Low-altitude unmanned aerial vehicle reconnaissance and disposal integrated protection system

Abstract

The invention provides a low-altitude unmanned aerial vehicle reconnaissance and disposal integrated protection system, and belongs to the technical field of low-altitude defense, airspace safety and unmanned aerial vehicle management, and the system comprises a low-altitude intrusion detection and tracking module which obtains target area information through a radar and a camera, carries out the 4DFFT preprocessing of radar data, and carries out the image preprocessing of an RGB image; unifying the preprocessed data to a format required by a target detection and tracking algorithm through respective input adaptation modules; and a multi-source information fusion decision-making mechanism is utilized to realize real-time and high-precision unmanned aerial vehicle detection and tracking functions. And the unmanned aerial vehicle identity recognition module obtains the identity information of the unmanned aerial vehicle through the RFID tag, and verifies the identity legality of all the unmanned aerial vehicles in the region by using a joint optimization power control and time slot allocation algorithm. And the unmanned aerial vehicle intelligent scheduling module optimizes path planning, task allocation and resource management through reinforcement learning, dynamically allocates tasks and optimizes route planning.

Description

Technical Field

[0001] The present invention relates to the fields of low-altitude defense, airspace safety and unmanned aerial vehicle management technology, and in particular to a low-altitude unmanned aerial vehicle reconnaissance and disposal integrated protection system. Background Art

[0002] With the rapid development of drone technology and 5G-A / 6G communication technology, drones are increasingly used in urban environments, covering multiple fields such as surveillance, logistics and transportation, and disaster relief. They have shown great potential in improving production efficiency, optimizing resource allocation, and promoting low-altitude economic construction. However, unauthorized drone activities pose potential security threats and pose hidden dangers to critical infrastructure and privacy. In response to illegal drone activities, anti-drone systems have received widespread attention, and their key functions include drone positioning, tracking, decision-making, and corresponding strategies. Among these functions, drone detection plays an intuitive and important role in achieving real-time tracking, evaluation, and decision-making. In addition, behavioral analysis based on precise positioning is essential for rapid response, effective crackdown on illegal activities, and protection of the security of the monitoring area. Therefore, improving the positioning and recognition accuracy of drones is the key to improving the overall performance of anti-drone systems. However, unlike the positioning of other targets (such as pedestrians or vehicles), drone detection in complex backgrounds faces severe challenges. First, due to the small size and low flight altitude of civilian drones, their signal characteristics are not significant to many sensors, making it difficult to distinguish them from the background and other flying targets (such as birds or aircraft). Secondly, drones have omnidirectional, high-speed and unpredictable movement characteristics in three-dimensional space, which requires the positioning algorithm to have powerful positioning capabilities with high precision, fast response and low false alarm rate.

[0003] Although there are many drone detection methods, there are still significant limitations in practical applications, which affect the overall effectiveness of anti-drone systems. Traditional radar detection methods have all-weather detection capabilities under different lighting conditions and high positioning accuracy. However, for drones with small radar cross-section (RCS), slow speed, and low flight altitude, the radar system is prone to detection blind spots, which limits its detection performance in low-altitude environments. Although microphone array-based technology can use the unique sound of the rotor to detect drones, the positioning effect is greatly reduced in noisy environments and the detection range is limited. Vision-based drone detection has unique advantages. It can achieve intuitive identification and tracking by capturing and analyzing the visual features of drones. However, in practical applications, it often faces problems such as large scale changes, low target resolution, insufficient detailed features, and susceptibility to background occlusion, which affect the overall detection performance of the system. Therefore, studying how to effectively detect and track drones is not only of great significance for urban airspace management and security monitoring, but also the key to promoting the rapid development of the low-altitude economy.

[0004] The information disclosed in this background technology section is only intended to enhance the understanding of the overall background of the invention and should not be regarded as an acknowledgment or any form of suggestion that the information constitutes the prior art already known to a person skilled in the art. Summary of the invention

[0005] The purpose of the present invention is to provide a low-altitude UAV reconnaissance and disposal integrated protection system capable of improving overall detection performance.

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] A low-altitude UAV reconnaissance and disposal integrated protection system, comprising:

[0008] A low-altitude intrusion detection and tracking module, which includes at least one radar and visual integration device;

[0009] The radar and vision integrated device is composed of a millimeter wave radar and a long-range camera; the radar and vision integrated device obtains the information of the detected area in real time through a wired transmission channel, a 5G-A or 6G wireless transmission channel, and the information is respectively encapsulated in a frame format;

[0010] The data analysis module is used to analyze radar information and visual information, and synchronize the time and space of radar information and visual information by downsampling at the lowest frequency;

[0011] The data preprocessing module is used to preprocess the radar-visual integrated information encapsulated by the calibrated radar information and visual information.

[0012] Optionally, the preprocessing of the radar-visual integrated information encapsulated from the calibrated radar information and visual information includes:

[0013] The radar information is preprocessed in the order of range fast Fourier transform, Doppler fast Fourier transform, elevation fast Fourier transform and azimuth fast Fourier transform to complete the 4DFFT cube data preprocessing;

[0014] Sending the 4DFFT cube data and visual information to an adaptive gated convolutional target detection and tracking network; the adaptive gated convolutional target detection and tracking network includes a radar adaptation module, a visual adaptation module and an adaptive gated convolutional neural network;

[0015] The adaptive gated convolution target detection and tracking network is used to receive the 4DFFT cube data and visual data sent by the data preprocessing module; and send the 4DFFT cube data to the radar adaptation module to ensure the uniformity of the input data; then the radar adaptation module and the adaptive gated convolutional neural network are used to perform feature extraction to determine the azimuth and pitch angle of the target, and the results are sent to the multi-source information fusion decision module.

