Aircraft obstacle avoidance trajectory planning method based on physical driving neural network

Through the physically driven neural network method, a state and control variable network is constructed to optimize the aircraft obstacle avoidance trajectory, the problems of large amount of computing and poor generalization capabilities in the existing technology are solved, and efficient and fast aircraft obstacle avoidance trajectory planning is achieved.

CN118963377AActive Publication Date: 2024-11-15BEIJING JIAOTONG UNIV

Patent Information

Application Number
CN202410951708.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-16
Publication Date
2024-11-15
Estimated Expiration
2044-07-16

AI Technical Summary

Technical Problem

The existing aircraft obstacle avoidance trajectory planning methods are large in calculations, slow in convergence speed when dealing with complex obstacle areas, and lack the ability to generalize problems outside the training data, making it difficult to meet the needs of rapid planning and practical application.

Method used

Using a physically driven neural network method, a feedforward neural network of state variables and control variables is constructed. The network is optimized by combining obstacle area constraints and physical equation residual loss function to generate obstacle avoidance trajectory and control angle sequences, and verified by numerical integral method. Whether the trajectory meets performance indicators, iteratively optimize until the requirements are met.

Benefits of technology

It improves the efficiency and quality of aircraft obstacle avoidance trajectory planning, avoids the cumbersome process of initial value estimation, has strong generalization ability and global optimization characteristics, and has better interpretability and optimization speed.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118963377A_ABST
    Figure CN118963377A_ABST
Patent Text Reader

Abstract

The invention provides an aircraft obstacle avoidance trajectory planning method based on a physical driving neural network. The method comprises the following steps: firstly, constructing a three-dimensional centroid motion model of an aircraft, and generating a nominal trajectory through numerical integration; then, two neural networks are designed to predict state changes and control angle sequences respectively, and joint optimization is carried out through a comprehensive loss function, so that the neural networks can learn and generate optimized trajectories meeting obstacle avoidance constraints and performance indexes; in addition, by pre-training the state variable network and adopting the adaptive optimization strategy, the efficiency and stability of trajectory planning are improved. According to the method, the efficiency and precision of trajectory planning are improved, the generalization ability of the model to unknown scenes is enhanced, and the method is suitable for complex and changeable flight environments.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of aircraft obstacle avoidance, and in particular to an aircraft obstacle avoidance trajectory planning method based on a physical driven neural network. Background Art

[0002] Due to the restrictions of natural geographical environment or political and military considerations, such as Figure 1 As shown in the figure, aircraft often need to avoid certain specific obstacle areas. To this end, the aircraft's lateral maneuverability must be utilized to plan a trajectory that avoids the obstacle area. The aircraft trajectory planning problem is essentially a constrained optimal control problem. The most mature method at present is the numerical solution, that is, first convert the trajectory planning problem into a general optimization problem in a standard form that can be solved by mathematical optimization methods, and then use a relatively mature optimization algorithm to find its numerical solution. According to the different conversion forms, these numerical methods can be divided into two categories: indirect method and direct method.

[0003] The idea of ​​the indirect method for solving the optimal control problem is to construct a two-point boundary value problem, use the Pontryagin maximum principle to derive the first-order necessary conditions for the optimal solution, and finally obtain the analytical relationship between the control variable, state variable and analytical solution. For problems with strong nonlinearity, it is difficult to obtain an analytical solution directly, so numerical methods are often used in engineering to solve boundary value problems. The main advantages of the indirect method are high accuracy and the solution satisfies first-order optimality, but in practical applications, there are disadvantages such as cumbersome derivation process, difficulty in estimating the initial values ​​of unknown variables, and small convergence domain, which affect its solution efficiency. In recent years, strategies such as co-state normalization and heuristic initial value search have been used to improve the performance of the indirect method and achieved good results.

[0004] Compared with the indirect method, the direct method has lower initial value sensitivity, a larger convergence domain, and can handle more complex constraints. The direct method first uses a parameterization method to convert the optimal control problem in the continuous space into a nonlinear programming (NLP) problem of the discrete system, and then uses a numerical method to directly solve the NLP problem to obtain the optimal solution. According to the different discrete objects, it can be divided into three categories: only discrete control variables, only discrete state variables, and simultaneous discrete control and state variables.

[0005] When dealing with complex problems, traditional numerical methods face the problems of large amount of calculation and slow convergence speed due to the huge initial search space and the unavoidable integration process, which makes it difficult to meet the needs of fast planning. Therefore, using neural networks and deep learning to solve optimization and control problems is very promising and valuable in improving solution efficiency and quality.

[0006] Based on direct or indirect methods, scholars have proposed many new methods for trajectory optimization problems with obstacle zone constraints in recent years. A method for rapid generation of aircraft obstacle avoidance trajectories in the prior art includes: constructing an aircraft obstacle avoidance trajectory optimization problem based on the aircraft's kinematic model and dynamic model. The constraints of the optimization problem are the endpoint constraints of the aircraft trajectory planning and the obstacle avoidance constraints during the aircraft's flight. The objective function is to minimize the aircraft's comprehensive performance index considering the time performance index function and the overload integral performance index function; by constructing a polynomial-characterized flight trajectory equation, the obstacle avoidance constraint is converted into an obstacle avoidance performance index function and a comprehensive performance index is added. The time performance index function, the overload integral performance index function, and the obstacle avoidance performance index function are simplified, and the obstacle avoidance trajectory optimization result is obtained by solving.

