Distributed unmanned aerial vehicle remote control method and system based on multi-source signal fusion

Abstract

The invention discloses a multi-source signal fusion distributed unmanned aerial vehicle remote control method and system, and relates to the technical field of unmanned aerial vehicle control, and the method comprises the steps: building a multi-source signal positioning link, and determining an unmanned aerial vehicle estimation position and a pilot estimation position; a dummy flying hand device is arranged; constructing a distributed control architecture to obtain N node data transmission strategies; interacting the estimated position of the unmanned aerial vehicle to obtain an unmanned aerial vehicle pilot remote control instruction; and creating an encrypted anti-interference communication link, and performing node forwarding processing and unmanned aerial vehicle remote control on the unmanned aerial vehicle pilot remote control instruction. The technical problems of insufficient positioning precision, weak anti-interference capability and poor communication link stability of the unmanned aerial vehicle in the prior art are solved, and the technical effects of high-precision positioning and anti-interference remote control of the unmanned aerial vehicle in a complex environment are achieved through multi-source signal fusion, deception interference, distributed adaptive transmission and encryption communication technologies.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle control, and in particular to a distributed unmanned aerial vehicle remote control method and system for multi-source signal fusion. Background Art

[0002] With the rapid development of drone technology, traditional drones rely on a single global navigation satellite system (GNSS) for positioning. However, in areas where satellite signals are easily blocked, such as urban canyons and indoors, GNSS signals are weakened or interrupted, resulting in serious lack of drone positioning accuracy and inability to accurately perform tasks. In addition, a single signal source is extremely susceptible to interference. The enemy or malicious users can disrupt the normal reception of positioning signals by transmitting interference signals, causing the drone's position to be out of control. At the communication link level, traditional communication methods have poor stability when facing complex electromagnetic environments. Signal interference, multipath effects and other factors often cause communication interruptions and data packet loss, making it impossible for pilots to convey remote control instructions to drones in a timely and accurate manner, seriously affecting the safe flight of drones. In terms of security risks, drone communication links lack effective encryption measures and are easily cracked, resulting in control instructions being tampered with and stolen, which not only threatens the safety of the drone itself, but may also cause serious safety accidents.

[0003] The existing technologies have technical problems such as insufficient positioning accuracy of drones, weak anti-interference capabilities, and poor communication link stability. Summary of the invention

[0004] The present application provides a distributed UAV remote control method and system with multi-source signal fusion, which is used to solve the technical problems of insufficient UAV positioning accuracy, weak anti-interference ability, and poor communication link stability in the prior art.

[0005] In view of the above problems, the present application provides a distributed UAV remote control method and system with multi-source signal fusion.

[0006] The first aspect of the present application provides a distributed UAV remote control method for multi-source signal fusion, the method comprising: A multi-source signal positioning link is constructed, wherein the multi-source signal positioning link is configured with a GNSS receiver, an RF receiver and a visual positioning sensor, and the multi-source positioning signal stream obtained by the multi-source signal positioning link is fused to determine the estimated position of the UAV and the estimated position of the pilot; a dummy pilot device is set, and the dummy pilot device modulates and emits a multi-source spoofing signal according to the estimated position of the pilot, and the multi-source spoofing signal is used to interfere with the pilot's position; a distributed control architecture is constructed, wherein the distributed control architecture includes N transmission control nodes, and N node data transmission strategies are adaptively obtained based on the real-time network status and interference status of the N transmission control nodes; the estimated position of the UAV is exchanged to obtain the remote control instructions of the UAV pilot; an encrypted anti-interference communication link is created, and the N node data transmission strategies are used to perform node forwarding processing and remote control of the UAV pilot remote control instructions through the encrypted anti-interference communication link.

[0007] The second aspect of the present application provides a distributed UAV remote control system with multi-source signal fusion, the system comprising: A multi-source signal positioning link building module is used to build a multi-source signal positioning link. The multi-source signal positioning link is configured with a GNSS receiver, an RF receiver and a visual positioning sensor. The multi-source positioning signal stream obtained by the multi-source signal positioning link is fused and processed to determine the estimated position of the UAV and the estimated position of the pilot. A dummy pilot device setting module is used to set a dummy pilot device. The dummy pilot device modulates and sends a multi-source spoofing signal according to the estimated position of the pilot. The multi-source spoofing signal is used to interfere with the position of the pilot. A data transmission strategy acquisition module is used to build a distributed control architecture. The distributed control architecture includes N transmission control nodes. Based on the real-time network status and interference status of the N transmission control nodes, N node data transmission strategies are adaptively obtained. A pilot remote control instruction acquisition module is used to exchange the estimated position of the UAV and obtain the remote control instruction of the UAV pilot. A UAV remote control module is used to create an encrypted anti-interference communication link. Through the encrypted anti-interference communication link, the N node data transmission strategy is used to perform node forwarding processing and remote control of the UAV pilot remote control instruction.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages: A multi-source signal positioning link is built, and the multi-source positioning signal stream obtained by the multi-source signal positioning link is fused and processed to determine the estimated position of the drone and the estimated position of the pilot; a dummy pilot device is set up to send out multi-source deception signals to interfere with the pilot's position; a distributed control architecture is constructed to adaptively obtain N node data transmission strategies based on the real-time network status and interference conditions of the N transmission control nodes; the estimated position of the drone is exchanged to obtain the remote control instructions of the drone pilot; an encrypted anti-interference communication link is created, and the N node data transmission strategy is used to perform node forwarding processing and remote control of the drone pilot's remote control instructions through the encrypted anti-interference communication link. The technical effect of achieving high-precision positioning and anti-interference remote control of drones in complex environments is achieved through multi-source signal fusion, deception interference, distributed adaptive transmission and encrypted communication technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0010] Figure 1 A schematic flow chart of a distributed UAV remote control method using multi-source signal fusion provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a distributed UAV remote control system with multi-source signal fusion provided in an embodiment of the present application.

[0011] Explanation of the reference numerals: multi-source signal positioning link building module 10, dummy pilot device setting module 20, data transmission strategy acquisition module 30, pilot remote control instruction acquisition module 40, drone remote control module 50. DETAILED DESCRIPTION

[0012] The present application provides a distributed UAV remote control method and system with multi-source signal fusion, which is used to solve the technical problems of insufficient UAV positioning accuracy, weak anti-interference ability and poor communication link stability in the prior art.

[0013] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0014] Embodiment 1, as Figure 1 As shown, the present application provides a distributed UAV remote control method with multi-source signal fusion, the method comprising: Step S100: Building a multi-source signal positioning link, wherein the multi-source signal positioning link is configured with a GNSS receiver, an RF receiver and a visual positioning sensor, and fusing the multi-source positioning signal stream obtained by the multi-source signal positioning link to determine the estimated position of the UAV and the estimated position of the pilot.

