Unmanned aerial vehicle open type control framework based on short-distance support

Abstract

The invention relates to the technical field of unmanned aerial vehicle control, in particular to an unmanned aerial vehicle open type control framework based on short-distance support, which comprises a task scheduling and sorting module, a path dynamic adjustment module, a model continuous learning module, a flight strategy verification module, an environment adaptability adjustment module and a flight performance optimization module. According to the invention, through the processing logic of real-time dynamic adjustment and continuous learning, the adaptive capability and efficiency are significantly improved when the unmanned aerial vehicle executes the short-distance support task, the task execution sequence is updated in real time, so that the unmanned aerial vehicle accurately responds to the urgent task demand, the scheduling is flexible, and the timeliness and accuracy are improved; flight environments are monitored, paths are adjusted to avoid obstacles, stable operation is kept, risks are reduced, optimal performance is ensured to be achieved in changing environments through flight data analysis, unmanned aerial vehicle flight strategy optimization, continuous learning and adaptive adjustment, and reliability and safety of long-term operation are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) control, and particularly to an open control architecture for UAVs based on close air support. Background Art

[0002] The technical field of UAV control is used to command and manage the behavior and task execution of UAVs, including flight control, navigation, path planning, automatic obstacle avoidance, communication systems, and interaction with ground control stations. The core of this field is to improve the autonomy and operation efficiency of UAVs so that they can complete complex tasks with minimal human intervention. UAV control technology also focuses on the reliability and safety of the system to ensure the stable operation of UAVs under various environmental conditions. With the progress of technology, UAV control is developing towards a more intelligent and networked direction, including using artificial intelligence algorithms to optimize flight paths and task strategies, and achieving wider network connections and data exchanges through Internet of Things technology.

[0003] Among them, the open control architecture for UAVs is a method of designing UAV control systems, aiming to provide higher flexibility and scalability. This architecture allows UAVs to access various control algorithms and hardware components in a modular manner, enabling UAVs to quickly adapt to different operation modes and environmental conditions according to specific task requirements. The main purpose of the open control architecture is to support rapid innovation and cross-platform compatibility, facilitating the integration of the latest technological developments in UAVs, such as artificial intelligence, machine learning, and automatic decision-making, enabling UAVs to perform more complex and efficient operations in changing task environments, such as disaster response, monitoring, and logistics.

[0004] Existing technologies already support basic flight control and task execution, but lack sufficient flexibility and adaptability, including in the face of complex or cyclically changing tasks and environmental conditions. Traditional UAV control adopts fixed flight strategies and path planning, which performs well in static or highly predictable environments, but in situations that require rapid response to changing environments and tasks, this fixed-mode control cannot effectively adapt, resulting in low task execution efficiency or failure. The existing technologies have limited capabilities in continuous learning and autonomous optimization, which restricts the ability of UAVs to gradually improve their performance during continuous tasks. This deficiency not only affects the operation efficiency of UAVs but also causes safety problems in complex environments, such as the inability to effectively avoid sudden obstacles, increasing the risk of task execution. Summary of the Invention

[0005] The purpose of the present invention is to solve the deficiencies existing in the prior art, and to propose an open control architecture for UAVs based on close air support.

[0006] To achieve the above object, the present invention adopts the following technical solutions: An open control architecture for an unmanned aerial vehicle based on close air support includes:

[0007] The task scheduling and sequencing module receives the close air support task requirements, evaluates the task urgency and complexity, dynamically adjusts the task execution order, rearranges the task queue, and generates a close air support task priority sequence;

[0008] The path dynamic adjustment module monitors the flight environment according to the close air support task priority sequence, adjusts the flight path in real time and avoids obstacles, and generates a close air support path adjustment result;

[0009] The model continuous learning module analyzes the flight data based on the close air support path adjustment result, updates the unmanned aerial vehicle behavior model, matches the environmental changes, and generates a close air support behavior optimization model;

[0010] The flight strategy verification module uses the close air support behavior optimization model to simulate multi-environment flights, verifies the strategy adaptability, corrects the strategy deviation, and generates a close air support strategy verification result;

[0011] The environmental adaptability adjustment module makes fine-tuning to the hardware and control logic of the unmanned aerial vehicle according to the close air support strategy verification result, and generates a close air support adaptability adjustment plan;

[0012] The flight performance optimization module analyzes the flight performance data of the unmanned aerial vehicle according to the close air support adaptability adjustment plan, optimizes the performance for the requirements of the close air support task, optimizes the reaction speed and task processing ability of the unmanned aerial vehicle, and generates a close air support performance adjustment result for the unmanned aerial vehicle.

[0013] As a further solution of the present invention, the close air support task priority sequence includes the execution order, resource allocation priority, and task urgency level. The close air support path adjustment result includes the newly calculated flight route, flight time estimation, and obstacle avoidance strategy. The close air support behavior optimization model includes behavior adjustment algorithms, flight mode adaptation, and control response optimization. The close air support strategy verification result includes strategy accuracy, adaptability evaluation, and operation stability. The close air support adaptability adjustment plan includes control algorithm upgrade, hardware interface adjustment, and feedback mechanism optimization. The close air support performance adjustment result for the unmanned aerial vehicle includes performance improvement index, energy consumption efficiency, and maintenance cycle optimization.

[0014] As a further solution of the present invention, the task scheduling and sequencing module includes:

[0015] The urgency evaluation sub-module receives the close air support task requirements, calculates the time sensitivity according to the expected start and end times of the task and the affected business scope, and performs urgency ranking to generate a task urgency index;

[0016] The complexity analysis sub-module uses the task urgency index to evaluate the amount of human resources and technical requirements needed for the task. With reference to the cross-departmental coordination requirements and combined with information, it evaluates the task complexity and obtains the complexity evaluation result.

[0017] Based on the complexity evaluation result, the execution queue reorganization sub-module rearranges the task priorities, adjusts the task queue, and obtains the near-distance support task priority sequence by dynamically updating the task execution order of the unmanned aerial vehicle.

