A method and system for controlling a hexacopter with disturbance and performance constraints

Abstract

The application discloses a kind of six rotor unmanned aerial vehicle control method and system with disturbance and performance constraint, comprising: step 1 establishes six rotor unmanned aerial vehicle power model;Step 2 base power model, confirm error, function is combined, confirm finite time scheme;Step 3 base power model, build observer, unknown disturbance state;Step 4 finite time performance control scheme and unknown disturbance state, build error power model, error power model, based on reinforcement learning, build scheme;Step 5 base scheme, set virtual and actual controller, and base neural network set adaptive law;Step 6 controller follower can track the leader, complete tracking control;Adopt backstepping method to build controller, build disturbance observer, compensate negative influence;Combining reinforcement learning algorithm and backstepping method technology, set controller to realize control;The method is proved stable by Lyapunov stability theorem, and simulation example verifies feasibility and effectiveness.

Description

Technical Field

[0001] This invention relates to the field of control technology for multi-rotor unmanned aerial vehicles (UAVs), and in particular to a control method and system for a six-rotor UAV with disturbances and performance constraints. Background Technology

[0002] In recent years, unmanned aerial vehicles (UAVs) have been widely used in disaster monitoring, rescue missions, and military reconnaissance due to their advantages such as hovering, high maneuverability, and agility. Hexacopter UAV systems are typically divided into a position subsystem and an attitude subsystem. This invention focuses on the position subsystem. A hexacopter UAV is a highly complex nonlinear system, subject to uncertainties such as external interference, actuator failures, and dead zones. Therefore, studying the modeling of hexacopter UAV systems, considering uncertainties and nonlinearities, and ultimately planning the UAV's trajectory under different mission conditions is of great significance.

[0003] Since nonlinearity is the most prevalent and essential characteristic of real-world dynamical systems, nonlinear control has wide applications in various fields and has received increasing attention in the past decade. It is well known that nonlinear strict feedback systems are the most common model form for engineering systems; therefore, the control of such systems is of valuable research value. In recent years, several control methods have been proposed for nonlinear strict feedback systems. However, these methods first convert the high-order system into a compact form and then design control by treating the converted system as a canonical system. Therefore, they cannot guarantee that the entire backstepping control sequence is optimal. It is worth mentioning that a new control technique has been proposed, called optimized backstepping (OB) for nonlinear strict feedback systems. Its basic idea is to design the control for each backstepping step as an optimal solution for the corresponding subsystem, thereby optimizing the control of the entire system. However, several common defects of optimal control have not been eliminated: 1) the update law of reinforcement learning (RL) is very complex and difficult to handle; 2) it assumes that the system dynamics are known. Therefore, this technique is difficult to apply to real-world engineering.

[0004] For the tracking and control problem of multi-UAV systems, good control performance and small residuals are required. However, it is difficult to determine the residual set without using trial and error, and the size of the residual set is often difficult to determine. Therefore, performance-defined control methods have received widespread attention from scholars as one of the effective methods to avoid this problem. However, it is worth noting that when considering finite-time control methods, backstepping control methods will have singularity problems, which encourages us to design a suitable method to improve the transient performance of multi-UAV systems with performance-defined characteristics.

[0005] In practical applications, UAVS often suffers from environmental interference, leading to a decline in system performance. If these adverse effects are not properly compensated, the performance of the UAV will be severely reduced, and even the instability of the UAV will be caused. To enhance the system's anti-interference performance, a disturbance observer can avoid the problem that the presence of disturbances may cause multiple UAVs to have difficulty achieving tracking and control performance, thus improving the robustness of the hexarotor UAV system. At the same time, considering that harsh environments, limited resources, and equipment wear and tear of UAVs can affect the control performance of the system and have a certain impact on the completion of control tasks, the control of UAV systems is also worthy of further research.