[0015] Specifically, we first need to build a multi-source signal positioning link, which is equipped with a GNSS receiver (GNSS is the global navigation satellite system, and the GNSS receiver is used to receive satellite signals to obtain information such as location, speed and time), an RF receiver (RF is radio frequency, and the RF receiver is used to receive radio frequency signals. It can be used for short-distance communication and positioning assistance in drone control scenarios) and a visual positioning sensor (determine the position by identifying the visual features of the surrounding environment). After the construction is completed, the multi-source signal positioning link starts to work, and it will obtain multi-source positioning signal streams, which include GNSS signal streams, RF signal streams and image signal streams. Next, these different types of signal streams are fused. During the fusion process, the characteristics and reliability of each signal stream are first analyzed. For example, GNSS signals have high accuracy but may be limited in occluded environments, RF signals are greatly affected by environmental interference but can provide supplementary information at close range, and visual positioning sensors can play a unique role in complex visual environments. Then, these signals are comprehensively analyzed and processed to remove noise and redundant information and extract key location features. Finally, the estimated position of the drone and the estimated position of the pilot are determined through fusion processing, providing accurate location data support for subsequent drone control and interference with opponent positioning operations.

[0016] Step S200: setting a dummy pilot device, wherein the dummy pilot device modulates and sends a multi-source spoofing signal according to the estimated position of the pilot, and the multi-source spoofing signal is used to interfere with the pilot's position.

[0017] Specifically, first, an inflatable model of a dummy pilot is made according to the body shape data of the target pilot, and a heating plate is installed on the model to simulate the physiological characteristics of the pilot. Inside the model, a multi-source signal transmitter including a GNSS signal transmitter, an RF signal transmitter and a visual deception signal transmitter is installed, and at the same time, a drone remote control device is arranged on the model so that the target pilot can remotely communicate and control the drone through it. After the installation of the above components is completed, the inflatable model of the dummy pilot, the heating plate, the multi-source signal transmitter, the drone remote control device and the power supply system are integrated to obtain a dummy pilot device. After obtaining the estimated position of the pilot, the dummy pilot device maps the position to its own target coordinate system to obtain the target pilot position information. According to the pre-set signal deception target effect, the deception signal modulation parameters are set, the target pilot position information is modulated, and multi-source deception signals such as GNSS deception signals, RF deception signals and visual deception signals are generated. Once the opponent's positioning behavior is detected, the multi-source signal transmitter in the dummy pilot device will send out these multi-source deception signals to interfere with the opponent's positioning of the pilot's true position and ensure the security of the pilot's position information.

[0018] Step S300: constructing a distributed control architecture, wherein the distributed control architecture includes N transmission control nodes, and adaptively obtaining N node data transmission strategies based on real-time network conditions and interference conditions of the N transmission control nodes.

[0019] Specifically, firstly, according to the distribution area, terrain characteristics and communication coverage density requirements of the UAV communication area, the number of transmission control nodes N required is accurately calculated and determined. Then, based on this number N, a detailed node deployment analysis is carried out in the UAV communication area to determine the specific location of the N transmission control nodes, and the communication parameters are configured and the network topology is identified on each node, so as to successfully build a distributed control architecture. In order to obtain the data transmission strategy of N nodes, the data transmission rules including bandwidth allocation, transmission rate adjustment, routing selection, communication frequency band switching and retransmission mechanism are first set. Based on these rules, historical communication data is mined and the transmission strategy is optimized to construct the communication data transmission strategy space. Finally, the real-time network status and interference of the N transmission control nodes are used as constraint parameters, and the strategy is adaptively matched in the strategy space, so as to obtain the N-node data transmission strategy applicable to each transmission control node, ensuring efficient and stable data transmission in different network environments.

[0020] Step S400: Interact with the estimated position of the drone to obtain remote control instructions from the drone pilot.

[0021] Specifically, after the estimated position of the drone is obtained through the fusion processing of the multi-source signal positioning link in the early stage, the interactive operation is carried out. The drone pilot interacts with the estimated position data of the drone fed back by the positioning system through the operation interface. For example, the pilot can intuitively see the approximate location information of the drone on the operation interface, and the interface is also connected to the control system of the drone. The pilot operates on the operation interface according to the task requirements and the actual position of the drone. These operation information will be identified and converted into remote control instructions for the drone pilot, such as controlling the drone to take off, land, change the flight direction and altitude, etc. These instructions are packaged, encoded, etc. to meet the communication transmission requirements, and prepare for the subsequent transmission and control of the drone through an encrypted anti-interference communication link.

[0022] Step S500: Create an encrypted anti-interference communication link, and use the N-node data transmission strategy to perform node forwarding processing on the drone pilot's remote control instructions and remote control of the drone through the encrypted anti-interference communication link.

[0023] Specifically, according to the data communication security goal, the quantum key distribution channel and the encryption algorithm channel are configured. These two channels respectively undertake different but complementary security functions. The quantum key distribution channel uses the principles of quantum mechanics to achieve secure key distribution and provide a basis for communication encryption; the encryption algorithm channel uses encryption algorithms to encrypt data. Then, the two channels are set up in parallel to create an encrypted anti-interference communication link. At this time, the remote control instructions of the drone pilot and the N-node data transmission strategy that have been obtained come into play, and the control instructions are transmitted through the encrypted anti-interference communication link. During the transmission process, according to the N-node data transmission strategy, these instructions are forwarded and processed in turn between the N transmission control nodes. Each node optimizes the instructions according to its own strategies, such as bandwidth allocation, transmission rate adjustment and other rules, and then forwards them to the next node. Finally, after a series of node forwarding, the control instructions are accurately transmitted to the drone, realizing remote control of the drone, and ensuring that the drone can stably and safely execute the pilot's control instructions in a complex communication environment.

[0024] In a possible implementation, step S100 further includes: Step S110: acquiring a multi-source positioning signal stream through the multi-source signal positioning link, wherein the multi-source positioning signal stream includes a GNSS signal stream, an RF signal stream and an image signal stream.

[0025] Step S120: performing noise characteristic analysis on the multi-source positioning signal stream to obtain noise characteristics of multi-source positioning data, and determining a multi-source positioning data denoising threshold according to the noise characteristics of the multi-source positioning data.

[0026] Step S130: performing noise data identification and filtering preprocessing on the multi-source positioning signal stream according to the multi-source positioning data denoising threshold to obtain a standard multi-source positioning signal stream.

[0027] Step S140: performing feature extraction, fusion and position estimation on the standard multi-source positioning signal to determine the estimated position of the UAV and the estimated position of the pilot.

[0028] Specifically, the multi-source signal positioning link starts the data collection work, and the GNSS receiver, RF receiver and visual positioning sensor equipped in the link perform their respective duties and start the signal collection process at the same time. The GNSS receiver receives the signals transmitted by the satellite, parses them and forms a GNSS signal stream. These signals carry location information based on the global satellite positioning system, providing basic geographic coordinate data for determining the location of the drone and the pilot; the RF receiver is responsible for collecting radio frequency signals of a specific frequency, and then generating an RF signal stream. With the characteristics of radio frequency signal propagation in space, it can achieve relatively accurate positioning and communication assistance within a certain range; the visual positioning sensor uses the principle of optical imaging to take real-time photos of the surrounding environment and convert the captured images into image signal streams. The image signal stream contains rich environmental visual features, such as landmarks, buildings, etc., which helps to further accurately locate. These three signal streams obtain positioning information from different dimensions and methods, and together constitute a multi-source positioning signal stream, which provides a comprehensive and diverse data source for the subsequent accurate determination of the location of the drone and the pilot.