[0018] As a further solution of the present invention, the path dynamic adjustment module includes:

[0019] Based on the near-distance support task priority sequence, the environmental monitoring sub-module collects environmental sensing data using the multivariate regression analysis method, analyzes the parameters of wind speed, temperature, and humidity, conducts terrain and landform evaluation, combines the instant weather information, updates the environmental status database, and generates the environmental status analysis result.

[0020] Using the environmental status analysis result, the path calculation sub-module sets the flight altitude and speed parameters, connects the path points using graph theory, optimizes the path and matches the environmental changes, reconstructs the flight trajectory, and obtains the optimal path plan.

[0021] Through the optimal path plan, the obstacle avoidance sub-module implements path dynamic adjustment, monitors and identifies sudden obstacles, adjusts the flight direction and speed, optimizes the trajectory and avoids obstacles, and generates the near-distance support path adjustment result.

[0022] As a further solution of the present invention, the formula of the multivariate regression analysis method is as follows:

[0023]

[0024] Calculate the environmental status index Y to obtain the environmental condition update value. Among them, β0 represents the intercept term, β1X1 represents the weighted influence of wind speed on the environmental status index, X1 is the measured value of wind speed, β1 is the influence weight of wind speed, β2X2 represents the weighted influence of temperature on the environmental status index, X2 is the measured value of temperature, β2 is the influence weight of temperature, β3X3 represents the weighted influence of humidity on the environmental status index, X3 is the measured value of humidity, β3 is the influence weight of humidity, is the adjustment coefficient representing the complexity of the terrain and landform, X4 represents the evaluation value of the terrain and landform complexity, and β4 is the adjustment coefficient of the terrain complexity on the environmental status index.

[0025] As a further solution of the present invention, the model continuous learning module includes:

[0026] The data parsing sub-module captures the flight data of the UAV in a differentiated environment according to the near-range support path adjustment result, including speed, altitude, and environmental parameters, aggregates the data, analyzes the change trend, extracts key flight parameters, and generates an environmental adaptability index set;

[0027] The behavior optimization sub-module re-adjusts the UAV flight parameters based on the environmental adaptability index set, including flight altitude and speed, optimizes the obstacle avoidance logic and the response speed to sudden obstacles, makes real-time parameter adjustments with reference to environmental changes, and obtains an optimized behavior strategy;

[0028] The model update sub-module uses the optimized behavior strategy to adjust the behavior model of the UAV, iteratively updates the model parameters through real-time data feedback, and generates a near-range support behavior optimization model.

[0029] As a further solution of the present invention, the flight strategy verification module includes:

[0030] The environment simulation sub-module conducts real-time flight scenario simulation according to the near-range support behavior optimization model by adjusting simulation environment parameters, including climate factors, wind speed, and terrain type, details the impact of various environmental conditions on flight, tests the environment matching ability of the model, and obtains environment simulation data;

[0031] The strategy applicability verification sub-module uses the environment simulation data to perform flight tasks under various simulation conditions, monitors the strategy response and adjustment in real time, evaluates the performance in a changing environment, verifies the applicability of the strategy, and obtains a preliminary applicability test result;

[0032] The strategy correction sub-module applies a multi-objective optimization algorithm according to the preliminary applicability test result, analyzes the deviation of the strategy in a differentiated simulation environment, makes fine-tuning of the strategy parameters, optimizes the strategy and matches the operating conditions, and generates a near-range support strategy verification result.

[0033] As a further solution of the present invention, the formula of the multi-objective optimization algorithm is as follows:

[0034]

[0035] Calculate the strategy deviation O to obtain the optimized strategy parameters, where p1 represents the average deviation of the strategy in a differentiated simulation environment, p1 represents the stability of the strategy execution, p3 represents the coefficient of variation of the operating conditions, and w1, w2, and w3 are all weight parameters.

[0036] As a further solution of the present invention, the environmental adaptability adjustment module includes:

[0037] Based on the verification result of the close support strategy, the hardware inspection sub-module conducts on-site tests on the key hardware components of the UAV, detects the response threshold of the voltage sensor and the battery output power, records the data and evaluates the performance criteria to obtain the hardware adaptability analysis result;

[0038] According to the hardware adaptability analysis result, the control logic adjustment sub-module adjusts the UAV flight control parameters, including the flight speed and altitude control thresholds, conducts simulation flight tests and verifies the effectiveness of the adjustment, monitors the responses of the configurations in real time, and optimizes the control parameters to obtain the control parameter optimization result;

[0039] Using the control parameter optimization result, the dynamic path planning sub-module rearranges the UAV flight strategy, including path selection and obstacle avoidance strategy adjustment, matches the target environmental conditions, and forms a close support adaptability adjustment plan through verification tests.

[0040] As a further solution of the present invention, the flight performance optimization module includes:

[0041] Based on the close support adaptability adjustment plan, the performance data analysis sub-module extracts real-time flight data from the UAV control configuration, including flight speed, altitude adjustment time, and mission execution reaction time, conducts data sorting and preliminary analysis, identifies performance optimization points, determines the adjustment direction by monitoring data fluctuations, and generates the performance benchmark analysis result;

[0042] Based on the performance benchmark analysis result, the performance tuning sub-module adjusts the key parameters in the flight control configuration, optimizes the reaction speed threshold and the task processing time interval, monitors the real-time effect of the adjustment through in-field flight tests, gradually adjusts and captures the performance data after adjustment to obtain the tuning verification result;

[0043] The performance adjustment plan implementation sub-module integrates the optimized data in the tuning verification result, records the adjusted flight parameters and behavior strategies, formulates an operation manual and a performance record form, and generates the UAV close support performance adjustment result.

