A UAV game decision-making system based on high-precision trajectory prediction

Abstract

The present invention discloses a UAV game decision-making system based on high-precision trajectory prediction, comprising: a data acquisition subsystem, a flight trajectory database, and a host computer subsystem; the data acquisition subsystem collects UAV flight data in real time through positioning radar, infrared sensors, and scanning gyroscopes, then performs graph-structured processing on the flight data to obtain the graph-structured flight data and store it in the flight trajectory database; the flight trajectory database is used to provide the graph-structured flight data to the host computer subsystem; the host computer subsystem is used to output the flight data at the next moment corresponding to the graph-structured flight data, then visually presents it and stores it in the flight trajectory database; the host computer subsystem includes a data set preprocessing module, a VGAE embedding generation module, a graph neural network modeling module, a trajectory prediction module, and a result display module, which are connected in sequence. The present invention innovatively introduces graph structuring and graph embedding representation to fully capture the multi-level dependencies in the UAV cluster, significantly improving the accuracy and applicability of UAV game decision-making flight trajectory prediction. Ultimately, combined with the game decision mechanism, it provides an efficient and reliable game decision-making solution for the collaborative task of UAV cluster game decision-making.

Description

Technical Field

[0001] The present invention belongs to the fields of drone game decision-making, graph structure learning and data-driven, and in particular relates to a drone game decision-making system based on high-precision trajectory prediction. Background Art

[0002] With the widespread application of drones in logistics, surveillance, and other fields, the demand for automated system control and efficient decision-making is increasing. In complex and ever-changing environments, different participants (such as drones and intelligent agents) need to make real-time strategic decisions during the game to optimize their own benefits and collaboratively complete the task. Traditional decision-making methods, which often rely on preset rules or physical models, have difficulty coping with the complex dependencies in multi-agent collaborative games. Furthermore, decision-making accuracy and efficiency are low in the face of dynamically changing environments.

[0003] In recent years, with the rapid development of deep learning and data-driven technologies, data-based game decision-making methods have gradually attracted attention. Graph neural networks, in particular, can effectively capture the spatiotemporal dependencies between multiple agents by modeling the interactions between game participants. The state data of game participants and their interactions can be naturally modeled as a graph structure, where nodes represent the strategic state of each agent at different time steps, and edges represent the mutual game relationships between participants. However, traditional graph neural networks have certain limitations when processing high-dimensional game data, making it difficult to efficiently extract underlying strategic features, especially when dealing with the temporal characteristics and dynamic changes in the game.

[0004] To address this problem, variational autoencoders (VAEs) provide a novel approach for extracting latent strategic features from complex, high-dimensional game data. By embedding the agent's temporal strategy data into a low-dimensional form and combining it with graph neural networks to model the game relationships and strategy evolution among multiple agents, the accuracy and real-time performance of decision-making can be significantly improved. Therefore, game decision-making systems based on variational graph autoencoders and graph neural networks have become an effective solution, capable of handling the complex temporal relationships in multi-agent collaborative games, accurately predicting future strategy evolution, and adapting to decision-making needs in complex dynamic scenarios. Summary of the Invention

[0005] The purpose of the present invention is to address the deficiencies of the existing technology and provide a drone game decision-making system based on high-precision trajectory prediction.

[0006] The objective of the present invention is achieved through the following technical solutions: a drone game decision-making system based on high-precision trajectory prediction, the drone game decision-making system comprising: a data acquisition subsystem, a flight trajectory database and a host computer subsystem; the data acquisition subsystem collects the flight data of the drone in real time through a positioning radar, an infrared sensor and a scanning gyroscope, and then performs graph-structured processing on the flight data to obtain the graph-structured flight data and store it in the flight trajectory database; the flight trajectory database is used to provide the graph-structured flight data to the host computer subsystem; the host computer subsystem is used to output the flight data of the next moment corresponding to the graph-structured flight data, and then performs visual presentation and stores it in the flight trajectory database; the host computer subsystem comprises a data set preprocessing module, a VGAE embedding generation module, a graph neural network modeling module, a trajectory prediction module and a result display module connected in sequence.

