212 results about "Flight formation" patented technology

The invention discloses a multi-agent cooperative control system based on adaptive learning, and belongs to the technical field of multi-agent system control, and the system specifically comprises the steps: collecting and analyzing the wind field data of the position of each agent; distinguishing two typical working conditions of a global uniform wind field and a local disturbance wind field based on a consistency analysis result; for a global uniform wind field, a model prediction control method is adopted to generate a wind field compensation strategy for keeping formation stability; for a local disturbance wind field, an accurate airflow disturbance state is obtained through environment three-dimensional reconstruction and fluid simulation, then the expected track deviation of each agent is predicted, and a collaborative avoidance instruction set is generated in combination with a relative position relationship. According to the method, adaptive cooperative control of multiple agents under different wind field working conditions is realized, the hidden conflict problem caused by local wind field disturbance is effectively solved, and the flight safety and task reliability of an agent cluster in a complex environment are remarkably improved.

The invention discloses a fleet formation flight implementation method and device, equipment, a medium and a product, and belongs to the technical field of aeronautical communication. The method comprises the following steps: establishing an air-ground interconnection communication link to realize real-time data interaction between a ground control unit and a plurality of flying civil aircrafts and between the plurality of civil aircrafts; based on an air-ground interconnection communication link, an airborne ad hoc network with a leading aircraft as a core is constructed, and an information interaction network in the formation is formed. Acquiring formation flight environment data; determining a safe area of formation flight based on the formation flight environment data, and calculating the maximum number of aircrafts in the formation and the relative positions of the aircrafts in the formation; and issuing the maximum number, the relative position and the flight decision information to each airplane in the formation through the airborne ad hoc network so as to execute formation flight. According to the embodiment of the invention, the real-time performance and accuracy of communication between the fleet can be effectively improved, and the airspace operation efficiency and flight safety are improved through the formation flight of the fleet.

The invention discloses an unmanned aerial vehicle formation flight control method and device, an unmanned aerial vehicle and a storage medium. The method comprises the steps that formation parameters, flight task instruction data and flight state data of other unmanned aerial vehicles in a formation are acquired or updated; judging a control mode according to the flight task instruction data, wherein the control mode comprises at least one of the following modes: a normal control enabling and conventional flight mode, a calculation mode, a suspended hovering mode or a disintegration mode; according to the judgment result of the control mode, based on an L1 guide algorithm of self-adaptive track tracking, fusing unmanned aerial vehicle spacing control logic and / or formation control logic of formation dynamic adjustment to obtain a control instruction of an expected track and / or attitude, and executing the control instruction; and circularly executing the steps to ensure the continuity and dynamic adaptability of the unmanned aerial vehicle and the formation flight thereof. According to the scheme, a completely decentralized distributed control architecture is adopted, and a fault-tolerant mechanism is matched, so that the reliability and survivability of the formation system are remarkably improved.

The invention provides a large model and reinforcement learning combined hierarchical command control method, which is based on agents of a hierarchical structure, and is characterized in that the first layer of agents are RAG-based large model intelligent formation command agents; the second-layer intelligent agent is composed of an air strike marshalling intelligent agent and a reconnaissance and strike mixed marshalling The second-layer intelligent agent judges which subtask is executed according to the instruction sent by the first-layer intelligent agent; comprising the following steps that S1, an RAG-based large-model intelligent formation command system comprises an offline knowledge preparation stage and an online decision execution stage; s2, setting a state space, an action space and a reward and punishment function; and S3, respectively training the air strike marshalling agent and the reconnaissance and strike mixed marshalling agent, and constructing an intelligent game model based on a multi-agent reinforcement learning algorithm. According to the invention, exclusive knowledge support is provided for the large model through the RAG technology, then the structured decision instruction is generated through the large model, training is carried out based on multi-agent reinforcement learning to obtain the agent of a specific task, and formation-level command control is realized.

