiment of the present invention is shown.

[0023] Specifically, the attitude control method for a rotary-wing unmanned aerial vehicle includes the following steps: Step S101: Receive firefighting work requirements, plan target firefighting routes, and select direct-operation drones and auxiliary monitoring drones from multiple rotary-wing drones.

[0024] In this embodiment of the invention, by receiving fire-fighting work requests, identifying the location of the requests, determining the target fire-fighting location, planning the target fire-fighting route according to the target location, and acquiring the drone status data of multiple standby rotary-wing drones, determining the endurance requirement according to the target fire-fighting route, and then comparing and analyzing the status data of multiple drones based on the endurance requirement, selecting direct-operation drones and auxiliary monitoring drones from the multiple rotary-wing drones. The direct-operation drones are rotary-wing drones that directly perform fire-fighting work; the auxiliary monitoring drones are rotary-wing drones that do not participate in direct fire-fighting work but perform real-time monitoring.

[0025] Specifically, Figure 2 A flowchart illustrating the selection of a direct-operation drone and an auxiliary monitoring drone in the method provided by an embodiment of the present invention is shown.

[0026] In a preferred embodiment of the present invention, the steps of receiving firefighting work requirements, planning target firefighting routes, and selecting direct-operation drones and auxiliary monitoring drones from multiple rotary-wing drones specifically include the following steps: Step S1011: Receive fire-fighting work requirements; Step S1012: Identify the fire-fighting work requirements and determine the target fire-fighting location; Step S1013: Plan the target fire route according to the target fire location; Step S1014: Obtain drone status data for multiple rotary-wing drones; Step S1015: Compare the status data of multiple UAVs, and select a direct-operation UAV and an auxiliary monitoring UAV from the multiple rotary-wing UAVs.

[0027] In a preferred embodiment of the present invention, the step of comparing the status data of multiple UAVs and selecting the direct-operation UAV and the auxiliary monitoring UAV from the multiple rotary-wing UAVs specifically includes the following steps: Acquire drone status data and target fire route. Drone status data includes battery level, flight speed, and payload capacity. Set a load adjustment coefficient based on the drone's payload capacity. Calculate the quantitative indicators of route demand based on the target fire route. The effective driving range is calculated by multiplying the battery capacity by the load adjustment factor. The theoretical flight time was calculated using the target fire route distance and flight speed. The comprehensive score for each drone is calculated based on its effective endurance and theoretical flight time. Sort all drones by their overall scores in descending order and label the sensor type of each drone to obtain a priority ranking list with device attributes. Set the minimum flight time threshold for the target fire route, and select the first drone that meets the requirement of having an effective flight time greater than the minimum flight time threshold from the priority sorting list with equipment attributes, based on the minimum flight time threshold of the target fire route, so as to select the drone for direct operation. If none of the top 30% of the drones in the priority sorting list with device attributes meet the threshold, a manual intervention alarm will be triggered to guide the manual selection of the drone to work directly. Using camera resolution as a screening criterion, several qualified drones were selected from a priority list with device attributes as auxiliary monitoring drones.

[0028] In this embodiment of the invention, the actual payload of the drone is incorporated into the power evaluation system by dynamically adjusting the battery life calculation in real time, thus preventing high-load drones from crashing mid-flight due to falsely advertised battery levels. Furthermore, a score is generated by comprehensively considering multiple parameters such as flight speed, route distance, and battery performance, overcoming the limitations of single-dimensional selection. Differential standards (primary weight endurance threshold, secondary weight image performance) are adopted to form a complementary selection logic, allowing the primary drone to focus on firefighting work, while the secondary monitoring drone focuses on auxiliary detection. Moreover, the primary and secondary drones are selected asymmetrically, achieving a "1+1>2" effect by combining the dynamic load attenuation coefficient with asymmetrical selection rules.

[0029] Furthermore, the attitude control method for the rotary-wing UAV also includes the following steps: Step S102: Perform basic flight control on the direct-operation drone and the auxiliary monitoring drone according to the target fire-fighting route, and receive basic environmental data transmitted by the auxiliary monitoring drone.

[0030] In this embodiment of the invention, basic flight control is performed on the direct-operation drone and the auxiliary monitoring drone according to the target fire-fighting route, so that the direct-operation drone and the auxiliary monitoring drone arrive at the target fire-fighting location, and the arrival feedback of the direct-operation drone and the auxiliary monitoring drone is received. Then, an environmental monitoring command is generated and sent to the auxiliary monitoring drone, and basic environmental data transmitted by the auxiliary monitoring drone is received.

[0031] Specifically, Figure 3 A flowchart illustrating basic flight control in the method provided by an embodiment of the present invention is shown.

[0032] In a preferred embodiment of the present invention, the step of performing basic flight control on the direct-operation drone and the auxiliary monitoring drone according to the target firefighting route, and receiving basic environmental data transmitted by the auxiliary monitoring drone, specifically includes the following steps: Step S1021: Perform basic flight control on the direct-operation drone and the auxiliary monitoring drone according to the target fire-fighting route; Step S1022: Receive arrival feedback from the direct working drone and the auxiliary monitoring drone; Step S1023: Generate and send environmental monitoring instructions to the auxiliary monitoring drone; Step S1024: Receive the basic environmental data transmitted by the auxiliary monitoring drone.