[0006] In summary, considering external environmental interference is important in practice, and studying optimal tracking control of hexacopter UAVs based on this has practical significance. In addition, studying the control problem of UAV systems based on reinforcement learning and disturbance observers helps to improve the system control performance and provides a theoretical basis for optimal tracking control of UAV systems in complex environments. Summary of the Invention

[0007] The purpose of this invention is to provide a control method and system for a hexacopter unmanned aerial vehicle with disturbance and performance constraints, so as to solve the problems existing in the prior art.

[0008] A control method for a hexacopter unmanned aerial vehicle with disturbances and performance constraints includes the following steps:

[0009] Step 1: Establish a dynamic model of a hexacopter UAV with lumped disturbances;

[0010] Step 2: Based on the dynamic model, determine the synchronization error, and combine the specified performance function with the velocity function to determine a finite-time specified performance control scheme;

[0011] Step 3: Based on the dynamic model, establish a disturbance observer to determine the unknown complex disturbance state information of the hexacopter UAV;

[0012] Step 4: Based on the finite-time performance control scheme and the unknown composite disturbance state information, construct an error dynamic model, and based on the error dynamic model, establish a control scheme for the hexarotor UAV using reinforcement learning methods.

[0013] Step 5: Based on the control scheme, design a virtual controller and an actual controller, and design an adaptive law for unknown parameters based on a neural network;

[0014] Step 6: Based on the virtual controller, the actual controller, and the adaptive law of the unknown parameters, the follower of the hexacopter UAV system is able to track the leader, thus completing the tracking control of the hexacopter UAV system.

[0015] Preferably, the dynamic model of the hexacopter unmanned aerial vehicle system with lumped disturbances established in step 1 specifically includes:

[0016] Define the angular velocity vector and the center-of-mass linear velocity vector of the dynamic model in the body coordinate system of the fixed object, and define the attitude angle vector and the position vector of the dynamic model in the inertial coordinate system of the fixed Earth.

[0017] Based on the angular velocity vector, the centroid linear velocity vector, the attitude angle vector, and the position vector, a dynamic model of the hexarotor unmanned aerial vehicle system is established. The dynamic model is as follows:

[0018]

[0019] in, These are the position vectors in the roll, pitch, and yaw directions within the position subsystem. for The derivative of , where T is the sign of the transpose operation; These are the linear velocity vectors of the center of mass in three directions. The linear velocity vector of the center of mass The derivative; This indicates the force generated by the motor. Indicates quality, and Represented as a transformation matrix, Represents gravitational acceleration; matrix , , as well as The drag coefficient; matrix ; Represents the attitude angle vectors in the roll, pitch, and yaw directions of the attitude subsystem. for The derivative, These are the angular velocity vectors in three directions; These are the moments of inertia in three directions. The gyro torque is in three directions; The torque generated by the six rotors, Represents the perturbation vector;

[0020] In the dynamic model, the first The dynamic equations of a system with one follower are:

[0021]

[0022] in, , Indicates the first The state of a follower system For the first The first state of a follower system For the first The second state of a follower system; , in , as well as The first The position vectors of the follower system in the three directions of roll, pitch, and yaw; , as well as The first The linear velocity vectors of the center of mass of a follower system in the roll, pitch, and yaw directions; Indicates the first The output of the follower system Represents an unknown function; This is represented as a lumped disturbance. Indicates control input; for The derivative; for The derivative of .

[0023] Preferably, in step 1, a dynamic model of a hexacopter UAV system with lumped disturbances is established, which is preceded by describing the communication topology between the hexacopter UAVs;

[0024] When describing the communication topology between hexacopter UAVs, a directed graph is used to describe the directed communication topology relationships between multiple UAVs, specifically including:

[0025] Using directed graphs This represents the directed communication topology between multiple UAVs; where, and Let N be a non-empty set of nodes and directed edges, respectively, where N is the number of nodes. This is the relevant adjacency weight matrix. For nodes and nodes Weights between them;

[0026] If node Can receive from node Communication information, ;otherwise ,node Cannot receive from node Communication information;

[0027] Indicates from node To the node An edge; define a node The neighbors are set as Then define Let be the in-degree matrix. For nodes in-degree, , It is a Laplace matrix;

[0028] If node Can receive from node The sent information, ,otherwise ;in, Indicates the leader, For nodes The weight between the leader and the leader.