The invention discloses a fixed-wing unmanned aerial vehicle distributed formation and obstacle avoidance method based on diffusion reinforcement learning, and the method comprises the steps: processing single observation data through a graph attention network, and enabling the single observation data to serve as a condition for generating an optimal action in a reverse denoising process; the method is suitable for distributed cluster control of a fixed-wing unmanned aerial vehicle cluster in an unknown and disordered environment, treats huge challenges brought by complex dynamics and non-integral constraints in the cluster, and effectively solves a series of problems that an existing method is difficult to capture multi-modal action distribution necessary for robust obstacle avoidance under an uncertain condition. A large number of numerical simulation results show that the method is obviously superior to an existing baseline method in the aspects of flight stability and collision rate, the potential of a diffusion model in the aspect of extensible and robust unmanned aerial vehicle flight control is highlighted, and the method has good theoretical popularization value and engineering application prospects.

The invention belongs to the technical field of clock synchronization, and particularly relates to a high-precision clock synchronization method in an aviation cluster high-speed relative motion scene, which comprises the following steps of: S1, acquiring round-trip time RTT data based on signal transmission among nodes in an aviation cluster, and acquiring a relative radial speed v by combining an inertial navigation module; calculating by using a motion correction formula to obtain a preliminary clock skew epsilon after motion correction; in order to solve the problems of asymmetric high-speed motion path time delay, URT interference, random and nonlinear error coexistence and the like, through a four-stage cooperative scheme of RTT motion correction, URT modeling compensation, Kalman filtering smoothing and BP neural network residual optimization, the clock synchronization precision is improved to 0.1-0.3 ns, the method has strong anti-interference robustness and engineering realizability, and the method is suitable for large-scale popularization and application. The method can be widely applied to aerospace, unmanned aerial vehicle formation, satellite communication and other fields requiring high-precision clock synchronization, and effectively solves the problems of insufficient precision and poor adaptability of a traditional method in a high-speed scene.

The invention discloses a multi-unmanned aerial vehicle integrated planning and control method based on distributed model predictive control. The method comprises the following steps: S1, judging an unmanned aerial vehicle communication topology mechanism in an offline stage, determining an expected target point of each unmanned aerial vehicle, initializing a predictive state value of each unmanned aerial vehicle, and setting controller parameters; s2, the front end performs unmanned aerial vehicle positioning and local map construction according to the sensor data, and searches a reference trajectory according to the local map; s3, the rear end uses an IDMPC controller to solve according to the error between the measured value and the predicted value, and an unmanned aerial vehicle input optimal value is obtained; s4, the solved optimal input is converted into unmanned aerial vehicle attitude control quantity input through differential flatness, and unmanned aerial vehicle formation trajectory tracking is achieved. According to the method, quick response and anti-disturbance capability under the high frequency of 100Hz are realized, and the superiority of the method in the aspects of success rate, calculation efficiency and anti-disturbance performance is verified through a simulation experiment.

The invention relates to a multi-source remote sensing cooperative system based on an unmanned aerial vehicle formation and a control method, and the system can synchronously collect laser radar point cloud data, multispectral images, thermal infrared images and hyperspectral images, and breaks through the limitation of single data dimension caused by the fact that a traditional single unmanned aerial vehicle platform can only carry a single sensor. Meanwhile, the formation control module controls the heterogeneous unmanned aerial vehicle cluster to form a preset formation and perform cooperative flight to ensure spatial position cooperation of the unmanned aerial vehicles in the operation process, and the task allocation module dynamically allocates route tasks and sensor working parameters to the unmanned aerial vehicles based on target area environment information. And the data fusion module performs geometric registration, spectrum fusion and three-dimensional reconstruction processing on the multi-source remote sensing data acquired by each unmanned aerial vehicle to generate a three-dimensional spectrogram of the target area, so that accurate integration of the multi-source data in space and spectrum dimensions is realized, and the multi-source remote sensing data is acquired. Therefore, the system gives consideration to large-range area coverage capability and high monitoring precision.