[0029] For multi-source positioning signal streams, spectrum analysis tools are used to perform spectrum analysis on GNSS signal streams, RF signal streams, and image signal streams, respectively, to obtain the energy distribution of each signal stream in different frequency bands, so as to identify the frequency characteristics of noise. By statistically analyzing the fluctuation of signal amplitude over a period of time, the amplitude characteristics of noise are studied, and then the noise characteristics of multi-source positioning data are summarized. For example, if it is found that GNSS signals have strong interference noise in a specific frequency range and its amplitude shows periodic changes, this characteristic can be recorded. When determining the denoising threshold, an adaptive threshold algorithm is used for calculation based on the signal-to-noise ratio requirements and noise distribution of the signal. The algorithm dynamically adjusts the threshold according to the local characteristics of the signal. For example, for areas with large fluctuations in noise amplitude, the threshold is appropriately increased to effectively remove noise; for areas with relatively stable signals, the threshold is lowered to avoid mistaken deletion of useful signals, and finally the denoising threshold suitable for multi-source positioning data is determined.

[0030] The noise data identification and filtering preprocessing work is carried out on the multi-source positioning signal stream including GNSS signal stream, RF signal stream and image signal stream. For the GNSS signal stream, the signal amplitude is compared with the denoising threshold by using the threshold comparison method, and the part with the amplitude exceeding the threshold is judged as noise data; for the RF signal stream, the noise is also identified based on the threshold, and the bandpass filtering technology is used to filter out the signal components within the noise frequency range; when processing the image signal stream, the gray value of each pixel is compared with the threshold to identify the noise pixel, and the noise pixel is processed with the help of algorithms such as median filtering and replaced with reasonable values ​​of the surrounding pixels. By performing noise data identification and filtering processing on these three signal streams respectively, interference information is removed, signal quality is improved, and finally a standard multi-source positioning signal stream is integrated to provide a stable and reliable signal basis for the subsequent determination of the location of the drone and the pilot.

[0031] For the standard multi-source positioning signals that have been obtained, feature extraction is performed separately according to the characteristics and advantages of GNSS signals, RF signals and image signals. Basic positioning features such as longitude and latitude, speed, etc. are extracted from GNSS signals; features related to distance and direction such as signal strength and angle of arrival are obtained from RF signals; environmental features such as landmarks and feature points are extracted from image signals using image recognition algorithms. Then, a weighted fusion algorithm is used to assign weights to different types of features based on the credibility and accuracy of the signal source, and the extracted multi-source features are fused to form a comprehensive positioning feature set. Finally, with the help of a position estimation model based on Kalman filtering, combined with the previously obtained comprehensive positioning feature set, through continuous iterative calculations, considering the dynamic changes of the signal and the influence of noise, the estimated position of the drone and the estimated position of the pilot are finally accurately determined, providing accurate position data support for the subsequent remote control of the drone.

[0032] In a possible implementation, step S140 further includes: Step S141: determining a multi-source signal feature extraction method and a multi-source signal position feature type according to data characteristic information of the standard multi-source positioning signal.

[0033] Step S142: extracting correlation features from the standard multi-source positioning signal according to the multi-source signal feature extraction method and the multi-source signal position feature type to obtain a multi-source signal correlation feature set.

[0034] Step S143: setting a dynamic signal source weight allocation rule according to the signal source credibility and signal source accuracy.

[0035] Step S144: Based on the signal source weight dynamic allocation rule, the multi-source signal association feature set is fused and estimated to determine the estimated position of the drone and the estimated position of the pilot.

[0036] Specifically, the data characteristics of the standard multi-source positioning signal obtained after denoising preprocessing are deeply analyzed. The characteristic of GNSS signal is that it can provide high-precision absolute positioning data worldwide. Based on this, the satellite positioning solution algorithm is used as its feature extraction method. The extracted multi-source signal position feature type is the precise longitude and latitude coordinates, so as to obtain the approximate position of the drone and the pilot in the global coordinate system. RF signal has advantages in close-range positioning and signal propagation characteristics. Its signal strength, arrival angle and propagation time can reflect the relative position relationship with the surrounding signal sources. Therefore, signal strength detection, angle measurement and time difference calculation algorithm are used as feature extraction methods. The corresponding position feature types are relative distance, azimuth, etc. Image signals contain rich environmental visual information. Features are extracted through algorithms such as feature point detection and template matching in image recognition technology. For example, unique landmarks and significant feature points in the image are extracted, which constitute the position feature types used for environmental matching and precise positioning. By integrating the data characteristics of these different signals, appropriate multi-source signal feature extraction methods and multi-source signal position feature types were determined respectively, laying the foundation for the subsequent accurate extraction of location-related feature information.

[0037] Extract correlation features from standard multi-source positioning signals. For GNSS signals, the positioning algorithm is used to obtain accurate longitude and latitude coordinates as location features; for RF signals, the signal strength and arrival time difference and other information are analyzed to obtain the relative position relationship features with surrounding signal sources; when processing image signals, the feature point detection algorithm is used to find representative landmarks and feature points to form environmental matching features. These features extracted from different signal sources are correlated and integrated to obtain a multi-source signal correlation feature set, which contains rich location-related information.

[0038] Since the credibility and accuracy of different signal sources vary, in order to more accurately integrate these features, a dynamic allocation rule for signal source weights is set based on the credibility and accuracy of the signal sources. GNSS signals are highly accurate and stable, so they are given a higher weight; RF signals have advantages in close-range positioning, but are more susceptible to environmental interference, so their weights are dynamically adjusted according to actual environmental conditions; image signals rely on environmental features, and their credibility increases in feature-rich environments, so their weights are increased accordingly. This dynamic allocation rule ensures that the role of each signal source can be reasonably allocated in different environments.

[0039] The multi-source signal correlation feature set is fused. The features of different signal sources are weighted and calculated according to the weights, so that the signal features with high accuracy and strong credibility occupy a more important position in the fusion result. After the fusion process, the position estimation model is used for position estimation. The model combines the fused features, considers the dynamic changes of the signal and the influence of environmental factors, and finally determines the estimated position of the drone and the estimated position of the pilot, providing key position data support for the remote control of the drone and ensuring the accuracy of the drone control.

[0040] In a possible implementation, step S144 further includes: Step S1441: performing weight allocation calculation on the multi-source signal association feature set based on the signal source weight dynamic allocation rule to obtain signal source weight factor information.

[0041] Step S1442: performing weighted fusion processing on the multi-source signal association feature set according to the signal source weight factor information to obtain a positioning signal fusion feature set.

[0042] Step S1443: classify and identify the positioning signal fusion feature set to obtain the UAV positioning fusion feature set and the pilot positioning fusion feature set.

[0043] Step S1444: Initialize the Kalman filter, and use the Kalman filter to iteratively estimate the position of the UAV positioning fusion feature set and the pilot positioning fusion feature set to determine the estimated position of the UAV and the estimated position of the pilot.

