5G and IMU tight coupling positioning method and system based on LSSVM

Abstract

The invention discloses a 5G and IMU tight coupling positioning method and system based on an LSSVM. The method comprises the steps that firstly, the actually measured distance between a target terminal and a 5G base station is obtained; constructing an LSSVM initial model, and training the LSSVM initial model by using the real distance and the actually measured distance between the target terminal and the 5G base station to obtain an LSSVM correction model; taking the actually measured distance as the input of an LSSVM correction model, and correcting the actually measured distance through the LSSVM correction model to obtain a corrected distance; taking the corrected distance as measurement input of an error state Kalman filter, and constructing a measurement equation by combining an estimated distance between the target terminal and the 5G base station obtained by using the IMU and a difference value between the estimated distance and an actually measured distance; and determining target positioning information of the target terminal by using the measurement equation and a preset Kalman state updating equation. By combining the LSSVM and the ESKF algorithm, efficient fusion of 5G and I MU data is realized, the positioning precision and reliability are remarkably improved, and the method has wide application prospects and remarkable technical advantages.

Description

Technical Field

[0001] The present invention belongs to the field of wireless communication technology, and in particular to a 5G and IMU tightly coupled positioning method and system based on LSSVM. Background Art

[0002] With the rapid development and application of 5G technology, it has shown great potential in positioning services. By introducing new positioning technologies such as OTDOA (Observed Time Difference of Arrival), 5G networks can provide more accurate positioning capabilities than traditional 4G networks. However, in practical applications, especially in complex environments such as urban canyons and indoors, 5G positioning still faces the problem of non-line-of-sight (NLOS), that is, there are obstructions in the signal propagation path, resulting in increased positioning errors.

[0003] As a mature inertial navigation device, IMU can provide acceleration and angular velocity information of the device, and has the advantages of high dynamic response and being unaffected by the external environment. However, IMU will accumulate errors after long-term use and needs to be corrected through external information.

[0004] Therefore, how to combine the advantages of 5G network positioning technology and IMU, overcome the limitations of their respective technologies, and successfully improve the positioning accuracy in indoor environments has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] The purpose of the present invention is to provide a tightly coupled positioning method of 5G and IMU based on LSSVM to solve the shortcomings of the prior art. It realizes the efficient fusion of 5G and IMU data by combining LSSVM and ESKF algorithms, significantly improves the positioning accuracy and reliability, and has broad application prospects and significant technical advantages.

[0006] An embodiment of the present application provides a 5G and IMU tightly coupled positioning method based on LSSVM, the method comprising:

[0007] Obtain the measured distance between the target terminal and the 5G base station;

[0008] Construct an LSSVM initial model, and use the actual distance and the measured distance between the target terminal and the 5G base station to train the LSSVM initial model to obtain an LSSVM revised model;

[0009] The measured distance is used as the input of the LSSVM correction model, and the measured distance is corrected by the LSSVM correction model to obtain a corrected distance;

[0010] The corrected distance is used as the measurement input of the error state Kalman filter, and the measurement equation is constructed by combining the estimated distance between the target terminal and the 5G base station obtained by using the IMU and the difference between the measured distance;

[0011] The target positioning information of the target terminal is determined by using the measurement equation and the preset Kalman state update equation.

[0012] Optionally, obtaining the measured distance between the target terminal and the 5G base station includes:

[0013] The 5G ranging module is used to measure the actual distance between the target terminal and the 5G base station.

[0014] Optionally, the LSSVM initial model replaces the non-equality constraints of the SVM optimization problem with equality constraints, and the LSSVM initial model with equality constraints is expressed by the following formula:

[0015]

[0016] Among them, w is the weight vector, η is the regularization parameter, ξ i is the random fitting error, y i =w T φ(x i )+b represents the regression equation, x i is the measured distance, y i is the actual distance between the target terminal and the 5G base station, φ(x i ) is the mapping between the input data of the LSSVM initial model and the high-dimensional feature space, and b is the deviation.

[0017] Optionally, the using the real distance and the measured distance between the target terminal and the 5G base station to train the LSSVM initial model to obtain the LSSVM revised model includes:

[0018] The measured distance between the target terminal and the 5G base station is selected as the input of the LSSVM initial model, the real distance between the target terminal and the 5G base station is selected as the output, the LSSVM initial model is trained, and the LSSVM revised model is obtained.