[0016] Optionally, the multi-source information fusion decision module is used to receive the target azimuth and pitch angle information, and analyze the regional position of the target in the visual information; crop the visual information according to the regional position, and send the cropped visual information to the visual adaptation module for further processing.

[0017] Optionally, the visual adaptation module is used to process the cropped visual information, extract target features, and generate a target tracking frame; map the target tracking frame back to the visual information before cropping, and confirm whether the target is a drone; if it is a drone, send the visual information to the drone identification module for identity verification; if it is other flying objects, send the visual information to the drone intelligent scheduling module and the alarm and disposal module respectively; if it is background interference, send abnormal information to the alarm and disposal module.

[0018] Optionally, also include:

[0019] The drone identity recognition module is used to provide energy for the drone passive RFID tag through the signal sent by the ground base station reader; the drone provides identity and status information to the ground base station by modulating the backscatter signal; determines the legitimacy of the drone identity; if the drone identity is legal, continues to determine the legitimacy of the drone flight path; if the flight path is legal, maintains the mission process; if the flight path is illegal, sends the information and drone status information to the drone intelligent scheduling module; if the drone identity is illegal, sends visual information and drone status information to the drone intelligent scheduling module and alarm and disposal module respectively.

[0020] Optionally, it also includes: a joint optimization power control and time slot allocation algorithm, wherein:

[0021] Multiple ground base station readers use power modulation to avoid overlapping recognition ranges;

[0022] Reduce signal interference when multiple drones compete for channels through time slot allocation strategies;

[0023] The time slot allocation strategy includes:

[0024] Multiple polling cycles, at the beginning of each cycle, randomly select whether to poll, working channel and transmit power;

[0025] The ground base station starts the frame operation by broadcasting a Query command. The frame contains multiple time slots, and each drone randomly selects a time slot to respond;

[0026] After the frame ends, the ground base station sends the drone RFID tag information to the registration server to determine the legitimacy;

[0027] The time slot response events include:

[0028] There are three types: idle, success and collision;

[0029] The number of drone RFID tags in the ground base station area is calculated based on maximum likelihood estimation, and the polling cycle and time are optimized.

[0030] Optionally, it also includes: a UAV intelligent dispatching module, which is used for state perception. The UAV sends its current environmental information and local information to the dispatching center to determine whether intelligent dispatching is required;

[0031] If dispatch is required, the intelligent dispatch center adjusts the drone’s path planning, cruising speed, and subsequent tasks and resource allocation based on the drone’s current status information and global events;

[0032] If no scheduling is required, maintain the current cruise or mission status.

[0033] Optionally, it also includes: a UAV intelligent scheduling strategy optimization module, which is used to optimize the preset initial strategy using a genetic algorithm according to the UAV status information;

[0034] Based on the initial strategy, Double Q-learning is used to dynamically update the strategy according to the local area environment information;

[0035] In Double Q-learning reinforcement learning, the intelligent dispatch center makes a trade-off between exploring new strategies and using existing strategies based on the drone status information;

[0036] Receive global regional data feedback in real time to analyze and optimize strategies;

[0037] The integrated dispatch center decision and Double Q-learning optimization strategy are used to re-plan the path and assign tasks for each drone;

[0038] For long-term emergencies and abnormal events, adaptive optimization strategies are used to maximize long-term benefits, thereby gradually improving scheduling efficiency and task completion.

[0039] Optionally, also include:

[0040] The alarm and handling module is characterized by comprising:

[0041] Large models assist analysis and decision-making. Based on the needs of intelligent dispatching of drones, large models are built to analyze drone status information in real time and provide optimized disposal decisions.

[0042] The large model assists in the analysis and decision-making model training. It obtains the required training data through crawler technology, and combines format conversion and data cleaning to generate high-quality data sets that meet training requirements.

[0043] The large model-assisted analysis and decision-making model combines pre-training, supervised fine-tuning and human preference optimization methods to improve the analysis and decision-making capabilities of the large model-assisted analysis and decision-making model for complex scenarios;

[0044] The large model-assisted analysis and decision-making model adopts the LLaMA series as a benchmark and expands its capabilities through knowledge enhancement and domain adaptation techniques;

[0045] The large model-assisted analysis and decision-making model prioritizes emergencies based on global and local environmental information, and formulates a hierarchical handling strategy to achieve dynamic alarm response efficiency.

[0046] Optionally, it also includes: an intrusion threat processing and response module, which is used to monitor the controlled airspace in real time and collect data such as target flight trajectory and spectrum characteristics;

[0047] Conduct preliminary threat identification of potential targets based on flight behavior, speed, and position parameters;

[0048] When abnormal flight behavior or possible low-altitude intrusion is detected, the intrusion threat processing and response module immediately generates an alarm signal and notifies the dispatch center;

[0049] After receiving the alarm signal, the dispatch center generates an auxiliary decision-making plan;

[0050] For targets determined to be non-threatening, the system continuously tracks and dynamically updates their threat registration;

[0051] For targets judged as high-threat, the system automatically initiates the emergency response process;

[0052] The emergency response process specifies the optimal response plan based on target characteristics, image information and current environment, combined with existing dispatchable resources;

[0053] The intrusion threat processing and response module executes the disposal plan in real time and transmits key information to relevant managers;

[0054] The relevant managers can view the target status, resource allocation and disposal progress in real time through the intelligent human-computer interaction interface;

[0055] The emergency response process supports manual intervention and dynamic command, which can further optimize the corresponding process;

[0056] It also includes a registration server for storing the RFID tag of each legally registered drone.

