Beidou satellite assisted positioning method based on 5G network
By building multiple sets of 5G base stations in dense urban environments and using predicted coordinate models, combined with CNN and RNN technologies, the problem of reduced positioning accuracy in signal occlusion and dynamic environments is solved, and higher positioning accuracy and reliability are achieved.
Patent Information
- Application Number
- CN202411059819.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-19
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In dense urban environments, due to the obstruction of buildings and obstacles, the satellite signal quality is affected, resulting in an increase in positioning error. When relying on 5G base stations to locate, the uneven layout of the base station and the complexity of signal propagation lead to additional errors. Traditional methods are difficult to deal with dynamics. The signal changes in the environment, especially when moving at high speed, the positioning accuracy decreases.
Build multiple groups of 5G base stations to form a positioning platform, collect positioning data through inspection robots, adopt predictive coordinate model and loss function minimization algorithm, combine CNN and RNN technologies to fusion signal strength attenuation model and multi-sensor data, optimize path planning, and reduce Error accumulation.
Improve the robustness and accuracy of the positioning system, reduce the probability of positioning failure caused by incomplete signal coverage, enhance the consistency and accuracy of positioning data, especially in dynamic environments, and improve the reliability of positioning. Sex and stability.
Smart Images

Figure CN118981035A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of communication technology, and in particular to a Beidou satellite assisted positioning method based on a 5G network. Background Art
[0002] In recent years, with the rapid development and application promotion of the fifth generation mobile communication technology 5G, its high bandwidth, low latency and large-scale connection characteristics have provided a basis for various emerging application scenarios. In the field of positioning technology, the combination of 5G network and global navigation satellite system GNSS has become one of the research hotspots. Although traditional satellite positioning technology has achieved a wide range of positioning services worldwide, its positioning accuracy and reliability are greatly limited in complex scenarios such as urban canyons and indoor environments due to signal obstruction and multipath effects. In order to overcome these limitations, researchers have explored a variety of methods to enhance positioning accuracy, including collaborative positioning technology with ground wireless communication networks.
[0003] With its advanced air interface technology and flexible network architecture, 5G networks provide new possibilities for achieving high-precision positioning. Base stations in 5G networks can not only provide high-speed data transmission services, but also serve as positioning reference points, using their precise time synchronization capabilities and powerful signal processing capabilities to improve positioning accuracy. In addition, 5G networks can also be integrated with a variety of positioning technologies, including ultra-wideband UWB and inertial navigation system INS, to further improve positioning performance. At present, the combination of 5G and GNSS has been applied to the fields of vehicle autonomous driving, drone navigation, and logistics tracking, and has achieved remarkable results. Summary of the invention
[0004] In view of the above existing problems, the present invention is proposed.
[0005] Therefore, the present invention provides a Beidou satellite-assisted positioning method based on a 5G network to solve the problem that in a dense urban environment, the quality of satellite signals will be affected due to obstruction by buildings and other obstacles, resulting in increased positioning errors. When relying solely on 5G base stations for positioning, additional positioning errors will also be caused due to the uneven layout of base stations and the complexity of signal propagation conditions. In addition, traditional positioning methods are difficult to effectively handle signal changes in dynamic environments, especially in the case of high-speed movement, and the positioning accuracy will be significantly reduced.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:
[0007] In a first aspect, an embodiment of the present invention provides a Beidou satellite assisted positioning method based on a 5G network, which includes:
[0008] Build multiple groups of 5G base stations in the positioning area to form a 5G network platform with positioning function;
[0009] The inspection robot detects and locates in the 5G base station area, obtains positioning data, and processes the positioning data;
[0010] Building a prediction coordinate model based on the processed positioning data, applying the processed positioning data to the prediction coordinate model, performing hybrid calculation on the positioning data, and obtaining the prediction positioning coordinates;
[0011] Based on the predicted positioning coordinates, a loss function is constructed to minimize the error between the predicted coordinates and the true coordinates to obtain the error positioning coordinates;
[0012] Obtain the optimal positioning result in the error positioning coordinates and output the optimal positioning result.