[0044] Specifically, according to the previously set signal source weight dynamic allocation rule, the multi-source signal correlation feature set is carefully calculated for weight allocation. This rule is formulated based on the credibility and accuracy of GNSS, RF and image signal sources. For example, GNSS signals are given a higher basic weight due to their high positioning accuracy and good global coverage; RF signals have advantages in short-range positioning and communication, and their weights will be dynamically adjusted according to factors such as the degree of signal interference and transmission stability in the specific environment; image signals have high positioning accuracy in specific scenarios due to their rich environmental features, and their weights will also be dynamically set according to the richness and recognition of environmental features in the scene. These weights are allocated to each feature in the multi-source signal correlation feature set to obtain signal source weight factor information, which accurately quantifies the importance of each signal source feature in subsequent fusion calculations.

[0045] According to the obtained signal source weight factor information, the multi-source signal correlation feature set is weighted fused. The features corresponding to the GNSS signal, such as longitude and latitude coordinates, are multiplied by their corresponding weight factors; the signal strength, relative distance and other features of the RF signal, as well as the landmarks, feature points and other environmental matching features of the image signal are also multiplied by their corresponding weight factors. Then these weighted features are summed up so that the advantages of different signal sources are reasonably reflected in the fusion process, and finally the positioning signal fusion feature set is obtained. This fusion feature set combines the advantages of multiple signals and more comprehensively and accurately reflects the location-related information of the drone and the pilot.

[0046] In order to distinguish and process the location information of the drone and the pilot separately, the positioning signal fusion feature set is classified and identified. According to the correlation between the signal features and the drone and the pilot, the features closely related to the drone's position in the positioning signal fusion feature set are screened out to form the drone positioning fusion feature set; similarly, the features related to the pilot's position are classified into the pilot positioning fusion feature set. For example, the features related to the drone's flight posture are classified into the drone positioning fusion feature set, while the features related to the pilot's operating position are included in the pilot positioning fusion feature set. Such classification and identification facilitates subsequent precise positioning.

[0047] In order to accurately determine the position of the drone and the pilot, the Kalman filter is first initialized. During the initialization process, the initial state of the filter is set, including the initial estimated values ​​of the state variables such as the position and speed of the drone and the pilot, and the covariance matrix is ​​determined to measure the uncertainty of the estimated value. Then, the previously obtained drone positioning fusion feature set and the pilot positioning fusion feature set are input into the Kalman filter in sequence. The filter uses its own prediction and update mechanism to iteratively process the input feature set. In the prediction stage, the current state is predicted based on the estimated state and system model of the previous moment; in the update stage, the prediction result is corrected by combining the positioning fusion feature set obtained by the current measurement. Through continuous iteration, the Kalman filter can effectively integrate the position information brought by multi-source signals and suppress the noise in the measurement process. With the increase of the number of iterations, the estimation results become more and more accurate, and finally the high-precision estimated position of the drone and the estimated position of the pilot are determined, providing key data support for the precise remote control of the drone.

[0048] In a possible implementation, step S200 further includes: Step S210: simulate and manufacture an inflatable model of a dummy pilot according to the body shape data of the target pilot, and install a heating sheet on the inflatable model of the dummy pilot to simulate the physiological characteristics of the pilot through the heating sheet.

[0049] Step S220: installing a multi-source signal transmitter inside the inflatable model of the dummy pilot, wherein the multi-source signal transmitter includes a GNSS signal transmitter, an RF signal transmitter and a visual deception signal transmitter.

[0050] Step S230: placing a drone remote control device on the inflatable model of the dummy pilot, and the target pilot performs remote communication control on the drone through the drone remote control device.

[0051] Step S240: Integrate the inflatable model of the dummy pilot, the heating sheet, the multi-source signal transmitter, the UAV remote control device and the power supply system to obtain the dummy pilot device.

[0052] Specifically, first collect the target pilot's precise body data, such as height, weight, limb proportions, body outline and other key information. Based on this data, select appropriate inflatable materials to simulate and produce an inflatable model of a dummy pilot, and restore the target pilot's body shape to the greatest extent in terms of appearance. In order to make the dummy pilot model more realistic and fit the physiological characteristics of a real pilot, a heating plate is installed on the model. Through the circuit design and temperature control system setting of the heating plate, the normal heat dissipation of the pilot's body is simulated, and the heat dissipation changes of the human body under different ambient temperatures make the dummy pilot model not only deceptive in appearance, but also in physiological thermal characteristics, thereby interfering with the opponent's detection of the pilot's true position by means of thermal sensing and other means.

[0053] After the inflatable model of the dummy pilot is completed and the heating plate is installed, the key multi-source signal transmitter installation work begins inside the model. In order to effectively interfere with the pilot's position, the multi-source signal transmitter includes a GNSS signal transmitter, an RF signal transmitter, and a visual deception signal transmitter. The GNSS signal transmitter is placed in a suitable position inside the model to ensure that it can work stably. The transmitter will emit false GNSS signals that imitate the characteristics of real satellite positioning signals, causing the enemy's GNSS positioning equipment to receive incorrect location information, thereby misleading the other party's judgment of the pilot's position. At the same time, the RF signal transmitter is also accurately installed. It will emit fake RF signals, using the characteristics of radio frequency signals propagating in space to interfere with the enemy's positioning and monitoring systems based on RF signals. In addition, the visual deception signal transmitter is also installed inside the model. Its function is to emit specific optical signals or simulate real-scene image signals to interfere with the enemy's visual positioning and monitoring equipment, making it difficult for the enemy to determine the true position of the pilot at the visual level. By properly installing these three different types of signal transmitters inside the inflatable model of the dummy pilot, a comprehensive signal jamming system was built, laying a solid foundation for subsequent interference with the opponent's positioning of the pilot's position.

[0054] After the multi-source signal transmitter has been installed on the inflatable model of the dummy pilot, the remote control device of the UAV is placed on the inflatable model of the dummy pilot. The selection of this position must ensure that the remote control device can be firmly attached to the model, and that the target pilot is convenient and comfortable when operating. The target pilot stands next to the inflatable model of the dummy pilot and operates the remote control device to send various control instructions to the UAV, such as take-off, landing, changing flight direction and altitude, etc. These instructions are transmitted in a specific wireless communication method, which is the same as the communication mechanism of the pilot controlling the UAV under normal circumstances, realizing remote communication control of the UAV, and at the same time cooperating with other parts of the dummy pilot device to enhance the overall confusion and interfere with the opponent's judgment of the pilot's true position.

[0055] The inflatable model of the dummy pilot, the heating sheet, the multi-source signal transmitter, the UAV remote control device and the power supply system are integrated and built. First, the inflatable model of the dummy pilot with the heating sheet installed is used as the basic carrier, and the components with the GNSS signal transmitter, RF signal transmitter and visual deception signal transmitter installed inside are fixed to ensure that they are stable inside the model and will not be affected by vibration and other factors. Next, the UAV remote control device is installed in a position convenient for the target pilot to operate on the inflatable model of the dummy pilot, and the relevant lines are connected to ensure the stability of signal transmission. Subsequently, the power supply system is connected, the wiring is carried out, and the power supply lines are connected to the heating sheet, the multi-source signal transmitter and the UAV remote control device respectively to provide a stable power supply for these devices so that they can operate normally. During the integration and construction process, each component needs to be debugged and calibrated to ensure that each part works together, and finally the integration and construction are completed, and the dummy pilot device is successfully set up, which can play a key role in the subsequent task of interfering with the position positioning of the pilot.