[0057] Compared with the prior art, the present invention has the following beneficial effects:

[0058] The low-altitude UAV reconnaissance and disposal integrated protection system provided by the present invention proposes a series of innovative methods and improvement measures to address the technical bottlenecks in the current UAV detection and protection field, effectively improving the ability of UAV detection, tracking, identification and disposal. The system uses radar and visual data fusion processing. The present invention effectively combines the characteristics of 4DFFT cube data and RGB images, and proposes an adaptive gated convolutional neural network to achieve accurate detection and tracking of slow-moving, hovering and complex background UAV targets, greatly reducing the blind spot problem of traditional radars when detecting low RCS targets, and significantly improving the accuracy and robustness of low-altitude UAV detection. In terms of UAV identity authentication, the present invention adopts RFID tag technology, combined with power control and time slot allocation optimization algorithms, to efficiently verify the legitimacy of the identity of UAVs in the area, and provide technical guarantees for the accurate identification of illegal targets. The system optimizes the UAV scheduling scheme through reinforcement learning, realizes dynamic adjustment in path planning, task allocation and resource management, ensures that the coverage is maximized and the task execution efficiency is optimized when multiple UAVs work together, can flexibly respond to emergencies in dynamic environments, and improve the monitoring capability and response speed of low-altitude protection areas. The warning and disposal module, combined with artificial intelligence algorithms, can assess the threat level in real time and trigger a variety of disposal strategies including warning, isolation, interference, and interception according to specific circumstances, ensuring the rapid control and effective strike against illegal drones.

[0059] The present invention is not only technologically innovative, but also has great value in terms of economic and social benefits. It significantly reduces the cost of low-altitude safety control and management by improving the intelligence level of low-altitude UAV management and dispatch, improves the safety of key infrastructure, promotes the healthy development of the low-altitude economy, and promotes the sustainable development of smart security. Therefore, the present invention provides a comprehensive and efficient technical solution for low-altitude UAV reconnaissance and disposal, and has broad application prospects and promotion value. BRIEF DESCRIPTION OF THE DRAWINGS

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

[0061] Figure 1 A schematic diagram of the overall system flow provided by an embodiment of the present invention.

[0062] Figure 2 A schematic diagram of timestamp synchronization provided by an embodiment of the present invention.

[0063] Figure 3 A flow chart of 4DFFT cube data processing provided by an embodiment of the present invention.

[0064] Figure 4 Schematic diagram of a target detection and tracking network based on adaptive gated convolution provided in an embodiment of the present invention.

[0065] Figure 5 A flow chart of adaptive gated convolution block feature extraction provided by an embodiment of the present invention.

[0066] Figure 6 A preprocessing flow chart of the input adaptation module provided in an embodiment of the present invention.

[0067] Figure 7 A multi-source information fusion decision flow chart provided for an embodiment of the present invention.

[0068] Figure 8 This is a processing flow chart of the intrusion detection and tracking module provided in an embodiment of the present invention.

[0069] Fig. 9 A schematic diagram of the flow of a joint optimization power control and time slot allocation algorithm provided in an embodiment of the present invention.

[0070] Fig.10 A flow chart of the intelligent dispatching strategy for unmanned aerial vehicles provided in an embodiment of the present invention.

[0071] Fig.11 A flowchart of the intelligent large model training of the dispatching center platform provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0072] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0073] The purpose of the present invention is to provide a low-altitude UAV reconnaissance and disposal integrated protection system capable of improving overall detection performance.

[0074] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0075] Embodiment 1:

[0076] This embodiment provides a low-altitude UAV reconnaissance and disposal integrated protection system, which includes the following modules: the low-altitude intrusion detection and tracking module obtains the target area information through radar and camera, performs 4DFFT preprocessing on the radar data and image preprocessing on the RGB image respectively; the preprocessed data is unified into the format required by the target detection and tracking algorithm through the respective input adaptation modules to ensure the consistency and compatibility of the algorithm processing; finally, the proposed multi-source information fusion decision-making mechanism is used to realize real-time and high-precision UAV detection and tracking functions. The UAV identification module obtains the UAV identity information through the RFID tag, and uses the joint optimization power control and time slot allocation algorithm to verify the legitimacy of the identity of all UAVs in the area. The UAV intelligent scheduling module optimizes path planning, task allocation and resource management through reinforcement learning, dynamically allocates tasks and optimizes route planning, ensures that the UAV can flexibly respond to and complete the reconnaissance mission, and ensures the continuous monitoring and timely response of the low-altitude protection area. The alarm and disposal module combines the large model to process data in real time and automatically evaluate the threat level, triggering the corresponding disposal measures. This application can effectively realize the reconnaissance and disposal of low-altitude UAVs and ensure the safety management in the security control area. The overall flow chart of the system is as follows Figure 1 The specific process includes:

[0077] Step 1: Low-altitude intrusion detection and tracking

[0078] (1) Radar and vision fusion preprocessing

[0079] The present invention combines a high-resolution camera and an ultra-long-range millimeter-wave radar to detect and track low-altitude drones. Since radar and cameras are different types of sensors and have inconsistent sampling frequencies, this leads to differences in time and space between the two types of data. Therefore, before fusing radar data and visual data, time synchronization and spatial calibration are required. Time synchronization is relatively simple. By unifying all sensors to the reference frequency of the lowest frequency sensor, frame synchronization is performed using down sampling, as detailed in Figure 2 shown.