[0013] As a preferred solution of the Beidou satellite assisted positioning method based on 5G network described in the present invention, wherein: multiple groups of 5G base stations are constructed in the positioning area to form a 5G network platform with positioning function, and the specific steps are as follows:
[0014] Based on the positioning accuracy requirements and base station signal coverage, the number of required 5G base stations is calculated as follows:
[0015]
[0016] Where N represents the number of 5G base stations required, A represents the area to be covered in the positioning area, R represents the maximum effective coverage radius of each base station, and π represents pi;
[0017] The distance, signal frequency and speed of light between each base station are collected to construct the path loss function, which is expressed as:
[0018]
[0019] Where L(d) represents the path loss, which indicates the degree to which the signal strength attenuates as the distance increases, f represents the signal frequency, d represents the distance, c represents the speed of light, log 10 represents the logarithmic function with base 10;
[0020] Based on the path loss function, the signal strength attenuation model is used to calculate the strength of the base station signal at different distances. The expression is:
[0021] P r (d) = P t +G t +G r -L(d)-η;
[0022] Among them, P r (d) represents the function of the received signal strength changing with the distance d, i.e., the signal strength information, P tIndicates the base station transmission power, G t represents the base station antenna gain, G r represents the receiving antenna gain, L(d) represents the path loss function, and η represents a random variable;
[0023] Based on the number N of 5G base stations and signal strength information P r (d) Install 5G base stations in selected areas to provide positioning, receive BeiDou satellite signals and perform positioning calculations;
[0024] The positioning data processing module is integrated inside the base station, which can clean and standardize the received signals;
[0025] transmitting the positioning data from the base station to the central processing system according to the transmission protocol;
[0026] Integrate all base stations and central processing systems to build a 5G network platform.
[0027] As a preferred solution of the Beidou satellite assisted positioning method based on the 5G network described in the present invention, the inspection robot in the 5G base station area performs detection and positioning, obtains positioning data, and processes the positioning data. The specific steps are as follows:
[0028] The robot patrols the 5G base station area to receive signal strength information, Beidou satellite positioning data, ultra-wideband positioning data, and inertial measurement unit data;
[0029] Use LiDAR to obtain environmental information around 5G base stations, and use SLAM to convert environmental information into obstacle locations on the map;
[0030] Standardize the collected Beidou satellite positioning data, inertial measurement unit data, ultra-wideband positioning data and signal strength information;
[0031] Set the signal strength information after normalization as P st (d);
[0032] The multi-sensor data fusion algorithm is used to fuse the standardized signal strength information, Beidou satellite positioning data, ultra-wideband positioning data and inertial measurement unit data. The expression is:
[0033] x f =K(P st (d),GPS,IMU,UWB);
[0034] Among them, x f represents the fused positioning coordinates, K represents the fusion algorithm, GPS represents the Beidou satellite positioning data, IMU represents the inertial measurement unit data, and UWB represents the ultra-wideband positioning data.
[0035] As a preferred solution of the Beidou satellite assisted positioning method based on 5G network described in the present invention, the fusion algorithm is expressed as:
[0036]
[0037] Among them, K represents the fusion algorithm, that is, the positioning coordinates after fusion, i represents the index of sensor data, and w i represents the weight of the i-th sensor, H i represents the Jacobian matrix of the i-th sensor, R i represents the covariance matrix of the i-th sensor, z i represents the actual observation value of the i-th sensor;
[0038] The random tree RRT algorithm is used to find the path from the starting point to the end point while avoiding obstacles;
[0039] Set the starting point to q s , the end point is q g ;
[0040] Randomly select a point q in the configuration space r ;
[0041] Find the distance q in the tree r The nearest node q n ;
[0042] From q n To q r Move a certain distance δ to generate a new node qne w ;
[0043] Check from q n To qne w Whether the path passes through any obstacles;
[0044] When no obstacles are crossed, w Add to number and connect it to q n ;
[0045] Set the number of iterations and the threshold PP. When the distance between the target node and the current node is less than PP, it means q new Close enough to the end point q new , then stop generating new nodes;
[0046] When the distance between the target node and the current node is greater than or equal to PP, it means q new If there is still some distance to go, the path from the starting point to the end point is searched repeatedly until the set number of iterations is reached;
[0047] Use smoothing algorithm to optimize the path and get the best path.