[0007] The disadvantages of the above-mentioned method for quickly generating an aircraft obstacle avoidance trajectory in the prior art include: this method chooses to construct a polynomial to characterize the flight trajectory, the accuracy is affected by the order, and it only considers the obstacle avoidance process method within the plumb plane.

[0008] Another obstacle avoidance flight control system for an aircraft in the prior art includes: the system includes an obstacle avoidance flight control module and a data storage module. By using data obtained by pseudo-spectral simulation as samples, a preset deep neural network is trained to obtain a preset obstacle avoidance trajectory planning model, an optimized trajectory is generated using the obstacle avoidance trajectory planning model, and the aircraft is controlled to fly according to the optimized trajectory. The obstacle avoidance flight control system improves the speed of obstacle avoidance trajectory planning, thereby improving the real-time performance of the aircraft's obstacle avoidance flight control.

[0009] The shortcomings of another aircraft obstacle avoidance flight control system in the above-mentioned prior art include: the system uses the data obtained by pseudo-spectral simulation as samples to train the deep neural network offline. Although it improves the speed of online planning, it lacks the ability to generalize to problems outside the training data and is difficult to apply to actual scenarios. Summary of the invention

[0010] An embodiment of the present invention provides an aircraft obstacle avoidance trajectory planning method based on a physics-driven neural network, so as to effectively plan the obstacle avoidance trajectory of the aircraft.

[0011] In order to achieve the above object, the present invention adopts the following technical scheme.

[0012] constructing a dynamics model of the aircraft, and generating a nominal trajectory of the aircraft using the dynamics model;

[0013] Constructing state variable network NN u , using the state variable network to construct the proposed state variable The state variable network is pre-trained using the nominal trajectory to obtain a pre-trained state variable network NN u ;

[0014] Constructing the control variable network NN ctrl , the normalized time series on the nominal trajectory of the aircraft is input into the pre-trained state variable network NN u and control variable network NN ctrl , using obstacle area information and nominal trajectory data to calculate the loss function including obstacle area constraints and physical equation residual constraints, and optimizing the two networks simultaneously by minimizing the loss function to obtain the trained state variable network NN u and control variable network NN ctrl ;

[0015] Using the trained control variable network NN ctrl Construct an obstacle avoidance control variable sequence and substitute it into the differential equation of the aircraft. u The differential equation is solved by numerical integration method to obtain the obstacle avoidance trajectory of the aircraft, and then verify whether the obstacle avoidance trajectory meets the predetermined performance index. If it does, the obstacle avoidance trajectory and control angle sequence are output; if it does not meet the requirements, the state variable network NN is optimized. u and control variable network NN ctrl , regenerate the aircraft's obstacle avoidance trajectory until the aircraft's obstacle avoidance trajectory meets the performance indicators.

[0016] Preferably, the step of constructing a dynamic model of the aircraft and generating a nominal trajectory of the aircraft using the dynamic model comprises:

[0017] Construct the dynamic model of the aircraft, and the kinematic model expression is as follows:

[0018]

[0019] Among them G V is the transformation matrix from the velocity coordinate system to the launch coordinate system, which is composed of the ballistic inclination angle θ V , ballistic deflection angle ψ V , tilt angle γ V Characterize, the expression is:

[0020]

[0021] Among them, the ballistic inclination angle and ballistic deviation angle can be calculated from the velocity component, and V is the magnitude of the velocity in the launch system:

[0022]

[0023] C in the equation D,C L ,C z is the aerodynamic coefficient, which is related to the angle of attack (α) and the Mach number (Ma). The variables to be determined in the equations are the angle of attack α and the roll angle γ V , these two variables are used as control variables to control the flight trajectory of the aircraft;

[0024] Based on the dynamic model of the aircraft, a nominal trajectory of the aircraft is generated by a fourth-order Runge-Kutta integration method, wherein the nominal trajectory is a flight trajectory when the obstacle avoidance control angle and the roll angle are constantly zero.

[0025] Preferably, the method of generating a nominal trajectory of the aircraft based on the dynamic model of the aircraft by a fourth-order Runge-Kutta integration method, wherein the nominal trajectory is a flight trajectory when the obstacle avoidance control angle and the roll angle are constantly 0, comprises:

[0026] The dynamic model of the aircraft constructed by the differential equations is a set of ordinary differential equations with t as the independent variable, which describes the changes of the six state variables and their relationship with each other. In this set of differential equations, the angle of attack α and the roll angle γ V is the variable that affects the aerodynamic term. Given the state variable u=(V x ,V y ,V Z ,x,y,z), and gives the angle of attack α and the roll angle γ V The sequence or calculation function is solved by the Runge-Kutta method to obtain the nominal trajectory information of the aircraft, which includes the geometric path of the aircraft, the speed and acceleration information of the aircraft, and the angle of attack α is the maximum lift-to-drag ratio C that the aircraft can achieve at the current speed. L / C D The angle of attack, the roll angle γ V As a control angle, it can avoid obstacles.

