Pseudo-satellite signal design method and device based on intelligent framework

Abstract

The present invention discloses a pseudolite signal design method and device based on an intelligent framework, belonging to the technical field of pseudolite signal enhancement. The method comprises: obtaining an electromagnetic environment spectrum and pseudolite signal reception performance; determining a pseudolite signal parameter selection range based on the electromagnetic environment spectrum and pseudolite signal reception performance; using reinforcement learning to determine the optimal pseudolite signal parameters based on the electromagnetic environment spectrum, pseudolite signal parameter selection range, and pseudolite signal model, with the goal of maximizing the value of a fusion gain function; and broadcasting the pseudolite signal into the electromagnetic environment based on the optimal pseudolite signal parameters. This invention improves the environmental adaptability of pseudolite signals, resolving the current technical problem of poor environmental adaptability of pseudolite signals.

Description

Technical Field

[0001] The present invention relates to the technical field of pseudolite signal enhancement, and in particular to a pseudolite signal design method and device based on an intelligent framework. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The pseudolite system is a typical navigation augmentation system. It was first used in the verification and debugging of the Global Navigation Satellite System (GNSS) system. Later, it was gradually developed for assisted positioning and independent positioning for satellite navigation, and is used in scenarios such as indoors, tunnels, and airports.

[0004] When current pseudolite systems broadcast pseudolite signals, they default to pulse modulation or direct broadcast of satellite navigation signals, and the pseudolite pulse distribution pattern is fixed. The broadcast pseudolite signals cannot be adjusted in real time based on the actual environment. Furthermore, to reduce the mutual influence between continuous pseudolite signals, the indoor power requirement is no less than -128dBm, which is 5dB higher than the outdoor satellite navigation signal, thus reducing the signal transmission power.

[0005] Therefore, the current pseudolite signal design method has the problems of poor environmental adaptability and parameter flexibility. Summary of the Invention

[0006] In order to solve the above problems, the present invention proposes a pseudolite signal design method and device based on an intelligent framework, which can adjust the broadcast of pseudolite signals according to changes in the electromagnetic environment, thereby improving the environmental adaptability of pseudolite signals.

[0007] To achieve the above object, the present invention adopts the following technical solutions:

[0008] First, a pseudolite signal design method based on an intelligent framework is proposed, including:

[0009] Obtain the electromagnetic environment spectrum and pseudo-satellite signal reception performance;

[0010] Determine the selection range of pseudolite signal parameters based on the electromagnetic environment spectrum and pseudolite signal reception performance;

[0011] With the goal of maximizing the fusion gain function, reinforcement learning is used to determine the optimal pseudolite signal parameters based on the electromagnetic environment spectrum, the pseudolite signal parameter selection range, and the pseudolite signal model. The fusion gain function value is the weighted fusion result after normalization of the actual value of the signal-to-noise ratio loss, the actual value of the measurement accuracy, the actual value of the anti-interference performance, and the actual value of the multipath suppression capability. The actual values of the signal-to-noise ratio loss, the actual value of the measurement accuracy, the actual value of the anti-interference performance, and the actual value of the multipath suppression capability are determined based on the pseudolite signal parameters and the electromagnetic environment spectrum.

[0012] According to the optimal pseudo-satellite signal parameters, the pseudo-satellite signal is broadcast into the electromagnetic environment.

[0013] Furthermore, when using reinforcement learning to determine the optimal pseudolite signal parameters, the pseudolite signal parameters are used as action functions, and the action state function and action reward function are determined according to the fusion gain function.

[0014] Furthermore, the pseudolite signal parameters include pseudolite signal transmission power, carrier frequency, time slot and bandwidth.

[0015] Furthermore, the measurement accuracy is characterized by the Cramer-Rao lower bound.

[0016] Furthermore, the anti-interference performance is characterized by the anti-interference quality factor.

[0017] Furthermore, the multipath suppression capability is characterized by the multipath error envelope.

[0018] Furthermore, based on the pseudolite signal parameter selection range, pseudolite signal measurement accuracy range and electromagnetic environment spectrum, pseudolite signal task optimization constraints are constructed;

[0019] With the goal of maximizing the fusion gain function value, the pseudolite signal model and pseudolite signal task optimization constraints are solved to obtain the optimal pseudolite signal parameters.