[0048] As a preferred solution of the Beidou satellite-assisted positioning method based on the 5G network described in the present invention, wherein: a predicted coordinate model is constructed based on the processed positioning data, the processed positioning data is applied to the predicted coordinate model, and a hybrid calculation is performed on the positioning data to obtain the predicted positioning coordinates. The specific steps are:
[0049] The prediction coordinate model is constructed by combining convolutional neural network CNN and recurrent neural network RNN;
[0050] The prediction coordinate model structure is set to include input layer, hidden layer, pooling layer, convolution layer and output layer;
[0051] The fused positioning coordinates x f Input the prediction coordinate model and output the prediction coordinate;
[0052] The prediction coordinate model is expressed as:
[0053]
[0054] Among them, x p represents the predicted positioning coordinates, W out represents the output layer weight matrix, W c Represents the convolutional layer weight matrix, W p represents the pooling layer weight matrix, W h represents the hidden layer weight matrix, W in represents the input layer weight matrix, dΩ represents the tiny volume element in the spatial domain where the convolution kernel acts, represents the weighted sum operation of the four sensor data, w k represents the weight of the kth sensor, z k represents the observation value of the kth sensor, μ k represents the mean of the kth sensor observations, σ k represents the standard deviation of the kth sensor observation, f Ω It represents the integral operation on the spatial domain of the convolution kernel, π represents the circumference of a circle, and e represents the base of the natural logarithm.
[0055] As a preferred solution of the Beidou satellite assisted positioning method based on 5G network described in the present invention, wherein: based on the predicted positioning coordinates, a loss function is constructed to minimize the error between the predicted coordinates and the true coordinates to obtain the error positioning coordinates, and the specific steps are as follows:
[0056] Construct the loss function L based on weighted square error, mean square error and regularization t , the expression is:
[0057]
[0058] Among them, w k represents the weight of the kth sensor, β k Indicates the proportional factor for adjusting the contribution of the x-axis and y-axis prediction errors, x k and k represents the predicted coordinates corresponding to the k-th sensor data, x k t and k t represents the actual coordinates corresponding to the kth sensor, Λ k represents the noise standard deviation of the kth sensor, γ represents the regularization coefficient, N h represents the number of neurons in the hidden layer, w j represents the weight vector of the jth hidden layer neuron;
[0059] Input the predicted positioning coordinates into the loss function formula, calculate the error between the predicted coordinates and the true value coordinates, and get the error positioning coordinates x fe .
[0060] As a preferred solution of the Beidou satellite assisted positioning method based on 5G network described in the present invention, wherein: obtaining the optimal positioning result in the error positioning coordinates, and outputting the optimal positioning result, the specific steps are:
[0061] Constructing nonlinear transformation function T(x fe ), the calculation formula is:
[0062]
[0063] Among them, exp represents the natural exponential function, α is a positive real number parameter used to adjust the shape of the nonlinear transformation, ln represents the natural logarithm function, and β is a positive real number parameter;
[0064] The penalty term B based on the Bayesian information criterion is calculated as follows:
[0065] B = γ·log(N h );
[0066] Among them, γ represents the parameter that controls the intensity of the penalty, N h represents the number of hidden layer neurons, and log represents the natural logarithm.
[0067] As a preferred solution of the Beidou satellite assisted positioning method based on 5G network described in the present invention, wherein: based on the nonlinear transformation function T(x fe ) and the penalty term B of the Bayesian information criterion to construct an optimization function, which is expressed as:
[0068]
[0069] Among them, O(x fe ) represents the output of the optimization function, T(x fe ) represents the nonlinear transformation function, σ k represents the standard deviation of the kth sensor observation, B represents the penalty term based on the Bayesian Information Criterion, μ fe represents the mean of the error positioning coordinates, σ fe represents the standard deviation of the error positioning coordinates, Represents the normal distribution function.
[0070] In a second aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the Beidou satellite-assisted positioning method based on the 5G network as described in the first aspect of the present invention is implemented.
[0071] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, wherein: when the computer program is executed by a processor, any step of the Beidou satellite-assisted positioning method based on a 5G network as described in the first aspect of the present invention is implemented.