[0033] In a preferred embodiment of the present invention, the basic flight control of the direct-operation drone and the auxiliary monitoring drone according to the target firefighting route specifically includes the following steps: The remaining flight distance is calculated based on the total length of the target fire route and the current distance already flown. The real-time wind speed vector is obtained by using an auxiliary drone, and the average wind speed benchmark value of the current area is obtained. The effective wind speed is calculated by using the real-time wind speed vector and the average wind speed benchmark value of the current area. The system acquires flight performance records from historical missions and current area terrain feature codes, and obtains terrain feature weights by fitting a machine learning model. The terrain feature weights are then converted into environmental degradation factors. Obtain the task urgency level and map the discretized task urgency level to a continuous numerical factor to obtain the emergency coefficient; The load adjustment coefficient is calculated based on the current liquid load and maximum payload of the drone. Obtain the drone's current remaining battery power, and use the emergency coefficient, load adjustment coefficient, and current remaining battery power to calculate the initial value of the flight speed; A wind resistance attenuation term is constructed using the effective wind speed and the environmental attenuation factor, and a distance attenuation term is constructed using the remaining flight distance and the environmental attenuation factor. The initial flight speed is adjusted using wind resistance attenuation and distance attenuation terms to obtain the optimal flight speed, which is then used as the basic flight control command for both the direct-operation UAV and the auxiliary monitoring UAV.

[0034] Furthermore, the attitude control method for the rotary-wing UAV also includes the following steps: Step S103: Analyze the basic environmental data, plan the direct working area and auxiliary monitoring location, and perform in-situ flight control on the direct working UAV and the auxiliary monitoring UAV.

[0035] In this embodiment of the invention, by analyzing basic environmental data, fire hazard areas are determined. Based on the fire hazard areas, nearby direct work areas are selected. Based on the direct work areas and preset auxiliary monitoring parameters, auxiliary monitoring positions are planned. Then, according to the direct work areas, the direct work drone is controlled to fly in place to carry out firefighting operations. And according to the auxiliary monitoring positions, the auxiliary monitoring drone is controlled to fly in place to carry out real-time monitoring.

[0036] Specifically, Figure 4 A flowchart illustrating in-situ flight control is shown in the method provided by an embodiment of the present invention.

[0037] In a preferred embodiment of the present invention, the steps of analyzing the basic environmental data, planning the direct working area and auxiliary monitoring location, and performing in-situ flight control of the direct working UAV and the auxiliary monitoring UAV specifically include the following steps: Step S1031: Analyze the basic environmental data to determine fire hazard areas; Step S1032: Based on the fire hazard area, plan the direct work area; Step S1033: Based on the direct working area, plan auxiliary monitoring locations; Step S1034: Perform in-situ flight control on the direct working UAV according to the direct working area; Step S1035: Perform in-situ flight control on the auxiliary monitoring UAV according to the auxiliary monitoring position.

[0038] In a preferred embodiment of the present invention, the step of planning auxiliary monitoring locations based on the direct working area specifically includes the following steps: Acquire data from the direct working area, including real-time temperature distribution data, fire spread vector, and wireless signal strength distribution map. Based on the fire spread vector analysis, the core coordinates of the fire source are determined, and a polar coordinate system is established with the core coordinates of the fire source as the center. In the polar coordinate system, the fire intensity influence weight of each location point is calculated based on the distance between the fire source and each location point, and a hazard level gradient map centered on the fire source is obtained. The temperature distribution data is subjected to second-order differential calculation to locate the temperature abrupt change boundary; Based on the temperature abrupt change boundary, the combustion front at the edge of the fire scene is identified, and potential deflagration risk areas are marked, resulting in an enhanced thermal map with key thermal features marked. Based on the wireless signal strength distribution map, morphological dilation is performed on the signal blind zone to construct a communication security buffer, resulting in a region segmentation map with communication protection weights. The hazard level gradient map centered on the fire source, the enhanced thermal map marked with key thermal features, and the region segmentation map with communication security weights are synthesized into an equivalent potential field with multi-physics coupling using a weighted superposition algorithm, resulting in a composite potential field that includes fire threat, thermal features, and communication security. The horizontal position coordinates of each drone are encoded into the probability amplitude of qubits, a dedicated quantum register is assigned to each drone, a two-dimensional quantum grid is established, and the initial quantum state probability cloud distribution map is obtained. Based on the initial quantum state probability cloud distribution map, the composite potential field is injected into the Hamiltonian of the quantum system, and the fire potential energy constraint term is embedded in the quantum state wave function to generate the optimized quantum state probability cloud distribution map. Based on the optimized quantum state probability cloud distribution map, a controlled NOT gate is applied between adjacent UAV qubits to establish the correlation and entanglement relationship between qubits; Using the cosine function of the viewpoint difference as the phase rotation factor, and applying phase modulation under the viewpoint difference constraint to the entangled state, a quantum state evolution equation is generated. Based on the quantum state evolution equation, an adjustable rotation gate is inserted into the quantum circuit to establish a mapping channel between quantum states and classical parameters, resulting in a trainable hybrid quantum-classical computing model. Based on a trainable hybrid quantum-classical computing model, the expected energy value of the quantum state in the composite potential field is calculated to evaluate the fidelity index of the monitoring network coverage and obtain the system energy assessment value under the current parameters. Based on the system energy assessment value under the current parameters, the rotating gate parameters are iteratively optimized using the gradient descent method. After optimization, the quantum state probability distribution under the optimal parameters is obtained. Based on the quantum state probability distribution under optimal parameters, the region with the maximum quantum state amplitude is extracted as candidate coordinates, and the probability amplitude is converted into actual geographic coordinate offset to adjust the candidate coordinates, thus obtaining a set of high-precision monitoring point coordinates. The high-precision set of monitoring point coordinates is input into the real-time path planner and fine-tuned in combination with wind speed and obstacle data to generate a flight trajectory instruction set with speed curves; A simulated monitoring perspective is generated based on the flight trajectory instruction set with velocity curves, and the three-dimensional overlapping area of ​​the simulated monitoring perspective is calculated. An auxiliary monitoring position is selected based on the coverage of the three-dimensional overlapping area of ​​the simulated monitoring perspective.