The invention provides a collaborative array position planning method for remote support interference of an electronic warfare aircraft, and belongs to the technical field of shipboard aircraft combat operation. The method comprises the following steps: firstly, in a long-distance support interference scene, determining an interference coverage range of an electronic jammer from two aspects of pitching and orientation; and secondly, calculating the interference effect of the electronic jammer based on the interference unified equation. Thirdly, based on the interference coverage range, designing constraint conditions and a target function, and establishing an electronic jammer collaborative array planning problem model; and finally, based on the electronic jammer collaborative array planning problem model, a genetic algorithm is utilized to solve an electronic jammer optimal array planning scheme of long-distance support interference. The method is suitable for a collaborative array planning problem of electronic warfare aircraft remote support interference, interferes the enemy radar when the jammer formation executes a remote support interference task, reduces the detection threat of the enemy radar to the strike formation, and guarantees the smooth execution of our strike task.

The invention relates to the technical field of unmanned aerial vehicle autonomous control, and discloses an unmanned aerial vehicle cluster formation control method and system based on a multi-level intelligent algorithm, and the method comprises the steps: obtaining the external environment monitoring data and motion state data of an unmanned aerial vehicle cluster, constructing a multi-target comprehensive cost function, and carrying out the optimization of a cluster formation initial track, obtaining an optimal trajectory set meeting dynamic constraints; executing collision risk assessment on the sampling points on the optimal trajectory set, and outputting a trajectory safety judgment result; performing mathematical characterization and eigenvalue modulation on the formation topological structure through a Laplacian matrix, and generating target formation parameters adapted to environmental constraints; and finally, converting the optimal track set and the target formation parameters into a bottom layer flight control instruction, driving the unmanned aerial vehicle to execute a flight action, and collecting real-time motion state data at the same time. Therefore, the problems that in the prior art, trajectory optimization convergence is slow, collision detection real-time performance is poor, formation dynamic adaptation is insufficient, and system module collaboration is weak are solved.

The invention discloses an aircraft multi-target performance constraint collaborative optimization method based on multi-dimensional virtual and real parameter mapping, and the method comprises the steps: constructing a real parameter space and a virtual parameter space, and uniformly organizing the task key elements, such as target arrival, obstacle risk, formation maintenance error and minimum safety margin, into multi-dimensional real parameter input; speed scheduling quantity is uniformly organized into virtual parameters to be output, so that consistent parameter expression and a unified decision interface of cross-scene and cross-risk levels are realized, and engineering applicability and reusability in a task constraint scene are improved; interaction response data are obtained in a multi-scene set, a track sample set is established, and PPO reinforcement learning is adopted to train a mapping network from actual parameters to speed virtual parameters, so that the system does not need to explicitly construct complex manual rules or segmented threshold control logic; therefore, self-adaptive tradeoff can be formed among multiple targets such as arrival efficiency, formation keeping and speed stability, so that the manual parameter debugging cost is reduced, and the strategy generalization capability is improved.

The invention discloses a multi-spacecraft attitude and orbit coupling all-drive convergence time controller generation method, which is applied to the technical field of aerospace and comprises the following steps: establishing a multi-spacecraft attitude and orbit coupling error system all-drive model based on all-drive characteristics of a tracking error model; wherein the multi-spacecraft attitude and orbit coupling error system all-drive model is a pseudo-linear system model aiming at the stability problem of a multi-spacecraft attitude and orbit coupling error system; aiming at the multi-spacecraft attitude and orbit coupling error system all-drive model, constructing an all-drive convergence time controller based on an all-drive system method, a sliding mode control method and a preset time control method, and adjusting the convergence time of the system based on the all-drive convergence time controller; the all-drive convergence time controller is a controller designed based on a preset time parameter and an adjustable time parameter. According to the method for adjusting the preset time through attitude and orbit coupling, the multiple spacecrafts can maneuver to the expected attitude and orbit within the preset time, formation is completed, and the formation efficiency is improved.