[0072] The beneficial effects of the present invention are as follows: the present invention ensures good signal coverage in the positioning area by constructing a 5G network platform with positioning function, enhances the robustness of the positioning system, reduces the probability of positioning failure caused by incomplete signal coverage, collects diversified positioning data through inspection robots, and adopts standardized processing and multi-sensor data fusion algorithms to improve the consistency and accuracy of positioning data, reduce the error influence of a single sensor, and improve the accuracy and reliability of positioning. The prediction coordinate model is constructed by combining CNN and RNN technology to further improve the positioning accuracy, especially in dynamic environments, it can respond quickly and provide accurate prediction results, minimize errors through loss functions, and further improve the accuracy and reliability of positioning, especially for positioning tasks in complex environments, it can effectively reduce error accumulation, and finally, by quantifying the reliability of positioning results, it can provide users with intuitive feedback on the positioning quality, so that users can make decisions based on actual conditions. BRIEF DESCRIPTION OF THE DRAWINGS
[0073] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.
[0074] Figure 1This is a flow chart of the Beidou satellite-assisted positioning method based on 5G network in Example 1.
[0075] Figure 2 This is a flow chart of the optimization function in Example 1. DETAILED DESCRIPTION
[0076] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.
[0077] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0078] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.
[0079] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, and provides a Beidou satellite assisted positioning method based on a 5G network, comprising the following steps:
[0080] S1 builds multiple groups of 5G base stations in the positioning area to form a 5G network platform with positioning function;
[0081] Build multiple groups of 5G base stations in the positioning area to form a 5G network platform with positioning function. The specific steps are as follows:
[0082] Based on the positioning accuracy requirements and base station signal coverage, the number of required 5G base stations is calculated as follows:
[0083]
[0084] Where N represents the number of 5G base stations required, A represents the area to be covered in the positioning area, R represents the maximum effective coverage radius of each base station, and π represents pi;
[0085] The distance, signal frequency and speed of light between each base station are collected to construct the path loss function, which is expressed as:
[0086]
[0087] Where L(d) represents the path loss, which indicates the degree to which the signal strength attenuates as the distance increases, f represents the signal frequency, d represents the distance, c represents the speed of light, log 10 represents the logarithmic function with base 10;
[0088] Based on the path loss function, the signal strength attenuation model is used to calculate the strength of the base station signal at different distances. The expression is:
[0089] P r (d) = P t +G t +G r -L(d)-η;
[0090] Among them, P r (d) represents the function of the received signal strength changing with the distance d, i.e., the signal strength information, P t Indicates the base station transmission power, G t represents the base station antenna gain, G r represents the receiving antenna gain, L(d) represents the path loss function, and η represents a random variable;
[0091] Based on the number N of 5G base stations and signal strength information P r (d) Install 5G base stations in selected areas to provide positioning, receive BeiDou satellite signals and perform positioning calculations;
[0092] The positioning data processing module is integrated inside the base station, which can clean and standardize the received signals;
[0093] transmitting the positioning data from the base station to the central processing system according to the transmission protocol;
[0094] Integrate all base stations and central processing systems to build a 5G network platform;
[0095] P r The value range of (d) is between -100dBm and -50dBm, representing the change of signal strength from weak to strong;
[0096] When P r (d) When it is close to -50dBm, it means that the signal strength is strong and suitable for high-precision positioning;
[0097] When P r (d) When it is close to -100dBm, it means that the signal is weak and will affect the positioning accuracy.
[0098] S2 detects and locates based on the inspection robot in the 5G base station area, obtains positioning data, and processes the positioning data;
[0099] The robot patrols the 5G base station area to receive signal strength information, Beidou satellite positioning data, ultra-wideband positioning data, and inertial measurement unit data;
[0100] Use LiDAR to obtain environmental information around 5G base stations, and use SLAM to convert environmental information into obstacle locations on the map;
[0101] Standardize the collected Beidou satellite positioning data, inertial measurement unit data, ultra-wideband positioning data and signal strength information;
[0102] Set the signal strength information after normalization as P st (d), the expression is:
[0103]
[0104] Among them, P st (d) represents the function of the standardized signal intensity varying with the distance d, μ represents the average value of all signal intensities, and σ represents the standard deviation of the signal intensity;