[0007] Furthermore, the data acquisition subsystem collects the UAV's flight data in real time through positioning radar, infrared sensor and scanning gyroscope, specifically:

[0008] The data acquisition subsystem collects the flight status of the UAV through positioning radar, infrared sensor and scanning gyroscope, and obtains the flight data H of the UAV at time step t. t : Where N represents the flight data H t Contains the flight feature vectors of N UAVs; represents the flight feature vector of the i-th UAV at time step t, i = 1, 2, …, i, …, N;

[0009] The flight characteristic vector for Among them, P i (t) represents the coordinate position vector of the positioning radar of the i-th UAV at time step t; v i (t) represents the flight velocity vector of the i-th UAV at time step t; a i (t) represents the aircraft attitude vector of the i-th UAV at time step t;

[0010] Coordinate position vector P i (t) is P i (t) = [x i (t),y i (t),z i (t)], where x i (t), y i (t) and z i (t) represents the three-dimensional coordinates of the i-th UAV at time step t;

[0011] Flight velocity vector v i (t) is v i (t)=[v x,i (t),v y,i (t),v z,i (t)], where v x,i (t) represents the velocity of the i-th UAV on the x-axis at time step t, v y,i (t) represents the velocity of the i-th UAV on the y-axis at time step t, v z,i (t) represents the velocity of the i-th UAV on the z-axis at time step t;

[0012] Aircraft attitude vector a i (t) is Among them, ω i (t) represents the roll angle of the i-th UAV at time step t, θ i (t) represents the pitch angle of the i-th UAV at time step t, represents the yaw angle of the i-th UAV at time step t.

[0013] Furthermore, the data acquisition subsystem performs graph-structured processing on the flight data to obtain the graph-structured flight data and stores the processed flight data in the flight trajectory database, which specifically includes the following sub-steps:

[0014] (a.1) The data acquisition subsystem first collects the flight data H t Construct edge matrix E t : Among them, e (i,t),(j,t) represents the trajectory dependency between the i-th UAV and the j-th UAV at the same time step t, j = 1, 2, …, j, …, N;

[0015] Then according to the matrix E t Get the weight matrix W t :

[0016] Among them, w (i,t),(j,t) represents the weight between the i-th UAV and the j-th UAV at the same time step t;

[0017] If the trajectory dependency between the i-th UAV and the j-th UAV at the same time step t exists, then the edge e (i,t),(j,t) Weight setting w (i,t),(j,t) is 1, otherwise the edge e (i,t),(j,t) The weight setting w (i,t),(j,t) If it is 0, the formula for determining whether there is a dependency relationship is as follows:

[0018]

[0019] Among them, ||·|| 2 represents norm2 function;∈ is the preset threshold;

[0020] (a.2) Then according to the edge matrix E t and the weight matrix W t , get the adjacency matrix A t :

[0021] Among them, a (i,t),(j,t) It represents the adjacency relationship between the i-th UAV and the j-th UAV at the same time step t. The calculation formula is as follows:

[0022]

[0023] (a.3) The flight data H t and the adjacency matrix A t The flight data G after graph structure processing t =(H t ,A t ) is stored in the flight trajectory database.

[0024] Furthermore, the host computer subsystem outputs the flight data at the next moment corresponding to the flight data after graph structure processing, and then performs visualization and stores it in the flight trajectory database, which specifically includes the following sub-steps:

[0025] (c.1) The host computer subsystem first converts the flight data G after graph structure processing t =(H t ,A t ) is input to the data set preprocessing module for preprocessing, and the normalized graph-structured flight data G is output. t ′=(H t ′,A t ′);

[0026] (c.2) The normalized graph-structured flight data G t ′=(H t ′,A t ′) is input into the VGAE embedding generation module, and the embedding generation model in the VGAE embedding generation module is optimized and trained to obtain the optimized embedding generation model; and the normalized graph-structured flight data G is trained by the optimized embedding generation model. t ′=(H t ′,A t ′) is processed to obtain the optimized potential embedding matrix Z t And the optimized reconstructed adjacency matrix