[0080] Since drones move randomly in three-dimensional space, it is difficult to effectively locate drones using traditional two-dimensional range-Doppler spectrum because the signal lacks pitch angle information. Therefore, in order to more accurately extract targets and suppress clutter, it is necessary to observe the time-varying motion state of the target, including distance, speed, azimuth, and pitch angle information. To this end, millimeter-wave radar can be used to obtain time-varying four-dimensional observation data of slow targets, thereby obtaining the three-dimensional motion trajectory of the target.

[0081] According to the Time Division Multiplexing Multiple-Input Multiple-Output (TDM-MIMO) strategy, N T Transmitting antenna and receiving antenna N R The MIMO array is combined into N T N R A two-dimensional virtual array of array elements. Taking the frequency modulated continuous wave (FMCM) millimeter wave radar as an example, assuming that the signal Transmitted to the monitoring area, the backscattered signal from the target can be approximately expressed as:

[0082]

[0083] Where A is the amplitude, τ = 2[R0+v0(t f +t p )] / c0 represents the round trip time, t f ∈[0,T c ] represents fast time, T c represents the pulse duration, t c =n c T c (n c =0,1,2,...,N c -1) is the pulse number, R0 is the emission chirp number, R0 is the initial tilt distance, v0 is the radial velocity of the target, c0 is the speed of light, k = c0 / f c is the wavelength, f c is the carrier frequency, θ0 and are the initial azimuth and elevation angles respectively, n a =0,1,2,...,N a -1 and n e =0,1,2,...,N e -1 are the column and row numbers of the two-dimensional virtual array, The rectangular function is shown as follows:

[0084]

[0085] The first antenna is used as the reference element. Applying the 4D Fast Fourier Transform (FFT) to the inputs in equation (1) yields:

[0086]

[0087] where f r , f v , f a and f e are the frequency variables of range, Doppler, azimuth and elevation respectively, sinc(·)=sin(·) / · represents the function, and A0 is a constant. The detailed 4DFFT cube data processing flow is as follows Figure 3 shown.

[0088] (2) Adaptive Gated Convolutional Object Detection and Tracking Network

[0089] After preprocessing, the radar 4D cube data and RGB images have significant differences in characteristics. In order to achieve compatible processing of these two heterogeneous modal data, this paper proposes a target detection and tracking network based on adaptive gated convolution, such as Figure 4 shown.

[0090] The adaptive gated convolution target detection and tracking network mainly consists of two parts: an input adaptation module and a feature extraction module. The present invention proposes an adaptive gated convolutional neural network in the feature extraction module, which can extract the deep semantic information of RGB images and the temporal features of 4D cube radar data for different types of input data. In addition, an adaptive calculation mechanism is proposed in the input adaptation module to process different types of input data, ensure the consistency of data input, and uniformly transmit it to the feature extraction module, and finally efficiently complete the perception, detection and tracking tasks.

[0091] The adaptive gated convolutional network is composed of a stack of adaptive gated convolutional blocks. The adaptive gated convolutional blocks include multi-scale kernel convolution and adaptive gating, which aims to extract information with spatiotemporal multi-scale features from complex input data. Figure 5 shown.

[0092] Specifically, the input data X inputThe size of is B×C×H×W. For RGB image input, C contains deep semantic information from different color channels; for radar 4D cube data, C contains the real and imaginary information of signals and frequencies from different chirps. First, the input data is biased by group normalization, and then the number of channels is expanded to twice the original through 1×1 convolution. Subsequently, after the data is split through the channels, it is passed to the multi-scale kernel convolution branch and the adaptive gating branch for feature extraction. In the multi-scale kernel convolution branch, the data is passed to multiple parallel convolution branches, each branch uses convolution kernels of different sizes for feature extraction; here, 3×3 and 7×7 depthwise separable convolutions are used for feature extraction to capture local and global spatiotemporal information of each dimension under different receptive fields; the extracted features are standardized by group normalization to ensure the stability and consistency of the features. In the adaptive gating branch, the input data is first reduced to 1 by different 1×1 convolutions to prepare for the subsequent calculation of attention. Then, 1×7 convolutions combined with S-type activation functions are used to refine channel attention, and 7×7 convolutions combined with S-type activation functions are used in another sub-branch to refine spatial attention. Next, adaptive attention gating of each unit is generated by performing dot product operations on the channel attention map and the spatial attention map, thereby enhancing the representation ability and task adaptability. Finally, the output results of the two branches are fused by element-by-element multiplication to achieve the joint expression of channel and spatial attention features. Subsequently, the fusion result is further fused by using 1×1 convolution as a channel confuser to further fuse the information of different channels and restore the dimension to C. Residual connections are introduced to ensure the original feature information and promote efficient propagation of gradients.

[0093] The input adaptation module is divided into two types: radar input adaptation module and image input adaptation module. It mainly preprocesses the input data of different modes to provide input optimization for feature extraction of feature encoder. Its detailed structure is as follows: Figure 6 shown.