[0044] Compared with the prior art, the advantages and positive effects of the present invention are as follows:

[0045] In the present invention, through the processing logic of real-time dynamic adjustment and continuous learning, the adaptive ability and efficiency of the unmanned aerial vehicle (UAV) during the execution of close-range support missions are greatly improved. By updating the task execution sequence in real time, the UAV can respond more precisely to urgent and complex task requirements. This flexible task scheduling significantly enhances the timeliness and accuracy of task completion. By real-time monitoring the flight environment and adjusting the flight path to avoid sudden obstacles, the UAV can maintain stable operation in various complex environments, reducing risks and delays during task execution. By analyzing flight data to update the behavior model, the UAV accumulates experience during multiple task executions and continuously optimizes the flight strategy. This continuous learning and adaptive adjustment of the model ensure that the UAV can achieve optimal performance in a changing environment. The application of this processing logic and technical means enables the UAV to not only perform excellently in a single task but also exhibit higher reliability and safety during long-term operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is the architecture flowchart of the present invention;

[0047] Figure 2 is the schematic diagram of the architecture framework of the present invention;

[0048] Figure 3 is the flowchart of the task scheduling and sorting module in the present invention;

[0049] Figure 4 is the flowchart of the path dynamic adjustment module in the present invention;

[0050] Figure 5 is the flowchart of the model continuous learning module in the present invention;

[0051] Figure 6 is the flowchart of the flight strategy verification module in the present invention;

[0052] Figure 7 is the flowchart of the environmental adaptability adjustment module in the present invention;

[0053] Figure 8 is the flowchart of the flight performance optimization module in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present 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 only used to explain the present invention and are not used to limit the present invention.

[0055] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by terms such as "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality of" is two or more unless otherwise specifically defined.

[0056] Embodiment 1

[0057] Please refer to Figures 1 to 2 , an open control architecture for an unmanned aerial vehicle based on close air support includes:

[0058] The task scheduling and sequencing module receives the close air support task requirements, dynamically evaluates the task priorities according to the urgency and complexity of the tasks, rearranges the task queue, updates the task execution order of the unmanned aerial vehicle in real time, and generates a close air support task priority sequence;

[0059] The path dynamic adjustment module monitors the flight environment in real time according to the close air support task priority sequence, calculates the path of the unmanned aerial vehicle to the target point, adjusts the flight path and avoids sudden obstacles, and generates a close air support path adjustment result;

[0060] The model continuous learning module analyzes the flight data based on the close air support path adjustment result, updates the unmanned aerial vehicle behavior model and matches the environmental changes and task requirements, optimizes the flight strategy, and generates a close air support behavior optimization model;

[0061] The flight strategy verification module uses the close air support behavior optimization model to conduct simulated flights under various environments and conditions, verifies the real-time applicability of the strategy, corrects the existing strategy deviations, and generates a close air support strategy verification result;

[0062] The environmental adaptability adjustment module makes fine adjustments to the hardware and control logic of the unmanned aerial vehicle according to the close air support strategy verification result, and generates a close air support adaptability adjustment plan;

[0063] The flight performance optimization module analyzes the flight performance data of the unmanned aerial vehicle according to the close air support adaptability adjustment plan, conducts performance tuning for the requirements of the close air support task, optimizes the reaction speed and task processing ability of the unmanned aerial vehicle, and generates a close air support performance adjustment result for the unmanned aerial vehicle.

[0064] The close air support mission priority sequence includes the execution order, resource allocation priority, and task urgency level. The close air support path adjustment results include the newly calculated flight route, estimated flight time, and obstacle avoidance strategy. The close air support behavior optimization model includes behavior adjustment algorithms, flight mode adaptation, and control response optimization. The close air support strategy verification results include strategy accuracy, adaptability assessment, and operation stability. The close air support adaptability adjustment plan includes control algorithm upgrades, hardware interface adjustments, and feedback mechanism optimization. The performance adjustment results of the UAV close air support include the performance improvement index, energy consumption efficiency, and maintenance cycle optimization.

[0065] Specifically, as Figure 2 , 3 shown, the task scheduling and sequencing module includes:

[0066] The urgency assessment sub-module receives the close air support mission requirements, calculates the time sensitivity based on the expected start and end times of the mission and the affected business scope, performs urgency ranking, and generates the execution process of the task urgency indicator as follows;

[0067] The urgency assessment sub-module receives the close air support mission requirements. The urgency assessment process first needs to determine the time sensitivity of the mission, which involves analyzing the expected start and end times of the mission. According to the scope and degree of impact on the affected business, calculate the time sensitivity of each task. The urgency assessment determines its priority by analyzing the degree of dependence of different tasks on time. The task start and end times, as the main time parameters, together with the business impact scope, are used as the input items for calculation. Through time sensitivity analysis, the task urgency indicator is generated. This indicator is presented in numerical form and reflects the urgency of the task for subsequent task ranking processing. The urgency assessment result is output as the task urgency indicator, which is used for subsequent complexity analysis and task queue reorganization.

[0068] The complexity analysis sub-module uses the task urgency indicator to evaluate the amount of human resources and technical requirements needed for the task, refers to the cross-departmental coordination requirements, and combines information to evaluate the task complexity and obtain the execution process of the complexity assessment result as follows;

[0069] Use the task urgency indicator to evaluate the task complexity, according to the formula:

[0070] C a = a·H + b·R + c·T

[0071] Calculate the task complexity, where C aLet C represent the task complexity, H represent the task urgency index, R represent the amount of human resources, T represent the level of technical requirements, and the parameters a, b, and c be the weights for each item. The calculation process of complexity analysis involves weighted aggregation of various resources and requirements according to their importance. The setting of weight parameters is based on previous statistical data and practical operation experience. By adjusting the weights, the evaluation accuracy of task complexity can be optimized, thereby more effectively sorting tasks and allocating resources;

[0072] Set the urgency index of a certain task as H = 0.8, the required amount of human resources as R = 5, the level of technical requirements as T = 3, and the weights are set as a = 0.5, b = 0.3, c = 0.2 respectively. Substitute the values into the formula according to the above formula to calculate C a :

[0073] C a = 0.5·0.8 + 0.3·5 + 0.2·3 = 0.4 + 1.5 + 0.6 = 2.5

[0074] This indicates that the comprehensive complexity of this task is 2.5, and the value helps the decision - maker identify the priority of resource allocation.