[0039] In this embodiment of the invention, by unifying the dimensions of three heterogeneous data types—fire dynamics, thermal characteristics, and communication constraints—a quantifiable physical field model is established to enable intelligent identification and avoidance of communication blind spots. Furthermore, quantum entanglement is used to enforce cooperative constraint relationships between UAVs, and a phase rotation factor is introduced to ensure the rigid requirements of the monitoring network's viewing angle difference, thereby reducing monitoring blind spots and ensuring that the selected auxiliary monitoring locations have better auxiliary effects. Geographic coordinates are converted into quantum state probability amplitudes, achieving a precise mapping between physical space and quantum computing space. By loading environmental parameters through Hamiltonians, a strong correlation between quantum computing and physical reality is established, improving positioning accuracy and maintaining a stable position encoding benchmark even under sudden changes in fire conditions.

[0040] Furthermore, the attitude control method for the rotary-wing UAV also includes the following steps: Step S104: Obtain the working space position of the direct working UAV in real time, adjust the monitoring attitude of the auxiliary monitoring UAV accordingly, and obtain the follow-up monitoring data of the auxiliary monitoring UAV in real time.

[0041] In this embodiment of the invention, by acquiring the working space position of the direct working UAV in the direct working area in real time, the auxiliary monitoring UAV is monitored according to the working space position, the attitude adjustment angle is determined, and then the monitoring attitude of the auxiliary monitoring UAV is adjusted according to the attitude adjustment angle, so that the auxiliary monitoring UAV can monitor the direct working UAV in real time and acquire the follow-up monitoring data of the auxiliary monitoring UAV in real time.

[0042] Specifically, Figure 5 A flowchart illustrating the follow-up adjustment of attitude monitoring in the method provided by an embodiment of the present invention is shown.

[0043] In a preferred embodiment of the present invention, the steps of acquiring the workspace position of the direct-operation UAV in real time, adjusting the monitoring attitude of the auxiliary monitoring UAV accordingly, and acquiring the follow-up monitoring data of the auxiliary monitoring UAV in real time specifically include the following steps: Step S1041: Obtain the workspace location of the direct-working UAV in real time; Step S1042: According to the workspace location, perform monitoring planning for the auxiliary monitoring drone and determine the attitude adjustment angle; Step S1043: Adjust the monitoring attitude of the auxiliary monitoring drone according to the attitude adjustment angle. Step S1044: Acquire the real-time follow-up monitoring data of the auxiliary monitoring drone.