The invention belongs to the technical field of aerospace, discloses a multi-gliding aircraft cooperative formation control method and system, and solves the problems that a multi-gliding aircraft is under-actuated in a high-speed reentry environment, a three-dimensional configuration and collision and obstacle avoidance are not considered in an existing method, and longitudinal errors are not converged. Firstly, a task scene is defined, a three-degree-of-freedom centroid dynamic model is established, and a three-dimensional configuration, collision and obstacle avoidance and control constraints are defined; then, preset time consistency control based on preset performance is designed, and lateral and height formation is achieved; respectively setting task condition correction for the same / different height scenes according to the longitudinal error, and leading a collaborative regulation strategy; setting a collision and obstacle avoidance strategy by using an improved artificial potential field method; and finally, constructing a control framework resolving instruction. According to the method, preset time error convergence, longitudinal configuration maintenance and collision avoidance safety are realized, and the aircraft clustering capability is improved.

The present application belongs to the field of aerospace technology, and discloses a kind of multi-glider aircraft cooperative formation control method and system, solve the problem of underactuated of multi-glider aircraft in high-speed reentry environment, the problem that three-dimensional configuration and collision avoidance and obstacle avoidance are not considered in existing method and longitudinal error does not converge.Firstly, the task scenario is defined, a three-degree-of-freedom mass center dynamics model is established, and three-dimensional configuration, collision avoidance and obstacle avoidance and control constraints are defined;Then, a preset time consistency control based on preset performance is designed to realize lateral and height formation;For longitudinal error, task condition correction and leader-follower cooperative control strategy are set for same / different height scenarios respectively;Improved artificial potential field method is used to set collision avoidance and obstacle avoidance strategy;Finally, a control framework is constructed to calculate the instruction.The present application realizes preset time error convergence, longitudinal configuration maintenance and collision avoidance safety, and improves the cluster capability of aircraft.

The invention discloses an unmanned aerial vehicle formation flight obstacle avoidance method and system based on monocular depth estimation, and relates to the field of unmanned aerial vehicle formation, and the method comprises the steps: enabling an internal unmanned aerial vehicle of a fleet to obtain first detection information composed of external obstacle depth information and current unmanned aerial vehicle flight position information; the unmanned aerial vehicles in the fleet publish first detection information to the ground station through the inter-aircraft networking communication module; the ground station receives the first detection information, resolves the first detection information to obtain an obstacle position map, obtains obstacle avoidance code information, and broadcasts the obstacle avoidance code information to the unmanned aerial vehicle group; and after receiving the obstacle avoidance code information of the ground station, the unmanned aerial vehicles in the fleet input the obstacle avoidance code information to the flight controller, and the flight controller controls the unmanned aerial vehicles to avoid obstacles to perform formation flight tasks. The method employs a learning-driven depth estimation method to perform obstacle avoidance, can accurately estimate the target depth information, and improves the flight efficiency of the unmanned plane formation.

The application relates to a multi-unmanned aerial vehicle power line inspection method based on real-time attention mechanism and fixed time, wherein the unmanned aerial vehicle collects data of a power transmission line through a visual sensor, detects the power transmission line by using an improved YOLOv5s model, calculates the length of the power transmission line by using the length of a detection frame, and outputs the end position; each unmanned aerial vehicle in the unmanned aerial vehicle formation adopts a neighbor communication rule, and the unmanned aerial vehicle adopts a fixed time distributed control strategy according to the end position coordinates, so that autonomous inspection of the formation is realized. Simulation shows that the application not only improves target recognition accuracy, but also proves stable operation of the control system. Flight experiments in a real environment show that the method has practicability and effectiveness for autonomous power line inspection of multiple unmanned aerial vehicles, and provides solid and highly accurate basic guarantee for a power line detection system of a smart power grid.

A monitoring system for an aircraft involved in a formation flight as a trailing aircraft or as a leading aircraft comprises electronic circuitry configured to repeatedly implement the steps of receiving barometric altitude information from the leading aircraft, receiving barometric altitude information from the trailing aircraft, computing a difference between the barometric altitude of the leading aircraft and the barometric altitude of the trailing aircraft, determining an inconsistency between the barometric altitude of the trailing aircraft and the barometric altitude of the leading aircraft, within the context of the formation flight, if the computed difference is greater than a height value of the vortex at a current position of the trailing aircraft, increased by a height margin, and commanding, if such an inconsistency is determined, a transmission of a warning in the cockpit of the aircraft.