[0105] The multi-sensor data fusion algorithm is used to fuse the standardized signal strength information, Beidou satellite positioning data, ultra-wideband positioning data and inertial measurement unit data. The expression is:
[0106] x f =K(P st (d),GPS,IMU,UWB);
[0107] Among them, x f represents the fused positioning coordinates, K represents the fusion algorithm, GPS represents the Beidou satellite positioning data, IMU represents the inertial measurement unit data, and UWB represents the ultra-wideband positioning data;
[0108] Fusion algorithm, the expression is:
[0109]
[0110] Where K represents the fusion algorithm, that is, the fused positioning coordinates, i represents the index of the sensor data, ranging from 1 to 4, corresponding to the standardized signal strength, Beidou satellite positioning data, inertial measurement unit data and ultra-wideband positioning data, respectively, and w i represents the weight of the i-th sensor, H i represents the Jacobian matrix of the i-th sensor, which represents the relationship between the sensor observation value and the state, R i represents the covariance matrix of the i-th sensor, z i represents the actual observation value of the i-th sensor;
[0111] The random tree RRT algorithm is used to find the path from the starting point to the end point while avoiding obstacles;
[0112] Set the starting point to q s , the end point is q g ;
[0113] Randomly select a point q in the configuration space r ;
[0114] Find the distance q in the tree r The nearest node q n ;
[0115] From q n To q r Move a certain distance δ to generate a new node qne w ;
[0116] Check from q n To qne w Whether the path passes through any obstacles;
[0117] When no obstacles are crossed, w Add to number and connect it to q n ;
[0118] Set the number of iterations and the threshold PP. When the distance between the target node and the current node is less than PP, it means qne w Close enough to the end w , then stop generating new nodes;
[0119] When the distance between the target node and the current node is greater than or equal to PP, it means q new If there is still some distance to go, the path from the starting point to the end point is searched repeatedly until the set number of iterations is reached;
[0120] Use smoothing algorithm to optimize the path and get the best path;
[0121] The RRT algorithm is expressed as:
[0122]
[0123] S3 builds a prediction coordinate model based on the processed positioning data, applies the processed positioning data to the prediction coordinate model, performs hybrid calculation on the positioning data, and obtains the predicted positioning coordinates;
[0124] The prediction coordinate model is constructed by combining convolutional neural network CNN and recurrent neural network RNN;
[0125] The prediction coordinate model structure is set to include input layer, hidden layer, pooling layer, convolution layer and output layer;
[0126] The fused positioning coordinates x f Input the prediction coordinate model and output the prediction coordinate;
[0127] The prediction coordinate model is expressed as:
[0128]
[0129] Among them, x p Represents the predicted positioning coordinates, which are composed of the x-axis and y-axis of the coordinate system, W out represents the output layer weight matrix, W c Represents the convolutional layer weight matrix, W p represents the pooling layer weight matrix, W h represents the hidden layer weight matrix, W in represents the input layer weight matrix, dΩ represents the tiny volume element in the spatial domain where the convolution kernel acts, represents the weighted sum operation of the four sensor data. The values of k are 1, 2, 3, and 4, which correspond to the standardized signal strength information, Beidou satellite positioning data, ultra-wideband positioning data, and inertial measurement unit data, respectively. k represents the weight of the kth sensor, z k represents the observation value of the kth sensor, μ k represents the mean of the kth sensor observations, σ k represents the standard deviation of the kth sensor observation, f Ω It represents the integral operation on the spatial domain of the convolution kernel, π represents the circumference of a circle, and e represents the base of the natural logarithm.
[0130] S4 constructs a loss function based on the predicted positioning coordinates to minimize the error between the predicted coordinates and the true coordinates, and obtains the error positioning coordinates;
[0131] Construct the loss function L based on weighted square error, mean square error and regularization t , the expression is:
[0132]
[0133] Among them, w k represents the weight of the kth sensor, β k Represents the proportional factor for adjusting the contribution of the x-axis and y-axis prediction errors, 0≤β k ≤1,x k and k represents the predicted coordinates corresponding to the k-th sensor data, x k t and k t represents the actual coordinates corresponding to the kth sensor, Λ krepresents the noise standard deviation of the kth sensor, γ represents the regularization coefficient, N h represents the number of neurons in the hidden layer, w j represents the weight vector of the jth hidden layer neuron;
[0134] Input the predicted positioning coordinates into the loss function formula, calculate the error between the predicted coordinates and the true value coordinates, and get the error positioning coordinates x fe ;
[0135] Error location coordinate x fe The value range is 0 to 1, where 0 indicates the minimum positioning error and 1 indicates the maximum positioning error.