[0044] In a preferred embodiment of the present invention, the step of planning the monitoring of the auxiliary monitoring drone according to the workspace location and determining the attitude adjustment angle specifically includes the following steps: Threshold segmentation is performed on real-time temperature distribution data to identify the outline of the core combustion region and obtain a temperature distribution segmentation map; Morphological closing operations are performed on the temperature distribution segmentation map to eliminate noise, and the shape features of the continuous fire front line are extracted to generate a dynamic fire evolution map with geometric feature annotations. Based on the dynamic evolution map of the fire scene with geometric feature annotations, a pre-trained fire point migration prediction model is used in conjunction with real-time wind speed to predict the coordinates of future fire points. Based on the current and future fire point coordinates, obtain the combustible material density distribution map around the fire point to calculate the combustion diffusion energy accumulation value, and normalize the combustion diffusion energy accumulation value to generate the fire point threat weight; Construct a three-dimensional spatial grid and record the real-time wind speed vector at each grid point; Kriging interpolation is performed on areas outside the sensor's measurement range to obtain the wind speed vector distribution matrix for the entire field. The wind speed magnitude of each grid point in the full-field wind speed vector distribution matrix is ​​normalized to a probability amplitude, and the three-dimensional wind field is mapped to the probability space of qubits through amplitude encoding to obtain a quantum superposition state characterizing the wind field distribution in the whole space. The quantum superposition state characterizing the wind field distribution in the whole space is subjected to a quantum Fourier transform operation to obtain the quantum Fourier transform result; The quantum state frequency components of the quantum Fourier transform results are measured to identify the dominant periodic characteristics, so as to extract the wind field dominant frequency characteristic parameters that affect the observation stability. The auxiliary drone is used to perform three-dimensional lidar scanning of obstacles in the workspace to obtain lidar point cloud data of the workspace location; The laser point cloud data of the workspace location is input into a graph convolutional network to predict the future occlusion probability of each spatial point in the workspace location. The future occlusion probability of each spatial point in the workspace location is dynamically adjusted using meteorological parameters to obtain a dynamic occlusion probability cloud map. Based on the dynamic occlusion probability cloud map, the coverage effectiveness index is defined as the information entropy value of the occlusion probability. A variational autoencoder is used to search for the observation path with the minimum entropy value in the attitude space to obtain the optimal observation path sequence and the corresponding attitude angle set. Substituting the wind field dominant frequency characteristic parameters into the basis function generator yields a wind disturbance-resistant basis function with phase compensation. The attitude angle set is decomposed into Fourier descriptors to extract the path geometric feature frequencies. The path geometric feature frequencies are then multiplied with the anti-wind disturbance basis functions with phase compensation using tensor products to obtain the anti-interference basis functions with fused path constraints. Project the coordinates of the fire points onto the observation view space of the UAV and calculate the visibility index of each fire point; The visibility index of each fire point is fused with the corresponding fire point threat weight to obtain a fire point coverage weight matrix with spatiotemporal characteristics. With fire point coverage, wind resistance stability, and energy efficiency as optimization objectives, a multi-objective optimization function is constructed using attitude angle set, fire point coverage weight matrix with spatiotemporal characteristics, and anti-interference basis function with fused path constraints. The alternating direction multiplier method is used to perform multi-objective collaborative optimization of the multi-objective optimization function. After optimization, the globally optimal attitude angle is obtained.

[0045] In this embodiment of the invention, a dynamic occlusion propagation model is constructed based on lidar point clouds and deep learning to predict future blind zone evolution trends. With the goal of minimizing information entropy, the observation path with the lowest occlusion risk is searched in the attitude space. By fusing spatiotemporal prediction, quantum wind field decomposition, and occlusion entropy suppression to optimize multimodal collaborative observation attitude, the problem of unpredictable blind spots in complex environments can be solved, making the allocation of multi-UAV missions more rational.

[0046] Furthermore, the attitude control method for the rotary-wing UAV also includes the following steps: Step S105: Analyze the follow-up monitoring data, plan and generate work adjustment data, and adjust the working attitude of the direct-working UAV accordingly based on the work adjustment data.

[0047] In this embodiment of the invention, by analyzing the follow-up monitoring data, the location of fire-fighting needs in the direct work area is determined. Based on the work space location and the fire-fighting need location, flight adjustment and attitude adjustment planning are carried out to generate work adjustment data. Then, based on the work adjustment data, flight adjustment instructions and attitude adjustment instructions are generated. In addition, the flight position of the direct work UAV is adjusted according to the flight adjustment instructions, and the flight attitude of the direct work UAV is adjusted according to the attitude adjustment instructions.

[0048] Specifically, Figure 6 A flowchart illustrating the corresponding adjustment of the working posture in the method provided by an embodiment of the present invention is shown.

[0049] In a preferred embodiment of the present invention, the step of analyzing the follow-up monitoring data, planning and generating work adjustment data, and adjusting the working attitude of the direct-working UAV according to the work adjustment data specifically includes the following steps: Step S1051: Analyze the follow-up monitoring data to determine the location of fire protection needs; Step S1052: Based on the workspace location and the fire-fighting requirement location, perform flight adjustment and attitude adjustment planning to generate work adjustment data; Step S1053: Generate flight adjustment commands and attitude adjustment commands based on the work adjustment data; Step S1054: Adjust the flight position of the direct-working UAV according to the flight adjustment command; Step S1055: Adjust the flight attitude of the direct-working UAV according to the attitude adjustment command.

[0050] Furthermore, Figure 7 An application architecture diagram of the system provided in an embodiment of the present invention is shown.

[0051] In another preferred embodiment of the present invention, the attitude control system for a rotary-wing unmanned aerial vehicle includes: The firefighting drone selection unit 101 is used to receive firefighting work requirements, plan target firefighting routes, and select direct-operation drones and auxiliary monitoring drones from multiple rotary-wing drones.

[0052] In this embodiment of the invention, the fire-fighting drone selection unit 101 receives fire-fighting work requirements, identifies the location of the fire-fighting work requirements, determines the target fire-fighting location, plans the target fire-fighting route according to the target fire-fighting location, acquires the drone status data of multiple standby rotary-wing drones, determines the endurance requirement according to the target fire-fighting route, and then compares and analyzes the status data of multiple drones based on the endurance requirement. From the multiple rotary-wing drones, it selects a direct-operation drone and an auxiliary monitoring drone. The direct-operation drone is a rotary-wing drone that directly performs fire-fighting work; the auxiliary monitoring drone is a rotary-wing drone that does not participate in direct fire-fighting work but performs real-time monitoring.