[0094] The image input adaptation module preprocesses the RGB image. First, a 7×7 convolution operation with a stride of 4 and a padding of 3 is used to adjust it to the input dimension of the model and compress the spatial dimension. Then, the nonlinear expression capability is introduced through the GELU activation function and normalized by GN. The radar input adaptation module preprocesses the radar 4D cube data. First, the input data is split according to the channel dimension and the channels are rearranged in a cross-stacked manner. Then, a 7×7 group convolution is performed to achieve information confusion between different groups of features. Then, similar to the image input adaptation module, a 7×7 convolution operation is used to adjust the features to the input dimension of the model, and the feature representation is further standardized and optimized through the GELU activation function and GN normalization to complete the preprocessing of the radar data. Since the radar data needs to be predicted in the 4D cube space, the stride of the 7×7 convolution is set to 1 to retain a higher spatial resolution.

[0095] (3) Decision-making based on multi-source information fusion

[0096] In a complex low-altitude environment, it is difficult to meet the needs of target detection and tracking by relying solely on radar or vision: radar is insufficient in resolution and semantic information, while vision is less robust to the environment. Using either technology alone will lead to performance bottlenecks in the perception system. In order to fully utilize the complementary advantages of the two modalities, this paper proposes a multi-information fusion decision, as detailed in Figure 7 shown.

[0097] Specifically, by detecting the 4D cube data, the approximate position and motion state of the candidate target can be obtained quickly and at low cost, and the predicted azimuth and pitch angles can be used to provide prior information for visual detection. Subsequently, visual detection can finely perceive and classify the candidate areas provided by the radar, making up for the shortcomings of the radar's low resolution and insufficient details. This avoids the high computational cost of visual global detection and ensures the accuracy of target detection.

[0098] The processing flow chart of the entire low-altitude intrusion detection and tracking module is as follows: Figure 8 As shown:

[0099] Step 2: Drone Identification

[0100] Drone RFID tags usually adopt a passive structure, and their operation depends on obtaining energy from the received reader signal and communicating with the ground base station by modulating the backscattered signal. During the communication process between the ground base station and the drone, especially when the ground base station reader performs data storage operations, communication failure may occur due to signal interference. Specifically, when the ground base station reader signal received by the drone tag is interfered with by other readers, or the drone tag signal received by the ground base station reader is interfered with by other drones, multiple signals with the same frequency may be received at the same time. In this case, the signals will interfere with each other, causing the ground base station to be unable to correctly identify the drone's identity information, which in turn causes signal collision problems. This collision phenomenon significantly affects the reliability and efficiency of communication, and is a challenge that needs to be addressed in drone RFID communications.

[0101] Aiming at the low-altitude safety control scenario, the present invention proposes a joint optimization power control and time slot allocation algorithm, as detailed in Fig. 9 shown.

[0102] The algorithm optimizes the recognition process of drone RFID tags by the ground base station by introducing a polling mechanism. Assume that the ground base station deploys n readers in a monitoring area with a radius of R. The transmission power of these readers can be adjusted to avoid overlapping recognition ranges. The working channel of the reader can be randomly selected from m channels. When the ground base station is active, each of its readers sends polling instructions to multiple drone tags within its coverage area. The drone tags return the ID information to the reader through backscatter modulation signals according to a predetermined communication protocol. Within the monitoring range of the base station, due to the mutual interference of signals between readers, especially as the number of readers increases, the interference phenomenon will become more serious. In addition, when multiple drones sharing the same channel respond to the reader instructions at the same time, signal collision problems will occur. In order to solve this problem, the present invention uses the widely used and standardized MAC layer protocol-EPC Global Class-1Generation-2 (C1G2). In this protocol, the operation cycle of each reader is T r At the beginning of each polling cycle, the reader randomly decides whether to perform polling, selects the working channel, and sets the transmission power. According to the EPC C1G2 protocol, the reader first issues a Query command to start the first frame. The rest of the frame contains multiple time slots. Each drone tag randomly selects a time slot to send a response message. After the frame ends, the base station uses maximum likelihood estimation to determine the number of drone tags N according to the drone response status of each time slot (including three types: idle, successful, and collision). r , and calculate the optimal true length based on this to start the next frame. Define the effective polling time of reader o as Q o, the polling period is T o This method improves the efficiency and reliability of drone cluster identification in complex scenarios by optimizing the polling process, reducing channel interference and collision probability.

[0103] Step 3: Drone Intelligent Scheduling Strategy

[0104] With the rapid popularization of drone technology, its application scope continues to expand, especially in the fields of real-time monitoring and security patrols, but it also poses new challenges to low-altitude safety and protection. The lowering of the threshold for drone operation has led to frequent "black flying" phenomena. These unauthorized drones may be active in no-fly zones or even maliciously used, directly threatening regional security. In addition, the low-altitude environment itself is full of complexity and dynamic changes (such as buildings, vegetation, birds and other interference factors), which further increases the difficulty of protection. The unpredictability and diversity of emergencies (such as drone power exhaustion, hardware failure or communication terminal, etc.) make low-altitude protection tasks more arduous. In multi-drone scheduling, the differences in task priority, flight status and resource distribution make university scheduling difficult, and the contradiction between the limited battery life of drones and the growing task requirements further aggravates the pressure of resource allocation. In view of the above problems, the present invention proposes a drone intelligent scheduling strategy, which can achieve efficient drone scheduling in complex dynamic environments by combining intelligent optimization and reinforcement learning. The algorithm is mainly used to optimize the task allocation, path planning and resource management of UAVs to ensure the efficient operation of the system in a changing environment, especially in low-altitude reconnaissance and protection missions. Fig.10 The specific steps are as follows:

[0105] (1) State perception: Each UAV perceives its local environment based on the current environmental state (e.g., low-altitude intrusion trajectory, wind speed, obstacles, etc.). The perception information includes target location, distance, speed, etc., which is transmitted as input to the dispatch center controller. This perception information helps the dispatch center optimize and adjust the UAV's mission.