[0027] (c.3) The optimized latent embedding matrix And the optimized reconstructed adjacency matrix Input to the graph neural network modeling module, and output the node feature matrix by updating the graph neural network parameters of the L layer

[0028] (c.4) Then the node feature matrix Input to the game decision trajectory prediction module, and the nonlinear neural network layer predicts the flight characteristic data of the next moment

[0029] (c.5) The flight characteristics data of the next moment will be predicted The game decision result display module is used to visualize the results and store them in the flight trajectory database.

[0030] Furthermore, the step (c.1) specifically includes the following sub-steps:

[0031] (c.1.1) Flight data G after graph structure processing t =(H t ,A t ) in the flight data H t Normalize and get the normalized flight data H t ′:H t ′=[h t ' 1 ,h t ' 2 ,…,h t ' i ,…,h t ' N ];

[0032] For each UAV’s flight feature vector at time step t Normalize and get the normalized flight feature vector h t ' i :

[0033]

[0034] in, Represents the flight feature vector The mean of all features in ; Represents the flight feature vector The standard deviation of all features in ;

[0035] (c.1.2) Flight data G after graph structure processing t =(H t ,At ) in the adjacency matrix A t Normalize and get the normalized adjacency matrix A t ′: Among them, D t Represents the adjacency matrix A t degree matrix of ;

[0036] Complete normalization and obtain the normalized graph-structured flight data G t ′=(H t ′,A t ′).

[0037] Furthermore, the step (c.2) specifically includes the following sub-steps:

[0038] (c.2.1) The normalized graph-structured flight data G t ′=(H t ′,A t ') is input into a VGAE embedding generation module, wherein the VGAE embedding generation module includes an embedding generation model composed of a decoder and an encoder;

[0039] Normalized flight data H t Each flight feature vector h in ′ t ' i After being processed by the encoder, the mean μ is obtained t ' i and variance σ t ' i :

[0040] μ t ' i ,log(σ t ' i ) 2 =Encoder(h t ' i );

[0041] Where, Encoder(·) represents the encoder;

[0042] Then the mean μ t ' i and variance σ t ' i Construct the flight feature vector h t ' i The corresponding latent embedding vector

[0043] For all flight feature vectors h t ' iAfter the above processing, the potential embedding matrix Z is obtained t :

[0044] (c.2.2) Use the decoder to pass the latent embedding matrix Z t Construct the reconstructed adjacency matrix

[0045] in, represents the potential similarity between the i-th UAV and the j-th UAV at the same time step t, and is calculated as follows:

[0046]

[0047] Where Decoder(·) represents the decoder, which uses the inner product operation or nonlinear activation function to calculate the potential similarity;

[0048] (c.2.3) Constructing the total loss function L to optimize the embedding generation model parameters and obtain the optimized embedding generation model;

[0049] The total loss function L is composed of the reconstruction error loss L recon And KL divergence loss function L KL composition;

[0050] The reconstruction error loss L recon for Among them, a′ (i,t),(j,t) Represents the normalized adjacency matrix A t Any adjacency relation in ′;

[0051] The KL divergence loss function L KL for Where Tr(·) represents the trace function of the matrix, that is, the sum of the diagonal elements of the variance matrix; det(·) represents the determinant of the matrix; d is the dimension of the potential embedding vector;

[0052] (c.2.4) Then the normalized graph-structured flight data G t ′=(H t ′,A t ′) is input into the optimized embedding generation model, and steps (c.2.1)-step (c.2.2) are repeated to obtain the optimized potential embedding matrix And the optimized reconstructed adjacency matrix

[0053] Furthermore, the step (c.3) specifically includes the following sub-steps:

[0054] (c.3.1) The optimized latent embedding matrix for in, represents the optimized latent embedding vector of the i-th drone;

[0055] The optimized reconstructed adjacency matrix for in, represents the optimized potential similarity between the i-th UAV and the j-th UAV at the same time step t;