[0053] Specifically, Figure 8 The diagram shows a structural block diagram of the fire-fighting drone selection unit 101 in the system provided by an embodiment of the present invention.

[0054] In a preferred embodiment of the present invention, the firefighting drone selection unit 101 specifically includes: The demand receiving module 1011 is used to receive fire protection work demands; The demand identification module 1012 is used to identify the fire protection work demand and determine the target fire protection location; The route planning module 1013 is used to plan the target fire route according to the target fire location; The status data acquisition module 1014 is used to acquire the status data of multiple rotary-wing drones; The drone selection module 1015 is used to compare the status data of multiple drones and select a direct-operation drone and an auxiliary monitoring drone from the multiple rotor drones.

[0055] Furthermore, the rotary-wing UAV attitude control system also includes: The basic flight control unit 102 is used to perform basic flight control on the direct-operation UAV and the auxiliary monitoring UAV according to the target fire-fighting route, and to receive basic environmental data transmitted by the auxiliary monitoring UAV.

[0056] In this embodiment of the invention, the basic flight control unit 102 performs basic flight control on the direct-operation drone and the auxiliary monitoring drone according to the target fire-fighting route, so that the direct-operation drone and the auxiliary monitoring drone arrive at the target fire-fighting location, and receives arrival feedback from the direct-operation drone and the auxiliary monitoring drone. Then, it generates environmental monitoring instructions and sends the environmental monitoring instructions to the auxiliary monitoring drone, and then receives basic environmental data transmitted by the auxiliary monitoring drone.

[0057] The in-situ flight control unit 103 is used to analyze the basic environmental data, plan the direct working area and the auxiliary monitoring position, and perform in-situ flight control on the direct working UAV and the auxiliary monitoring UAV.

[0058] In this embodiment of the invention, the in-situ flight control unit 103 analyzes basic environmental data to determine fire hazard areas, selects nearby direct work areas based on the fire hazard areas, and plans auxiliary monitoring positions based on the direct work areas and preset auxiliary monitoring parameters. Then, according to the direct work areas, it performs in-situ flight control on the direct work drone, so that the direct work drone flies to the direct work areas to carry out firefighting operations. And according to the auxiliary monitoring positions, it performs in-situ flight control on the auxiliary monitoring drone, so that the auxiliary monitoring drone flies to the auxiliary monitoring positions to carry out real-time monitoring.

[0059] Specifically, Figure 9 A structural block diagram of the in-situ flight control unit 103 in the system provided by an embodiment of the present invention is shown.

[0060] In a preferred embodiment provided by the present invention, the in-situ flight control unit 103 specifically includes: The environmental analysis module 1031 is used to analyze the basic environmental data and determine fire hazard areas; The work area planning module 1032 is used to plan the direct work area based on the fire hazard area; The monitoring location planning module 1033 is used to plan auxiliary monitoring locations based on the direct working area; The first in-place flight control module 1034 is used to perform in-place flight control on the direct working UAV according to the direct working area; The second in-place flight control module 1035 is used to perform in-place flight control on the auxiliary monitoring UAV according to the auxiliary monitoring position.

[0061] Furthermore, the rotary-wing UAV attitude control system also includes: The monitoring and follow-up adjustment unit 104 is used to acquire the working space position of the direct working UAV in real time, perform follow-up adjustment of the monitoring attitude of the auxiliary monitoring UAV, and acquire the follow-up monitoring data of the auxiliary monitoring UAV in real time.

[0062] In this embodiment of the invention, the monitoring and follow-up adjustment unit 104 acquires the working space position of the direct working UAV in the direct working area in real time, performs monitoring planning for the auxiliary monitoring UAV according to the working space position, determines the attitude adjustment angle, and then performs follow-up adjustment of the monitoring attitude of the auxiliary monitoring UAV according to the attitude adjustment angle, so that the auxiliary monitoring UAV can monitor the direct working UAV in real time and acquire the follow-up monitoring data of the auxiliary monitoring UAV in real time.

[0063] Specifically, Figure 10 A structural block diagram of the monitoring and follow-up adjustment unit 104 in the system provided by an embodiment of the present invention is shown.

[0064] In a preferred embodiment of the present invention, the monitoring and follow-up adjustment unit 104 specifically includes: Real-time positioning module 1041 is used to acquire the workspace position of the direct-working UAV in real time; The monitoring planning module 1042 is used to perform monitoring planning for the auxiliary monitoring drone according to the workspace location and determine the attitude adjustment angle; The attitude adjustment module 1043 is used to adjust the attitude of the auxiliary monitoring UAV according to the attitude adjustment angle. The monitoring data acquisition module 1044 is used to acquire the follow-up monitoring data of the auxiliary monitoring drone in real time.

[0065] Furthermore, the rotary-wing UAV attitude control system also includes: The work-corresponding adjustment unit 105 is used to analyze the follow-up monitoring data, plan and generate work adjustment data, and adjust the working attitude of the direct-working UAV according to the work adjustment data.