[0029] Preferably, based on the dynamic model, the synchronization error is determined, specifically including:

[0030] Based on the leader signal given in the dynamic model, a synchronization error is constructed; the synchronization error is:

[0031]

[0032] in, Indicates synchronization error. Indicates the hexacopter UAV's first The output of a follower system Indicates the hexacopter UAV's first The output of a follower system This indicates the output of the six-rotor UAV leader system. For the first The first follower UAV and the first Weights among the follower UAVs For the first The weights between follower UAVs and leaders.

[0033] Preferably, step 2 combines the specified performance function with the speed function to determine a finite-time specified performance control scheme, specifically including:

[0034] To ensure that the synchronization error converges to a predetermined neighborhood of the origin, and that all closed-loop signals are bounded, a finite-time performance control scheme is determined by combining the specified performance with the velocity function; the finite-time performance control scheme is as follows:

[0035]

[0036] in, Let velocity be the function. To specify a limited time, , Represented as a non-decreasing smooth function, Represents time, where α is a constant. To ensure Continuous everywhere, definition ,definition for .

[0037] Preferably, based on the error dynamics model, a control scheme for the hexarotor UAV is established using reinforcement learning methods, which further includes:

[0038] Identifying unknown, uncertain, and nonlinear dynamics in UAVs using radial basis function neural networks; in compact sets Above, radial basis function neural network Capable of achieving arbitrary precision Approximating an unknown nonlinear function ;

[0039]

[0040] Where x is the input to the neural network, , It is the approximation error. It is a constant; It is an ideal weight vector. , For the basis function vector, Let i be a Gaussian function, i = 1, 2, 3, ..., p, and p be the number of nodes in the radial basis function neural network. W is the weight vector; Let m be the set of real matrices with p rows and m columns, where m is the number of columns in the matrix.

[0041] Preferably, based on the dynamic model, a disturbance observer is established to estimate the unknown complex disturbance state information of the hexacopter UAV, specifically including:

[0042] use Estimate the unknown complex disturbance state information of the hexarotor UAV;

[0043] Among them, the definition for , yes The estimate, It is the approximation error of the radial basis function neural network. It is a lumped disturbance. It is a constant. ; As an auxiliary variable, for The derivative, It is used to identify the ideal weights of a radial basis function neural network. The estimate, It is a basis function vector; Indicates control input, It is the system status. It is a virtual tracking error.

[0044] Preferably, based on the control scheme, a virtual controller and an actual controller are designed, specifically including:

[0045] In response to the design process of the actual controller, a virtual controller is designed based on the system dynamic equations of the aforementioned dynamic model; the virtual controller is:

[0046]

[0047] in, It is a velocity function. for The derivative, For synchronization error, To specify the performance function, ,definition for , for , for The derivative, For smooth functions, , For the upper realm, The lower realm , ;definition ,in ;

[0048] The objective of performance control is to ensure Converging to the specified boundary middle; This is the conversion error; For nodes in-degree, N is the number of follower UAVs. For the first A follower UAV's neighboring follower, For followers and neighbors and followers The weights between them To critique the adaptive laws of neural networks, State transitions defined according to specified performance; To identify ideal weights for a neural network The estimate, A vector of basis functions; Output for leaders The derivative; For followers The weight between the leader and the leader.

[0049] A hexacopter unmanned aerial vehicle (UAV) control system with disturbance and performance constraints, employing the aforementioned hexacopter UAV control method with disturbance and performance constraints, wherein the hexacopter UAV control system with disturbance and performance constraints includes:

[0050] The data acquisition module is used to obtain the physical characteristics of the hexacopter drone;

[0051] The data processing module is used to obtain a dynamic model of the hexacopter unmanned aerial vehicle system based on the physical characteristics.