[0056] (c.3.2) Get the set of all adjacent drones of the i-th drone at the same time step t in, represents the neighboring drones of any i-th drone at the same time step t, E i represents the number of all neighboring drones of the i-th drone at the same time step t;

[0057] The optimized latent embedding vector for the i-th drone Update the parameters of the graph neural network of layer L;

[0058] First, any optimized latent embedding vector Node features as the output of the first layer of graph neural network

[0059] Then the node features output by the l-th layer graph neural network for Among them, W l is the learnable parameter matrix of the l-th layer graph neural network; σ(·) is the nonlinear Sigmoid activation function;

[0060] After updating the L-layer graph neural network, the node features output by the L-layer graph neural network are obtained

[0061] (c.3.2) For the optimized latent embedding matrix Z t Repeat step (c.3.2) for each optimized latent embedding vector in and output the node feature matrix

[0062] The beneficial effects of the present invention are: 1. The variational graph autoencoder is innovatively introduced to embed and generate UAV trajectories, effectively extracting the potential features of the UAV's multi-dimensional time series data, and at the same time obtaining an optimized reconstructed adjacency matrix, thereby enhancing the system's prediction accuracy in complex game tasks; 2. The collaborative relationship and spatiotemporal dependency between UAVs are modeled through a graph neural network, and the algorithm has a high degree of optimization, can handle complex scenarios of multi-agent collaborative games, and achieve high-precision trajectory prediction; 3. The system can identify changes in various game strategies in real time, has strong intelligence, and can adapt to the game decision-making needs in complex dynamic environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 This is a structural diagram of a UAV game decision-making system based on high-precision trajectory prediction;

[0064] In the figure, 1-data acquisition subsystem; 2-flight trajectory database; 3-host computer subsystem; 4-dataset preprocessing module; 5-VGAE embedding generation module; 6-graph neural network modeling module; 7-trajectory prediction module; 8-result display module. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to illustrate the present invention, rather than to represent all embodiments. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments of the present invention without creative work are within the scope of protection of the present invention.

[0066] Example 1

[0067] like Figure 1 As shown, the present invention provides a UAV game decision system based on high-precision trajectory prediction, and the UAV game decision system includes: a data acquisition subsystem 1, a flight trajectory database and a host computer subsystem; the data acquisition subsystem 1 collects the flight data of the UAV in real time through a positioning radar, an infrared sensor and a scanning gyroscope, and then performs graph-structured processing on the flight data to obtain the flight data after graph-structured processing and stores it in the flight trajectory database 2; the flight trajectory database 2 is used to provide the flight data after graph-structured processing to the host computer subsystem 3; the host computer subsystem 3 is used to output the flight data of the next moment corresponding to the flight data after graph-structured processing, and then visualizes it and stores it in the flight trajectory database 2; the host computer subsystem 3 includes a data set preprocessing module 4, a VGAE embedding generation module 5, a graph neural network modeling module 6, a trajectory prediction module 7 and a result display module 8 connected in sequence.

[0068] The data acquisition subsystem 1 collects the flight data of the UAV in real time through positioning radar, infrared sensor and scanning gyroscope, specifically:

[0069] The data acquisition subsystem 1 collects the flight status of the UAV through positioning radar, infrared sensor and scanning gyroscope, and obtains the flight data H of the UAV at time step t. t : Where N represents the flight data H t Contains the flight feature vectors of N UAVs; represents the flight feature vector of the i-th UAV at time step t, i = 1, 2, …, i, …, N.

[0070] The flight characteristic vector for Among them, P i (t) represents the coordinate position vector of the positioning radar of the i-th UAV at time step t; v i (t) represents the flight velocity vector of the i-th UAV at time step t; a i (t) represents the aircraft attitude vector of the i-th UAV at time step t.