[0066] In this embodiment of the invention, the work-corresponding adjustment unit 105 analyzes the follow-up monitoring data to determine the fire-fighting demand location in the direct work area. Based on the work space location and the fire-fighting demand location, it performs flight adjustment and attitude adjustment planning, generates work adjustment data, and then generates flight adjustment instructions and attitude adjustment instructions according to the work adjustment data. In turn, it adjusts the flight position of the direct work UAV according to the flight adjustment instructions and adjusts the flight attitude of the direct work UAV according to the attitude adjustment instructions.

[0067] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0068] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0069] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0070] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0071] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method of attitude control for a rotorcraft unmanned aerial vehicle, characterized by, The method specifically includes the following steps: Receive firefighting work requirements, plan target firefighting routes, and select direct-operation drones and auxiliary monitoring drones from multiple rotary-wing drones; According to the target firefighting route, perform basic flight control on the direct-operation drone and the auxiliary monitoring drone, and receive basic environmental data transmitted by the auxiliary monitoring drone; The basic environmental data is analyzed to plan the direct working area and auxiliary monitoring location, and the direct working UAV and the auxiliary monitoring UAV are controlled in place for flight. The system acquires the workspace position of the direct-working UAV in real time, adjusts the monitoring attitude of the auxiliary monitoring UAV accordingly, and acquires the follow-up monitoring data of the auxiliary monitoring UAV in real time. The motion monitoring data is analyzed to generate work adjustment data, and the working attitude of the direct-working UAV is adjusted accordingly based on the work adjustment data. The process of receiving firefighting work requests, planning target firefighting routes, and selecting direct-operation drones and auxiliary monitoring drones from multiple rotary-wing drones specifically includes the following steps: Receive fire protection work requests; Identify the fire protection needs and determine the target fire protection locations; Plan the target fire route according to the target fire location; Acquire drone status data from multiple rotary-wing drones; Compare the status data of multiple UAVs, and select a direct-operation UAV and an auxiliary monitoring UAV from the multiple rotary-wing UAVs; The process of analyzing the basic environmental data, planning the direct working area and auxiliary monitoring locations, and performing in-situ flight control of the direct working UAV and the auxiliary monitoring UAV specifically includes the following steps: The basic environmental data is analyzed to identify fire hazard areas; Based on the aforementioned fire hazard areas, the direct work area is planned; Based on the aforementioned direct working area, plan the locations for auxiliary monitoring; According to the direct working area, perform in-situ flight control on the direct working UAV; According to the auxiliary monitoring location, the auxiliary monitoring UAV is controlled to fly in place. The specific steps for planning auxiliary monitoring locations based on the direct working area include: Acquire data from the direct working area, including real-time temperature distribution data, fire spread vector, and wireless signal strength distribution map. Based on the fire spread vector analysis, the core coordinates of the fire source are determined, and a polar coordinate system is established with the core coordinates of the fire source as the center. In the polar coordinate system, the fire intensity influence weight of each location point is calculated based on the distance between the fire source and each location point, and a hazard level gradient map centered on the fire source is obtained. The temperature distribution data is subjected to second-order differential operations to locate the temperature abrupt change boundary; based on the temperature abrupt change boundary, the combustion front at the edge of the fire is identified, potential deflagration risk areas are marked, and an enhanced thermal map with key thermal features marked is obtained. Based on the wireless signal strength distribution map, morphological dilation is performed on the signal blind zone to construct a communication security buffer, resulting in a region segmentation map with communication protection weights. The hazard level gradient map centered on the fire source, the enhanced thermal map marked with key thermal features, and the region segmentation map with communication security weights are synthesized into an equivalent potential field with multi-physics coupling using a weighted superposition algorithm, resulting in a composite potential field that includes fire threat, thermal features, and communication security. The horizontal position coordinates of each drone are encoded into the probability amplitude of qubits, a dedicated quantum register is assigned to each drone, a two-dimensional quantum grid is established, and the initial quantum state probability cloud distribution map is obtained. Based on the initial quantum state probability cloud distribution map, the composite potential field is injected into the Hamiltonian of the quantum system, and the fire potential energy constraint term is embedded in the quantum state wave function to generate the optimized quantum state probability cloud distribution map. Based on the optimized quantum state probability cloud distribution map, a controlled NOT gate is applied between adjacent UAV qubits to establish the correlation and entanglement relationship between qubits; Using the cosine function of the viewpoint difference as the phase rotation factor, and applying phase modulation under the viewpoint difference constraint to the entangled state, a quantum state evolution equation is generated. Based on the quantum state evolution equation, an adjustable rotation gate is inserted into the quantum circuit to establish a mapping channel between quantum states and classical parameters, resulting in a trainable hybrid quantum-classical computing model. Based on a trainable hybrid quantum-classical computing model, the expected energy value of the quantum state in the composite potential field is calculated to evaluate the fidelity index of the monitoring network coverage and obtain the system energy assessment value under the current parameters. Based on the system energy assessment value under the current parameters, the rotating gate parameters are iteratively optimized using the gradient descent method. After optimization, the quantum state probability distribution under the optimal parameters is obtained. Based on the quantum state probability distribution under optimal parameters, the region with the maximum quantum state amplitude is extracted as candidate coordinates, and the probability amplitude is converted into actual geographic coordinate offset to adjust the candidate coordinates, thus obtaining a set of high-precision monitoring point coordinates. The high-precision set of monitoring point coordinates is input into the real-time path planner and fine-tuned in combination with wind speed and obstacle data to generate a flight trajectory instruction set with speed curves; A simulated monitoring perspective is generated based on the flight trajectory instruction set with velocity curves, and the three-dimensional overlapping area of ​​the simulated monitoring perspective is calculated. An auxiliary monitoring position is selected based on the coverage of the three-dimensional overlapping area of ​​the simulated monitoring perspective.