[0075] Based on the complexity evaluation results, the execution queue reorganization sub - module rearranges the task priorities, adjusts the task queue, and obtains the execution process of the close - range support task priority sequence by dynamically updating the task execution order of the UAV as follows;

[0076] Based on the complexity evaluation results, the execution queue reorganization sub - module rearranges the task priorities. The queue reorganization operation mainly depends on the calculated task complexity indicators. First, all tasks to be executed are sorted according to the complexity indicators, and high - complexity tasks obtain higher priorities. Such sorting ensures that urgent and complex tasks can obtain resources first. The reorganized task queue further adjusts the task execution order of the UAV. By dynamically updating the task list, optimal allocation and use of resources are achieved. After the queue adjustment, the generated close - range support task priority sequence will directly affect the operation strategy and flight path of the UAV, ensuring the most efficient support effect during implementation. The optimization of the execution queue not only improves the task execution efficiency but also ensures that high - priority tasks can obtain sufficient support when necessary.

[0077] Specifically, as Figure 2 、 4 shown, the path dynamic adjustment module includes:

[0078] Based on the close - range support task priority sequence, the environmental monitoring sub - module collects environmental sensing data using the multivariate regression analysis method, analyzes the parameters of wind speed, temperature, and humidity, and conducts terrain and landform evaluation. Combining real - time weather information, it updates the environmental status database and generates the execution process of the environmental status analysis result as follows;

[0079] The formula for the multivariate regression analysis method is as follows:

[0080]

[0081] Calculate the environmental status index Y to obtain the updated value of the environmental condition. Among them, β0 represents the intercept term, β1X1 represents the weighted impact of wind speed on the environmental status index, X1 is the measured value of wind speed, β1 is the impact weight of wind speed, β2X2 represents the weighted impact of temperature on the environmental status index, X2 is the measured value of temperature, β2 is the impact weight of temperature, β3X3 represents the weighted impact of humidity on the environmental status index, X3 is the measured value of humidity, β3 is the impact weight of humidity, is the adjustment coefficient representing the complexity of the terrain and landform, X4 represents the evaluation value of the terrain and landform complexity, and β4 is the adjustment coefficient of the terrain complexity on the environmental status index.

[0082] Detailed explanation of the formula and the derivation process of formula calculation:

[0083] In this multivariate regression analysis, the parameters are defined and calculated as follows:

[0084] β0 is the intercept term, which is determined by analyzing historical data and is set to 15. This represents the environmental status baseline when there is no environmental input (such as wind speed, temperature, humidity, and terrain complexity are 0);

[0085] β1 is the weight of wind speed, which is determined by studying the historical impact of actual measurement data on the environmental status and is set to 0.05. This means that for every one-unit increase in wind speed, the environmental status index increases by 0.05 units;

[0086] X1 is the actual measured value of wind speed, which is obtained through a high-precision meteorological sensor and is set to 20 km / h;

[0087] β2 is the weight of temperature, which is determined by studying the actual impact of temperature changes on the environmental status and is set to 0.1, indicating that for every 1°C increase in temperature, the environmental status index increases by 0.1 units;

[0088] X2 is the actual measured value of temperature, which is obtained through an environmental monitoring system and is set to 25°C;

[0089] β3 is the weight of humidity, which is determined by an empirical study of the relationship between humidity and the environmental status and is set to 0.03. This means that for every 1%RH increase in humidity, the environmental status index increases by 0.03 units;

[0090] X3 is the actual measured value of humidity, which is measured through an environmental sensor and is set to 60%RH;

[0091] β4 is the adjustment coefficient of terrain complexity to the environmental state index, which is determined by analyzing data on the impact of different terrains on the environment. It is set to 5, indicating that an increase in terrain complexity will adjust the environmental state index through the effect of this coefficient.

[0092] X4 is the evaluation value of terrain and landform complexity, which is calculated by professional terrain analysis software and set to 10. Calculate the contribution of wind speed to the environmental state index:

[0093] β1X1 = 0.05 × 20 = 1

[0094] Calculate the contribution of temperature to the environmental state index:

[0095] β2X2 = 0.1 × 25 = 2.5

[0096] Calculate the contribution of humidity to the environmental state index:

[0097] β3X3 = 0.03 × 60 = 1.8

[0098] Calculate the impact of the adjustment coefficient of terrain complexity on the environmental state index:

[0099]

[0100] Calculate the total environmental state index:

[0101] Y = 15 + 1 + 2.5 + 1.8 + 1.58 = 21.88. This result indicates that under the current environmental parameters, the obtained environmental state index is 21.88. This value can be used to evaluate the overall environmental condition and make further environmental management and adjustment decisions based on this value.

[0102] The path calculation sub-module uses the environmental state analysis results, sets the flight altitude and speed parameters, connects the path points using graph theory, optimizes the path and matches the environmental changes, reconstructs the flight trajectory, and the execution process for obtaining the optimal path plan is as follows;

[0103] Based on the analysis results of the environmental status, the flight altitude and speed parameters are set. The operating system of the aircraft will first process the environmental data, extract the current meteorological conditions, terrain features, and potential obstacle information. The data is collected in real time through sensors and then analyzed by the central processor to determine the initial values of the flight altitude and speed. The graph theory is used to connect each predetermined path point, including calculating the shortest path between each two points, and referring to the influence of environmental factors such as wind speed and terrain on the flight path. It will also receive real-time data updates from environmental monitoring devices to dynamically optimize the flight path and ensure the practicality and safety of the path. In the process of connecting path points, it specifically includes constructing a graph model using nodes and edges. Each node represents a stop point or a key turning point, and the edge represents the feasible flight path between nodes. According to the weights of each edge, that is, the flight costs, such as time, energy consumption, and safety risks, etc., the path with the smallest weight is selected. The path calculation sub-module not only optimizes the flight path but also can reconstruct the path in real time according to environmental changes, so as to obtain the optimal path plan, reconstruct the flight trajectory, and obtain the optimal path plan.