[0020] Secondly, a pseudolite signal design device based on an intelligent framework is proposed, including:

[0021] A data acquisition unit, used to obtain the electromagnetic environment spectrum and pseudo-satellite signal reception performance;

[0022] A signal parameter range prediction unit, configured to determine a selection range of pseudolite signal parameters based on an electromagnetic environment spectrum and pseudolite signal reception performance;

[0023] an optimal pseudolite signal parameter determination unit, configured to determine the optimal pseudolite signal parameters using reinforcement learning, with the goal of maximizing a fusion gain function value, based on an electromagnetic environment spectrum, a pseudolite signal parameter selection range, and a pseudolite signal model; wherein the fusion gain function value is a weighted fusion result obtained by normalizing an actual value of signal-to-noise ratio loss, an actual value of measurement accuracy, an actual value of anti-interference performance, and an actual value of multipath suppression capability; and wherein the actual value of signal-to-noise ratio loss, an actual value of measurement accuracy, an actual value of anti-interference performance, and an actual value of multipath suppression capability are determined based on the pseudolite signal parameters and the electromagnetic environment spectrum;

[0024] The pseudolite signal broadcasting unit is used to broadcast the pseudolite signal into the electromagnetic environment according to the optimal pseudolite signal parameters.

[0025] Furthermore, the optimal pseudolite signal parameter determination unit is further configured to use the pseudolite signal parameters as an action function when determining the optimal pseudolite signal parameters using reinforcement learning, and determine an action state function and an action reward function according to a fusion gain function.

[0026] Furthermore, the optimal pseudolite signal parameter determination unit is further configured to construct pseudolite signal task optimization constraints based on a pseudolite signal parameter selection range, a pseudolite signal measurement accuracy range, and an electromagnetic environment spectrum;

[0027] With the goal of maximizing the fusion gain function value, the pseudolite signal model and pseudolite signal task optimization constraints are solved to obtain the optimal pseudolite signal parameters.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] The present invention proposes a pseudolite signal design method and device based on an intelligent framework. The method obtains an electromagnetic environment spectrum and pseudolite signal reception performance, and then determines a pseudolite signal parameter selection range based on the electromagnetic environment spectrum and the pseudolite signal reception performance. Then, with the goal of maximizing the value of a fusion gain function, the optimal pseudolite signal parameters are determined based on the electromagnetic environment spectrum, the pseudolite signal parameter selection range, and the pseudolite signal model. The pseudolite signal is broadcast into the electromagnetic environment based on the optimal pseudolite signal parameters. Since the electromagnetic environment spectrum is taken into account when determining the optimal pseudolite signal parameters, the pseudolite signal broadcast into the electromagnetic environment can adapt to complex environments. In addition, the fusion gain function comprehensively considers signal-to-noise ratio loss, measurement accuracy, anti-interference performance, and multipath suppression performance, so that the ultimately determined pseudolite signal parameters can reach the optimal value, have flexibility and autonomous adaptability, and alleviate the problem of poor pseudolite signal performance in complex time-varying electromagnetic environments.

[0030] Advantages of additional aspects of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The drawings in the specification, which constitute a part of this application, are used to provide further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute improper limitations on this application.

[0032] Figure 1 Flowchart of the pseudolite signal design method based on the intelligent framework disclosed in the embodiment;

[0033] Figure 2 An intelligent framework for the pseudolite signal design method based on the intelligent framework disclosed in the embodiment;

[0034] Figure 3 A block diagram of the Bayesian inference algorithm disclosed in the embodiment;

[0035] Figure 4 This is a structural block diagram of the neural network algorithm disclosed in the embodiment. DETAILED DESCRIPTION

[0036] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0037] It should be noted that the following detailed descriptions are illustrative and intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present application belongs.

[0038] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, they indicate the presence of features, steps, operations, devices, components and / or combinations thereof.