2. The rotor drone attitude control method of claim 1, wherein, The comparison of status data from multiple UAVs, and the selection of direct-operation UAVs and auxiliary monitoring UAVs from the multiple rotary-wing UAVs, specifically includes the following steps: Acquire drone status data and target fire route. Drone status data includes battery level, flight speed, and payload capacity. Set a load adjustment coefficient based on the drone's payload capacity. Calculate the quantitative indicators of route demand based on the target fire route. The effective driving range is calculated by multiplying the battery capacity by the load adjustment factor. The theoretical flight time was calculated using the target fire route distance and flight speed. The comprehensive score for each drone is calculated based on its effective endurance and theoretical flight time. Sort all drones by their overall scores in descending order and label the sensor type of each drone to obtain a priority ranking list with device attributes. Set the minimum flight time threshold for the target fire route, and select the first drone that meets the requirement of having an effective flight time greater than the minimum flight time threshold from the priority sorting list with equipment attributes, based on the minimum flight time threshold of the target fire route, so as to select the drone for direct operation. If none of the top 30% of the drones in the priority sorting list with device attributes meet the threshold, a manual intervention alarm will be triggered to guide the manual selection of a drone for direct operation. Using camera resolution as a screening criterion, several qualified drones were selected from a priority list with device attributes as auxiliary monitoring drones.

3. The rotor drone attitude control method of claim 2, wherein, The process of performing basic flight control on the direct-operation drone and the auxiliary monitoring drone according to the target firefighting route, and receiving basic environmental data transmitted by the auxiliary monitoring drone, specifically includes the following steps: According to the target firefighting route, perform basic flight control on the direct-operation UAV and the auxiliary monitoring UAV; Receive arrival feedback from the direct-operation drone and the auxiliary monitoring drone; Generate and send environmental monitoring commands to the auxiliary monitoring drone; Receive basic environmental data transmitted by the auxiliary monitoring drone.

4. The rotor drone attitude control method of claim 3, wherein, The basic flight control of the direct-operation drone and the auxiliary monitoring drone according to the target firefighting route specifically includes the following steps: The remaining flight distance is calculated based on the total length of the target fire route and the current distance already flown. The real-time wind speed vector is obtained by using an auxiliary drone, and the average wind speed benchmark value of the current area is obtained. The effective wind speed is calculated by using the real-time wind speed vector and the average wind speed benchmark value of the current area. The system acquires flight performance records from historical missions and current area terrain feature codes, and obtains terrain feature weights by fitting a machine learning model. The terrain feature weights are then converted into environmental degradation factors. Obtain the task urgency level and map the discretized task urgency level to a continuous numerical factor to obtain the emergency coefficient; The load adjustment coefficient is calculated based on the current liquid load and maximum payload of the drone. Obtain the drone's current remaining battery power, and use the emergency coefficient, load adjustment coefficient, and current remaining battery power to calculate the initial flight speed value; A wind resistance attenuation term is constructed using the effective wind speed and the environmental attenuation factor, and a distance attenuation term is constructed using the remaining flight distance and the environmental attenuation factor. The initial flight speed is adjusted using wind resistance attenuation and distance attenuation terms to obtain the optimal flight speed, which is then used as the basic flight control command for both the direct-operation UAV and the auxiliary monitoring UAV.

5. The attitude control method for a rotary-wing unmanned aerial vehicle according to claim 1, characterized in that, The process of acquiring the workspace position of the direct-operation UAV in real time, adjusting the monitoring attitude of the auxiliary monitoring UAV accordingly, and acquiring the follow-up monitoring data of the auxiliary monitoring UAV in real time specifically includes the following steps: The workspace location of the directly operating UAV is obtained in real time; Based on the workspace location, a monitoring plan is made for the auxiliary monitoring drone, and the attitude adjustment angle is determined; The monitoring attitude of the auxiliary monitoring drone is adjusted according to the aforementioned attitude adjustment angle. The system acquires real-time tracking monitoring data from the auxiliary monitoring drone.