[0019] Optionally, before using the corrected distance as a measurement input of the error state Kalman filter and constructing a measurement equation by combining the estimated distance between the target terminal and the 5G base station obtained by using the IMU with the difference between the measured distance, the method further includes:

[0020] Step 1: Initialize the state of the IMU device, which includes the position, velocity, attitude, accelerometer and gyroscope measurements, and set the sampling time interval;

[0021] Step 2: In each sampling period, the acceleration is calculated based on the measured value of the accelerometer, and the speed at the previous moment and the sampling time interval are combined to calculate the speed at the current moment by integration;

[0022] Step 3: Calculate the angular velocity using the gyroscope's measurement value, and calculate the current attitude by integrating the attitude at the previous moment and the sampling time interval;

[0023] Step 4: Combine the current speed, posture and the position at the previous moment to calculate the current position by integration;

[0024] Step 5: Repeat steps 2 to 4 to update the state of the IMU in each sampling period.

[0025] Optionally, the preset Kalman state update equation is expressed by the following formula:

[0026]

[0027] Among them, X k is the updated state at time k, is the prior state estimate at time k, K is the Kalman gain, d k is the corrected distance, h is the estimated distance between the target terminal and the 5G base station obtained by IMU, satisfying h=||p k -c||,p k is the target terminal position calculated by the inertial navigation system, and c is the position of the 5G base station.

[0028] Another embodiment of the present application provides a tightly coupled positioning system of 5G and IMU based on LSSVM, the system comprising:

[0029] An acquisition module is used to obtain the measured distance between the target terminal and the 5G base station;

[0030] A construction module is used to construct an LSSVM initial model, and train the LSSVM initial model using the actual distance and the measured distance between the target terminal and the 5G base station to obtain an LSSVM revised model;

[0031] A correction module, used for taking the measured distance as the input of the LSSVM correction model, and correcting the measured distance by the LSSVM correction model to obtain a corrected distance;

[0032] A construction module, used to use the corrected distance as a measurement input of an error state Kalman filter, and to construct a measurement equation by combining the estimated distance between the target terminal and the 5G base station obtained by using the IMU and the difference between the actual distance;

[0033] The determination module is used to determine the target positioning information of the target terminal by using the measurement equation and the preset Kalman state update equation.

[0034] Optionally, the obtaining module includes:

[0035] The measuring unit is used to measure the actual distance between the target terminal and the 5G base station using the 5G ranging module.

[0036] Yet another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, wherein the computer program is configured to implement any of the above methods when executed.

[0037] Another embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to implement any of the above methods.

[0038] Compared with the prior art, the present invention first obtains the measured distance between the target terminal and the 5G base station; constructs an LSSVM initial model, uses the real distance and the measured distance between the target terminal and the 5G base station to train the LSSVM initial model, and obtains an LSSVM correction model; uses the measured distance as the input of the LSSVM correction model, and corrects the measured distance through the LSSVM correction model to obtain a corrected distance; uses the corrected distance as the measurement input of the error state Kalman filter, and combines the estimated distance between the target terminal and the 5G base station obtained by using the IMU, and constructs a measurement equation with the difference between the measured distance; uses the measurement equation and the preset Kalman state update equation to determine the target positioning information of the target terminal. It realizes the efficient fusion of 5G and IMU data by combining the LSSVM and ESKF algorithms, significantly improves the positioning accuracy and reliability, and has broad application prospects and significant technical advantages. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A hardware structure block diagram of a computer terminal for a tightly coupled positioning method of 5G and IMU based on LSSVM provided in an embodiment of the present invention;

[0040] Figure 2 A flowchart of a tightly coupled positioning method of 5G and IMU based on LSSVM provided in an embodiment of the present invention;

[0041] Figure 3 A schematic diagram of the full process steps of a 5G and IMU tightly coupled positioning method based on LSSVM provided in an embodiment of the present invention;

[0042] Figure 4A structural schematic diagram of a 5G and IMU tightly coupled positioning system based on LSSVM provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0043] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, but should not be construed as limiting the present invention.

[0044] The embodiment of the present invention first provides a tightly coupled positioning method of 5G and IMU based on LSSVM, which can be applied to electronic devices such as computer terminals, specifically ordinary computers, tablets, etc.