[0106] (2) Strategy generation (genetic algorithm initialization): Use genetic algorithms to optimize the initial strategy of the UAV. The genetic algorithm generates a set of initial scheduling strategies, which may include action selection in terms of path planning, task allocation, cruising speed, etc. The genetic algorithm enables the UAV to initially have the ability to perform tasks by simulating evolutionary operations such as selection, crossover, and mutation.

[0107] (3) Reinforcement learning update: Based on the initial strategy, the drone uses DoubleQ-learning to update its strategy through interaction with the environment. Compared with the traditional Q-learning method, Double Q-learning reduces the problem of overestimation bias and improves the stability of learning by introducing two Q networks (Q1 and Q2). After each action is performed, the drone adjusts its strategy based on feedback (such as rewards or penalties). The reward function is constrained by the drone's mission, coverage, and confidence level of low-altitude intrusion targets.

[0108] (4) Balance between exploration and exploitation: In reinforcement learning, drones need to strike a balance between exploring new strategies and exploiting existing strategies. Drones explore unknown strategies to discover potential better solutions, while using existing strategies to perform current tasks. By dynamically adjusting the ratio of exploration and exploitation, drones can improve the efficiency of the overall reconnaissance mission.

[0109] (5) Real-time feedback and optimization: The dispatch center receives data feedback from each drone (such as target detection results, environmental changes, etc.) and performs real-time analysis and decision adjustments. The reinforcement learning algorithm continuously optimizes the drone's behavior strategy by analyzing the feedback to ensure that it can flexibly respond to different low-altitude intrusion threats in a complex and dynamic environment.

[0110] (6) Task allocation and path planning: Based on the strategy of reinforcement learning optimization, the intelligent dispatch center replans the path and assigns tasks to each drone. Path planning can dynamically avoid obstacles and ensure that there are no task conflicts between drones. In this way, the system can achieve all-round, no-dead-angle low-altitude reconnaissance and protection.

[0111] (7) Long-term reward optimization: The goal of reinforcement learning is to maximize the long-term cumulative reward. Therefore, during the mission execution, the drone will continuously optimize its strategy through trial and error, pursuing long-term benefits rather than short-term returns. Through this process, the system can gradually improve scheduling efficiency and task completion in different mission scenarios.

[0112] Step 4: Alert and Handling

[0113] (1) Large-scale model-assisted analysis and decision-making model construction

[0114] Artificial Intelligence Generated Content (AIGC) is one of the latest achievements in the field of artificial intelligence. It can generate original content, including text, images, audio and other multimedia content, by learning data patterns and rules. AIGC can play an important role in the reconnaissance and disposal of low-altitude drones. Low-altitude disposal methods are usually recorded in various regulations and books, while the airspace records of the measured area and the low-altitude route records are stored in an information system with inspection logs as the core. At the same time, the latest guidelines for low-altitude management often exist in the form of articles or regulations. Low-altitude reconnaissance and disposal tasks rely on a full understanding and judgment of airspace, mission resources and guidelines. In some cases, dispatchers do not have a full understanding of the disposal resources currently available, which may lead to incorrect disposal decisions. For example, when identifying the phenomenon of illegal flying, dispatchers may lack comprehensive resource information and make less than optimal response decisions. At this time, the auxiliary strategy generated by the large model can help dispatchers fully understand the current dispatchable resources and formulate more accurate and complete disposal plans.

[0115] In order to make full use of advanced technology to realize the integrated protection of UAV low-altitude reconnaissance and disposal, the present invention constructs an intelligent large model of the dispatching center platform, as shown in detail. Fig.11 shown.

[0116] The training process mainly includes the following steps: 1) Corpus collection and preprocessing: Through crawler technology, format conversion and data cleaning, the corpus data required for experimental training is preliminarily collected; 2) Constructing a question-answering data set for low-altitude applications and management: Using knowledge to guide the generation of question-answering data, and optimizing the data quality, finally generating a high-quality question-answering data set for the supervised fine-tuning stage. 3) Model training and evaluation: Based on the benchmark model, through three stages of continued pre-training, supervised fine-tuning and direct preference optimization, the intelligent large model of the dispatching center platform is gradually constructed. Finally, the model is verified by automatic evaluation and manual evaluation. Considering the high cost of ChatGPT fine-tuning, the present invention uses open source general models such as the LLaMA series as a benchmark. The training data mainly comes from open source data sets and automatically constructed small batch question-answering data. Although it has not been cleaned and iterated for optimization, it basically meets the requirements. The training method is mainly supervised fine-tuning or fine-tuning combined with continued pre-training, and there are currently few studies on further optimization based on human feedback preferences. Therefore, the present invention proposes to realize the full-process training from continued pre-training to human preference optimization through massive and high-quality dialogue data.