[0071] Coordinate position vector P i (t) is P i (t) = [x i (t),y i (t),z i (t)], where x i (t), y i (t) and z i (t) represents the three-dimensional coordinates of the i-th UAV at time step t;

[0072] Flight velocity vector v i (t) is v i (t)=[v x,i (t),v y,i (t),v z,i (t)], where v x,i (t) represents the velocity of the i-th UAV on the x-axis at time step t, v y,i (t) represents the velocity of the i-th UAV on the y-axis at time step t, v z,i (t) represents the velocity of the i-th UAV on the z-axis at time step t.

[0073] Aircraft attitude vector a i (t) is Among them, ω i (t) represents the roll angle of the i-th UAV at time step t, θ i(t) represents the pitch angle of the i-th UAV at time step t, represents the yaw angle of the i-th UAV at time step t.

[0074] The data acquisition subsystem 1 performs graph-structured processing on the flight data to obtain the graph-structured flight data and stores the processed flight data in the flight trajectory database 2, which specifically includes the following sub-steps:

[0075] (a.1) The data acquisition subsystem 1 first collects the flight data H t Construct edge matrix E t : Among them, e (i,t),(j,t) represents the trajectory dependency between the i-th UAV and the j-th UAV at the same time step t, j = 1, 2, …, j, …, N.

[0076] Then according to the matrix E t Get the weight matrix W t :

[0077] Among them, w (i,t),(j,t) represents the weight between the i-th UAV and the j-th UAV at the same time step t.

[0078] If the trajectory dependency between the i-th UAV and the j-th UAV at the same time step t exists, then the edge e (i,t),(j,t) Weight setting w (i,t),(j,t) is 1, otherwise the edge e (i,t),(j,t) The weight setting w (i,t),(j,t) is 0, the formula is as follows:

[0079]

[0080] Among them, ||·|| 2 Represents norm2 function; ∈ is the preset threshold.

[0081] (a.2) Then according to the edge matrix E t and the weight matrix W t , get the adjacency matrix A t :

[0082] Among them, a (i,t),(j,t) It represents the adjacency relationship between the i-th UAV and the j-th UAV at the same time step t. The calculation formula is as follows:

[0083]

[0084] (a.3) The flight data H t and the adjacency matrix At The flight data G after graph structure processing t =(H t ,A t ) is stored in the flight trajectory database 2.

[0085] The host computer subsystem 3 outputs the flight data of the next moment corresponding to the flight data after graph structure processing, and then performs visualization and stores it in the flight trajectory database 2, which specifically includes the following sub-steps:

[0086] (c.1) The host computer subsystem 3 first converts the flight data G into graph structured data. t =(H t ,A t ) is input to the data set preprocessing module 4 for preprocessing, and the normalized graph-structured flight data G is output. t ′=(H t ′,A t ′).

[0087] The step (c.1) specifically includes the following sub-steps:

[0088] (c.1.1) To ensure the consistency of feature ranges and prevent data of different dimensions from affecting model training, the dataset preprocessing module performs normalization.

[0089] For the flight data G after graph structured processing t =(H t ,A t ) in the flight data H t Normalize and get the normalized flight data H t ′:H t ′=[h t ' 1 ,h t ' 2 ,…,h t ' i ,…,h t ' N ].

[0090] For each UAV’s flight feature vector at time step t Normalize and get the normalized flight feature vector h t ' i :

[0091]

[0092] in, Represents the flight feature vector The mean of all features in ; Represents the flight feature vector The standard deviation of all features in .

[0093] (c.1.2) is to make the adjacency matrix A t The interaction between the nodes in the game can contribute fairly in the optimization process. The dataset preprocessing module can make a fair contribution to the adjacency matrix A. t Perform normalization.

[0094] For the flight data G after graph structured processing t =(H t ,A t ) in the adjacency matrix A t Normalize and get the normalized adjacency matrix A t ′: Among them, D t Represents the adjacency matrix A t The degree matrix of .

[0095] Complete normalization and obtain the normalized graph-structured flight data G t ′=(H t ′,A t ′).