[0045] The following describes it in detail by taking running on a computer terminal as an example. Figure 1 The hardware structure block diagram of a computer terminal for a tightly coupled positioning method of 5G and IMU based on LSSVM provided in an embodiment of the present invention. Figure 1 As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0046] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any one of the confidential communication methods for big data.

[0047] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0048] The internal memory provides an environment for the operation of computer programs in non-volatile storage media. When the computer program is executed by the processor, the processor can execute any confidential communication method for big data.

[0049] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 1 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0050] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0051] LSSVM (Least Squares Support Vector Machine) is a regression algorithm based on statistical learning theory, proposed by Suykens and Van Gestel in 2002. It is a variant of support vector machine (SVM), mainly used to solve regression problems (i.e. SVR, Support Vector Regression), and can also be used for classification problems. The key idea of ​​LSSVM is to remove the error term in the traditional SVM from the loss function, convert it into a least squares problem, and solve it by minimizing a quadratic loss function. The advantage of doing this is that a closed form solution can be obtained, which is more computationally efficient and more effective for large-scale data sets.

[0052] OTDOA (Observed Time Difference of Arrival) is a positioning technology used in 5G networks. It determines the location of a target terminal by measuring the time difference between signals received by the target terminal or user equipment (UE) from different base stations (BS). This technology is particularly important in 5G networks because it can provide more accurate indoor positioning capabilities than traditional GPS.

[0053] See also Figure 2 , Figure 2 A flow chart of a tightly coupled positioning method of 5G and IMU based on LSSVM provided in an embodiment of the present invention may include the following steps:

[0054] S201: Obtain the measured distance between the target terminal and the 5G base station.

[0055] Specifically, obtaining the measured distance between the target terminal and the 5G base station may include:

[0056] The 5G ranging module is used to measure the actual distance between the target terminal and the 5G base station.

[0057] Among them, the 5G ranging module is a device that uses 5G communication technology to measure distance. The 5G ranging module can adopt a variety of ranging principles, such as calculating the distance between the two by measuring the time difference between the signal transmitted from the 5G base station to the target terminal and returning to the base station, and then multiplying it by the speed of light. Or estimate the distance based on the attenuation degree of the signal during propagation, and this application does not limit it here.

[0058] S202: Construct an LSSVM initial model, and use the actual distance and measured distance between the target terminal and the 5G base station to train the LSSVM initial model to obtain a LSSVM revised model.

[0059] Specifically, there is a training set x i is the measured distance obtained by the 5G ranging module, which is used as the input value of the LSSVM initial model. i is the actual distance between the target terminal and the 5G base station, as the expected output value of the LSSVM model, and l is the number of samples in the training set. By mapping the data in the sample to a high-dimensional space, the regression equation can be obtained:

[0060] y i =w T φ(x i )+b

[0061] Among them, w is the weight vector, φ(x i ) is the mapping between the input data and the high-dimensional feature space, which converts the nonlinear samples into linearly separable data. T represents the matrix transposition of the weight vector, and b is the deviation.

[0062] The LSSVM initial model replaces the non-equality constraints of the SVM optimization problem with equality constraints. The LSSVM initial model with equality constraints is described as:

[0063]

[0064] Among them, η is the regularization parameter, ξ i is the random fitting error.

[0065] The Lagrangian method is introduced to solve the optimization problem in the above formula, and the constructor is shown as follows:

[0066]

[0067] Among them, L is the Lagrangian function, α i is the Lagrange multiplier. Taking partial derivatives of the above formula, we can get:

[0068]

[0069] The decision function definition is as follows:

[0070]

[0071] Among them, y j is the 5G ranging information correction value, H(x i ,x j ) is the kernel function, x j is the measured value obtained by the 5G ranging module during the positioning of the target terminal. The Gaussian radial basis function is selected as the kernel function, and the kernel function width is σ, then the kernel function is as shown in the formula:

[0072]

[0073] Finally, the measured distance between the target terminal and the 5G base station is selected as the input of the LSSVM initial model, the real distance between the target terminal and the 5G base station is selected as the output, the LSSVM initial model is trained, and the LSSVM revised model is obtained.

[0074] S203: taking the measured distance as the input of the LSSVM correction model, and correcting the measured distance by the LSSVM correction model to obtain a corrected distance.