[0117] (2) Intrusion threat processing and response

[0118] In the integrated protection system for low-altitude UAV reconnaissance and disposal, the process of warning and intrusion disposal mainly depends on the threat identification and decision support function of the intelligent large model. First, the system continuously monitors the measured airspace through all-weather detection equipment, and collects data such as target flight trajectory and spectrum characteristics in real time. For each potential target, the system will perform preliminary threat identification based on flight behavior, speed, location and other information. When an abnormal or possible low-altitude intrusion phenomenon is identified, the system will immediately issue an alarm signal to notify the dispatch center. After the alarm signal is triggered, the dispatch center platform will combine the intelligent large model to generate an auxiliary decision-making plan to further analyze and process the intrusion target. For targets that are judged to be non-threatening, the system will continue to track and monitor their threat level changes; for targets that are judged to be high-threatening, the system will immediately start the disposal program, automatically guide the video surveillance to aim at the target and accurately track it, collect image data and transmit it to the dispatch center for analysis. The dispatch center will analyze the image information and target characteristics, combined with the currently dispatchable resources, to develop the best disposal plan. The plan will automatically link and pass it to relevant personnel to command and dispatch appropriate drones, patrol cars or other embodied equipment for real-time response. Dispatchers can also conduct real-time command and dispatch through the intelligent human-computer interaction interface to ensure rapid and accurate handling of intrusion incidents and to maximize the safety and stability of low-altitude airspace.

[0119] The low-altitude UAV reconnaissance and disposal integrated protection system provided by the present invention proposes a series of innovative methods and improvement measures to address the technical bottlenecks in the current UAV detection and protection field, effectively improving the ability of UAV detection, tracking, identification and disposal. The system uses radar and visual data fusion processing. The present invention effectively combines the characteristics of 4DFFT cube data and RGB images, and proposes an adaptive gated convolutional neural network to achieve accurate detection and tracking of slow-moving, hovering and complex background UAV targets, greatly reducing the blind spot problem of traditional radars when detecting low RCS targets, and significantly improving the accuracy and robustness of low-altitude UAV detection. In terms of UAV identity authentication, the present invention adopts RFID tag technology, combined with power control and time slot allocation optimization algorithms, to efficiently verify the legitimacy of the identity of UAVs in the area, and provide technical guarantees for the accurate identification of illegal targets. The system optimizes the UAV scheduling scheme through reinforcement learning, realizes dynamic adjustment in path planning, task allocation and resource management, ensures that the coverage is maximized and the task execution efficiency is optimized when multiple UAVs work together, can flexibly respond to emergencies in dynamic environments, and improve the monitoring capability and response speed of low-altitude protection areas. The warning and disposal module, combined with artificial intelligence algorithms, can assess the threat level in real time and trigger a variety of disposal strategies including warning, isolation, interference, and interception according to specific circumstances, ensuring the rapid control and effective strike against illegal drones.

[0120] The present invention is not only technologically innovative, but also has great value in terms of economic and social benefits. It significantly reduces the cost of low-altitude safety control and management by improving the intelligence level of low-altitude UAV management and dispatch, improves the safety of key infrastructure, promotes the healthy development of the low-altitude economy, and promotes the sustainable development of smart security. Therefore, the present invention provides a comprehensive and efficient technical solution for low-altitude UAV reconnaissance and disposal, and has broad application prospects and promotion value.

[0121] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0122] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A low-altitude UAV reconnaissance and disposal integrated protection system, characterized in that: include: A low-altitude intrusion detection and tracking module, which includes at least one radar and visual integration device; The radar and vision integrated device is composed of a millimeter wave radar and a long-range camera; the radar and vision integrated device obtains the information of the detected area in real time through a wired transmission channel, a 5G-A or 6G wireless transmission channel, and the information is respectively encapsulated in a frame format; The data analysis module is used to analyze radar information and visual information, and synchronize the time and space of radar information and visual information by downsampling at the lowest frequency; The data preprocessing module is used to preprocess the radar-visual integrated information encapsulated by the calibrated radar information and visual information.

2. The low-altitude UAV reconnaissance and disposal integrated protection system according to claim 1 is characterized in that: The preprocessing of the radar-visual integrated information encapsulated by the calibrated radar information and the visual information includes: The radar information is preprocessed in the order of range fast Fourier transform, Doppler fast Fourier transform, elevation fast Fourier transform and azimuth fast Fourier transform to complete the 4DFFT cube data preprocessing; Sending the 4DFFT cube data and visual information to an adaptive gated convolutional target detection and tracking network; the adaptive gated convolutional target detection and tracking network includes a radar adaptation module, a visual adaptation module and an adaptive gated convolutional neural network; The adaptive gated convolution target detection and tracking network is used to receive the 4DFFT cube data and visual data sent by the data preprocessing module; and send the 4DFFT cube data to the radar adaptation module to ensure the uniformity of the input data; then the radar adaptation module and the adaptive gated convolutional neural network are used to perform feature extraction to determine the azimuth and pitch angle of the target, and the results are sent to the multi-source information fusion decision module.

3. The low-altitude UAV reconnaissance and disposal integrated protection system according to claim 2 is characterized in that: The multi-source information fusion decision module is used to receive the target azimuth and pitch angle information, analyze the regional position of the target in the visual information; crop the visual information according to the regional position, and send the cropped visual information to the visual adaptation module for further processing.