The invention relates to a multi-aircraft control method and system considering thrust saturation of a piston engine, and the method comprises the steps: carrying out the dynamic modeling of a cruise type guidance aircraft, and obtaining a kinematical equation and a kinetic equation under a trajectory system; modeling a multi-aircraft system to obtain a leader following type formation control model; an average value model is established for the two-stroke piston engine, a transfer function is obtained through linear processing, and a rotating speed controller is designed based on the active disturbance rejection control theory; constructing a non-singular terminal sliding mode surface matrix with fixed time convergence according to the formation error state; taking the deviation between the actual control input and the expected control input as a state quantity to construct a saturation suppression system; and combining a saturation suppression system with the nonsingular terminal sliding mode surface matrix, and designing an anti-saturation fixed time convergence nonsingular terminal sliding mode formation control law, so that the formation error is converged to zero within fixed time. The formation time can be shortened, and the formation control precision is improved.

This application provides a multi-agent reinforcement learning-based underwater glider formation control method, which can be applied to the field of underwater glider control technology. The method is applied to a control terminal capable of communicating with an underwater glider group, and includes: in an observation scenario where the underwater glider group is in a preset formation, determining the state spaces of the leader underwater glider and at least one follower underwater glider, and determining the action spaces of all underwater gliders in the group; predicting the leader underwater glider's state at time t; predicting the leader underwater glider's action at time t that enables it to reach its destination; outputting the follower actions at time t for each of the at least one follower underwater glider through a follower agent; and sending the follower actions at time t so that each of the at least one follower underwater glider maintains a preset formation with the leader underwater glider based on its follower actions at time t.

The application discloses a UAV cluster integrated control system based on formation flight, and relates to the field of flight control technology.The system comprises a flight acquisition module, an atmosphere acquisition module, a cluster control module and a display module.The flight acquisition module acquires data and stabilizes the output of posterior coordinates, ground speed and attitude angle through drift compensation Kalman filtering.The atmosphere acquisition module relies on a database of aerodynamic characteristics, and solves airspeed, barometric altitude and angle of attack through a model of atmospheric solution that is fused with model-specific aerodynamic correction coefficients and adaptive weighting.The cluster control module establishes an airflow disturbance model to quantify airflow disturbance intensity and generate disturbance coefficients of UAVs and adjacent UAVs, and dynamically outputs adjustment instructions with the minimum formation deviation and the stable attitude of a single machine as the target.The display module is used for 3D visualization monitoring of flight formation.The system significantly improves the stability and adaptability of formation flight, and is suitable for UAV cluster cooperative operation in complex scenarios.

The application provides a flapping-wing aircraft formation flight energy-saving method and device, the method comprising: inputting geometric parameters of a required control flapping-wing aircraft; calculating a required relative flight distance to be kept when the flapping-wing aircraft flies in formation according to the input geometric parameters of the flapping-wing aircraft; determining a lead aircraft and wingman according to an evaluation function selection to form a formation flight; detecting a residual power of a current lead aircraft, and replacing the lead aircraft when the current lead aircraft consumes energy exceeding a set value; and continuously replacing the lead aircraft before the end of a flight task, and selecting a new lead aircraft according to the evaluation function. The method can keep the energy distribution of the flapping-wing aircraft group balanced when the flapping-wing aircraft flies in formation, effectively saves the energy of the flapping-wing aircraft, and improves the endurance of the flapping-wing aircraft.