[0056] In a possible implementation, step S200 further includes: Step S250: Acquire the target coordinate system of the dummy pilot device, transform the estimated pilot position mapping into the target coordinate system, and obtain target pilot position information.

[0057] Step S260: setting the spoof signal modulation parameters according to the preset target effect of the signal spoofing.

[0058] Step S270: Perform spoofing signal modulation on the target pilot's position information based on the spoofing signal modulation parameters to generate a multi-source spoofing signal, where the multi-source spoofing signal includes a GNSS spoofing signal, an RF spoofing signal, and a visual spoofing signal.

[0059] Step S280: When the opponent's positioning behavior is detected, the multi-source deception signal is sent out through the multi-source signal transmitter in the dummy pilot device.

[0060] Specifically, the target coordinate system of the dummy pilot device is determined. This coordinate system is the spatial reference for subsequent signal processing and is set based on the installation environment and interference strategy of the dummy pilot device. After the target coordinate system is determined, the estimated position of the pilot obtained by multi-source signal fusion is mapped and converted from the original coordinate system to the target coordinate system with the help of a coordinate conversion algorithm, thereby obtaining the target pilot position information, which is the key basic data for the subsequent generation of deception signals.

[0061] In order to achieve the purpose of interfering with the opponent's positioning system, the modulation parameters of the deception signal are set in a targeted manner according to the pre-set signal deception target effect. If it is expected that the opponent's GNSS positioning device will produce deviations in a specific direction and distance, the structure and characteristics of the GNSS signal should be studied in depth, and the difference between the deception signal and the real signal should be changed by adjusting the signal's carrier frequency, code phase, signal strength and other parameters to mislead the opponent's positioning solution. For RF deception signals, the transmission frequency, power, modulation mode and other parameters of the deception signal are set according to the operating frequency band and sensitivity of the opponent's RF positioning device, so that the opponent's RF receiver receives a false signal and misjudges the pilot's position. The modulation parameter setting of the visual deception signal should be combined with the principle of object recognition by the visual positioning system, such as adjusting the image's brightness, contrast, edge features and other parameters to generate an image similar to the real scene but with incorrect position information, interfering with the opponent's visual positioning device's recognition of the pilot's position, thereby interfering with the opponent's different types of positioning methods in an all-round way and achieving the expected deception effect.

[0062] In order to achieve the generation of multi-source deception signals including GNSS deception signals, RF deception signals and visual deception signals, a variety of specific means are used. For GNSS deception signals, the carrier, pseudo code and other characteristics of real satellite signals are simulated by using GNSS signal generation equipment according to the modulation parameters of deception signals. By adjusting the frequency, phase and amplitude of the signal, the generated signal is consistent with the real GNSS signal in format, but carries false location information, such as modifying the latitude and longitude data in the signal to mislead the opponent's GNSS positioning device. For RF deception signals, with the help of radio frequency signal generator, the transmission frequency, power and modulation mode are adjusted according to the modulation parameters. Direct digital frequency synthesis technology is used to accurately generate deception signals that match the target frequency band, and transmit them within the receiving range of the opponent's RF positioning device to interfere with its judgment of the pilot's position, so that it receives false signal strength, arrival angle and other information. In terms of visual deception signal generation, the image containing the target pilot's position is processed according to the modulation parameters. By changing the brightness, contrast, color and other attributes of the image, and adding or modifying the feature points, landmarks and other elements in the image, an image signal similar to the real scene but with incorrect pilot position information is simulated to interfere with the opponent's visual positioning system.

[0063] The dummy pilot device is always in a monitoring state. Its monitoring system continuously scans the surrounding environment and uses signal detection technology to analyze various electromagnetic signals. Once the monitoring system identifies a signal that matches the characteristics of the opponent's positioning behavior, it immediately triggers the dummy pilot device. The multi-source signal transmitter integrated inside the dummy pilot device is a key component for implementing interference. The transmitter includes a GNSS signal transmitter, an RF signal transmitter, and a visual deception signal transmitter. When triggered, the GNSS signal transmitter transmits a GNSS deception signal that is extremely similar to the real GNSS signal but carries false location information according to the pre-set deception parameters, interfering with the opponent's satellite positioning system. The RF signal transmitter transmits RF deception signals at a specific frequency and power to disrupt the opponent's positioning device based on radio frequency signals. At the same time, the visual deception signal transmitter transmits the pre-generated visual deception signal to interfere with the opponent's visual positioning method. These multi-source deception signals act simultaneously from different dimensions, causing the opponent's positioning device to receive wrong information, thereby misleading the opponent's judgment of the pilot's position and effectively protecting the pilot's true position from being exposed.

[0064] In a possible implementation, step S300 further includes: Step S310: Determine the number of transmission control nodes N based on the distribution area and terrain distribution of the drone communication area, as well as the communication coverage density requirements.

[0065] Step S320: Perform node deployment analysis on the UAV communication area based on the number of transmission control nodes N to obtain N transmission control nodes.

[0066] Step S330: performing communication parameter configuration and network topology identification on the N transmission control nodes respectively to construct the distributed control architecture.

[0067] Specifically, when constructing a distributed control architecture for remote control of drones, the precise distribution area and detailed terrain data of the drone communication area are obtained with the help of geographic information system (GIS) technology, including the location and height information of geographical elements such as mountains, buildings, and waters. At the same time, combined with the communication coverage density requirements, the signal strength, data transmission rate, and signal stability standards required for each area are determined. For areas with a large distribution area, the required node base is preliminarily estimated. Then, based on the terrain distribution, if there are areas where signals are easily blocked, such as mountainous areas, signal propagation models, such as ray tracing-based models, are used to analyze the attenuation and occlusion of signals under different terrains, and the number of nodes is appropriately increased in areas where the signal is severely attenuated or easily blocked. In response to the communication coverage density requirements, the communication load of the area is determined by calculating the number of users in each area and the frequency of drone flight missions. Based on the communication load, a genetic algorithm is used to optimize the distribution of transmission control nodes while meeting the communication quality requirements, and finally the number of transmission control nodes N is determined.

[0068] Analyze the geographical characteristics of the communication area, including topography, building distribution, etc. If there are complex terrains such as mountains and canyons in the communication area, which will block and reflect the signal propagation, then it is necessary to arrange the transmission control nodes reasonably near these terrains to ensure that the signal can effectively cover the surrounding area; if there are densely built areas, the signal is easily blocked and interfered, so it is necessary to increase the node density in this area appropriately to ensure the stability of the signal. At the same time, the use scenarios and user distribution of the communication area must also be considered. For example, in crowded activity places, there is a large demand for drone communication. In order to meet the requirements of many users using drones for communication at the same time, it is necessary to centrally deploy transmission control nodes in these areas to improve the strength and quality of signal coverage; in remote areas with sparse population, the number of node deployments can be appropriately reduced to reduce the construction cost while meeting basic communication needs. Finally, the accurate deployment positions of N transmission control nodes are obtained, thereby realizing the effective construction of a distributed control architecture and providing stable and efficient support for subsequent drone communications.