[0096] (c.2) The normalized graph-structured flight data G t ′=(H t ′,A t ′) is input to the VGAE embedding generation module 5, and the embedding generation model in the VGAE embedding generation module 5 is optimized and trained to obtain the optimized embedding generation model; and the normalized graph-structured flight data G is trained by the optimized embedding generation model. t ′=(H t ′,A t ′) is processed to obtain the optimized potential embedding matrix And the optimized reconstructed adjacency matrix

[0097] The step (c.2) specifically includes the following sub-steps:

[0098] (c.2.1) The normalized graph-structured flight data G t ′=(H t ′,A t ′) is input into the VGAE embedding generation module 5, which includes an embedding generation model composed of a decoder and an encoder.

[0099] Normalized flight data H t Each flight feature vector h in ′ t ' i After being processed by the encoder, the mean μ is obtainedt ' i and variance σ t ' i :

[0100] μ t ' i ,log(σ t ' i ) 2 =Encoder(h t ' i );

[0101] Wherein, Encoder(·) represents an encoder.

[0102] Then the mean μ t ' i and variance σ t ' i Construct the flight feature vector h t ' i The corresponding latent embedding vector ε is a noise vector sampled from a standard normal distribution, ensuring the randomness of the latent embedding vector.

[0103] For all flight feature vectors h t ' i After the above processing, the potential embedding matrix Z is obtained t :

[0104] (c.2.2) Use the decoder to pass the latent embedding matrix Z t Construct the reconstructed adjacency matrix

[0105] in, represents the potential similarity between the i-th UAV and the j-th UAV at the same time step t, and is calculated as follows:

[0106]

[0107] Where Decoder(·) represents a decoder, and the potential similarity is calculated by the decoder using an inner product operation or a nonlinear activation function.

[0108] (c.2.3) Construct the total loss function L to optimize the model parameters of the embedding generation model to obtain the optimized embedding generation model.

[0109] The total loss function L is composed of the reconstruction error loss L recon And KL divergence loss function LKL composition.

[0110] The reconstruction error loss L recon for Among them, a′ (i,t),(j,t) Represents the normalized adjacency matrix A t Any adjacency relationship in ′.

[0111] The KL divergence loss function L KL for Where Tr(·) represents the trace function of the matrix, i.e., the sum of the diagonal elements of the variance matrix; det(·) represents the determinant of the matrix; and d is the dimension of the potential embedding vector.

[0112] (c.2.4) Then the normalized graph-structured flight data G t ′=(H t ′,A t ′) is input into the optimized embedding generation model, and steps (c.2.1)-step (c.2.2) are repeated to obtain the optimized potential embedding matrix And the optimized reconstructed adjacency matrix A t .

[0113] (c.3) The optimized latent embedding matrix And the optimized reconstructed adjacency matrix Input to the graph neural network modeling module 6, and output the node feature matrix by updating the graph neural network parameters of the L layer

[0114] The step (c.3) specifically includes the following sub-steps:

[0115] (c.3.1) The optimized latent embedding matrix for in, represents the optimized latent embedding vector of the i-th drone;

[0116] The optimized reconstructed adjacency matrix for in, represents the optimized potential similarity between the i-th UAV and the j-th UAV at the same time step t.

[0117] (c.3.2) Get the set of all adjacent drones of the i-th drone at the same time step t in, represents the neighboring drones of any i-th drone at the same time step t, E i represents the number of all neighboring drones of the i-th drone at the same time step t.

[0118] The optimized latent embedding vector for the i-th drone Update the L-layer graph neural network.

[0119] First, any optimized latent embedding vector Node features as the output of the first layer of graph neural network

[0120] Then the node features output by the l-th layer graph neural network Among them, W l is the learnable parameter matrix of the l-th layer graph neural network; σ(·) is the nonlinear Sigmoid activation function.

[0121] After updating the L-layer graph neural network, the node features output by the L-layer graph neural network are obtained

[0122] (c.3.2) For the optimized latent embedding matrix Repeat step (c.3.2) for each optimized latent embedding vector in and output the node feature matrix

[0123] (c.4) Then the node feature matrix Input to the game decision trajectory prediction module 7, and the nonlinear neural network layer predicts the flight characteristic data of the next moment

[0124] The flight characteristic data at the next moment includes the future coordinate position vector of each drone at the next moment t+1 Flight velocity vector and the aircraft attitude vector Among them, f p (·),f v (·) and f a (·) are nonlinear functions used for predicting coordinate position, flight speed and aircraft attitude, respectively, and are usually implemented by neural networks.