[0052] The control module is used to construct an adaptive controller based on the data acquisition module and the data processing module using backstepping technology, estimate the unknown complex disturbance state information of the hexacopter UAV according to the disturbance observer, and design a virtual controller for the hexacopter UAV by combining backstepping technology and reinforcement learning algorithm, and perform adaptive control design for the hexacopter UAV.

[0053] Preferably, the control module specifically includes:

[0054] The observation and adaptive update law design unit is used to construct an adaptive controller using the backstepping method, and to construct a disturbance observer to observe the unknown complex disturbance state information of the six-rotor UAV. Based on the stability judgment method of Lyapunov function stability theory, an adaptive update law for the recognition-execution-evaluation neural network weights is designed.

[0055] An adaptive law design unit is used to design an adaptive law for an unknown nonlinear term based on a neural network and according to the adaptive update law; the neural network is a radial basis neural network.

[0056] An adaptive control unit is used to adaptively control a hexacopter UAV based on the adaptive law and according to the constructed controller.

[0057] Compared with the prior art, the present invention provides a control method and system for a hexacopter unmanned aerial vehicle with disturbance and performance constraints, which has the following beneficial effects:

[0058] 1. The technical solution of this invention proposes a finite-time performance specification strategy. Unlike traditional performance specification methods, this invention introduces a velocity function, which can effectively ensure that the tracking error converges to the specified bounded set within a finite time without the occurrence of singularity problems.

[0059] 2. The technical solution of this invention designs a disturbance observer to compensate for the negative impact of lumped disturbances on the hexacopter UAV system, avoid the problem that the presence of disturbances may cause multiple UAVs to have difficulty achieving tracking and control performance, and improve the robustness of the hexacopter UAV system.

[0060] 3. The technical solution of this invention utilizes the learning capability of reinforcement learning algorithms to design a performance index function that can evaluate tracking error and energy loss, ensuring that the system achieves stability while consuming less energy. Furthermore, by designing a simple positive definite function, an adaptive update law for the evaluation and execution neural network is constructed, which guarantees the smooth execution of the reinforcement learning algorithm.

[0061] Other features and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0062] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0063] Figure 1 This is a communication topology diagram of a six-rotor UAV system;

[0064] Figure 2 Here is a flowchart of the tracking control process for a six-rotor UAV system;

[0065] Figure 3 A trajectory diagram for a six-rotor UAV system to perform tracking and control tasks;

[0066] Figure 4 For when and hour and The trajectory diagram;

[0067] Figure 5 For when Trajectory diagram of synchronization error and performance boundary of a six-rotor UAV system;

[0068] Figure 6 The control input curves for the six-rotor UAV system under performance constraints and a disturbance observer are shown. Detailed Implementation

[0069] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0070] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0071] like Figure 1-6 As shown, this invention provides a control method and system for a hexacopter unmanned aerial vehicle (UAV) with disturbances and performance constraints. The control structure and overall process of the control system are as follows: Figure 1 and Figure 2 As shown;

[0072] Taking a hexacopter UAV system as an example, this paper details a control method for a hexacopter UAV with disturbances and performance constraints. The detailed implementation process includes:

[0073] Step 1: Establish the dynamic model of the six-rotor UAV as follows:

[0074]

[0075] Among them, the definition For the roll, pitch, and yaw position vectors in the position subsystem, The vectors representing the linear velocities of the center of mass in three directions; This indicates the force generated by the motor. Indicates quality, and Represented as a transformation matrix, Represents gravitational acceleration. Matrix ,in , as well as The drag coefficient is the matrix. ; Represents the attitude angle vectors in the roll, pitch, and yaw directions of the attitude subsystem. for The derivative, Define the angular velocity vectors in three directions. These are the moments of inertia in three directions. Defined as the gyro torque in three directions. The torque generated by the six rotors, Represents the perturbation vector;

[0076] its first The dynamic equation of a system with one follower can be written as:

[0077]

[0078] in, , Indicates the first The state of a follower system is defined. , ,in , and The first The position vectors of a follower system in the three directions of roll, pitch, and yaw; , and The first The linear velocity vectors of the center of mass of a follower system in the roll, pitch, and yaw directions; Indicates the first The system output of each follower Represents an unknown function; This is represented as a lumped disturbance. This indicates a control input.