[0039] Example 1

[0040] Before describing in detail the pseudolite signal design method based on the intelligent framework proposed in this embodiment, the application scenario and system architecture involved in this embodiment are first explained.

[0041] First, the application scenarios involved in this embodiment are introduced.

[0042] Navigation augmentation systems are primarily categorized as information augmentation and signal augmentation. Information augmentation systems primarily broadcast correction information to users via satellite or ground-based methods, combining it with received basic navigation information to enhance basic navigation performance. Signal augmentation systems autonomously broadcast navigation augmentation ranging signals to users via satellite or ground-based methods. Users can combine these signals with existing satellite navigation signals for positioning, further improving satellite navigation availability. They also provide independent navigation and positioning capabilities, serving as a regional backup for satellite navigation.

[0043] Based on this scenario, this embodiment proposes a pseudolite signal design method based on an intelligent framework. This method is based on the electromagnetic environment spectrum and pseudolite signal reception performance, and includes three parts: pseudolite signal fusion prediction, pseudolite signal parameter optimization, and electromagnetic environment spectrum monitoring.

[0044] Next, the system architecture involved in this embodiment is introduced.

[0045] The pseudolite signal design method based on an intelligent framework proposed in this embodiment is applied to a pseudolite system. The pseudolite system includes two devices: a pseudolite signal transmitter and a pseudolite signal receiver terminal. The pseudolite signal transmitter is responsible for determining a pseudolite signal parameter selection range, optimizing pseudolite signal parameters based on an intelligent framework, and broadcasting pseudolite signals. The pseudolite signal receiver terminal is responsible for monitoring the electromagnetic environment spectrum and receiving pseudolite signals. A communication link is provided between the pseudolite signal receiver terminal and the transmitter, enabling uplink and downlink communication to transmit information such as electromagnetic environment spectrum data and pseudolite signal reception performance parameters.

[0046] It should be noted that the application scenario and system architecture described in this embodiment are intended to more clearly illustrate the technical solution proposed in this embodiment, and do not constitute a limitation on the technical solution provided in this embodiment. Ordinary technicians in this field can know that with the emergence of new application scenarios and the evolution of the implementation environment, the technical solution proposed in this embodiment is also applicable to similar technical problems.

[0047] Next, the pseudolite signal design method based on the intelligent framework proposed in this embodiment is described in detail.

[0048] like Figure 2As shown, the pseudolite signal design method based on the intelligent framework proposed in this embodiment relies on the electromagnetic environment spectrum and pseudolite signal reception performance, and is fed back to the pseudolite signal fusion prediction link through a communication link. Based on the electromagnetic environment spectrum and pseudolite signal reception performance, the pseudolite signal parameter selection range for the next step is predicted and determined, laying the foundation for the pseudolite signal optimization based on the reinforcement learning intelligent framework for the next step. The pseudolite signal optimization link based on the intelligent framework uses the pseudolite signal parameter selection range and pseudolite signal model predicted in the previous link, and uses reinforcement learning to determine the optimal pseudolite signal parameters with the goal of maximizing the fusion gain function value. Subsequently, based on the optimal pseudolite signal parameters, the pseudolite signal is broadcast into the electromagnetic environment. Finally, the spectrum monitoring link provides feedback on the electromagnetic environment spectrum and pseudolite signal reception performance, forming a closed-loop verification structure of the reinforcement learning intelligent framework.

[0049] When using reinforcement learning to determine the optimal pseudolite signal parameters, the pseudolite signal parameters are used as action functions, and the action state function and action reward function are determined according to the fusion gain function.

[0050] The pseudolite signal design method based on the intelligent framework proposed in this embodiment is described in detail. Figure 1 As shown, the pseudolite signal design method based on the intelligent framework proposed in this embodiment includes:

[0051] Obtain the electromagnetic environment spectrum and pseudo-satellite signal reception performance;

[0052] Determine the selection range of pseudolite signal parameters based on the electromagnetic environment spectrum and pseudolite signal reception performance;

[0053] With the goal of maximizing the fusion gain function, reinforcement learning is used to determine the optimal pseudolite signal parameters based on the electromagnetic environment spectrum, the pseudolite signal parameter selection range, and the pseudolite signal model. The fusion gain function value is the weighted fusion result after normalization of the actual value of the signal-to-noise ratio loss, the actual value of the measurement accuracy, the actual value of the anti-interference performance, and the actual value of the multipath suppression capability. The actual values of the signal-to-noise ratio loss, the actual value of the measurement accuracy, the actual value of the anti-interference performance, and the actual value of the multipath suppression capability are determined based on the pseudolite signal parameters and the electromagnetic environment spectrum.