[0069] For the N transmission control nodes with determined positions, the communication parameters are configured and the network topology is identified one by one to build a distributed control architecture. The first is the communication parameter configuration. According to the communication requirements of the drone and the environment of each node, the transmission power, communication frequency, bandwidth and other parameters are set. For example, for nodes in areas with strong signal interference, the transmission power is appropriately increased to ensure stable signal transmission; according to the business requirements and frequency band resources of different nodes, the communication frequency is reasonably allocated to avoid frequency band conflicts. At the same time, the appropriate bandwidth is set to ensure the efficiency of data transmission and meet the timely transmission of remote control instructions of the drone. After completing the communication parameter configuration, the network topology of the N transmission control nodes is identified. This includes assigning a unique network address to each node, clarifying the connection relationship and data transmission path between nodes. Through the network topology identification, each node can clearly know the other nodes connected to it, as well as the transmission direction and priority of data in the network. For example, a tree, mesh or hybrid network topology structure is used to connect each node in an orderly manner, so that the entire distributed control architecture forms an organic whole. Through such communication parameter configuration and network topology identification, a stable and efficient distributed control architecture is eventually built to provide strong support for drone remote control.

[0070] In a possible implementation, step S300 further includes: Step S340: Setting data transmission rules, wherein the data transmission rules include bandwidth allocation, transmission rate adjustment, route selection, communication frequency band switching, and retransmission mechanism.

[0071] Step S350: Perform historical communication data mining and transmission strategy optimization based on the data transmission rules to construct a communication data transmission strategy space.

[0072] Step S360: Using the real-time network status and interference conditions of the N transmission control nodes as constraint parameters, adaptively matching the strategies in the communication data transmission strategy space to obtain the data transmission strategies of the N nodes.

[0073] Specifically, according to the requirements of remote control of drones for data transmission, detailed data transmission rules are formulated. In terms of bandwidth allocation, the bandwidth resources available to each transmission control node are divided according to the data volume requirements of different tasks to ensure that important instructions and key data can obtain sufficient bandwidth for transmission first. The transmission rate adjustment dynamically changes the data transmission rate according to the network load and signal quality. When the network conditions are good, the rate is increased to speed up data transmission. When there is more interference or network congestion, the rate is reduced to ensure the accuracy of data transmission. In terms of routing selection, the connection quality, distance and data transmission priority between nodes are comprehensively considered to select the optimal data transmission path to avoid data delay or loss during transmission. Communication band switching is used to switch between different frequency bands. When a frequency band is interfered with, it quickly switches to other available frequency bands to maintain stable communication. The retransmission mechanism stipulates how to resend data when data transmission fails, including the number of retransmissions, interval time, etc., to ensure reliable data transmission.

[0074] Collect and integrate historical communication data, and classify and store them according to different network conditions (such as network delay, packet loss rate), interference conditions (interference signal strength, frequency), and data transmission rules (bandwidth allocation, transmission rate adjustment, routing selection, communication frequency band switching, retransmission mechanism). Then, for each combination of data transmission rules, traverse the historical data and extract the transmission performance indicators under different network and interference conditions, such as data transmission success rate, average transmission delay, throughput, etc. Using these performance indicators, each transmission strategy is evaluated through a scoring mechanism. The higher the score, the better the transmission effect of the strategy under the corresponding conditions. Then, set a screening threshold to filter out those strategies with scores below the threshold and retain strategies with better performance. Finally, these screened strategies are sorted and summarized according to different rule combinations and applicable scenarios to construct a communication data transmission strategy space, which provides rich options for selecting appropriate transmission strategies based on real-time network conditions and interference conditions.

[0075] Real-time monitoring and data collection of the real-time network status and interference conditions of N transmission control nodes are performed. Network monitoring tools such as network probes and signal strength detection equipment are used to obtain network status data such as network bandwidth occupancy, signal transmission delay, packet loss rate, and interference data such as the frequency, strength, and direction of interference signals. These real-time data are input into the communication data transmission strategy space as constraint parameters. The communication data transmission strategy space is pre-constructed and contains a variety of different transmission strategies, each of which is optimized for different network conditions and interference conditions. When performing strategy adaptive matching, a genetic algorithm is used to treat different transmission strategies as individuals in the genetic algorithm, and a better strategy is selected by calculating the matching degree (fitness) of each individual with the current real-time network status and interference conditions. For example, for nodes with high network delay, those strategies with data caching and asynchronous transmission mechanisms are preferred; for nodes interfered by a specific frequency band, a strategy that can automatically switch to other available frequency bands is selected. After multiple rounds of selection, crossover and mutation operations, the transmission strategy that best suits the current situation of each node is found from the communication data transmission strategy space, and finally the data transmission strategies of N nodes are obtained to ensure that the remote control commands of the UAV can be transmitted efficiently and stably through these nodes.

[0076] In a possible implementation, step S500 further includes: Step S510: Configure the quantum key distribution channel and encryption algorithm channel according to the data communication security goal.

[0077] Step S520: The quantum key distribution channel and the encryption algorithm channel are set up in parallel to create the encrypted anti-interference communication link.

[0078] Specifically, the security requirements of drone remote control data communication are analyzed based on the data communication security goals, such as ensuring that instruction transmission is not stolen or tampered with, and maintaining the authenticity of the identities of both parties in communication. In response to these requirements, select an adaptive quantum key distribution technology, such as a quantum key distribution scheme based on a decoy state, which can effectively improve the security of key distribution in long-distance communication. When configuring the quantum key distribution channel, set the transmission power, wavelength and other parameters of the quantum signal to ensure that the quantum key can be transmitted stably and securely. At the same time, deploy the quantum key receiving device, calibrate and debug it, so that it can accurately receive and process quantum signals. For the encryption algorithm channel, select a suitable encryption algorithm based on the sensitivity of the data and the processing efficiency requirements. If you pursue efficient symmetric encryption, use the AES algorithm; if you need the characteristics of asymmetric encryption, the RSA algorithm is an optional solution. In the process of configuring the encryption algorithm channel, set the encryption key length, encryption mode and other parameters to balance the encryption strength and computing resource consumption. For example, for critical drone control commands, a longer key length is selected to enhance encryption security; while for some general status feedback data, a shorter key length is selected to increase the speed of encryption and decryption while ensuring security. This rigorous method completes the configuration of the quantum key distribution channel and encryption algorithm channel, laying the foundation for the subsequent construction of encrypted anti-interference communication links.

[0079] The configured quantum key distribution channel and encryption algorithm channel are set up in parallel to create an encrypted anti-interference communication link. At the hardware level, the quantum key distribution device is connected to the encryption algorithm processing device through communication lines and interface devices. Ensure that the quantum key distribution channel and the encryption algorithm channel are physically independent of each other, but can work together. For example, high-speed transmission media such as optical fiber are used to connect the quantum key distribution device and the encryption algorithm device respectively to ensure the rapid transmission of data between the two channels. At the software level, develop corresponding control programs and protocols so that the two channels can operate in coordination. When data needs to be transmitted, the quantum key distribution channel first generates and distributes encryption keys. These keys are transmitted to the receiving end through a secure quantum channel, and the encryption algorithm channel at the receiving end uses the received keys to encrypt the data. The encryption algorithm channel at the sending end encrypts the data based on the same key, and then transmits the encrypted data through the communication link. At the receiving end, the quantum key distribution channel first receives the key, and then the encryption algorithm channel uses the key to decrypt the received encrypted data. Through this link parallel setting method that combines hardware and software, the high security of the quantum key distribution channel and the efficient encryption characteristics of the encryption algorithm channel can be fully utilized to effectively resist external interference and attacks, thereby creating an encrypted and anti-interference communication link that meets the remote control needs of drones, and ensuring the security, accuracy and integrity of drone pilots' remote control commands during transmission.