[0079] Step 2: Design synchronization error:

[0080]

[0081] in, Indicates synchronization error. Indicates the hexacopter UAV's first The output of the position subsystem Indicates the hexacopter UAV's first The output of the position subsystem This indicates the leader output of the six-rotor UAV position subsystem.

[0082] Step 3: Combining the specified performance with the speed function, a finite-time specified performance control scheme is proposed as follows:

[0083]

[0084] Wherein, the velocity function is defined as The definition specifies a limited time as , Represented as a non-decreasing smooth function, Representing time, the constant α is defined as... In order to ensure Continuous everywhere, definition ;

[0085] Design a virtual tracking error transformation function:

[0086]

[0087]

[0088] in, Indicates virtual tracking error. It is a virtual control signal for the position subsystem. Indicates the output of the filter. It is filter error.

[0089] Step 4: Establish a disturbance observer to estimate the unknown complex disturbance state information of the hexarotor UAV:

[0090]

[0091] Among them, the definition , yes The estimate, It is the approximation error of the neural network. It is a lumped disturbance, defined as a constant. ;definition As an auxiliary variable, It is to identify the ideal weights of a neural network. The estimate, It is a basis function vector; This indicates a control input. It is the system status. It is a virtual tracking error.

[0092] Step 5: Design a tracking controller by combining backstepping techniques and reinforcement learning algorithms;

[0093] Based on the system dynamic equations of the given dynamic model of a hexarotor UAV system, design the virtual controller and the actual controller respectively:

[0094] The first step is to establish the following performance metric function:

[0095]

[0096] in, It is a compact set that includes the origin. It is a permissive control set. It is a virtual controller. It is a virtual controller. It is a cost function. State transitions defined according to specified performance.

[0097] Differentiating both sides of equation (1.8) yields the Hamilton–Jacobi–Bellman (HJB) equation as follows:

[0098]

[0099] By solving The resulting virtual controller is shown below:

[0100]

[0101] Will Decomposed into:

[0102]

[0103] in,

[0104] , These are positive design parameters;

[0105] Substituting formula (1.11) into formula (1.10), we get:

[0106]

[0107] By approximating the virtual controller using a reinforcement learning algorithm based on an execution-evaluation neural network, we can obtain:

[0108]

[0109]

[0110] in, yes The estimated value, yes The estimated value; neural network Approaching Unknown dynamics within, It is an ideal estimate of the weights of a neural network; neural network Approaching Unknown dynamics within, It is an ideal estimate of the weights of the neural network; These are fuzzy basis functions.

[0111] The approximate HJB function is shown below:

[0112]

[0113] The Bellman residual is defined as follows:

[0114]

[0115] Step 2: Establish the performance metric function as follows:

[0116]

[0117] in, It is a cost function. It is a virtual controller. It is a virtual controller.

[0118] The corresponding HJB equation is as follows:

[0119]

[0120] Similar to the first step, an approximate controller is obtained by employing a reinforcement learning algorithm:

[0121]

[0122] Among them, neural networks Used for approximation Unknown dynamics within, It is an estimate of the ideal weights for the neural network. These are fuzzy basis functions.

[0123] Step Six: To ensure the smooth execution of the reinforcement learning algorithm, a simple positive definite function is designed, and the following adaptive update law for evaluating and executing the neural network is constructed;

[0124]

[0125]

[0126]

[0127]

[0128] in, and It is used to evaluate the design parameters of a neural network. and These are the design parameters for executing the neural network;

[0129] To demonstrate the feasibility, effectiveness, and correctness of this example, the present invention conducts the following simulation experiments:

[0130] In this simulation experiment, an adaptive controller based on a disturbance observer and reinforcement learning was designed for a hexacopter UAV system with disturbances and performance constraints to achieve tracking control of the hexacopter UAV system.

[0131] During the controller design process, the system model parameters are set as follows:

[0132] The trajectories of UAV leaders in three directions are as follows: , , The nonlinear function is: , The initial state of the follower system is: , .