[0027] Preferably, the state variable network NN is constructed u , using the state variable network to construct the proposed state variable The state variable network is pre-trained using the nominal trajectory to obtain a pre-trained state variable network NN u ,include:

[0028] Constructing state variable network NN u , the state variable network NN u The structure is a feedforward neural network, and the input is the normalized time series t on the nominal trajectory. * , output The normalization method of time variables is:

[0029]

[0030] Where t is the normalized time series on the nominal trajectory, μ t is the mean of the sequence, μ is the variance of the sequence, The calculation formula is:

[0031]

[0032] The proposed method for constructing the state variables is to transform the state variable network NN u Output After denormalization, the position variable is assumed to be Then the predicted speed variable is obtained through automatic differentiation The specific expression is:

[0033]

[0034] By minimizing the error between the state variable assumption and the nominal trajectory state variable, the state variable network NN is adjusted according to the error. u Parameters of the pre-trained state variable network NN u Repeat the above process continuously. After the training is completed, the pre-trained state variable network NN is obtained. u .

[0035] Preferably, the obstacle area information and the nominal trajectory data are used to calculate the loss function including the obstacle area constraint and the physical equation residual constraint, and the two networks are optimized simultaneously by minimizing the loss function to obtain the trained state variable network NN u and control variable network NN ctrl ,include:

[0036] Constructing state variable network NN ctrl , state variable network NN ctrl The structure is a feedforward neural network, and the input is the normalized time series t on the nominal trajectory. * , output The range is between [-1,1], multiplied by the maximum value allowed by the control angle to obtain the proposed obstacle avoidance control angle It satisfies the range constraint; the normalized time series on the nominal trajectory of the aircraft is input into the pre-trained state variable network NN u and control variable network NN ctrl , calculate the state variables and control variables Set the loss function to state error loss Loss u , initial state loss Loss start , differential equation residual loss Loss res 、Control angle loss Loss ctrl, and obstacle area constraint loss Loss forbid The weighted sum of and optimizes the pre-trained state variable network NN by minimizing the loss function u and control variable network NN ctrl Parameters;

[0037] State error loss Loss u Calculate the mean square error between the proposed state variable and the nominal trajectory, expressed as:

[0038]

[0039] Where N t Indicates the selected N t time points; initial state loss Loss start is the Loss at t = 0 u ; Differential equation residual loss Loss res Minimize the residual error of the differential equation, Loss res The calculation formula is as follows:

[0040]

[0041] Where rk4() represents one-step integration using the Runge-Kutta integration method, and the step length is equal to the time interval;

[0042] Control angle loss Loss ctrl Make the control angle as small as possible. The calculation method is as follows:

[0043]

[0044] Obstacle area constraint loss Loss forbid Calculate the distance from the aircraft to the center of each no-fly zone. If it is greater than the radius of the no-fly zone, record it as 0. If it is less than the radius of the no-fly zone, record it as the maximum distance d from the aircraft to the edge of the no-fly zone. Finally, sum all d. The closer the point is to the center of the obstacle zone, the greater the loss applied. forbid The greater the loss, the greater the forbid The calculation formula is as follows:

[0045]

[0046] Among them A i for is the center of the jth obstacle area, is the radius of the jth obstacle zone, ∈ “relaxation factor”, which is 2% of the maximum radius of the obstacle zone;

[0047] The loss function Loss is expressed as:

[0048] Loss = w1*Loss u +w2*Loss start +w3*Loss res +w4*Loss ctrl +w5*Loss forbid ;

[0049] Optimize the pre-trained state variable network NN by minimizing the value of the loss function Loss u and control variable network NN ctrl Parameters of the trained state variable network NN u and control variable network NN ctrl .

[0050] Preferably, the performance indicators include:

[0051] a. Maximum absolute value of the roll angle (°): This indicator reflects the maximum roll angle that the aircraft needs to perform during the entire obstacle avoidance process;

[0052] b. Maximum rate of change of roll angle (° / s): This indicator reflects the maximum rate of change of roll angle during obstacle avoidance;

[0053] c. Longest range ratio: This indicator calculates the ratio of the longest range of the obstacle avoidance trajectory to the nominal trajectory under the same time;

[0054] d. End point distance (km): This indicator calculates the distance between the obstacle avoidance trajectory and the end point of the nominal trajectory under the same time. The smaller the end point distance, the more conducive it is to complete the subsequent flight mission;

[0055] e. Shortest distance to the center of the obstacle area: This indicator calculates the shortest distance between the aircraft and the center of the obstacle during obstacle avoidance.

[0056] Preferably, the control variable network NN that is trained is used ctrl Construct an obstacle avoidance control variable sequence and substitute it into the differential equation of the aircraft. u The numerical integration method is used to solve the differential equations to obtain the obstacle avoidance trajectory of the aircraft, including:

[0057] Using the trained control variable network NN ctrl Construct an obstacle avoidance control variable sequence, substitute the obstacle avoidance control variable sequence into the differential equation of the aircraft, set the optimization goal and constraint conditions of the differential equation of the aircraft, the constraint conditions include obstacle area constraint, endpoint constraint, starting point constraint, thermal environment constraint, normal overload constraint and control amount constraint, based on the trained state variable network NN u The numerical integration method is used to solve the differential equation and obtain the obstacle avoidance trajectory of the aircraft.

[0058] It can be seen from the technical solutions provided by the above-mentioned embodiments of the present invention that, compared with traditional numerical methods, the method of the present invention combines physical modeling with neural networks, utilizes the general approximation ability of neural networks for functions, and has the advantages of no need for initial value estimation and strong generalization ability; compared with biological intelligence optimization algorithms, it has the characteristics of global optimization and a faster optimization speed; compared with current artificial intelligence methods, this method embeds physical knowledge into the network in the form of differential equations, does not require the trajectory planning data to be obtained by other methods in advance, and has better interpretability and generalization ability.