[0054] According to the optimal pseudo-satellite signal parameters, the pseudo-satellite signal is broadcast into the electromagnetic environment.

[0055] The pseudolite signal parameters determined in this embodiment include pseudolite signal transmission power P, carrier frequency f c , time slot t and bandwidth B .

[0056] Among them, the carrier frequency of the pseudo-satellite signal is determined according to the electromagnetic environment spectrumf c Select range and bandwidth B Selection range; determine the time slot based on pseudo-satellite signal reception performance t Selection range; determine the transmission power based on the pseudolite signal reception performance and pseudolite hardware equipment parameters P Selection range, pseudo-satellite hardware equipment includes antenna and power amplifier.

[0057] Referring to the Locata system model, time division is used to reduce the near-far effect between pseudolite signals. The method disclosed in this embodiment differs in that the time slots of each pseudolite transmitter can be adjusted based on the actual pseudolite signal reception performance, thereby reducing pseudolite signal performance differences caused by insufficient synchronization between pseudolites.

[0058] To enhance the flexibility of pseudolite signals, this embodiment considers signal parameters of particular interest to pseudolite signals, such as power, frequency, bandwidth, and time slot, and establishes a pseudolite signal model to characterize multi-dimensional resources in the time, frequency, and code domains. For time and frequency resources, time slots, bandwidth, and carrier frequencies are mathematically described. For available coding resources, amplitude and phase coding sequences are used for characterization, including both information and signal coding.

[0059] The pseudolite signal model of this embodiment is:

[0060] ;

[0061] Where, is a pseudo-satellite signal, j is the imaginary unit, is the amplitude of the signal, and the signal transmission power P Related, P=A 2 , Characterize amplitude and phase coding resources, including waveform and bandwidth B , information rate and other factors, according to different amplitude and phase coding, the signal model c ( n ) further evolved into specific common amplitude and phase coding models for satellite navigation, such as BPSK, QPSK, and BOC; is the signal carrier frequency; Represents a block of time resources, t is the pseudolite signal time slot (signal duration), corresponding to the duty cycle in the pseudolite signal; is a rectangular window function.

[0062] when c ( n ) When the BPSK amplitude-phase coding model is adopted, the pseudolite signal model is rewritten as:

[0063] ;

[0064] in, am is a pseudo-random spread spectrum code of {+1, -1}, and the duration of the code is Tc , the spreading code rate is 1 / Tc , BPSK signal bandwidth , the entire signal frequency f Range , Characteristic pulse width is Tc The rectangular pulse function is , m is the parameter of the number of spreading code chips, and M is the total number of spreading codes.

[0065] when c ( n ) When the BOC amplitude and phase coding model is adopted, the pseudolite signal model is rewritten as:

[0066] ;

[0067] in, am is a pseudo-random spread spectrum code of {+1, -1}, and the duration of the code is Tc , BOC signal bandwidth , Characteristic pulse width is Tc The rectangular pulse function, sc ( t ) is the signal subcarrier, and its expression is:

[0068] ;

[0069] in, fs is the subcarrier frequency, fs =α*1.023MHz, pseudo-random spread spectrum code am The spreading code rate is β *1.023MHz, recorded as BOC (α,β ), the bandwidth of the BOC signal is , the upper sideband frequency range of the entire BOC signal spectrum is: ; The lower sideband frequency range of the entire BOC signal spectrum is: .