[0133] The system disturbance is: The relevant parameters for finite-time performance are: , , , , , , .

[0134] Evaluation Neural Network and and execution neural network and Each neural network contains 7 neurons, with the center point evenly distributed in the range [-3, 3]. The initial weights of the neural network are: , .

[0135] The parameters related to the virtual and physical controllers are designed as follows: , , , The adaptive law parameters are: , , , .

[0136] The effectiveness of this simulation is further illustrated by referring to the accompanying diagram:

[0137] The mathematical model established in the control method of this embodiment was simulated using Matrix Laboratory (MATLAB) and Simulation and Link (SIMULINK) software. Figure 1 In this context, "leader" refers to the leader, and the four below represent followers. Figure 1 The simulation results depict the communication relationship between the follower UAV and the leader UAV. Figure 3-5 For simulation results, Figure 4 and Figure 5 In this context, Time(s) means time. Figure 4 In this context, "Time (sec)" means time, and the unit is seconds. Figure 5 In this context, "Upper bound" means the upper limit or maximum value, and the black line at the top of the graph, from high to low, represents the upper limit or maximum value of the value. Figure 5 In this context, "Lower bound" means the lower limit or minimum value, and the black line at the bottom of the graph, from low to high, represents the lower limit or minimum value of the value. Figure 3 The tracking trajectory of the six-rotor UAV system was demonstrated, achieving precise tracking of the reference signal; Figure 4 Showing when and hour and The trajectory curve shows that it can track the leader according to the designed control scheme, proving the effectiveness of the strategy proposed in this invention. Figure 5 Showing when The trajectory diagram of the synchronization error and performance boundary of the six-rotor UAV system shows that the synchronization error converges to the finite time performance boundary range to ensure that all closed-loop signals are bounded. Figure 6 The trajectory of the control input under performance constraints and a disturbance observer is shown, indicating that the control input signal converges uniformly and the system's control task is successfully achieved.

[0138] In summary, all signals in the system are uniformly bounded, and simulation results demonstrate the effectiveness of the proposed tracking control scheme.

[0139] This embodiment uses backstepping recursion and reinforcement learning techniques as its design framework to study the adaptive tracking control problem for a hexacopter UAV system with disturbances and performance constraints. Furthermore, this invention assumes that the hexacopter UAV system has unmeasurable states and is affected by unknown disturbance information, making the system more general. By designing a disturbance observer, simultaneous observation of the system's state and disturbance information is achieved. This embodiment utilizes the approximation capability of reinforcement learning neural networks for nonlinear functions, and uses reinforcement learning algorithms to approximate the actual controller, solving the problem of the difficulty in directly solving the HJB equation. A controller that meets the control requirements is designed, and the weights of the neural network are adjusted through an adaptive law, enabling the designed approximate controller to closely approximate the actual controller. Finally, simulation verification shows that the proposed adaptive tracking control strategy can guarantee that all signals are bounded. The widespread application of this invention in the tracking control of hexacopter UAVs is one of the important future research directions.