[0059] Additional aspects and advantages of the present invention will be given in part in the following description, which will become obvious from the following description, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0061] Figure 1 A schematic diagram of an obstacle avoidance task in the prior art;

[0062] Figure 2 A framework diagram of an obstacle avoidance trajectory planning model based on a physics-driven neural network provided in an embodiment of the present invention;

[0063] Figure 3 A schematic diagram of the specific steps of an obstacle avoidance trajectory planning algorithm after given planning starting point and obstacle area information proposed in an embodiment of the present invention. DETAILED DESCRIPTION

[0064] The embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be interpreted as limiting the present invention.

[0065] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be intermediate elements. In addition, the "connection" or "coupling" used herein may include wireless connection or coupling. The term "and / or" used herein includes any unit and all combinations of one or more associated listed items.

[0066] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in common dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless defined as herein.

[0067] To facilitate understanding of the embodiments of the present invention, several specific embodiments will be further explained below with reference to the accompanying drawings, and each embodiment does not constitute a limitation on the embodiments of the present invention.

[0068] The present invention proposes a method for aircraft obstacle avoidance trajectory planning based on physics-driven neural networks. This method constructs proxy models of state variables and control variables through a feedforward neural network, then jointly optimizes the two networks using a loss function that integrates obstacle zone constraints and physical equation residual constraints, and finally outputs the obstacle avoidance trajectory and the corresponding control angle sequence simultaneously.

[0069] The processing flow chart of a method for aircraft obstacle avoidance trajectory planning based on a physical driven neural network provided by an embodiment of the present invention is as follows: Figure 3 As shown, the process includes the following steps:

[0070] Step S10: constructing a dynamic model of the aircraft, and using the dynamic model to generate a nominal trajectory of the aircraft.

[0071] Apply Newtonian mechanics and kinematics principles to establish a differential equation group of the aircraft in three-dimensional space, input the initial state of the aircraft (including position, speed and direction) and physical parameters (such as drag coefficient, lift coefficient, etc.), solve the differential equation group through numerical integration methods (such as Runge-Kutta method), and output the nominal trajectory of the aircraft without control. This step uses existing numerical simulation technology for aircraft motion to build a dynamic model of the aircraft, and uses the dynamic model to generate the nominal trajectory of the aircraft through the fourth-order Runge-Kutta integration method, which is used for the calculation of the loss function in step S20 "pre-training of state variable network" and step S30 "joint optimization of state variable and control variable network".

[0072] Step S20: state variable network pre-training.

[0073] Constructing state variable network NN u , whose structure is a feedforward neural network, whose input is a normalized time series on the nominal trajectory, and the output of the network is used to construct the proposed assumption of the state variable By minimizing the error between the state variable assumption and the nominal trajectory state variable, the state variable network NN is adjusted according to the error. u Parameters of the pre-trained state variable network NN u Repeat the above process continuously. After the training is completed, the pre-trained state variable network NN is obtained. u ; The network will be further optimized in subsequent steps.

[0074] Step S30: Jointly optimize the state variable and control variable network.

[0075] Constructing the control variable network NN ctrl , whose structure is a feedforward neural network. The normalized time series on the nominal trajectory of the aircraft is input into the pre-trained state variable network NN u and control variable network NN ctrl , using the obstacle area information, the nominal trajectory data output in step S10, and the variables constructed by the two networks to simulate and calculate the loss function including the obstacle area constraint and the physical equation residual constraint, and by minimizing the weighted sum of the loss function, simultaneously optimize the pre-trained state variable network NN u and control variable network NN ctrl , in order to generate obstacle avoidance trajectories and corresponding control angle sequences. Finally, this step outputs the trained state variable network NN u and control variable network NN ctrl .

[0076] NN_ctrl is a neural network, whose input is normalized time, and output is a value in the range of [-1,1]. This value is multiplied by a control variable (the roll angle gamma_v in the equation), and the predicted obstacle avoidance control variable is obtained. If a time series is input, the output is a control variable sequence. Step S40: Verification and output.

[0077] The input of this step is the control angle sequence constructed by the control variable network NN_ctrl.

[0078] First, NN ctrl The output control angle sequence is substituted into the differential equation of the aircraft, and the numerical integration method is used again to solve it to obtain the obstacle avoidance trajectory. Then, it is verified whether the obstacle avoidance trajectory under this control meets the predetermined performance index. If it does, the obstacle avoidance trajectory and the control angle sequence are output; if not, it returns to step S30 and continues to optimize the network until a trajectory that meets the performance index is found.

[0079] The modeling and problem definition of the three-dimensional center of mass motion of the aircraft are as follows:

[0080] Motion modeling, in the launch coordinate system with the sub-satellite point of the gliding starting point as the coordinate origin and the initial heading as the x-axis, according to the principles of Newtonian mechanics and kinematics, the differential equations of the aircraft motion in the launch system are:

[0081]

[0082] Among them G V is the transformation matrix from the velocity coordinate system to the launch coordinate system, which is composed of the ballistic inclination angle (velocity inclination angle) θ V , trajectory deviation angle (track yaw angle) ψ V , roll angle (speed tilt angle) γ V Characterize. The expression is:

[0083]

[0084] Among them, the ballistic inclination angle and ballistic deviation angle can be calculated from the velocity component, and V is the magnitude of the velocity in the launch system:

[0085]

[0086] C in the equation D ,C L ,C z is the aerodynamic coefficient, which is related to the angle of attack (α) and the Mach number (Ma).