[0070] In order to ensure that the broadcast pseudolite signal has the best performance, this embodiment constructs a fusion gain function that characterizes the pseudolite signal performance. The fusion gain function value is a weighted fusion result after normalization of the actual value of the signal-to-noise ratio loss, the actual value of the measurement accuracy, the actual value of the anti-interference performance, and the actual value of the multipath suppression capability. The specific fusion gain function is:

[0071] ;

[0072] in, is the fusion gain function value, is the total set of parameters to be optimized, 、 、 and are the weights of signal-to-noise ratio loss, measurement accuracy, anti-interference performance, and multipath suppression capability, respectively; is the actual value of the signal-to-noise ratio loss, The maximum signal-to-noise ratio loss, is the actual value of measurement accuracy, is the maximum measurement accuracy, is the actual value of anti-interference performance, is the maximum value of anti-interference performance, is the actual value of multipath suppression capability, is the maximum value of multipath suppression capability; 、 、 、 , used for 、 、 and Perform normalization.

[0073] Specifically, the near-far effect is essentially the effect of a stronger signal affecting the reception of a weaker signal. The cross-correlation between the strong and weak signals results in a significant signal-to-noise ratio loss. The impact of the near-far effect is characterized by the signal-to-noise ratio loss of the weak signal output caused by the strong signal interference. The expression for the signal-to-noise ratio loss is:

[0074] ;

[0075] in, is the actual value of the signal-to-noise ratio loss, G p is the coherent integration gain, C is the average value of the cross-correlation of the amplitude and phase coded signals between strong and weak signals, is the signal-to-noise ratio of the strong signal, P 2 is the power of the strong signal in the near-far effect, is the white noise variance. The smaller the SNR loss, the smaller the impact of the near-far effect. Considering the large number of pseudolites, the SNR loss caused by the near-far effect is the sum of the SNR losses caused by multiple strong pseudolites.

[0076] The measurement accuracy is characterized by the Cramer-Rao lower bound, where

[0077] ;

[0078] in, is the actual value of measurement accuracy, is the signal power, S(f) is the power spectral density function of the signal, is the white noise power spectral density, is the signal time slot duty cycle factor, .

[0079] Considering the complex electromagnetic environment such as cities and shielding, the anti-interference performance of the signal is particularly important. The anti-interference performance of this embodiment is characterized by the anti-interference quality factor.

[0080] ;

[0081] in, Q is the actual value of anti-interference performance, Rc is the signal spreading code rate, is the power spectral density of the interference signal.

[0082] During the propagation of pseudolite signals, there are multipath obstructions. The multipath suppression capability of this embodiment is characterized by the multipath error envelope, which is expressed as follows:

[0083] ;

[0084] in, is the power spectrum density of the signal, and the carrier frequency fc and bandwidth B Related, f is the frequency of the signal, is the actual value of the multipath suppression capability. The smaller the multipath error envelope area, the stronger the multipath suppression capability. a The amplitude ratio of the multipath signal to the direct signal is generally set to 0.25, but can also be adjusted based on actual test conditions. Signal receiving bandwidth, determined by the pseudo-satellite receiver front-end RF and filter, generally greater than or equal to the signal bandwidth B , d To track the code spacing in the loop, it is generally set to 1 / 2, but can also be set according to the actual loop value; S(f) is the power spectral density function of the signal, and τ is the multipath delay. The above expression takes a positive sign when the phase difference between the multipath signal and the direct signal is 0°, and a negative sign when the phase difference between the multipath signal and the direct signal is 180°.

[0085] This embodiment also constructs pseudolite signal task optimization constraints based on the pseudolite signal parameter selection range, pseudolite signal measurement accuracy range, and electromagnetic environment spectrum. The pseudolite signal task optimization constraints are:

[0086] ;

[0087] in, is the pseudolite signal transmission power, Select the upper limit of the range for pseudolite signal transmission power, is the pseudolite signal bandwidth, Select the lower limit of the range for the pseudolite signal bandwidth, Select the upper limit of the range for the pseudolite signal bandwidth, is the pseudolite signal measurement accuracy, is the upper limit of pseudolite signal measurement accuracy, f c is the carrier frequency of pseudo-satellite signal; The lower limit of the pseudo-satellite signal carrier frequency selection range is Select the upper limit of the range for the pseudo-satellite signal carrier frequency, It is the signal time resource block, which is generally the duration of the spreading code chip.