[0080] Embodiment 2 is based on the same inventive concept as the distributed UAV remote control method of multi-source signal fusion in the above embodiment. Figure 2 As shown, the present application provides a distributed UAV remote control system with multi-source signal fusion, and the system and method embodiments in the present application are based on the same inventive concept. The system includes: The multi-source signal positioning link building module 10 is used to build a multi-source signal positioning link. The multi-source signal positioning link is configured with a GNSS receiver, an RF receiver and a visual positioning sensor, and the multi-source positioning signal stream obtained by the multi-source signal positioning link is fused to determine the estimated position of the drone and the estimated position of the pilot.

[0081] The dummy pilot device setting module 20 is used to set a dummy pilot device, and the dummy pilot device modulates and sends a multi-source spoofing signal according to the estimated position of the pilot, and the multi-source spoofing signal is used to interfere with the pilot's position.

[0082] The data transmission strategy acquisition module 30 is used to construct a distributed control architecture, which includes N transmission control nodes, and adaptively obtains N node data transmission strategies based on the real-time network status and interference conditions of the N transmission control nodes.

[0083] The pilot remote control instruction acquisition module 40 is used to interact with the estimated position of the drone and obtain the drone pilot remote control instructions.

[0084] The UAV remote control module 50 is used to create an encrypted anti-interference communication link, and use the N-node data transmission strategy to perform node forwarding processing and UAV remote control on the UAV pilot's remote control instructions through the encrypted anti-interference communication link.

[0085] Furthermore, the system is also used to implement the following functions: A multi-source positioning signal stream is acquired through the multi-source signal positioning link collection, and the multi-source positioning signal stream includes a GNSS signal stream, an RF signal stream and an image signal stream; noise characteristics of the multi-source positioning signal stream are analyzed to obtain multi-source positioning data noise characteristics, and a multi-source positioning data denoising threshold is determined according to the multi-source positioning data noise characteristics; noise data identification and filtering preprocessing are performed on the multi-source positioning signal stream according to the multi-source positioning data denoising threshold to obtain a standard multi-source positioning signal stream; feature extraction, fusion and position estimation are performed on the standard multi-source positioning signal to determine the estimated position of the UAV and the estimated position of the pilot.

[0086] Furthermore, the system is also used to implement the following functions: According to the data characteristic information of the standard multi-source positioning signal, the multi-source signal feature extraction method and the multi-source signal position feature type are determined; the standard multi-source positioning signal is subjected to correlation feature extraction according to the multi-source signal feature extraction method and the multi-source signal position feature type to obtain a multi-source signal correlation feature set; according to the signal source credibility and the signal source accuracy, a signal source weight dynamic allocation rule is set; based on the signal source weight dynamic allocation rule, the multi-source signal correlation feature set is subjected to fusion processing and position estimation to determine the estimated position of the UAV and the estimated position of the pilot.

[0087] Furthermore, the system is also used to implement the following functions: Based on the signal source weight dynamic allocation rule, the multi-source signal association feature set is weighted and calculated to obtain signal source weight factor information; the multi-source signal association feature set is weighted and fused according to the signal source weight factor information to obtain a positioning signal fusion feature set; the positioning signal fusion feature set is classified and identified to obtain a UAV positioning fusion feature set and a pilot positioning fusion feature set; the Kalman filter is initialized, and the Kalman filter is used to iteratively estimate the position of the UAV positioning fusion feature set and the pilot positioning fusion feature set to determine the estimated position of the UAV and the estimated position of the pilot.

[0088] Furthermore, the system is also used to implement the following functions: An inflatable model of a dummy pilot is simulated and manufactured according to the body data of a target pilot, and a heating sheet is installed on the inflatable model of the dummy pilot to simulate the physiological characteristics of the pilot; a multi-source signal transmitter is installed inside the inflatable model of the dummy pilot, and the multi-source signal transmitter includes a GNSS signal transmitter, an RF signal transmitter and a visual deception signal transmitter; an unmanned aerial vehicle remote control device is arranged on the inflatable model of the dummy pilot, and the target pilot performs remote communication control on the unmanned aerial vehicle through the unmanned aerial vehicle remote control device; the inflatable model of the dummy pilot, the heating sheet, the multi-source signal transmitter, the unmanned aerial vehicle remote control device and the power supply system are integrated and constructed to obtain the dummy pilot device.

[0089] Furthermore, the system is also used to implement the following functions: The target coordinate system of the dummy pilot device is obtained, and the estimated position mapping of the pilot is converted into the target coordinate system to obtain the target pilot position information; according to the preset target effect of signal spoofing, the spoof signal modulation parameters are set; based on the spoof signal modulation parameters, the target pilot position information is modulated by a spoof signal to generate a multi-source spoof signal, wherein the multi-source spoof signal includes a GNSS spoof signal, an RF spoof signal and a visual spoof signal; when the opponent's positioning behavior is detected, the multi-source spoof signal is emitted by the multi-source signal transmitter in the dummy pilot device.

[0090] Furthermore, the system is also used to implement the following functions: According to the distribution area and terrain distribution of the UAV communication area, as well as the communication coverage density requirements, the number of transmission control nodes N is determined; based on the number of transmission control nodes N, the node deployment analysis of the UAV communication area is performed to obtain N transmission control nodes; communication parameter configuration and network topology identification are performed on the N transmission control nodes respectively to construct the distributed control architecture.

[0091] Furthermore, the system is also used to implement the following functions: Data transmission rules are set, and the data transmission rules include bandwidth allocation, transmission rate adjustment, route selection, communication frequency band switching and retransmission mechanism; historical communication data mining and transmission strategy optimization are performed based on the data transmission rules to construct a communication data transmission strategy space; the real-time network status and interference conditions of the N transmission control nodes are used as constraint parameters, and strategy adaptive matching is performed in the communication data transmission strategy space to obtain the data transmission strategies of the N nodes.

[0092] Furthermore, the system is also used to implement the following functions: According to the data communication security goal, a quantum key distribution channel and an encryption algorithm channel are configured; the quantum key distribution channel and the encryption algorithm channel are set up in parallel as links to create the encrypted anti-interference communication link.

[0093] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0094] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0095] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A distributed UAV remote control method based on multi-source signal fusion, characterized in that: The method comprises: Build a multi-source signal positioning link, which is equipped with a GNSS receiver, an RF receiver and a visual positioning sensor, and perform fusion processing on the multi-source positioning signal stream obtained by the multi-source signal positioning link to determine the estimated position of the drone and the estimated position of the pilot; A dummy pilot device is provided, wherein the dummy pilot device modulates and sends a multi-source spoofing signal according to the estimated position of the pilot, and the multi-source spoofing signal is used to interfere with the position of the pilot; Constructing a distributed control architecture, the distributed control architecture comprising N transmission control nodes, and adaptively obtaining N node data transmission strategies based on real-time network conditions and interference conditions of the N transmission control nodes; Interact with the estimated position of the drone to obtain remote control instructions from the drone pilot; An encrypted anti-interference communication link is created, and the N-node data transmission strategy is used to perform node forwarding processing and remote control of the drone pilot's remote control instructions through the encrypted anti-interference communication link.