[0075] Exemplarily, the above steps can be divided into the following three sub-steps:

[0076] (1) In the data collection scenario, use the 5G ranging module to measure different real distances (1, 2, ..., 30m) 300 times and take the average value as the measured value of different real distances. (Here, the typical maximum distance of the 5G positioning base station is 30m);

[0077] (2) Initializing the parameters of the LSSVM initial model, and inputting 30 true values ​​and their corresponding 30 measured values ​​into the LSSVM initial model for training to obtain the LSSVM revised model;

[0078] (3) The actual measured values ​​of 5G terminal ranging (including non-line-of-sight measurement) during terminal movement are input into the trained LSSVM correction model for prediction to obtain more accurate 5G ranging information.

[0079] S204: Use the corrected distance as the measurement input of the error state Kalman filter, and construct a measurement equation by combining the estimated distance between the target terminal and the 5G base station obtained by using the IMU and the difference between the actual distance.

[0080] Specifically, the mathematical model of IMU positioning principle can be expressed as:

[0081]

[0082] Among them, the IMU positioning principle involves a typical iterative process, and the transfer process from stage k-1 to stage k is used as an example of an iterative process to characterize the whole. k is used in the subscript to indicate the number of stages, p indicates position, v indicates velocity, q indicates attitude, and is generally expressed in quaternions, T indicates time, R indicates rotation transformation matrix, a indicates acceleration, Ω indicates quaternion transformation matrix, ω indicates angular velocity, and the subscript indicates the coordinate system.

[0083] Therefore, the IMU dead reckoning process can be divided into the following steps:

[0084] Step 1: Initialize the state of the IMU device, which includes the position, velocity, attitude, accelerometer and gyroscope measurements, and set the sampling time interval;

[0085] Step 2: In each sampling period, the acceleration is calculated based on the measured value of the accelerometer, and the speed at the previous moment and the sampling time interval are combined to calculate the speed at the current moment by integration;

[0086] Step 3: Calculate the angular velocity using the gyroscope's measurement value, and calculate the current attitude by integrating the attitude at the previous moment and the sampling time interval;

[0087] Step 4: Combine the current speed, posture and the position at the previous moment to calculate the current position by integration;

[0088] Step 5: Repeat steps 2 to 4 to update the state of the IMU in each sampling period.

[0089] The terminal clock has a built-in IMU chip, which can output the terminal's three-axis acceleration and three-axis angular beam information; the 5G module can measure the Euclidean distance of the terminal from each 5G base station. The tight combination uses 5G and IMU as a measurement sensor, and uses the terminal position information obtained by IMU to estimate the distance between the terminal and the 5G base station, and combines it with the distance information between the terminal and the 5G base station measured by 5G. The 5G and IMU tight combination positioning method mainly consists of the 5G ranging value correction part and the data fusion part.

[0090] Use ESKF to tightly combine 5G and IMU. Here we design the position error δp of the target terminal. N (3D), velocity error δv of target point N (3D), misalignment angle (3D), acceleration bias error δb a (3D) and gyro bias error δb g (3D) is the state vector, and the state equation is obtained:

[0091]

[0092] in, F(t) is the dynamic matrix, G(t) is the noise input coefficient matrix, and s(t) is the noise.

[0093] Since IMU usually samples data at a high rate, it is necessary to convert the continuous-time system equations into the corresponding discrete system equations:

[0094] δX k =ψ k-1 δX k-1 +s k- 1

[0095] ψ k-1 ≈I+F(t)T s

[0096] Among them, X k is the updated state at time k, ψ k-1 is the state transfer matrix, X k-1 is the state at time k-1, s k-1 is the noise at time k-1, and I is the unit matrix.

[0097] The terminal position information obtained by IMU is used to estimate the distance between the terminal and the 5G base station, and the difference with the 5G ranging information is used to construct the measurement equation.

[0098] S205: Determine the target positioning information of the target terminal by using the measurement equation and the preset Kalman state update equation.

[0099] Specifically, the measurement input of ESKF is the 5G ranging correction value d of the target terminal from each 5G base station after being corrected by the LSSVM model. k , the preset Kalman state update equation is expressed by the following formula:

[0100]

[0101] Among them, X k is the updated state at time k, is the prior state estimate at time k, K is the Kalman gain, d k is the corrected distance, h is the estimated distance between the target terminal and the 5G base station obtained by IMU, satisfying h=||p k -c||,p k is the target terminal position calculated by the inertial navigation system, and c is the position of the 5G base station.