[0087] Thus, the variables to be determined in the equations are the angle of attack α and the roll angle γ V, these two variables can be used as control variables to control the flight trajectory of the aircraft. Since the angle of attack has a great influence on the change of aerodynamic force, in order to give full play to the aerodynamic capability of the aircraft, the angle of attack can be designed using a certain procedure (for example, the angle of attack that obtains the maximum lift-to-drag ratio), and the roll angle is selected as the obstacle avoidance control variable.

[0088] The mathematical model of the aircraft constructed by the above differential equations is a set of ordinary differential equations with t as the independent variable, which describes the changes of the six state variables and their relationship with each other. In this set of differential equations, the angle of attack α and the roll angle γ V is a variable that affects the aerodynamic term and needs to be given as an additional input. Given the state variable u=(V x ,V y ,V Z ,x,y,z), and gives the angle of attack α and the roll angle γ V The sequence or calculation function can be used to solve the complete set of ordinary differential equations using the Runge-Kutta method to obtain the complete trajectory information of the aircraft. It should be noted that the "trajectory" not only presents the geometric path of the aircraft, but also includes the velocity and acceleration information of the aircraft. In the present invention, the angle of attack α is the maximum lift-to-drag ratio (C L / C D ) so that the aircraft can achieve the longest possible range, and the roll angle γ V As a control angle, it can avoid obstacles.

[0089] Obstacle avoidance trajectory planning is essentially a multi-constrained optimization problem. In the present invention, the optimization goal is to make the planned trajectory as close to the nominal trajectory as possible, and the constraints include obstacle area constraints and endpoint constraints of the starting point and end point.

[0090] Optimization objective: Let the uncontrolled trajectory sequence be s(t), where the optimized variable is the roll angle γ V Always equal to 0; trajectory sequence u(t) after obstacle avoidance, roll angle sequence γ V (t). The optimization goal is to make the planned trajectory as close to the nominal trajectory as possible and the control amount as small as possible:

[0091]

[0092] Obstacle zone constraint: The obstacle zone refers to the area that the aircraft needs to avoid during flight. For ease of processing, assume that the threat zone is an infinitely high cylinder, and the closer to the center of the circle, the greater the threat. Suppose the center of the i-th obstacle zone is at point The radius is The position of the aircraft is A(λ a ,φ a ), then the obstacle constraint can be expressed as:

[0093]

[0094] in The geographical distance between points A and B can be calculated using the following formula:

[0095]

[0096] Endpoint constraints are constraints on the state variables of the starting point and end point after optimization, including starting point constraints and end point constraints.

[0097] The starting point constraint expression is:

[0098] u(t M )=s(t M )

[0099] Since the present invention does not use the angle of attack as a design variable, but always takes the angle of attack that enables the aircraft to obtain the maximum lift-to-drag ratio to obtain the longest range, there is no constraint on the terminal position. However, it is still hoped that the aircraft can fly as far as possible after avoiding obstacles, and the terminal can be as close to the nominal trajectory as possible, which is more conducive to completing subsequent flight missions.

[0100] Thermal environment constraints: To avoid aerodynamic ablation, the dynamic pressure q and the stagnation heat flux q need to be s To restrict:

[0101]

[0102] Among them C q =9.4369×10 ―5 .

[0103] Normal overload constraint: To meet the structural strength limit, a normal overload constraint needs to be applied:

[0104]

[0105] Control quantity constraints: To avoid stalling, the control quantity size and change rate are also limited:

[0106] |α|≤α max ,|γ V |≤γ Vmax

[0107]

[0108] This paper proposes a model framework for obstacle avoidance trajectory planning based on a physical driven neural network. Figure 2As shown in the figure, it contains three main parts: deep feedforward network, variable reconstruction and loss calculation. The two deep feedforward networks act as function fitters, mapping the timestamp t to the state variable and the control variable respectively; the variable reconstruction part processes the network input and output through normalization, automatic differentiation and other means to make them conform to the range constraints and accelerate the training process; the loss calculation part integrates various constraints and objective functions for training the network.

[0109] Specifically, the state variable network NN u The input is the normalized independent variable t, and the output is the normalized position variable The three state variables are denormalized to obtain Then the speed variable is obtained through automatic differentiation Control variable network NN ctrl The input is also the normalized independent variable t * , N.N. ctrl Output After a layer of tanh, it is scaled to the range of [-1,1] and then multiplied by the maximum value, so that the control variable Satisfy the range constraints. Finally, by minimizing the four losses (Loss u ,Loss res ,Loss ctrl ,Loss forbid ) to optimize NN u and NN ctrl Parameters of the four losses. u and Loss ctrl Corresponding optimization target; Loss forbid Corresponding to obstacle area constraints; Loss res Minimize the residual of the differential equation, the goal is to learn the control variables and ensure that the various physical quantities are physically consistent

[0110] Using the above model framework, the specific steps of an obstacle avoidance trajectory planning algorithm after given planning starting point and obstacle area information are as follows: Figure 3 As shown in Figure 1. First, the input starting point information is used as the initial value, the roll angle is always kept at 0, and the fourth-order Runge-Kutta method is used to integrate the dynamic equations of the aircraft to obtain a nominal trajectory. Since we hope that the planned trajectory is as close to the nominal trajectory as possible, we first u Pre-training is performed to learn the mapping from normalized time to normalized state variables. Experiments show that pre-training is not necessary, but it can speed up the subsequent trajectory planning and make the planning process more stable. Then, within a fixed training round, the above model framework is used to jointly train the state variable network NN u and control variable network NNctrl , while optimizing the state variables and control variables. Finally, NN ctrl Output control variable sequence Substitute it into the differential equation of the aircraft, and use the fourth-order Runge-Kutta method to integrate again to verify whether the flight trajectory under this control can meet the predetermined performance indicators. If it does, output Otherwise, continue to train the neural network until a trajectory that meets the performance indicators is found. In this way, a flight trajectory that is as close to the nominal trajectory as possible and avoids obstacles can be planned to achieve safe flight of the aircraft.