[0104] The obstacle avoidance sub-module implements path dynamic adjustment through the optimal path plan, monitors and identifies sudden obstacles, adjusts the flight direction and speed, optimizes the trajectory and avoids obstacles. The execution process of generating the near-distance support path adjustment result is as follows;

[0105] Through the optimal path plan, path dynamic adjustment is implemented. During the flight process, the obstacle recognition system continuously monitors the space obstacles in front of the aircraft, such as tall buildings, protruding antennas, or aircraft, etc. Once a potential obstacle is recognized, the system will immediately calculate the distance and relative speed to the obstacle, and judge whether it is necessary to adjust the flight trajectory. If necessary, the obstacle avoidance sub-module will adjust the direction and speed of the aircraft, modify the flight parameters to avoid obstacles, ensure flight safety, and can also generate a backup path, that is, a near-distance support path, to cope with more sudden situations, so as to optimize the trajectory and avoid obstacles, generate the near-distance support path adjustment result, and perform dynamic adjustment and optimization, ensuring the smooth completion of the flight mission, and at the same time improving the flexibility of the path plan and the ability to respond to emergencies.

[0106] Specifically, as Figure 2 、 5 shown, the model continuous learning module includes:

[0107] The data parsing sub-module captures the flight data of the UAV in different environments according to the near-distance support path adjustment result, including speed, altitude, and environmental parameters, aggregates and processes the data, analyzes the change trend, extracts the key flight parameters, and the execution process of generating the environmental adaptability index set is as follows;

[0108] Capture the UAV flight data and perform aggregation processing according to the formula:

[0109] E = α·v + β·h + γ·p

[0110] Calculate the environmental adaptability index set, where E represents the environmental adaptability index set, v represents speed, h represents altitude, p represents environmental parameters, and the parameters α, β, and γ are weight coefficients;

[0111] During the data aggregation process, each flight parameter such as speed and altitude is converted into a corresponding impact index, and the index combines environmental parameters to measure the adaptability of the UAV to the environment. Speed and altitude data are collected in real time through sensors, and environmental parameters are obtained through external environmental monitoring devices;

[0112] Set the speed of the UAV during actual flight as v = 50 m / s, the altitude as h = 1200 m, the environmental parameter (such as the impact index of temperature or humidity) as p = 0.5, and the weight coefficients as α = 0.3, β = 0.5, γ = 0.2. Then the environmental adaptability index set can be calculated as

[0113] E = 0.3·50 + 0.5·1200 + 0.2·0.5 = 15 + 600 + 0.1 = 615.1;

[0114] This calculation result shows that the adaptability score of the UAV under the given environmental conditions is 615.1, and a higher value indicates good environmental adaptability.

[0115] Based on the environmental adaptability index set, the behavior optimization sub-module re-adjusts the UAV flight parameters, including flight altitude and speed, optimizes the obstacle avoidance logic and the response speed to sudden obstacles, makes real-time parameter adjustments with reference to environmental changes, and the execution process of obtaining the optimized behavior strategy is as follows;

[0116] Re-adjust the UAV flight parameters according to the environmental adaptability index set. The adjustment of the UAV flight parameters is mainly based on real-time environmental data and previous flight performance evaluations. The implementation of behavior optimization involves adjusting flight altitude and speed to adapt to the cyclically changing external environment. By optimizing the UAV's obstacle avoidance logic and response strategy to sudden obstacles, the operation flexibility and safety of the UAV in complex environments are effectively improved. Real-time parameter adjustments are based on environmental changes to ensure that the UAV can maintain the best flight state under various environmental conditions. The optimized behavior strategy dynamically adjusts flight parameters by analyzing the relationship between the environmental adaptability index set and real-time environmental data, so that the UAV is more accurate and safe when performing tasks.

[0117] The model update sub-module uses the optimized behavior strategy to adjust the UAV's behavior model, iteratively updates the model parameters through real-time data feedback, and the execution process of generating the near-distance support behavior optimization model is as follows;

[0118] Adjust the behavior model of the drone using an optimized behavior strategy, which includes real-time data feedback and iterative updates of model parameters. The key to model update lies in cyclically adjusting the behavior model according to flight data and environmental adaptability evaluation results to adapt to environmental changes. The updated model parameters are calculated by analyzing previous flight data and current environmental conditions. This data-driven update strategy ensures that the behavior logic of the drone always remains up-to-date. Through this continuous self-optimization process, the close air support behavior optimization model improves the response speed and accuracy of the drone to environmental changes, enabling it to more effectively adapt to complex flight environments when performing close air support tasks.

[0119] Specifically, as Figure 2 、 6 shown, the flight strategy verification module includes:

[0120] The environmental simulation sub-module, based on the close air support behavior optimization model, conducts real-time flight scenario simulations by adjusting simulation environment parameters, including climate factors, wind speed, and terrain type, to refine the impact of various environmental conditions on flight and test the environment matching ability of the model. The execution process of obtaining environmental simulation data is as follows;

[0121] Based on the close air support behavior optimization model, real-time flight scenario simulations are conducted by adjusting simulation environment parameters, including climate factors, wind speed, and terrain type. An advanced computational model is used to create near-real flight conditions and simulate flight performance under different climates, such as weather conditions like rain, fog, and strong winds. By changing wind speed and direction parameters, the simulation sub-module can test the stability and maneuverability of the aircraft under crosswind or headwind conditions. Terrain simulation includes mountains, highlands, urban building complexes, etc., which are constructed using data obtained from a terrain database to ensure the diversity and complexity of the simulation environment. When conducting environmental simulations, the system generates multiple flight scenarios based on differentiated climate and terrain data, and each scenario specifically details the specific impact of various environmental conditions on flight. For example, when flying in mountainous areas, the system will refer to the instability of airflows and the blocking effect of terrain; in urban areas, it will focus on simulating the vent effect between high-rise buildings and GPS signal interference, and refine the simulation to assist in detecting the response ability of the flight control system and the accuracy of the navigation system. The simulation results will be output in the form of data packets, including the dynamic response data of the aircraft and environmental adaptability analysis, which are all key data for testing the environment matching ability of the model to obtain environmental simulation data.