The application discloses a kind of aircraft formation position reconstruction analytical optimization method, it is related to aircraft cooperative guidance and control technical field.Combining the distance between the original position of aircraft and new position, velocity vector front angle two factors, the individual benefit of single aircraft from original position to reach new position is evaluated, preliminary screening scheme is obtained according to individual benefit to scheme, and the individual benefit of scheme is calculated, the time difference value of last aircraft to new position and first aircraft to new position is multiplied by proportionality coefficient, as the time cooperative benefit of scheme, the number of trajectory intersection in the flight trajectory of each aircraft flying to new position is used to evaluate the trajectory intersection benefit of scheme.According to time cooperative benefit and trajectory intersection benefit, the cooperative benefit of scheme is calculated.The comprehensive benefit is obtained by weighted summation of scheme individual benefit and cooperative benefit, and the scheme with maximum comprehensive benefit is selected as the final aircraft formation position reconstruction scheme.

The invention relates to the technical field of data link communication abnormal flow detection, in particular to a high-speed aircraft data link communication abnormal flow detection method and system, and the method comprises the steps: judging a communication message which accords with a preset data link communication protocol specification as a protocol layer compliance message, and carrying out the analysis to obtain a formation cooperation instruction; collecting multi-source task context information of a local high-speed aircraft to generate a task execution field snapshot; projecting the formation cooperation instruction to the task execution field snapshot for comparison and analysis to obtain a multi-dimensional semantic comparison result; if all the multi-dimensional semantic comparison results are passed, the corresponding communication flow is judged to be task-driven normal collaborative flow; and if the judgment result of the multi-dimensional semantic comparison result is that the flow does not pass, judging the corresponding communication flow as the intention camouflage type spoofing abnormal flow. The deception traffic of which the protocol layer is compliant but the tactical intention is abnormal is effectively identified, so that the accuracy of high-speed aircraft data link communication abnormal traffic detection is improved.

The application relates to the technical field of unmanned aerial vehicle autonomous control, and discloses a multi-level intelligent algorithm-based unmanned aerial vehicle cluster formation control method and system, which obtains external environment monitoring data and motion state data of an unmanned aerial vehicle cluster, constructs a multi-target comprehensive cost function, performs optimization on an initial trajectory of cluster formation, obtains an optimal trajectory set satisfying a dynamic constraint, performs collision risk evaluation on sampling points on the optimal trajectory set, and outputs a trajectory safety judgment result; a Laplace matrix is used to perform mathematical representation and eigenvalue modulation on a formation topological structure, target formation parameters adapted to environment constraints are generated, and finally, the optimal trajectory set and the target formation parameters are converted into bottom-layer flight control instructions to drive the unmanned aerial vehicle to perform a flight action while collecting real-time motion state data. Therefore, the application solves the problems of slow trajectory optimization convergence, poor real-time collision detection, insufficient formation dynamic adaptation and weak system module cooperation in the prior art.

The present application relates to the technical field of multi-rotor unmanned aerial vehicle cluster cooperative control, and particularly relates to a distributed multi-unmanned aerial vehicle consistency formation control method for coping with communication delay, each unmanned aerial vehicle performing the following steps: time synchronization with neighboring machines and periodically obtaining communication quality measurement values to generate a link quality index; classifying communication links based on the link quality index, constructing an information pair composed of an expected trajectory sequence and a deviation feedback sequence in the same predicted time domain, and broadcasting; receiving neighboring machine information pairs, and when the link is degraded or interrupted, superimposing the deviation feedback sequence on the expected trajectory sequence corresponding to the absolute time point according to the time stamp to generate a closed-loop correction estimate; adjusting consistency control law parameters according to real-time link classification results, enabling or disabling compensation control based on the closed-loop correction estimate to generate flight control instructions; when all neighboring machine links are interrupted, generating a dynamic safety window based on the inertial measurement unit drift rate and the flight state, and performing cooperative flight within the window based on the last closed-loop correction estimate.

The invention discloses an unmanned aerial vehicle cooperative formation interface unit, a control system and a control method, the interface unit can be called as a functional module in a simulation environment of computing equipment, and when the interface unit is called, the interface unit is configured to be capable of directly communicating and connecting an indoor optical motion capture system and multiple unmanned aerial vehicles; and receiving real-time flight data of the plurality of unmanned aerial vehicles collected by the indoor optical motion capture system, converting the real-time flight data into body flight data under the unmanned aerial vehicle matrix coordinate system, and sending a control instruction to the plurality of unmanned aerial vehicles to realize cooperative formation control of the plurality of unmanned aerial vehicles. According to the invention, the compatibility of the unmanned aerial vehicle flight control platform and the optical motion capture system can be improved, and the real-time performance, the control precision and the overall system efficiency of unmanned aerial vehicle formation control are improved.