[0111] Algorithm Implementation

[0112] Data normalization

[0113] In order to unify the data to the same level and eliminate the dimensional effects between different features, the convergence of the model can be accelerated, providing a more stable and reliable foundation for subsequent modeling and analysis. One normalization method is Z-Score normalization:

[0114]

[0115] It should be noted that for z, its value in the nominal trajectory is always 0, which does not conform to the expected planned trajectory. Therefore, the mean of z is set to the maximum radius of the obstacle area and the variance is 0.

[0116] Variable Refactoring

[0117] The differential equations for the motion of the aircraft in the launch system contain 6 equations, corresponding to 6 state variables. x ,V y ,V z The relationship between is relatively simple, so NN u Only three variables are output, and the speed state is further obtained through the automatic differentiation mechanism. Due to the application of Z score normalization, the calculation formula from the neural network output to the predicted value of each state variable is as follows:

[0118]

[0119] AD is the abbreviation of Automatic Differentiation, which stands for automatic differentiation.

[0120] For the control variable γ V , in order to ensure that it is within a certain range, it is reconstructed by the following formula:

[0121]

[0122] in It is NNctrl Output.

[0123] Loss function construction

[0124] The present invention converts the initial value equality constraint, path inequality constraint and differential equation equality constraint of the system into the form of penalty function, which together with the optimization target is called loss function. Specifically, the loss function consists of the following items:

[0125] ①Loss u

[0126] This loss calculates the mean square error between the normalized state variable proxy model and the nominal trajectory, with the goal of making the predicted trajectory as close to the nominal trajectory as possible. It can be expressed as:

[0127]

[0128] Where N t Indicates the selected N t Time point. Initial state loss Loss start In fact, it is the Loss at t = 0 u , this item is given a larger weight in order to make the planning trajectory satisfy the initial value constraints as much as possible.

[0129] ②Loss start

[0130] Loss start In fact, it is the Loss at t = 0 u , this item is given a larger weight in order to make the planning trajectory satisfy the initial value constraints as much as possible.

[0131] ③Loss res

[0132] This loss attempts to minimize the residual of the differential equation. This loss can be used to jointly optimize the NN u and NN ctrl , on the one hand, the predicted trajectory is self-consistent, and on the other hand, the corresponding obstacle avoidance control angle sequence is obtained. res The calculation formula is as follows:

[0133]

[0134] Among them, rk4() represents one-step integration using the Runge-Kutta integration method, and the step size is equal to the time interval.

[0135] ④Loss ctrl

[0136] The purpose of this item is to make the control angle as small as possible to ensure that the aircraft flies as smoothly as possible. The calculation method is as follows:

[0137]

[0138] ⑥Loss forbid

[0139] For each coordinate position, this item calculates its distance to the center of each no-fly zone. If it is greater than the radius of the no-fly zone, it is recorded as 0. If it is less than the radius of the no-fly zone, it is recorded as the maximum distance d to the edge of the no-fly zone. Finally, all d are summed. In this way, the closer the point is to the center of the obstacle zone, the greater the loss applied. forbid The greater the loss. forbid The calculation formula is as follows:

[0140]

[0141] Among them A i for is the center of the jth obstacle area, is the radius of the jth obstacle area, ∈ "relaxation factor", which is 2% of the maximum radius of the obstacle area.

[0142] In summary, the loss function Loss can be expressed as:

[0143] Loss = w1*Loss u +w2*Loss start +w3*Loss res +w4*Loss ctrl +w5*Loss forbid

[0144] If there are other constraints such as thermal environment constraints, normal overload constraints, etc. during flight, the Loss forbid A similar form is added to the loss function.

[0145] 1) Network optimization

[0146] From the specific expression of the loss function, we can see that NN u With Loss u ,Loss start ,Loss res ,Loss forbid Related, and NN ctrl With Loss res ,Loss ctrl By minimizing the weighted sum of the loss function through a gradient-based optimizer, we can theoretically obtain a trajectory that can avoid obstacles and the corresponding obstacle avoidance control. u ,Loss start and Loss forbid It mainly plays the role of planning trajectory, while Lossres Used to optimize control variables.

[0147] The optimization process of the neural network is non-convex, and hyperparameters such as the loss function weight and the learning rate will affect the accuracy of the solution. For the loss function weight, the present invention manually sets it according to the importance of each item in the loss function, and adjusts it according to the actual planning effect after the order is fixed.

[0148] The present invention adopts an Adaptive Moment Estimation (Adam) optimizer. Adam integrates the advantages of momentum and RMSprop algorithms, dynamically adjusts the learning rate of each parameter through first-order moment estimation and second-order moment estimation, thereby improving the optimization efficiency. The optimizer is insensitive to parameter initialization, is suitable for non-stationary targets, and has high computational efficiency.