[0122] The strategy applicability verification sub-module uses environmental simulation data to perform flight tasks under various simulation conditions, monitors strategy responses and adjustments in real-time, evaluates performance in changing environments, and verifies the applicability of the strategy. The execution process of obtaining preliminary applicability test results is as follows;

[0123] Using environmental simulation data, flight missions are carried out under various simulation conditions. The main function of this module is to evaluate the adaptability and effectiveness of flight control strategies under different environmental conditions. Through simulation data, the verification sub-module can set multiple flight missions, such as flying through complex terrains and maintaining routes in unstable climates. For each mission, the response time, adjustment accuracy, and final flight effect of the strategy are recorded to monitor the performance of the strategy in real time. The module also analyzes the timeliness and accuracy of strategy adjustments, evaluates its response capabilities in emergencies and extreme conditions. Through comprehensive tests, the verification sub-module can evaluate the performance of various strategies in changing environments and comprehensively verify the applicability of the strategies, obtaining preliminary applicability test results. This process not only ensures the safety and efficiency of flight missions but also improves the accuracy and scope of application of strategy adjustments.

[0124] Based on the preliminary applicability test results, the strategy correction sub-module applies a multi-objective optimization algorithm to analyze the deviations of the strategy in different simulated environments, fine-tune the strategy parameters, optimize the strategy and match the operating conditions. The execution process of generating the verification results of the close air support strategy is as follows;

[0125] The formula of the multi-objective optimization algorithm is as follows:

[0126]

[0127] Calculate the strategy deviation O to obtain the optimized strategy parameters. Here, p1 represents the average deviation of the strategy in different simulated environments, p2 represents the stability of the strategy execution, p3 represents the coefficient of variation of the operating conditions, and w1, w2, and w3 are all weight parameters.

[0128] Detailed explanation of the formula and the derivation process of formula calculation:

[0129] p1: The average deviation of the strategy in different simulated environments, which is calculated by simulating the execution of the strategy under different operating conditions and recording the deviation results under each condition. The average deviation is the arithmetic mean of the deviation values;

[0130] p2: The stability of the strategy execution, which is obtained by calculating the standard deviation of the strategy results. The smaller the standard deviation, the closer the results of the strategy under different simulated conditions are, and the higher the stability;

[0131] p3: The coefficient of variation of the operating conditions, which is a quantitative index of the uncertainty of the operating conditions and is obtained by calculating the ratio of the standard deviation to the mean value of the operating condition data;

[0132] Weight parameters w1, w2, w3. w1 adjusts the sensitivity of the policy deviation. A high weight means that the deviation accounts for a higher proportion in the total evaluation. w2 adjusts the influence of stability. A higher value indicates an increased importance of stability in policy evaluation. w3 is used to balance the impact of the uncertainty of operating conditions on the policy. A higher weight indicates an enhanced sensitivity to environmental variability;

[0133] Set the following specific values: p1 = 0.05 (average deviation obtained through multiple simulations), p3 = 0.03 (calculated through the standard deviation of stability), p3 = 0.10 (calculated through the coefficient of variation), w1 = 1.5, w2 = 2.0, w3 = 1.2;

[0134] Calculate w1·p1 + w2·p2: 1.5×0.05 + 2.0×0.03 = 0.075 + 006 = 0.1352;

[0135] Take the square root of the above result:

[0136] Calculate w3·|p3|: 1.2×0.10×0.12;

[0137] Calculate the final formula O:

[0138] This result indicates that after the policy is adjusted with reference to the differential weight factors, the quantified effect of the deviation adjustment is 3.064, indicating that the adaptability of the policy after weight adjustment has improved under actual operating conditions. This relatively large value indicates that the policy adjustment effect is significant and can maintain higher execution quality and stability in a differential environment.

[0139] Specifically, as Figure 2 、 7 shown, the environmental adaptability adjustment module includes:

[0140] According to the verification result of the close support policy, the hardware inspection sub-module conducts on-site tests on the key hardware components of the UAV, detects the response threshold of the voltage sensor and the battery output power, records the data and evaluates the performance standards. The execution process for obtaining the hardware adaptability analysis result is as follows;

[0141] The hardware inspection sub-module conducts on-site tests on the key hardware components of the UAV, according to the formula:

[0142] P c = η·V

[0143] Calculate the battery output power, where P c represents the battery output power, V represents the response threshold of the voltage sensor, and the parameter η is the conversion efficiency coefficient;

[0144] In field tests, the response threshold of the voltage sensor is determined by actual measurement, and the output power of the battery is calculated based on the voltage value feedback by the sensor and the known battery characteristics. By comparing the measured data with the performance standards, a hardware adaptability analysis is conducted;

[0145] Suppose the measured response threshold of the voltage sensor is V = 3.7 volts, and the conversion efficiency coefficient is set as η = 0.85. Then the battery output power can be calculated as P c = 0.85 × 3.7 = 3.145 watts;

[0146] This calculation result shows the output performance of the battery under given conditions. After comparing with the performance standards, a conclusion can be drawn on whether the hardware is suitable for the current operation requirements.

[0147] According to the results of the hardware adaptability analysis, the control logic adjustment sub-module adjusts the UAV flight control parameters, including the flight speed and altitude control thresholds, conducts simulated flight tests and verifies the effectiveness of the adjustment, monitors the responses of the configuration in real time, and optimizes the control parameters. The execution process for obtaining the optimized results of the control parameters is as follows;

[0148] According to the results of the hardware adaptability analysis, the UAV flight control parameters are adjusted, including the flight speed and altitude control thresholds. Through simulated flight tests, the effectiveness of the adjustment is tested. During the adjustment process, the key implementation steps include collecting initial flight data, setting new flight parameters, performing simulated flights to monitor the adjusted flight performance, and monitoring the responses of the configuration in real time, which can ensure the stability and safety of the UAV during actual flights. The optimization of the control parameters is based on real-time data and preset performance goals. Through the detailed implementation of the steps, the optimized results of the control parameters are finally obtained, ensuring that the UAV can maintain the best performance under various flight conditions.