[0140] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention; it should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions; these computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, produce implementations of the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0141] In the description of this invention, it should be understood that the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features; thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0142] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from the spirit and scope of this invention; thus, if these modifications and variations of this invention fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A control method for a hexacopter unmanned aerial vehicle with disturbance and performance constraints, characterized in that, Includes the following steps, Step 1: Establish a dynamic model of a hexacopter UAV with lumped disturbances; Step 2: Based on the dynamic model, determine the synchronization error, and combine the specified performance function with the velocity function to determine a finite-time specified performance control scheme; Step 3: Based on the dynamic model, establish a disturbance observer to determine the unknown complex disturbance state information of the hexacopter UAV; Step 4: Based on the finite-time performance control scheme and the unknown composite disturbance state information, construct an error dynamic model, and based on the error dynamic model, establish a control scheme for the hexarotor UAV using reinforcement learning methods. Step 5: Based on the control scheme, design a virtual controller and an actual controller, and design an adaptive law for unknown parameters based on a neural network; Step 6: Based on the virtual controller, the actual controller, and the adaptive law of the unknown parameters, the follower of the hexacopter UAV system is able to track the leader, thus completing the tracking control of the hexacopter UAV system. Step 2 involves combining the specified performance function with the speed function to determine a finite-time specified performance control scheme, specifically including: To ensure that the synchronization error converges to a predetermined neighborhood of the origin, and that all closed-loop signals are bounded, a finite-time performance control scheme is determined by combining the specified performance with the velocity function; among which, in, It is a velocity function. To specify a limited time, , Represented as a non-decreasing smooth function, Represents time, where α is a constant. ; To define the performance function; ,definition for , for The finite-time performance control scheme is as follows: the objective of performance control is to ensure... Converging to the specified boundary middle; It is a smooth function; , For the upper realm, The lower realm , , This is the synchronization error; Based on the aforementioned control scheme, a virtual controller and a physical controller are designed, specifically including: In response to the design process of the actual controller, a virtual controller is designed based on the system dynamic equations of the aforementioned dynamic model; the virtual controller is: in, These are positive design parameters; These are fuzzy basis functions; It is a velocity function. for The derivative, for The derivative, definition , ; This is the conversion error; For nodes in-degree, N is the number of follower UAVs. For the first A follower UAV's neighboring follower, For followers and neighbors and followers The weights between them To critique the adaptive laws of neural networks, State transitions defined according to specified performance; To identify ideal weights for a neural network The estimate, A vector of basis functions; Output for leaders The derivative; For followers The weight between the leader and the leader.

2. The control method for a hexacopter unmanned aerial vehicle with disturbance and performance constraints according to claim 1, characterized in that, Step 1 involves establishing a dynamic model of a hexarotor UAV system with lumped disturbances, specifically including: Define the angular velocity vector and the center-of-mass linear velocity vector of the dynamic model in the body coordinate system of the fixed object, and define the attitude angle vector and the position vector of the dynamic model in the inertial coordinate system of the fixed Earth. Based on the angular velocity vector, the centroid linear velocity vector, the attitude angle vector, and the position vector, a dynamic model of the hexarotor unmanned aerial vehicle system is established. The dynamic model is as follows: in, These are the position vectors in the roll, pitch, and yaw directions within the position subsystem. for The derivative of , where T is the sign of the transpose operation; These are the linear velocity vectors of the center of mass in three directions. The linear velocity vector of the center of mass The derivative; This indicates the force generated by the motor. Indicates quality, and Represented as a transformation matrix, Represents gravitational acceleration; matrix , , as well as The drag coefficient; matrix ; Represents the attitude angle vectors in the roll, pitch, and yaw directions of the attitude subsystem. for The derivative, These are the angular velocity vectors in three directions; These are the moments of inertia in three directions. The gyro torque is in three directions; The torque generated by the six rotors, Represents the perturbation vector; In the dynamic model, the first The dynamic equations of a system with one follower are: in, , Indicates the first The state of a follower system For the first The first state of a follower system For the first The second state of a follower system; ,in , as well as The first The position vectors of the follower system in the three directions of roll, pitch, and yaw; , , as well as The first The linear velocity vectors of the center of mass of a follower system in the roll, pitch, and yaw directions; Indicates the first The output of the follower system Represents an unknown function; This is represented as a lumped disturbance. Indicates control input; for The derivative; for The derivative of .

3. The control method for a hexacopter unmanned aerial vehicle with disturbance and performance constraints according to claim 1, characterized in that, In step 1, before establishing the dynamic model of the hexacopter UAV system with lumped disturbances, the following steps are also included: describing the communication topology between the hexacopter UAVs; When describing the communication topology between hexacopter UAVs, a directed graph is used to describe the directed communication topology relationships between multiple UAVs, specifically including: Using directed graphs This represents the directed communication topology between multiple UAVs; where, and Let N be a non-empty set of nodes and directed edges, respectively, where N is the number of nodes. This is the relevant adjacency weight matrix. For nodes and nodes Weights between them; If node Can receive from node Communication information, ;otherwise ,node Cannot receive from node Communication information; Indicates from node To the node An edge; define a node The neighbors are set as Then define Let be the in-degree matrix. For nodes in-degree, , It is a Laplace matrix; If node Can receive from node The sent information, ,otherwise ;in, Indicates the leader, For nodes The weight between the leader and the leader.