[0088] This example also predicts pseudolite signal parameters based on a fusion of the electromagnetic environment spectrum and pseudolite signal reception performance, providing initial values for subsequent reinforcement learning optimization. Generally, Bayesian inference models based on a priori confusion matrices or neural network models with rich samples are used to obtain pseudolite signal parameter predictions, which can then serve as reinforcement learning validation evidence and optimization directions.

[0089] When using the Bayesian inference model to predict pseudolite signal parameters, the input of the Bayesian inference model is the electromagnetic environment spectrum and pseudolite signal reception performance, and the output is the prediction result of the pseudolite signal parameters. The process of using the Bayesian inference model to predict pseudolite signal parameters is as follows: Figure 3 As shown, training data is obtained, which includes a training electromagnetic environment spectrum and a training pseudolite signal reception performance, and corresponding pseudolite signal parameters. The training data is preprocessed, and a confusion matrix is generated using the preprocessed data. Based on the confusion matrix, a class prior probability and a likelihood probability are determined. A Bayesian inference model is trained using the preprocessed data and its corresponding class prior probability and likelihood probability. After the training is completed, a trained Bayesian inference model is obtained. When the trained Bayesian inference model is used to predict the pseudolite signal parameters in real time, data preprocessing is performed on the electromagnetic environment spectrum and pseudolite signal reception performance obtained in real time, and the preprocessed data is processed using the trained Bayesian inference model to obtain a real-time prediction result of the pseudolite signal parameters.

[0090] When using a neural network model to predict pseudolite signal parameters, the input of the neural network model is the electromagnetic environment spectrum and pseudolite signal reception performance, and the output is the prediction result of the pseudolite signal parameters. The neural network model can be a multilayer perceptron network model; the process of using the multilayer perceptron network model to predict pseudolite signal parameters is as follows: Figure 4 As shown, training data is obtained, which includes a training electromagnetic environment spectrum and training pseudolite signal reception performance, and corresponding pseudolite signal parameters. Data preprocessing is performed on the training data to obtain preprocessed data. Training electromagnetic environment spectrum characteristics and training pseudolite signal reception performance characteristics are extracted from the preprocessed data. The pseudolite signal parameters are used as labels to annotate the corresponding electromagnetic environment spectrum characteristics and training pseudolite signal reception performance characteristics. A multilayer perceptron network is trained using the annotated data. After training is completed, a trained multilayer perceptron network is obtained. When the trained multilayer perceptron network is used to predict the pseudolite signal parameters in real time, data preprocessing is performed on the real-time obtained electromagnetic environment spectrum and pseudolite signal reception performance, and the preprocessed data characteristics are extracted. The preprocessed data characteristics are processed using the trained multilayer perceptron network to obtain real-time prediction results of the pseudolite signal parameters.

[0091] This embodiment aims to maximize the value of the fusion gain function, solves the pseudolite signal model and pseudolite signal task optimization constraints, and obtains the optimal pseudolite signal parameters.

[0092] In order to improve the accuracy and calculation rate of determining the optimal pseudolite signal parameters, this embodiment uses reinforcement learning to determine the optimal pseudolite signal parameters.

[0093] When using reinforcement learning to determine the optimal pseudolite signal parameters, the prediction results of the pseudolite signal parameters predicted by the fusion are used as the initial values, the pseudolite signal parameters are used as the action function, and the action state function and action reward function are determined according to the fusion gain function.

[0094] That is: action function for: , where n is any integer.

[0095] The action state function is: .

[0096] The corresponding action reward function is expressed as:

[0097] ;

[0098] in, represents the action reward, It indicates the maximum fusion gain that can be obtained when the action state satisfies the optimization constraints of the pseudolite signal task. Indicates the minimum fusion gain that can be obtained when the action state satisfies the constraints. When the constraints are not met, the reward value is , in order to play the role of "punishment".

[0099] The purpose of the method disclosed in this embodiment is to find the optimal pseudolite signal parameters that meet the optimization constraints of the pseudolite signal task through the intelligent framework of reinforcement learning, so as to maximize the fusion gain and achieve the global optimal pseudolite signal design.