[0149] The dynamic path planning sub-module uses the optimized results of the control parameters to re-arrange the UAV flight strategy, including path selection and obstacle avoidance strategy adjustment, to match the target environmental conditions. The execution process for forming a close support adaptability adjustment plan through verification tests is as follows;

[0150] Using the optimized results of the control parameters, the UAV flight strategy is re-arranged. During the process, the path selection and obstacle avoidance strategies are adjusted to match the target environmental conditions. The key execution steps include analyzing the current environmental conditions, setting a new flight path, adjusting the obstacle avoidance logic, performing simulated flight tests, and forming a close support adaptability adjustment plan through actual verification tests. The plan takes into account the impact of environmental changes on the UAV flight path and ensures that the UAV can effectively cope with various obstacles in the environment through dynamic adjustment, improving the flexibility and safety of mission execution.

[0151] Specifically, such as Figure 2 、8 As shown in the figure, the flight performance optimization module includes:

[0152] According to the close air support adaptability adjustment plan, the performance data analysis sub-module extracts real-time flight data from the control configuration of the UAV, including flight speed, altitude adjustment time, and mission execution response time, conducts data sorting and preliminary analysis, identifies performance optimization points, determines the adjustment direction by monitoring data fluctuations, and the execution process of generating the performance benchmark analysis result is as follows;

[0153] Execute the task of extracting real-time flight data from the UAV control configuration, involving data capture of flight speed, altitude adjustment time, and mission execution response time. During the process of data sorting and preliminary analysis, the analysis team focuses on identifying performance optimization points through data fluctuations to determine the adjustment direction, including sorting and comparative analysis of the change trend of flight speed, the response time of altitude adjustment, and the rapidity of mission execution. Through systematic processing of data, the performance benchmark analysis result is generated, which reflects the performance of the UAV in different flight stages and mission executions and points out the optimization direction.

[0154] Based on the performance benchmark analysis result, the performance tuning sub-module adjusts the key parameters in the flight control configuration, optimizes the threshold of the reaction speed and the time interval of task processing, monitors the real-time effect of the adjustment through in-field flight tests, gradually adjusts and captures the performance data after adjustment, and the execution process of obtaining the tuning verification result is as follows;

[0155] Adjust the key parameters based on the performance benchmark analysis result, according to the formula:

[0156]

[0157] Calculate the optimization result of the task processing time interval, where Δt represents the task processing time interval, Δv represents the change in flight speed, A represents the acceleration, and τ represents the threshold of the reaction speed;

[0158] During the parameter adjustment process, the adjustment of key performance indicators such as the reaction speed threshold and time interval is based on the real-time flight test data in the flight field. The data monitors the adjustment effect in real time through the real-time adjustment and test of the flight control configuration to ensure the effectiveness of the optimization measures;

[0159] Set the change in flight speed as Δv = 5m / s, the preset acceleration as A = 2m / s 2 , set the reaction speed threshold as τ = 0.5s, substitute into the formula to calculate

[0160] This indicates that the adjusted task processing time interval is 3 seconds, and through field tests, it is verified that the time interval can significantly optimize the mission execution efficiency of the UAV.

[0161] Integrate and optimize the optimization data in the verification results of the performance adjustment plan implementation sub-module, record the adjusted flight parameters and behavior strategies, formulate an operation manual and a performance record form, and the execution process of generating the performance adjustment results for close-range support of the UAV is as follows;

[0162] Integrate and optimize the verification results, record and formulate the flight parameters and behavior strategies of the UAV. The process includes detailed recording of the adjusted flight speed, altitude, and key control parameters. The work of formulating the operation manual and the performance record form is completed by a dedicated technical team to ensure that all data is accurately recorded and archived. The records not only provide detailed guidance for UAV operators but also provide basic data for future performance evaluation and further adjustment. The generated close-range support performance adjustment results provide clear performance optimization guidelines and execution standards for UAV operations.

[0163] The above is only a preferred embodiment of the present invention and does not limit the present invention in other forms. Any person skilled in the art may use the technical content disclosed above to make changes or modifications into equivalent embodiments with equivalent changes and apply them to other fields. However, as long as it does not depart from the technical solution content of the present invention, any simple modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention still fall within the protection scope of the technical solution of the present invention.

Claims

1. An open control architecture for an unmanned aerial vehicle based on close air support, characterized in that The architecture includes: The task scheduling and sorting module receives the close air support task requirements, evaluates the task urgency and complexity, dynamically adjusts the task execution order, rearranges the task queue, and generates the close air support task priority sequence; The path dynamic adjustment module monitors the flight environment according to the close air support task priority sequence, adjusts the flight path in real time and avoids obstacles, and generates the close air support path adjustment result; The model continuous learning module analyzes the flight data based on the close air support path adjustment result, updates the UAV behavior model, matches the environmental changes, and generates the close air support behavior optimization model; The flight strategy verification module uses the close air support behavior optimization model to simulate multi-environment flight, verifies the strategy adaptability, corrects the strategy deviation, and generates the close air support strategy verification result; The environmental adaptability adjustment module fine-tunes the UAV's hardware and control logic according to the close air support strategy verification result, and generates the close air support adaptability adjustment plan; The flight performance optimization module analyzes the UAV's flight performance data according to the close air support adaptability adjustment plan, optimizes the performance for the requirements of close air support tasks, optimizes the UAV's reaction speed and task processing ability, and generates the UAV close air support performance adjustment result.

2. The open control architecture of the unmanned aerial vehicle based on close air support according to claim 1, characterized in that: The close air support task priority sequence includes the execution order, resource allocation priority, and task urgency level. The close air support path adjustment result includes the newly calculated route, flight time estimate, and obstacle avoidance strategy. The close air support behavior optimization model includes behavior adjustment algorithms, flight mode adaptation, and control response optimization. The close air support strategy verification result includes strategy accuracy, adaptability assessment, and operation stability. The close air support adaptability adjustment plan includes control algorithm upgrade, hardware interface adjustment, and feedback mechanism optimization. The UAV close air support performance adjustment result includes performance improvement index, energy consumption efficiency, and maintenance cycle optimization.

3. The open control architecture for a close range support UAV according to claim 1, characterized in that: The task scheduling and sorting module includes: The urgency assessment sub-module receives the close air support task requirements, calculates the time sensitivity based on the expected start and end times of the task and the affected business scope, and performs urgency ranking to generate the task urgency index; The complexity analysis sub-module uses the task urgency index to evaluate the required human resources and technical requirements of the task, refers to the cross-departmental coordination requirements, and combines information to evaluate the task complexity to obtain the complexity evaluation result; The execution queue reorganization sub-module rearranges the task priorities based on the complexity evaluation result, adjusts the task queue, and obtains the close air support task priority sequence by dynamically updating the UAV's task execution order.