[0102] Summarizing the above steps, see Figure 3 , Figure 3 A schematic diagram of the full process steps of a 5G and IMU tightly coupled positioning method based on LSSVM provided in an embodiment of the present invention, Figure 3 The above steps involved in this application are shown in the figure except for the terminal sensor, which is the basic condition for the implementation of this application. Figure 3 Through the whole process steps, this application can complete the tightly coupled positioning method of 5G and IMU based on LSSVM.

[0103] The beneficial effects of this application include:

[0104] (1) The LSSVM model is used to correct the 5G positioning base station ranging data, improving the ranging accuracy. Through the training of measured values ​​and true values, the LSSVM correction model can effectively correct the errors in 5G ranging, thereby obtaining more accurate ranging information. This machine learning-based correction method can adapt to complex and changeable wireless propagation environments, improve the robustness of the positioning system, and make 5G positioning, which was originally unable to be accurately measured under non-line-of-sight conditions, more accurate.

[0105] (2) The tightly coupled fusion positioning method based on ESKF realizes the effective fusion of 5G and IMU data. The ESKF algorithm can handle the noise and error of IMU and 5G ranging data, and optimizes the positioning results through state estimation and Kalman gain calculation. This tightly coupled method not only improves the positioning accuracy, but also enhances the system's anti-interference ability.

[0106] (3) This application can provide high-precision positioning services within the coverage of the 5G network, and is particularly suitable for complex environments such as indoors and in urban canyons. Compared with traditional GPS positioning, this method is not affected by satellite signal obstruction and has higher availability and reliability. It should be noted that this method is applicable to end-side 5G positioning methods based on triangulation, including but not limited to 5G OTDOA and 5G positioning by similar methods such as Muti-RTT. It is a method patent with strong versatility rather than a method limited to a single positioning capability.

[0107] (4) This application also has low computational complexity and high real-time performance, and is suitable for positioning application scenarios that require rapid response, such as autonomous driving, robot navigation, smart wearable devices, etc.

[0108] In summary, the invention to be protected in this application realizes the efficient fusion of 5G and IMU data by combining LSSVM and ESKF algorithms, significantly improves positioning accuracy and reliability, and has broad application prospects and significant technical advantages.

[0109] Compared with the prior art, the present invention first obtains the measured distance between the target terminal and the 5G base station; constructs an LSSVM initial model, uses the real distance and the measured distance between the target terminal and the 5G base station to train the LSSVM initial model, and obtains an LSSVM correction model; uses the measured distance as the input of the LSSVM correction model, and corrects the measured distance through the LSSVM correction model to obtain a corrected distance; uses the corrected distance as the measurement input of the error state Kalman filter, and combines the estimated distance between the target terminal and the 5G base station obtained by using the IMU, and constructs a measurement equation with the difference between the measured distance; uses the measurement equation and the preset Kalman state update equation to determine the target positioning information of the target terminal. It realizes the efficient fusion of 5G and IMU data by combining the LSSVM and ESKF algorithms, significantly improves the positioning accuracy and reliability, and has broad application prospects and significant technical advantages.

[0110] Another embodiment of the present application provides a tightly coupled positioning system of 5G and IMU based on LSSVM, such as Figure 4 A structural schematic diagram of a tightly coupled positioning system of 5G and IMU based on LSSVM is shown, and the system includes:

[0111] An obtaining module 401 is used to obtain a measured distance between a target terminal and a 5G base station;

[0112] A construction module 402 is used to construct an LSSVM initial model, and train the LSSVM initial model using the actual distance and the measured distance between the target terminal and the 5G base station to obtain an LSSVM revised model;

[0113] A correction module 403 is used to use the measured distance as an input of the LSSVM correction model, and correct the measured distance through the LSSVM correction model to obtain a corrected distance;

[0114] A construction module 404 is used to use the corrected distance as a measurement input of an error state Kalman filter, and to construct a measurement equation by combining the estimated distance between the target terminal and the 5G base station obtained by using the IMU and the difference between the actual distance;

[0115] The determination module 405 is used to determine the target positioning information of the target terminal by using the measurement equation and the preset Kalman state update equation.

[0116] Specifically, the acquisition module includes:

[0117] The measuring unit is used to measure the actual distance between the target terminal and the 5G base station using the 5G ranging module.