[0100] Traditional pseudolite signals generally utilize code division and time division sharing to mitigate the near-far effect. Similar to GNSS signal systems, these require minimal terminal modifications. However, their integration methods are fixed, lacking environmental awareness and poor environmental adaptability. They are not well-suited for complex and changing electromagnetic environments, such as urban areas and those exposed to obstructions. There is an urgent need to design flexible pseudolite signal solutions for these new scenarios. The pseudolite signal design method based on an intelligent framework, proposed in this embodiment, offers flexibility and autonomous adaptability, alleviating the problem of poor pseudolite signal performance in complex and time-varying electromagnetic environments. Traditional pseudolite signals can adapt well to specific scenarios. However, the widespread use of ground-based radio systems in urban areas, obstructed environments, indoor environments, and tunnels has necessitated the design of pseudolite signals suitable for these complex and changing electromagnetic environments. This has led to increased demands for pseudolite signal availability and reliability. Therefore, solely using existing pseudolite signal solutions can result in performance degradation or even render them unusable. The pseudolite signal design method based on an intelligent framework, proposed in this embodiment, can flexibly generate optimal pseudolite signals based on the electromagnetic environment spectrum, offering the advantages of high flexibility and strong environmental adaptability.

[0101] Example 2

[0102] In this embodiment, a pseudolite signal design device based on an intelligent framework is disclosed, comprising:

[0103] A data acquisition unit, used to obtain the electromagnetic environment spectrum and pseudo-satellite signal reception performance;

[0104] A signal parameter range prediction unit, configured to determine a selection range of pseudolite signal parameters based on an electromagnetic environment spectrum and pseudolite signal reception performance;

[0105] an optimal pseudolite signal parameter determination unit, configured to determine the optimal pseudolite signal parameters using reinforcement learning, with the goal of maximizing a fusion gain function value, based on an electromagnetic environment spectrum, a pseudolite signal parameter selection range, and a pseudolite signal model; wherein the fusion gain function value is a weighted fusion result obtained by normalizing an actual value of signal-to-noise ratio loss, an actual value of measurement accuracy, an actual value of anti-interference performance, and an actual value of multipath suppression capability; and wherein the actual value of signal-to-noise ratio loss, an actual value of measurement accuracy, an actual value of anti-interference performance, and an actual value of multipath suppression capability are determined based on the pseudolite signal parameters and the electromagnetic environment spectrum;

[0106] The pseudolite signal broadcasting unit is used to broadcast the pseudolite signal into the electromagnetic environment according to the optimal pseudolite signal parameters.

[0107] Preferably, the optimal pseudolite signal parameter determination unit is further configured to use the pseudolite signal parameters as an action function when determining the optimal pseudolite signal parameters using reinforcement learning, and determine an action state function and an action reward function according to a fusion gain function.

[0108] Preferably, the optimal pseudolite signal parameter determination unit is further configured to construct pseudolite signal task optimization constraints based on a pseudolite signal parameter selection range, a pseudolite signal measurement accuracy range, and an electromagnetic environment spectrum; and solve the pseudolite signal model and the pseudolite signal task optimization constraints with the goal of maximizing the fusion gain function value to obtain the optimal pseudolite signal parameters.

[0109] The method disclosed in Example 1 can be directly implemented as a hardware processor, or can be implemented using a combination of hardware and software modules in the processor. The software module can be located in a storage medium mature in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. The storage medium is located in the memory, and the processor reads the information in the memory and, in conjunction with its hardware, completes the steps of the above method. To avoid repetition, it will not be described in detail here.

[0110] Those skilled in the art will appreciate that the units and algorithm steps of the various examples described in conjunction with this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0111] Although the above describes the specific embodiments of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without any creative work are still within the scope of protection of the present invention.