[0125] (c.5) The flight data for the next moment will then be predicted The game decision result display module 8 performs visual presentation and stores it in the flight trajectory database 2 for subsequent system evaluation, prediction and further game analysis.

[0126] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A drone game decision-making system based on high-precision trajectory prediction, characterized by: The UAV game decision-making system includes: a data acquisition subsystem, a flight trajectory database and a host computer subsystem; the data acquisition subsystem collects the UAV's flight data in real time through a positioning radar, an infrared sensor and a scanning gyroscope, and then performs graph-structured processing on the flight data to obtain the flight data after graph-structured processing and stores it in the flight trajectory database; the flight trajectory database is used to provide the host computer subsystem with the flight data after graph-structured processing; the host computer subsystem is used to output the flight data of the next moment corresponding to the flight data after graph-structured processing, and then visualizes it and stores it in the flight trajectory database; the host computer subsystem includes a data set preprocessing module, a VGAE embedding generation module, a graph neural network modeling module, a trajectory prediction module and a result display module connected in sequence; The data acquisition subsystem collects the UAV's flight data in real time through positioning radar, infrared sensor and scanning gyroscope, specifically: The data acquisition subsystem collects the flight status of the UAV through positioning radar, infrared sensor and scanning gyroscope, and obtains the flight status of the UAV at the time step. Flight data below : ,in, Indicates flight data Contains The flight feature vector of each UAV; Indicates the UAVs at time step The flight characteristic vector under ; The flight characteristic vector for ,in, Indicates the UAVs at time step The coordinate position vector of the positioning radar under ; Indicates the UAVs at time step The flight velocity vector under ; Indicates the UAVs at time step The aircraft attitude vector under Coordinate position vector for ,in, 、 and Indicates the UAVs at time step The three-dimensional coordinates of Flight velocity vector for ,in, Indicates the UAVs at time step Under The speed of the axis, Indicates the UAVs at time step Under The speed of the axis, Indicates the UAVs at time step Under Speed ​​on the axis; Aircraft attitude vector for ,in, Indicates the UAVs at time step The roll angle below, Indicates the UAVs at time step The pitch angle below, Indicates the UAVs at time step The yaw angle of the next The data acquisition subsystem performs graph-structured processing on the flight data, obtains the graph-structured flight data, and stores the processed flight data in the flight trajectory database, specifically including the following sub-steps: (a.1) The data acquisition subsystem first targets flight data Constructing the edge matrix : ,in, Indicates the drone and the UAVs at the same time step The trajectory dependencies between ; Then according to the matrix Get the weight matrix : ; in, Indicates the drone and the UAVs at the same time step The weight between Jordi drone and the UAVs at the same time step If the trajectory dependency relationship between Weight setting is 1, otherwise the edge Weight setting If it is 0, the formula for determining whether there is a dependency relationship is as follows: ； in, represents the norm 2 function; is the preset threshold; (a.2) Then according to the edge matrix and the weight matrix , and get the adjacency matrix : ； in, Indicates the drone and the UAVs at the same time step The adjacency relationship between them is calculated as follows: ； (a.3) Flight data and the adjacency matrix Flight data after graph structure processing Store in flight trajectory database; The host computer subsystem outputs the flight data corresponding to the next moment after the graph structured processing, and then visualizes and stores it in the flight trajectory database, which specifically includes the following sub-steps: (c.1) The host computer subsystem first processes the flight data after graph structure processing Input to the dataset preprocessing module for preprocessing, and output normalized graph-structured flight data ; (c.2) Convert the normalized graph structured flight data Input it into the VGAE embedding generation module, and optimize the embedding generation model in the VGAE embedding generation module to obtain the optimized embedding generation model; and use the optimized embedding generation model to train the normalized graph-structured flight data. Processing is performed to obtain the optimized potential embedding matrix And the optimized reconstructed adjacency matrix ; (c.3) The optimized latent embedding matrix is ​​then And the optimized reconstructed adjacency matrix Input to the graph neural network modeling module, through Update the parameters of the graph neural network layer and output the node feature matrix ; (c.4) Then the node feature matrix Input to the game decision trajectory prediction module, and the nonlinear neural network layer predicts the flight characteristic data of the next moment ; (c.5) The flight characteristics data of the next moment will be predicted The game decision result display module is used to visualize the results and store them in the flight trajectory database.