[0118] Compared with the prior art, the present invention first obtains the measured distance between the target terminal and the 5G base station; constructs an LSSVM initial model, uses the real distance and the measured distance between the target terminal and the 5G base station to train the LSSVM initial model, and obtains an LSSVM correction model; uses the measured distance as the input of the LSSVM correction model, and corrects the measured distance through the LSSVM correction model to obtain a corrected distance; uses the corrected distance as the measurement input of the error state Kalman filter, and combines the estimated distance between the target terminal and the 5G base station obtained by using the IMU, and constructs a measurement equation with the difference between the measured distance; uses the measurement equation and the preset Kalman state update equation to determine the target positioning information of the target terminal. It realizes the efficient fusion of 5G and IMU data by combining the LSSVM and ESKF algorithms, significantly improves the positioning accuracy and reliability, and has broad application prospects and significant technical advantages.

[0119] An embodiment of the present invention further provides a storage medium, in which a computer program is stored, wherein the computer program is configured to implement the steps in the above method embodiment when running.

[0120] Specifically, in this embodiment, the above storage medium may be configured to store a computer program for performing the following steps:

[0121] S201: Obtaining the measured distance between the target terminal and the 5G base station;

[0122] S202: construct an LSSVM initial model, and use the actual distance and the measured distance between the target terminal and the 5G base station to train the LSSVM initial model to obtain an LSSVM revised model;

[0123] S203: taking the measured distance as the input of the LSSVM correction model, and correcting the measured distance by the LSSVM correction model to obtain a corrected distance;

[0124] S204: Using the corrected distance as a measurement input of the error state Kalman filter, and constructing a measurement equation based on the difference between the estimated distance between the target terminal and the 5G base station obtained by using the IMU and the actual distance;

[0125] S205: Determine the target positioning information of the target terminal by using the measurement equation and the preset Kalman state update equation.

[0126] Specifically, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0127] Compared with the prior art, the present invention first obtains the measured distance between the target terminal and the 5G base station; constructs an LSSVM initial model, uses the real distance and the measured distance between the target terminal and the 5G base station to train the LSSVM initial model, and obtains an LSSVM correction model; uses the measured distance as the input of the LSSVM correction model, and corrects the measured distance through the LSSVM correction model to obtain a corrected distance; uses the corrected distance as the measurement input of the error state Kalman filter, and combines the estimated distance between the target terminal and the 5G base station obtained by using the IMU, and constructs a measurement equation with the difference between the measured distance; uses the measurement equation and the preset Kalman state update equation to determine the target positioning information of the target terminal. It realizes the efficient fusion of 5G and IMU data by combining the LSSVM and ESKF algorithms, significantly improves the positioning accuracy and reliability, and has broad application prospects and significant technical advantages.

[0128] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in the above method embodiment.

[0129] Specifically, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0130] Specifically, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0131] S201: Obtaining the measured distance between the target terminal and the 5G base station;

[0132] S202: construct an LSSVM initial model, and use the actual distance and the measured distance between the target terminal and the 5G base station to train the LSSVM initial model to obtain an LSSVM revised model;

[0133] S203: taking the measured distance as the input of the LSSVM correction model, and correcting the measured distance by the LSSVM correction model to obtain a corrected distance;

[0134] S204: Using the corrected distance as a measurement input of the error state Kalman filter, and constructing a measurement equation based on the difference between the estimated distance between the target terminal and the 5G base station obtained by using the IMU and the actual distance;

[0135] S205: Determine the target positioning information of the target terminal by using the measurement equation and the preset Kalman state update equation.

[0136] Compared with the prior art, the present invention first obtains the measured distance between the target terminal and the 5G base station; constructs an LSSVM initial model, uses the real distance and the measured distance between the target terminal and the 5G base station to train the LSSVM initial model, and obtains an LSSVM correction model; uses the measured distance as the input of the LSSVM correction model, and corrects the measured distance through the LSSVM correction model to obtain a corrected distance; uses the corrected distance as the measurement input of the error state Kalman filter, and combines the estimated distance between the target terminal and the 5G base station obtained by using the IMU, and constructs a measurement equation with the difference between the measured distance; uses the measurement equation and the preset Kalman state update equation to determine the target positioning information of the target terminal. It realizes the efficient fusion of 5G and IMU data by combining the LSSVM and ESKF algorithms, significantly improves the positioning accuracy and reliability, and has broad application prospects and significant technical advantages.