Claims

1. A pseudolite signal design method based on an intelligent framework, characterized in that: include: Obtain the electromagnetic environment spectrum and pseudo-satellite signal reception performance; Determine the selection range of pseudolite signal parameters based on the electromagnetic environment spectrum and pseudolite signal reception performance; With the goal of maximizing the fusion gain function, reinforcement learning is used to determine the optimal pseudolite signal parameters based on the electromagnetic environment spectrum, the pseudolite signal parameter selection range, and the pseudolite signal model. The fusion gain function value is the weighted fusion result after normalization of the actual value of the signal-to-noise ratio loss, the actual value of the measurement accuracy, the actual value of the anti-interference performance, and the actual value of the multipath suppression capability. The actual values of the signal-to-noise ratio loss, the actual value of the measurement accuracy, the actual value of the anti-interference performance, and the actual value of the multipath suppression capability are determined based on the pseudolite signal parameters and the electromagnetic environment spectrum. According to the optimal pseudo-satellite signal parameters, the pseudo-satellite signal is broadcast into the electromagnetic environment.

2. The pseudolite signal design method based on the intelligent framework according to claim 1, characterized in that: When using reinforcement learning to determine the optimal pseudolite signal parameters, the pseudolite signal parameters are used as action functions, and the action state function and action reward function are determined based on the fusion gain function.

3. The pseudolite signal design method based on the intelligent framework according to claim 1, characterized in that: Pseudolite signal parameters include pseudolite signal transmission power, carrier frequency, time slot and bandwidth.

4. The pseudolite signal design method based on the intelligent framework according to claim 1, characterized in that: The measurement accuracy is characterized by the Cramer-Rao lower bound.

5. The pseudolite signal design method based on the intelligent framework according to claim 1, characterized in that: The anti-interference performance is characterized by the anti-interference quality factor.

6. The pseudolite signal design method based on the intelligent framework according to claim 1, characterized in that: The multipath suppression capability is characterized by the multipath error envelope.

7. The pseudolite signal design method based on the intelligent framework according to claim 1, characterized in that: Based on the pseudolite signal parameter selection range, pseudolite signal measurement accuracy range and electromagnetic environment spectrum, pseudolite signal mission optimization constraints are constructed. With the goal of maximizing the fusion gain function value, the pseudolite signal model is solved under the pseudolite signal mission optimization constraints to obtain the optimal pseudolite signal parameters.

8. A pseudolite signal design device based on an intelligent framework, characterized in that: include: A data acquisition unit, used to obtain the electromagnetic environment spectrum and pseudo-satellite signal reception performance; A signal parameter range prediction unit, configured to determine a selection range of pseudolite signal parameters based on an electromagnetic environment spectrum and pseudolite signal reception performance; an optimal pseudolite signal parameter determination unit, configured to determine the optimal pseudolite signal parameters using reinforcement learning, with the goal of maximizing a fusion gain function value, based on an electromagnetic environment spectrum, a pseudolite signal parameter selection range, and a pseudolite signal model; wherein the fusion gain function value is a weighted fusion result obtained by normalizing an actual value of signal-to-noise ratio loss, an actual value of measurement accuracy, an actual value of anti-interference performance, and an actual value of multipath suppression capability; and wherein the actual value of signal-to-noise ratio loss, an actual value of measurement accuracy, an actual value of anti-interference performance, and an actual value of multipath suppression capability are determined based on the pseudolite signal parameters and the electromagnetic environment spectrum; The pseudolite signal broadcasting unit is used to broadcast the pseudolite signal into the electromagnetic environment according to the optimal pseudolite signal parameters.

9. The pseudolite signal design device based on the intelligent framework according to claim 8, characterized in that: The optimal pseudolite signal parameter determination unit is further configured to use the pseudolite signal parameters as an action function when determining the optimal pseudolite signal parameters using reinforcement learning, and determine an action state function and an action reward function according to a fusion gain function.

10. The pseudolite signal design device based on the intelligent framework according to claim 8, characterized in that: The optimal pseudolite signal parameter determination unit is further used to construct pseudolite signal task optimization constraints based on the pseudolite signal parameter selection range, the pseudolite signal measurement accuracy range and the electromagnetic environment spectrum; With the goal of maximizing the fusion gain function value, the pseudolite signal model is solved under the pseudolite signal task optimization constraints to obtain the optimal pseudolite signal parameters.

Images