2. The UAV game decision-making system based on high-precision trajectory prediction according to claim 1 is characterized in that: The step (c.1) specifically includes the following sub-steps: (c.1.1) Flight data after graph structured processing Flight data in Normalize and get normalized flight data : ; For each UAV at time step Flight characteristic vector under Normalize and get the normalized flight feature vector : ； in, Represents the flight feature vector The mean of all features in ; Represents the flight feature vector The standard deviation of all features in ; (c.1.2) Flight data after graph structured processing The adjacency matrix in Normalize and get the normalized adjacency matrix : ,in, Represents the adjacency matrix degree matrix of ; Complete normalization and obtain normalized graph-structured flight data .

3. The UAV game decision-making system based on high-precision trajectory prediction according to claim 2 is characterized in that: The step (c.2) specifically includes the following sub-steps: (c.2.1) Convert the normalized graph structured flight data Input to the VGAE embedding generation module, which includes an embedding generation model composed of a decoder and an encoder; Normalized flight data Each flight feature vector After being processed by the encoder, the mean is obtained and variance : ； in, represents the encoder; Then the mean and variance Construct the flight feature vector The corresponding latent embedding vector : ； For all flight feature vectors After the above processing, the potential embedding matrix is ​​obtained : ； (c.2.2) Use the decoder to pass the latent embedding matrix Construct the reconstructed adjacency matrix : ； in, Indicates the drone and the UAVs at the same time step The potential similarity between them is calculated as follows: ； in, represents the decoder, which calculates the potential similarity using the inner product operation or nonlinear activation function; (c.2.3) Construct the total loss function Optimize the model parameters of the embedding generation model to obtain the optimized embedding generation model; The total loss function The reconstruction error loss and Divergence loss function composition; The reconstruction error loss for ,in, Represents the normalized adjacency matrix Any adjacency relationship in described Divergence loss function for ,in, represents the trace function of the matrix, that is, the sum of the diagonal elements of the variance matrix; represents the determinant of a matrix; is the dimension of the latent embedding vector; (c.2.4) Then the normalized graph structured flight data Input into the optimized embedding generation model and repeat steps (c.2.1)-step (c.2.2) to obtain the optimized potential embedding matrix And the optimized reconstructed adjacency matrix .

4. The UAV game decision-making system based on high-precision trajectory prediction according to claim 3 is characterized in that: The step (c.3) specifically includes the following sub-steps: (c.3.1) The optimized latent embedding matrix for ,in, Indicates the The optimized latent embedding vector of each drone; The optimized reconstructed adjacency matrix for ,in, Indicates the drone and the UAVs at the same time step The optimized potential similarity between (c.3.2) Get UAVs at the same time step The collection of all adjacent drones under ,in, Indicates any UAVs at the same time step The adjacent drones under Indicates the UAVs at the same time step The number of all adjacent drones under ; For the The optimized latent embedding vector of the drone conduct Update of the parameters of the graph neural network layer; First, any optimized latent embedding vector Node features as the output of the first layer of graph neural network ; Then Node features output by layer graph neural network for ,in, For the Learnable parameter matrices of layer graph neural networks; is the nonlinear Sigmoid activation function; go through After updating the graph neural network of the layer, we get Node features output by layer graph neural network ; (c.3.2) For the optimized latent embedding matrix Repeat step (c.3.2) for each optimized latent embedding vector in, outputting the node feature matrix : .

Images