6. The rotor drone attitude control method of claim 5, wherein, The process of planning the monitoring of the auxiliary monitoring drone according to the workspace location and determining the attitude adjustment angle specifically includes the following steps: Threshold segmentation is performed on real-time temperature distribution data to identify the outline of the core combustion region and obtain a temperature distribution segmentation map; Morphological closing operations are performed on the temperature distribution segmentation map to eliminate noise, and the shape features of the continuous fire front line are extracted to generate a dynamic fire evolution map with geometric feature annotations. Based on the dynamic evolution map of the fire scene with geometric feature annotations, a pre-trained fire point migration prediction model is used in conjunction with real-time wind speed to predict the coordinates of future fire points. Based on the current and future fire point coordinates, obtain the combustible material density distribution map around the fire point to calculate the combustion diffusion energy accumulation value, and normalize the combustion diffusion energy accumulation value to generate the fire point threat weight; Construct a three-dimensional spatial grid and record the real-time wind speed vector at each grid point; Kriging interpolation is performed on areas outside the sensor's measurement range to obtain the wind speed vector distribution matrix for the entire field. The wind speed magnitude of each grid point in the full-field wind speed vector distribution matrix is ​​normalized to a probability amplitude, and the three-dimensional wind field is mapped to the probability space of qubits through amplitude encoding to obtain a quantum superposition state characterizing the wind field distribution in the whole space. The quantum superposition state characterizing the wind field distribution in the whole space is subjected to a quantum Fourier transform operation to obtain the quantum Fourier transform result; The quantum state frequency components of the quantum Fourier transform results are measured to identify the dominant periodic characteristics, so as to extract the wind field dominant frequency characteristic parameters that affect the observation stability. The auxiliary drone is used to perform three-dimensional lidar scanning of obstacles in the workspace to obtain lidar point cloud data of the workspace location; The laser point cloud data of the workspace location is input into a graph convolutional network to predict the future occlusion probability of each spatial point in the workspace location. The future occlusion probability of each spatial point in the workspace location is dynamically adjusted using meteorological parameters to obtain a dynamic occlusion probability cloud map. Based on the dynamic occlusion probability cloud map, the coverage effectiveness index is defined as the information entropy value of the occlusion probability. A variational autoencoder is used to search for the observation path with the minimum entropy value in the attitude space to obtain the optimal observation path sequence and the corresponding attitude angle set. Substituting the wind field dominant frequency characteristic parameters into the basis function generator yields a wind disturbance-resistant basis function with phase compensation. The attitude angle set is decomposed into Fourier descriptors to extract the path geometric feature frequencies. The path geometric feature frequencies are then multiplied with the anti-wind disturbance basis functions with phase compensation using tensor products to obtain the anti-interference basis functions with fused path constraints. Project the coordinates of the fire points onto the observation view space of the UAV and calculate the visibility index of each fire point; The visibility index of each fire point is fused with the corresponding fire point threat weight to obtain a fire point coverage weight matrix with spatiotemporal characteristics. With fire point coverage, wind resistance stability, and energy efficiency as optimization objectives, a multi-objective optimization function is constructed using attitude angle set, fire point coverage weight matrix with spatiotemporal characteristics, and anti-interference basis function with fused path constraints. The alternating direction multiplier method is used to perform multi-objective collaborative optimization of the multi-objective optimization function. After optimization, the globally optimal attitude angle is obtained.

7. The rotor drone attitude control method of claim 6, wherein, The process of analyzing the motion monitoring data, generating work adjustment data, and adjusting the working attitude of the direct-working UAV according to the work adjustment data specifically includes the following steps: The location of fire protection needs is determined by analyzing the dynamic monitoring data. Based on the workspace location and the fire-fighting requirement location, flight adjustment and attitude adjustment planning are carried out to generate work adjustment data; Based on the work adjustment data, generate flight adjustment commands and attitude adjustment commands; The flight position of the direct-working UAV is adjusted according to the flight adjustment command. The flight attitude of the direct-working UAV is adjusted according to the attitude adjustment command.

8. A rotorcraft attitude control system employing the rotorcraft attitude control method of any one of claims 1 to 7, characterized by, The system includes a firefighting drone selection unit, a basic flight control unit, a positioning flight control unit, a monitoring and follow-up adjustment unit, and a work-corresponding adjustment unit, wherein: The firefighting drone selection unit is used to receive firefighting work requirements, plan target firefighting routes, and select direct-operation drones and auxiliary monitoring drones from multiple rotary-wing drones. The basic flight control unit is used to perform basic flight control on the direct-operation UAV and the auxiliary monitoring UAV according to the target fire-fighting route, and to receive basic environmental data transmitted by the auxiliary monitoring UAV. The in-situ flight control unit is used to analyze the basic environmental data, plan the direct working area and auxiliary monitoring position, and perform in-situ flight control on the direct working UAV and the auxiliary monitoring UAV. The monitoring and follow-up adjustment unit is used to acquire the workspace position of the direct working UAV in real time, perform follow-up adjustment of the monitoring attitude of the auxiliary monitoring UAV, and acquire the follow-up monitoring data of the auxiliary monitoring UAV in real time. The work-corresponding adjustment unit is used to analyze the follow-up monitoring data, plan and generate work adjustment data, and adjust the working attitude of the direct-working UAV according to the work adjustment data.

Images