[0149] In order to better optimize the loss function, the present invention also introduces a u Pre-training of NN u In the pre-training phase, learn to fit the nominal trajectory, and then focus on optimizing the Loss in the trajectory planning phase. forbid Loss term, experiments have found that this approach can significantly improve the planning speed and the stability of the solution; it is especially beneficial for tasks with fixed initial values ​​that need to plan trajectories for different obstacle areas.

[0150] In summary, the method of the embodiment of the present invention constructs a proxy model of state variables and control variables, and jointly optimizes the two networks by using the loss function that integrates the obstacle zone constraint and the physical equation residual constraint to output the obstacle avoidance trajectory and the corresponding control angle sequence. Compared with the traditional numerical method, this method utilizes the general approximation ability of the neural network, avoids the tedious process of initial value estimation, and improves the generalization ability; compared with genetic algorithms, reinforcement learning and other methods, it has the characteristics of global optimization and a faster optimization speed; compared with the base data driven method, by embedding physical knowledge, the present invention has better interpretability and generalization ability, and does not require a large amount of training data. In addition, through pre-training and Adam optimizer selection, the present invention improves the computational efficiency of the algorithm and shortens the planning time. The present invention has a wide range of applicability and can be applied to different types of aircraft. It can also include constraints required by other tasks by adding loss function terms.

[0151] Those skilled in the art can understand that the accompanying drawings are only schematic diagrams of an embodiment, and the modules or processes in the accompanying drawings are not necessarily required to implement the present invention.

[0152] It can be known from the description of the above implementation methods that those skilled in the art can clearly understand that the present invention can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present invention or certain parts of the embodiments.

[0153] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The device and system embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0154] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for aircraft obstacle avoidance trajectory planning based on a physical driven neural network, characterized in that: include: constructing a dynamics model of the aircraft, and generating a nominal trajectory of the aircraft using the dynamics model; Constructing state variable network NN u , using the state variable network to construct the proposed state variable The state variable network is pre-trained using the nominal trajectory to obtain a pre-trained state variable network NN u ; Constructing the control variable network NN ctrl , the normalized time series on the nominal trajectory of the aircraft is input into the pre-trained state variable network NN u and control variable network NN ctrl , using obstacle area information and nominal trajectory data to calculate the loss function including obstacle area constraints and physical equation residual constraints, and optimizing the two networks simultaneously by minimizing the loss function to obtain the trained state variable network NN u and control variable network NN ctrl ; Using the trained control variable network NN ctrl Construct an obstacle avoidance control variable sequence and substitute it into the differential equation of the aircraft. u The differential equation is solved by numerical integration method to obtain the obstacle avoidance trajectory of the aircraft, and then verify whether the obstacle avoidance trajectory meets the predetermined performance index. If it does, the obstacle avoidance trajectory and control angle sequence are output; if it does not meet the requirements, the state variable network NN is optimized. u and control variable network NN ctrl , regenerate the aircraft's obstacle avoidance trajectory until the aircraft's obstacle avoidance trajectory meets the performance indicators.

2. The method according to claim 1, characterized in that The step of constructing a dynamic model of the aircraft and generating a nominal trajectory of the aircraft using the dynamic model includes: Construct the dynamic model of the aircraft, and the kinematic model expression is as follows: Among them G V is the transformation matrix from the velocity coordinate system to the launch coordinate system, which is composed of the ballistic inclination angle θ V , ballistic deflection angle ψ V , tilt angle γ V Characterize, the expression is: Among them, the ballistic inclination angle and ballistic deviation angle can be calculated from the velocity component, and V is the magnitude of the velocity in the launch system: C in the equation D ,C L ,C z is the aerodynamic coefficient, which is related to the angle of attack (α) and the Mach number (Ma). The variables to be determined in the equations are the angle of attack α and the roll angle γ V , these two variables are used as control variables to control the flight trajectory of the aircraft; Based on the dynamic model of the aircraft, a nominal trajectory of the aircraft is generated by a fourth-order Runge-Kutta integration method, wherein the nominal trajectory is a flight trajectory when the obstacle avoidance control angle and the roll angle are constantly zero.

3. The method according to claim 2, characterized in that The method of generating a nominal trajectory of the aircraft based on the dynamic model of the aircraft by the fourth-order Runge-Kutta integration method, wherein the nominal trajectory is a flight trajectory when the obstacle avoidance control angle and the roll angle are always 0, comprises: The dynamic model of the aircraft constructed by the differential equations is a set of ordinary differential equations with t as the independent variable, which describes the changes of the six state variables and their relationship with each other. In this set of differential equations, the angle of attack α and the roll angle γ V is the variable that affects the aerodynamic term. Given the state variable u=(V x ,V y ,V Z ,x,y,z), and gives the angle of attack α and the roll angle γ V The sequence or calculation function is solved by the Runge-Kutta method to obtain the nominal trajectory information of the aircraft, which includes the geometric path of the aircraft, the speed and acceleration information of the aircraft, and the angle of attack α is the maximum lift-to-drag ratio C that the aircraft can achieve at the current speed. L / C D Angle of attack, roll angle γ V As a control angle, it can avoid obstacles.