4. The low-altitude UAV reconnaissance and disposal integrated protection system according to claim 3 is characterized by: The visual adaptation module is used to process the cropped visual information, extract target features, and generate a target tracking frame; map the target tracking frame back to the visual information before cropping, and confirm whether the target is a drone; if it is a drone, send the visual information to the drone identification module for identity verification; if it is other flying objects, send the visual information to the drone intelligent scheduling module and the alarm and disposal module respectively; if it is background interference, send abnormal information to the alarm and disposal module.

5. The low-altitude UAV reconnaissance and disposal integrated protection system according to claim 1 is characterized in that: Also includes: The drone identity recognition module is used to provide energy for the drone passive RFID tag through the signal sent by the ground base station reader; the drone provides identity and status information to the ground base station by modulating the backscatter signal; determines the legitimacy of the drone identity; if the drone identity is legal, continues to determine the legitimacy of the drone flight path; if the flight path is legal, maintains the mission process; if the flight path is illegal, sends the information and drone status information to the drone intelligent scheduling module; if the drone identity is illegal, sends visual information and drone status information to the drone intelligent scheduling module and alarm and disposal module respectively.

6. The low-altitude UAV reconnaissance and disposal integrated protection system according to claim 1 is characterized in that: Also includes: Jointly optimize power control and time slot allocation algorithm, where: Multiple ground base station readers use power modulation to avoid overlapping recognition ranges; Reduce signal interference when multiple drones compete for channels through time slot allocation strategies; The time slot allocation strategy includes: Multiple polling cycles, at the beginning of each cycle, randomly select whether to poll, working channel and transmit power; The ground base station starts the frame operation by broadcasting a Query command. The frame contains multiple time slots, and each drone randomly selects a time slot to respond; After the frame ends, the ground base station sends the drone RFID tag information to the registration server to determine the legitimacy; The time slot response events include: There are three types: idle, success and collision; The number of drone RFID tags in the ground base station area is calculated based on maximum likelihood estimation, and the polling cycle and time are optimized.

7. The low-altitude UAV reconnaissance and disposal integrated protection system according to claim 5 is characterized in that: Also includes: The UAV intelligent dispatch module is used for state perception. The UAV sends its current environmental information and local information to the dispatch center to determine whether intelligent dispatch is needed; If dispatch is required, the intelligent dispatch center adjusts the drone’s path planning, cruising speed, and subsequent tasks and resource allocation based on the drone’s current status information and global events; If no scheduling is required, maintain the current cruise or mission status.

8. The low-altitude UAV reconnaissance and disposal integrated protection system according to claim 7 is characterized in that: Also includes: The UAV intelligent scheduling strategy optimization module is used to optimize the preset initial strategy using genetic algorithms according to the UAV status information; Based on the initial strategy, Double Q-learning is used to dynamically update the strategy according to the local area environment information; In Double Q-learning reinforcement learning, the intelligent dispatch center makes a trade-off between exploring new strategies and using existing strategies based on the drone status information; Receive global regional data feedback in real time to analyze and optimize strategies; The integrated dispatch center decision-making and Double Q-learning optimization strategy are used to re-plan the path and assign tasks for each drone; For long-term emergencies and abnormal events, adaptive optimization strategies are used to maximize long-term benefits, thereby gradually improving scheduling efficiency and task completion.

9. The low-altitude UAV reconnaissance and disposal integrated protection system according to claim 1 is characterized in that: Also includes: The alarm and handling module is characterized by comprising: Large models assist analysis and decision-making. Based on the needs of intelligent dispatching of drones, large models are built to analyze drone status information in real time and provide optimized disposal decisions. The large model assists in the analysis and decision-making model training. It obtains the required training data through crawler technology, and combines format conversion and data cleaning to generate high-quality data sets that meet training requirements. The large model-assisted analysis and decision-making model combines pre-training, supervised fine-tuning and human preference optimization methods to improve the analysis and decision-making capabilities of the large model-assisted analysis and decision-making model for complex scenarios; The large model-assisted analysis and decision-making model adopts the LLaMA series as a benchmark and expands its capabilities through knowledge enhancement and domain adaptation techniques; The large model-assisted analysis and decision-making model prioritizes emergencies based on global and local environmental information, and formulates a hierarchical handling strategy to achieve dynamic alarm response efficiency.

10. The low-altitude UAV reconnaissance and disposal integrated protection system according to claim 1 is characterized in that: Also includes: Intrusion threat processing and response module, used to monitor the controlled airspace in real time and collect data such as target flight trajectory and spectrum characteristics; Conduct preliminary threat identification of potential targets based on flight behavior, speed, and position parameters; When abnormal flight behavior or possible low-altitude intrusion is detected, the intrusion threat processing and response module immediately generates an alarm signal and notifies the dispatch center; After receiving the alarm signal, the dispatch center generates an auxiliary decision-making plan; For targets determined to be non-threatening, the system continuously tracks and dynamically updates their threat registration; For targets judged as high-threat, the system automatically initiates the emergency response process; The emergency response process specifies the optimal response plan based on target characteristics, image information and current environment, combined with existing dispatchable resources; The intrusion threat processing and response module executes the disposal plan in real time and transmits key information to relevant managers; The relevant managers can view the target status, resource allocation and disposal progress in real time through the intelligent human-computer interaction interface; The emergency response process supports manual intervention and dynamic command, which can further optimize the corresponding process; It also includes a registration server for storing the RFID tag of each legally registered drone.

Images