This invention discloses a method and system for close following control of a spherical airship robot under strong airflow disturbances. The method includes: establishing a three-dimensional kinematic model for close following; establishing an aerodynamic influence model mimicking bird flock close following; establishing the spatial dynamic equations of the spherical airship; establishing collision detection-assisted control based on tactile sensors; and constructing model predictive control equations for close following. This invention addresses the technical shortcomings of traditional control methods by drawing on bird flock formation strategies, constructing a dynamic model integrating aerodynamic characteristics, employing tactile sensor collision detection-assisted control, and using precise model predictive control algorithms. It overcomes the technical deficiencies of traditional control methods in effectively establishing aerodynamic interactions between airships and addressing collision problems caused by missing positioning data during close flight. This achieves stable close following control of the airship, providing technical support for multi-airship collaborative tasks in complex, confined spaces.

The application discloses a kind of unmanned plane path planning method and device based on reinforcement learning, it is related to unmanned plane technical field, the method includes: setting unmanned plane formation three-dimensional flight environment size;Obtain the position of the starting point of the long machine in the unmanned plane formation, target point position, and simultaneously determine the number and position of obstacles;According to the number and position of obstacles, determine the unmanned plane simulation three-dimensional flight environment, the grid map of the unmanned plane simulation three-dimensional flight environment is discretized;According to the unmanned plane simulation three-dimensional flight environment, establish the unmanned plane state in three-dimensional discretization space, state space and discretized unmanned plane action space;Based on the starting point of the long machine, target point position uses IDDQN algorithm to obtain the initial path of long machine, and adopts Bezier curve to optimize initial path and obtains final path information.The application solves the problem of low efficiency of the existing unmanned plane path planning mode.

The application provides a UAV cluster fault-tolerant formation control method combining MAPPO and predictive allocation, which improves the formation stability, task allocation efficiency and fault tolerance of the UAV cluster in a dynamic environment. First, a UAV cluster model is established, a six-degree-of-freedom kinematics model and a Markov decision model are constructed, and a distributed formation controller is designed; then a state real-time monitoring unit is deployed to monitor the flight state in real time and determine the activation of the fault tolerance mechanism, and when a fault is detected, a dynamic task allocation unit is started, which combines the current task cost and the future task cost to achieve the optimal task pairing of the rescue UAV through weighted scoring; finally, according to the allocation result, direct replacement or serial response mode is selected to execute fault recovery. The application combines the reinforcement learning framework of centralized training and decentralized execution with the predictive task allocation mechanism, which significantly improves the distributed collaborative control capability, global task optimization level and fault response speed of the UAV cluster.

The invention discloses a multi-quad-rotor unmanned aerial vehicle formation collision avoidance fault-tolerant control method, and relates to the technical field of unmanned aerial vehicle control, and the method comprises the steps: constructing a kinetic model and a dual-state constraint model of a multi-quad-rotor unmanned aerial vehicle, and building an inertial coordinate system and a vehicle body coordinate system; according to the invention, the dynamic model and the dual-state constraint model are constructed, unified modeling processing is carried out on the motion behavior and the space safety boundary of the multi-quad-rotor unmanned aerial vehicle, and real-time acquisition and dynamic compensation are carried out on the state and fault information of the unmanned aerial vehicle in combination with an online estimation mechanism of a distributed fault diagnosis observer. The system can still maintain stable operation under the conditions of actuator faults and coupling disturbance; the position error and the formation error of the unmanned aerial vehicle are constrained, the mapping from virtual control to actual control is realized in combination with an attitude coupling compensation mechanism, the collision risk in the formation flight process is effectively avoided, and the trajectory tracking precision is improved.