4. The method according to claim 2 or 3, characterized in that: The construction state variable network NN u , using the state variable network to construct the proposed state variable The state variable network is pre-trained using the nominal trajectory to obtain a pre-trained state variable network NN u ,include: Constructing state variable network NN u , the state variable network NN u The structure is a feedforward neural network, and the input is the normalized time series t on the nominal trajectory. * , output The normalization method of time variables is: Where t is the normalized time series on the nominal trajectory, μ t is the mean of the sequence, μ is the variance of the sequence, The calculation formula is: The proposed method for constructing the state variables is to transform the state variable network NN u Output After denormalization, the position variable is assumed to be Then the predicted speed variable is obtained through automatic differentiation The specific expression is: By minimizing the error between the state variable assumption and the nominal trajectory state variable, the state variable network NN is adjusted according to the error. u Parameters of the pre-trained state variable network NN u Repeat the above process continuously. After the training is completed, the pre-trained state variable network NN is obtained. u .

5. The method according to claim 1, characterized in that The obstacle area information and the nominal trajectory data are used to calculate the loss function including the obstacle area constraint and the physical equation residual constraint, and the two networks are optimized simultaneously by minimizing the loss function to obtain the trained state variable network NN u and control variable network NN ctrl ,include: Constructing state variable network NN ctrl , state variable network NN ctrl The structure is a feedforward neural network, and the input is the normalized time series t on the nominal trajectory. * , output The range is between [-1,1], multiplied by the maximum value allowed by the control angle to obtain the proposed obstacle avoidance control angle It satisfies the range constraint; the normalized time series on the nominal trajectory of the aircraft is input into the pre-trained state variable network NN u and control variable network NN ctrl , calculate the state variables and control variables Set the loss function to state error loss Loss u , initial state loss Loss start , differential equation residual loss Loss res 、Control angle loss Loss ctrl , and obstacle area constraint loss Loss forbid The weighted sum of and optimizes the pre-trained state variable network NN by minimizing the loss function u and control variable network NN ctrl Parameters; State error loss Loss u Calculate the mean square error between the proposed state variable and the nominal trajectory, expressed as: Where N t Indicates the selected N t time points; initial state loss Loss start is the Loss at t = 0 u ; Differential equation residual loss Loss res Minimize the residual error of the differential equation, Loss res The calculation formula is as follows: Where rk4() represents one-step integration using the Runge-Kutta integration method, and the step length is equal to the time interval; Control angle loss Loss ctrl Make the control angle as small as possible. The calculation method is as follows: Obstacle area constraint loss Loss forbid Calculate the distance from the aircraft to the center of each no-fly zone. If it is greater than the radius of the no-fly zone, record it as 0. If it is less than the radius of the no-fly zone, record it as the maximum distance d from the aircraft to the edge of the no-fly zone. Finally, sum all d. The closer the point is to the center of the obstacle zone, the greater the loss applied. forbid The greater the loss, the greater the forbid The calculation formula is as follows: Among them A i for is the center of the jth obstacle area, is the radius of the jth obstacle zone, ∈ "relaxation factor", which is 2% of the maximum radius of the obstacle zone; The loss function Loss is expressed as: Loss=w1*Loss u +w2*Loss atart +w3*Loss res +w4*Loss ctrl +w5*Loss forbi; Optimize the pre-trained state variable network NN by minimizing the value of the loss function Loss u and control variable network NN ctrl Parameters of the trained state variable network NN u and control variable network NN ctrl .

6. The method according to claim 1, characterized in that The performance indicators include: a. Maximum absolute value of the roll angle (°): This indicator reflects the maximum roll angle that the aircraft needs to perform during the entire obstacle avoidance process; b. Maximum rate of change of roll angle (° / s): This indicator reflects the maximum rate of change of roll angle during obstacle avoidance; c. Longest range ratio: This indicator calculates the ratio of the longest range of the obstacle avoidance trajectory to the nominal trajectory under the same time; d. End point distance (km): This indicator calculates the distance between the obstacle avoidance trajectory and the end point of the nominal trajectory under the same time. The smaller the end point distance, the more conducive it is to complete the subsequent flight mission; e. Shortest distance to the center of the obstacle area: This indicator calculates the shortest distance between the aircraft and the center of the obstacle during obstacle avoidance.

7. The method according to claim 5 or 6, characterized in that: The control variable network NN that is trained is used ctrl Construct an obstacle avoidance control variable sequence and substitute it into the differential equation of the aircraft. u The numerical integration method is used to solve the differential equations to obtain the obstacle avoidance trajectory of the aircraft, including: Using the trained control variable network NN ctrl Construct an obstacle avoidance control variable sequence, substitute the obstacle avoidance control variable sequence into the differential equation of the aircraft, set the optimization goal and constraint conditions of the differential equation of the aircraft, the constraint conditions include obstacle area constraint, endpoint constraint, starting point constraint, thermal environment constraint, normal overload constraint and control amount constraint, based on the trained state variable network NN u The numerical integration method is used to solve the differential equation and obtain the obstacle avoidance trajectory of the aircraft.

Citation Information

Patent Citations

  • Method for programming cooperated gaming path based on neural network and artificial potential field

    CN108827312A

  • Obstacle avoidance flight control method, device and system of aircraft

    CN114545976A

  • Virtual aircraft control method and device, storage medium and electronic equipment

    CN118059494A

  • Controller for Optimizing Motion Trajectory to Control Motion of One or More Devices

    US20230074148A1

  • KR20230142202A

Cited By

  • Aerodynamic parameter identification method based on improved physical information neural network

    CN119623260A

  • Space target trajectory parallel mapping method based on physical information network

    CN119989894A

  • Logistics trajectory optimization method and device for industrial chain and electronic equipment

    CN120447590A

  • Logistics track optimization method, device and electronic equipment for industrial chain

    CN120447590B

  • Cluster adaptive path planning method based on geometric PDE and PINN

    CN120469239A