[0137] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0138] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0139] In the several embodiments provided by the present invention, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0140] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0141] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0142] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present invention. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0143] The embodiments of the present invention are described in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A tightly coupled positioning method of 5G and IMU based on LSSVM, characterized in that: The method comprises: Obtain the measured distance between the target terminal and the 5G base station; Construct an LSSVM initial model, and use the actual distance and the measured distance between the target terminal and the 5G base station to train the LSSVM initial model to obtain an LSSVM revised model; The measured distance is used as the input of the LSSVM correction model, and the measured distance is corrected by the LSSVM correction model to obtain a corrected distance; The corrected distance is used as the measurement input of the error state Kalman filter, and the measurement equation is constructed by combining the estimated distance between the target terminal and the 5G base station obtained by using the IMU and the difference between the measured distance; The target positioning information of the target terminal is determined by using the measurement equation and the preset Kalman state update equation.

2. The method according to claim 1, characterized in that The obtaining of the measured distance between the target terminal and the 5G base station includes: The 5G ranging module is used to measure the actual distance between the target terminal and the 5G base station.

3. The method according to claim 2, characterized in that The LSSVM initial model replaces the non-equality constraints of the SVM optimization problem with equality constraints. The LSSVM initial model with equality constraints is expressed by the following formula: Among them, w is the weight vector, η is the regularization parameter, ξ i is the random fitting error, represents the regression equation, x i is the measured distance, y i is the actual distance between the target terminal and the 5G base station, φ(x i ) is the mapping between the input data of the LSSVM initial model and the high-dimensional feature space, and b is the deviation.

4. The method according to claim 3, characterized in that The method of using the actual distance and the measured distance between the target terminal and the 5G base station to train the LSSVM initial model to obtain the LSSVM revised model includes: The measured distance between the target terminal and the 5G base station is selected as the input of the LSSVM initial model, the real distance between the target terminal and the 5G base station is selected as the output, the LSSVM initial model is trained, and the LSSVM revised model is obtained.

5. The method according to claim 4, characterized in that Before constructing a measurement equation by using the corrected distance as a measurement input of the error state Kalman filter and combining the estimated distance between the target terminal and the 5G base station obtained by using the IMU with the difference between the actual distance, the method further includes: Step 1: Initialize the state of the IMU device, which includes the position, velocity, attitude, accelerometer and gyroscope measurements, and set the sampling time interval; Step 2: In each sampling period, the acceleration is calculated based on the measured value of the accelerometer, and the speed at the previous moment and the sampling time interval are combined to calculate the speed at the current moment by integration; Step 3: Calculate the angular velocity using the gyroscope's measurement value, and calculate the current attitude by integrating the attitude at the previous moment and the sampling time interval; Step 4: Combine the current speed, posture and the position at the previous moment to calculate the current position by integration; Step 5: Repeat steps 2 to 4 to update the state of the IMU in each sampling period.

6. The method according to claim 5, characterized in that The preset Kalman state update equation is expressed by the following formula: Among them, X k is the updated state at time k, is the prior state estimate at time k, K is the Kalman gain, d k is the corrected distance, h is the estimated distance between the target terminal and the 5G base station obtained by IMU, satisfying h=∥p k -c∥,p k is the target terminal position calculated by the inertial navigation system, and c is the position of the 5G base station.

7. A tightly coupled positioning system of 5G and IMU based on LSSVM, characterized in that: The system comprises: An acquisition module is used to obtain the measured distance between the target terminal and the 5G base station; A construction module is used to construct an LSSVM initial model, and train the LSSVM initial model using the actual distance and the measured distance between the target terminal and the 5G base station to obtain an LSSVM revised model; A correction module, used for taking the measured distance as the input of the LSSVM correction model, and correcting the measured distance by the LSSVM correction model to obtain a corrected distance; A construction module, used to use the corrected distance as a measurement input of an error state Kalman filter, and to construct a measurement equation by combining the estimated distance between the target terminal and the 5G base station obtained by using the IMU and the difference between the actual distance; The determination module is used to determine the target positioning information of the target terminal by using the measurement equation and the preset Kalman state update equation.

8. The system according to claim 7, characterized in that The obtaining module comprises: The measuring unit is used to measure the actual distance between the target terminal and the 5G base station using the 5G ranging module.

9. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to implement the method according to any one of claims 1 to 6 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the computer program to implement the method according to any one of claims 1 to 6.

Images