2. A distributed UAV remote control method based on multi-source signal fusion as claimed in claim 1, characterized in that: Determining the estimated position of the drone and the estimated position of the pilot includes: Acquire a multi-source positioning signal stream through the multi-source signal positioning link collection, wherein the multi-source positioning signal stream includes a GNSS signal stream, an RF signal stream and an image signal stream; Performing noise characteristic analysis on the multi-source positioning signal stream to obtain noise characteristics of multi-source positioning data, and determining a multi-source positioning data denoising threshold according to the noise characteristics of the multi-source positioning data; Perform noise data identification and filtering preprocessing on the multi-source positioning signal stream according to the multi-source positioning data denoising threshold to obtain a standard multi-source positioning signal stream; The standard multi-source positioning signal is subjected to feature extraction, fusion and position estimation to determine the estimated position of the UAV and the estimated position of the pilot.

3. A distributed UAV remote control method with multi-source signal fusion as claimed in claim 2, characterized in that: Determining the estimated position of the drone and the estimated position of the pilot includes: Determining a multi-source signal feature extraction method and a multi-source signal position feature type according to the data characteristic information of the standard multi-source positioning signal; Extracting correlation features from the standard multi-source positioning signal according to the multi-source signal feature extraction method and the multi-source signal position feature type to obtain a multi-source signal correlation feature set; According to the signal source credibility and signal source accuracy, set the signal source weight dynamic allocation rules; Based on the signal source weight dynamic allocation rule, the multi-source signal association feature set is fused and position estimated to determine the estimated position of the drone and the estimated position of the pilot.

4. A distributed UAV remote control method based on multi-source signal fusion as claimed in claim 3, characterized in that: Determining the estimated position of the drone and the estimated position of the pilot includes: Performing weight allocation calculation on the multi-source signal association feature set based on the signal source weight dynamic allocation rule to obtain signal source weight factor information; Performing weighted fusion processing on the multi-source signal correlation feature set according to the signal source weight factor information to obtain a positioning signal fusion feature set; Classifying and labeling the positioning signal fusion feature set to obtain a UAV positioning fusion feature set and a pilot positioning fusion feature set; Initialize the Kalman filter, use the Kalman filter to iteratively estimate the position of the UAV positioning fusion feature set and the pilot positioning fusion feature set, and determine the estimated position of the UAV and the estimated position of the pilot.

5. The distributed UAV remote control method of multi-source signal fusion according to claim 1, characterized in that: The method of providing a dummy flying hands device comprises: According to the body shape data of the target pilot, an inflatable model of a dummy pilot is simulated and manufactured, and a heating sheet is installed on the inflatable model of the dummy pilot to simulate the physiological characteristics of the pilot through the heating sheet; A multi-source signal transmitter is installed inside the inflatable model of the dummy pilot, wherein the multi-source signal transmitter includes a GNSS signal transmitter, an RF signal transmitter and a visual deception signal transmitter; The drone remote control device is arranged on the inflatable model of the dummy pilot, and the target pilot performs remote communication control on the drone through the drone remote control device; The inflatable model of the dummy pilot, the heating sheet, the multi-source signal transmitter, the UAV remote control device and the power supply system are integrated and constructed to obtain the dummy pilot device.

6. A distributed UAV remote control method with multi-source signal fusion as claimed in claim 5, characterized in that: The dummy pilot device modulates and sends a multi-source deception signal according to the estimated position of the pilot, including: Acquire the target coordinate system of the dummy pilot device, transform the estimated position mapping of the pilot into the target coordinate system, and obtain the target pilot position information; According to the preset target effect of signal deception, set the modulation parameters of the deception signal; Performing spoofing signal modulation on the target pilot's position information based on the spoofing signal modulation parameters to generate a multi-source spoofing signal, wherein the multi-source spoofing signal includes a GNSS spoofing signal, an RF spoofing signal, and a visual spoofing signal; When the positioning behavior of the opponent is monitored, the multi-source deception signal is sent out through the multi-source signal transmitter in the dummy pilot device.

7. A distributed UAV remote control method based on multi-source signal fusion as claimed in claim 1, characterized in that: The construction of a distributed control architecture includes: Determine the number of transmission control nodes N based on the distribution area and terrain distribution of the drone communication area, as well as the communication coverage density requirements; Performing node deployment analysis on the UAV communication area based on the number of transmission control nodes N to obtain N transmission control nodes; Communication parameter configuration and network topology identification are performed on the N transmission control nodes respectively to construct the distributed control architecture.

8. The distributed UAV remote control method of multi-source signal fusion according to claim 1, characterized in that: The adjusting and obtaining the N node data transmission strategies based on the real-time network status and interference conditions of the N transmission control nodes includes: Setting data transmission rules, wherein the data transmission rules include bandwidth allocation, transmission rate adjustment, route selection, communication frequency band switching, and retransmission mechanism; Based on the data transmission rules, historical communication data mining and transmission strategy optimization are performed to construct a communication data transmission strategy space; The real-time network status and interference conditions of the N transmission control nodes are used as constraint parameters, and strategy adaptive matching is performed in the communication data transmission strategy space to obtain the data transmission strategy of the N nodes.

9. A distributed UAV remote control method with multi-source signal fusion as claimed in claim 1, characterized in that: The step of creating an encrypted anti-interference communication link comprises: Configure quantum key distribution channels and encryption algorithm channels according to data communication security goals; The quantum key distribution channel and the encryption algorithm channel are set up in parallel to create the encrypted anti-interference communication link.

10. A distributed UAV remote control system with multi-source signal fusion, characterized in that: The system is used to implement a distributed UAV remote control method for multi-source signal fusion according to any one of claims 1 to 9, and the system comprises: A multi-source signal positioning link building module is used to build a multi-source signal positioning link. The multi-source signal positioning link is configured with a GNSS receiver, an RF receiver and a visual positioning sensor, and the multi-source positioning signal stream obtained by the multi-source signal positioning link is fused to determine the estimated position of the UAV and the estimated position of the pilot; A dummy pilot device setting module, used to set a dummy pilot device, wherein the dummy pilot device modulates and sends a multi-source deception signal according to the estimated position of the pilot, and the multi-source deception signal is used to interfere with the position of the pilot; A data transmission strategy acquisition module, used to construct a distributed control architecture, the distributed control architecture includes N transmission control nodes, and adaptively obtains N node data transmission strategies based on the real-time network status and interference conditions of the N transmission control nodes; A pilot remote control command acquisition module is used to interact with the estimated position of the drone and obtain the drone pilot remote control command; The UAV remote control module is used to create an encrypted anti-interference communication link, and adopt the N-node data transmission strategy to perform node forwarding processing and UAV remote control on the UAV pilot remote control instructions through the encrypted anti-interference communication link.

Images