4. The control method for a hexacopter unmanned aerial vehicle with disturbance and performance constraints according to claim 1, characterized in that, Based on the aforementioned dynamic model, the synchronization error is determined, specifically including: Based on the leader signal given in the dynamic model, a synchronization error is constructed; the synchronization error is: in, Indicates synchronization error. Indicates the hexacopter UAV's first The output of a follower system Indicates the hexacopter UAV's first The output of a follower system This indicates the output of the six-rotor UAV leader system. For the first The first follower UAV and the first Weights among the follower UAVs For the first The weights between follower UAVs and leaders.

5. The control method for a hexacopter unmanned aerial vehicle with disturbance and performance constraints according to claim 1, characterized in that, Based on the aforementioned error dynamics model, a control scheme for a hexarotor UAV is established using reinforcement learning methods, which also includes: Identifying unknown, uncertain, and nonlinear dynamics in UAVs using radial basis function neural networks; in compact sets Above, radial basis function neural network Capable of achieving arbitrary precision Approximating an unknown nonlinear function ; Where x is the input to the neural network, , It is the approximation error. It is a constant; It is an ideal weight vector. ; For the basis function vector, Let i be a Gaussian function, i = 1, 2, 3, ..., p, and p be the number of nodes in the radial basis function neural network. W is the weight vector; Let m be the set of real matrices with p rows and m columns, where m is the number of columns in the matrix.

6. The control method for a hexacopter unmanned aerial vehicle with disturbance and performance constraints according to claim 1, characterized in that, Based on the aforementioned dynamic model, a disturbance observer is established to estimate the unknown complex disturbance state information of the hexarotor UAV, specifically including: use Estimate the unknown complex disturbance state information of the hexarotor UAV; Among them, the definition for , yes The estimate, It is the approximation error of the radial basis function neural network. It is a lumped disturbance. It is a constant. ; As an auxiliary variable, for The derivative, It is used to identify the ideal weights of a radial basis function neural network. The estimate, It is a basis function vector; Indicates control input, It is the system status. It is a virtual tracking error.

7. A control system for a hexacopter unmanned aerial vehicle with disturbance and performance constraints, characterized in that, The hexacopter UAV control system with disturbances and performance constraints adopts the hexacopter UAV control method with disturbances and performance constraints as described in any one of claims 1-6. The hexacopter UAV control system with disturbances and performance constraints specifically includes: The data acquisition module is used to obtain the physical characteristics of the hexacopter drone; The data processing module is used to obtain a dynamic model of the hexacopter unmanned aerial vehicle system based on the physical characteristics. The control module is used to construct an adaptive controller based on the data acquisition module and the data processing module using backstepping technology, estimate the unknown complex disturbance state information of the hexacopter UAV according to the disturbance observer, and design a virtual controller for the hexacopter UAV by combining backstepping technology and reinforcement learning algorithm, and perform adaptive control design for the hexacopter UAV.

8. A hexacopter unmanned aerial vehicle control system with disturbance and performance constraints according to claim 7, characterized in that, The control module specifically includes: The observation and adaptive update law design unit is used to construct an adaptive controller using the backstepping method, and to construct a disturbance observer to observe the unknown complex disturbance state information of the six-rotor UAV. Based on the stability judgment method of Lyapunov function stability theory, an adaptive update law for the recognition-execution-evaluation neural network weights is designed. An adaptive law design unit is used to design an adaptive law for an unknown nonlinear term based on a neural network and according to the adaptive update law; the neural network is a radial basis neural network. An adaptive control unit, based on the adaptive law and according to the constructed controller, performs adaptive control on the hexacopter UAV.

Images