4. The open control architecture of the unmanned aerial vehicle based on close air support according to claim 1, characterized in that: The path dynamic adjustment module includes: The environment monitoring sub-module collects environmental sensing data using the multivariate regression analysis method based on the close air support task priority sequence, analyzes the parameters of wind speed, temperature, and humidity, and conducts terrain and landform assessment. Combining the real-time weather information, it updates the environmental status database and generates the environmental status analysis result; The path calculation sub-module uses the environmental state analysis results to set the flight altitude and speed parameters, connects the path points using graph theory, optimizes the path and matches the environmental changes, reconstructs the flight trajectory, and obtains the optimal path plan; The obstacle avoidance sub-module implements dynamic path adjustment through the optimal path plan, monitors and identifies sudden obstacles, adjusts the flight direction and speed, optimizes the trajectory and avoids obstacles, and generates the near-distance support path adjustment result.

5. The open control architecture of the drone based on close air support according to claim 4, characterized in that: The formula of the multivariate regression analysis method is as follows: Calculate the environmental status index Y and obtain the updated value of the environmental condition. Among them, β0 represents the intercept term, β1X1 represents the weighted impact of wind speed on the environmental status index, X1 is the measured value of wind speed, β1 is the impact weight of wind speed, β2X2 represents the weighted impact of temperature on the environmental status index, X2 is the measured value of temperature, β2 is the impact weight of temperature, β3X3 represents the weighted impact of humidity on the environmental status index, X3 is the measured value of humidity, β3 is the impact weight of humidity, is the adjustment coefficient representing the complexity of terrain and landform, X4 represents the evaluation value of the complexity of terrain and landform, and β4 is the adjustment coefficient of terrain complexity on the environmental status index.

6. The open control architecture of the unmanned aerial vehicle based on close air support according to claim 1, characterized in that: The model continuous learning module includes: The data parsing sub-module captures the flight data of the UAV in different environments according to the near-distance support path adjustment result, including speed, altitude and environmental parameters, aggregates the data, analyzes the change trend, extracts the key flight parameters, and generates the environmental adaptability index set; The behavior optimization sub-module re-adjusts the UAV flight parameters based on the environmental adaptability index set, including flight altitude and speed, optimizes the obstacle avoidance logic and the response speed to sudden obstacles, makes real-time parameter adjustments with reference to environmental changes, and obtains the optimized behavior strategy; The model update sub-module uses the optimized behavior strategy to adjust the behavior model of the UAV, iteratively updates the model parameters through real-time data feedback, and generates the near-distance support behavior optimization model.

7. The open control architecture of the unmanned aerial vehicle based on close air support according to claim 1, characterized in that: The flight strategy verification module includes: The environmental simulation sub-module conducts real-time flight scenario simulation according to the near-distance support behavior optimization model by adjusting the simulation environment parameters, including climate factors, wind speed and terrain type, refines the influence of various environmental conditions on flight, tests the environmental matching ability of the model, and obtains the environmental simulation data; The strategy applicability verification sub-module uses the environmental simulation data to perform flight tasks under various simulation conditions, monitors the strategy response and adjustment in real time, evaluates the performance in changing environments, verifies the applicability of the strategy, and obtains the preliminary applicability test result; The strategy correction sub-module applies the multi-objective optimization algorithm according to the preliminary applicability test result, analyzes the deviation of the strategy in different simulation environments, makes fine-tuning of the strategy parameters, optimizes the strategy and matches the operating conditions, and generates the near-distance support strategy verification result.

8. The open control architecture of the unmanned aerial vehicle based on close air support according to claim 7, characterized in that: The formula of the multi-objective optimization algorithm is as follows: Calculate the strategy deviation O to obtain the optimized strategy parameters, where p1 represents the average deviation of the strategy in different simulation environments, p2 represents the stability of the strategy execution, p3 represents the coefficient of variation of the operating conditions, and w1, w2, and w3 are all weight parameters.

9. The open control architecture of the drone based on close air support according to claim 1, wherein: The environmental adaptability adjustment module includes: The hardware inspection sub-module conducts on-site tests on the key hardware components of the UAV according to the near-distance support strategy verification result, detects the response threshold of the voltage sensor and the battery output power, records the data and evaluates the performance standard, and obtains the hardware adaptability analysis result; The control logic adjustment sub-module adjusts the UAV flight control parameters according to the hardware adaptability analysis result, including the flight speed and altitude control thresholds, conducts simulation flight tests and verifies the effectiveness of the adjustment, monitors the response of the configuration in real time, and optimizes the control parameters to obtain the control parameter optimization result; The dynamic path planning sub-module utilizes the optimized results of the control parameters to re-arrange the flight strategy of the UAV, including path selection and obstacle avoidance strategy adjustment, matches the target environmental conditions, and forms a near-distance support adaptability adjustment plan through verification tests.

10. The open control architecture of the unmanned aerial vehicle based on close air support according to claim 1, wherein: The flight performance optimization module includes: The performance data analysis sub-module extracts real-time flight data from the UAV's control configuration according to the near-distance support adaptability adjustment plan, including flight speed, altitude adjustment time, and mission execution response time, conducts data sorting and preliminary analysis, identifies performance optimization points, determines the adjustment direction by monitoring data fluctuations, and generates a performance benchmark analysis result; The performance tuning sub-module adjusts the key parameters in the flight control configuration based on the performance benchmark analysis result, optimizes the threshold of the reaction speed and the time interval of task processing, monitors the real-time effect of the adjustment through in-field flight tests, gradually adjusts and captures the performance data after adjustment, and obtains a tuning verification result; The performance adjustment plan implementation sub-module integrates the optimized data in the tuning verification result, records the adjusted flight parameters and behavior strategies, formulates an operation manual and a performance record form, and generates the UAV near-distance support performance adjustment result.

Images