[0136] S5 obtains the optimal positioning result in the error positioning coordinates and outputs the optimal positioning result;
[0137] Constructing nonlinear transformation function T(x fe ), the calculation formula is:
[0138]
[0139] Among them, exp represents the natural exponential function, α is a positive real number parameter used to adjust the shape of the nonlinear transformation, ln represents the natural logarithm function, and β is a positive real number parameter used to adjust x fe Bisection The sensitivity of the fraction to x is affected by the larger β value. fe More sensitive to changes in
[0140] The penalty term B based on the Bayesian information criterion is calculated as follows:
[0141] B = γ·log(N h );
[0142] Among them, γ represents the parameter that controls the intensity of the penalty, N h represents the number of neurons in the hidden layer, and log represents the natural logarithm;
[0143] Based on the nonlinear transformation function T(x fe ) and the penalty term B of the Bayesian information criterion to construct an optimization function, which is expressed as:
[0144]
[0145] Among them, O(x fe ) represents the output of the optimization function, T(x fe ) represents the nonlinear transformation function, σ k represents the standard deviation of the k-th sensor observation value, B represents the penalty term based on the Bayesian Information Criterion, which is used to balance the model complexity and positioning accuracy, μ ferepresents the mean of the error positioning coordinates, σ fe represents the standard deviation of the error positioning coordinates, represents the normal distribution function;
[0146] O(x fe ) has a range of (-∞,+∞);
[0147] When O(x fe ) is close to +∞, indicating that x fe The quality is very high and the positioning results are very reliable;
[0148] When O(x fe ) is close to -∞, indicating that x fe The quality is very low and the positioning results are unreliable;
[0149] When O(x fe ) is close to 0, indicating that x fe The quality is average and the reliability of positioning results is low.
[0150] This embodiment also provides a computer device, which is suitable for the Beidou satellite-assisted positioning method based on the 5G network, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the Beidou satellite-assisted positioning method based on the 5G network proposed in the above embodiment.
[0151] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.
[0152] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by the processor, the Beidou satellite assisted positioning method based on the 5G network proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.
[0153] In summary, the present invention ensures good signal coverage in the positioning area by: constructing a 5G network platform with positioning function, enhancing the robustness of the positioning system, reducing the probability of positioning failure due to incomplete signal coverage, collecting diversified positioning data through inspection robots, and adopting standardized processing and multi-sensor data fusion algorithms to improve the consistency and accuracy of positioning data, reduce the error influence of a single sensor, and improve the accuracy and reliability of positioning, and use the combination of CNN and RNN technology to construct a prediction coordinate model to further improve the positioning accuracy, especially in a dynamic environment, it can respond quickly and provide accurate prediction results, and minimize the error through the loss function, which further improves the accuracy and reliability of positioning, especially for positioning tasks in complex environments, it can effectively reduce error accumulation, and finally, by quantifying the reliability of the positioning results, it can provide users with intuitive feedback on the positioning quality, so that users can make decisions based on actual conditions.
[0154] Example 2, referring to Table 1, is the second example of the present invention. In order to further verify the advancement of the present invention, experimental simulation data of the Beidou satellite assisted positioning method based on the 5G network is provided.
[0155] In the positioning area, the number of required 5G base stations is first calculated. The positioning area is set to 500 square kilometers, and the maximum effective coverage radius of each base station is 1 kilometer. According to the formula The calculation shows that the number of base stations required is about 80. The distance, signal frequency and speed of light data between each base station are collected to construct the path loss function.
[0156] Based on this function, the strength of the base station signal at different distances was calculated, and a 5G base station was installed, a positioning data processing module was integrated, and a 5G network platform was built;
[0157] In the 5G base station area, inspection robots are deployed for detection and positioning. The robots receive signal strength information, Beidou satellite positioning data, ultra-wideband positioning data, and inertial measurement unit data, obtain environmental information through lidar, and use SLAM technology to convert it into the position of obstacles on the map. After standardized processing and multi-sensor data fusion algorithm, the robots can accurately locate;
[0158] A prediction coordinate model was constructed by combining convolutional neural network (CNN) with recurrent neural network (RNN). The model structure includes input layer, hidden layer, pooling layer, convolution layer and output layer. The fused positioning coordinates are input into the model and the predicted coordinates are output.
[0159] Based on the weighted square error, mean square error and regularization term, the loss function L is constructed. t (x f ), by calculating the error between the predicted coordinates and the true value coordinates, the error location coordinates are obtained;
[0160] By constructing nonlinear transformation function and optimization function, the optimal positioning result is obtained from the error positioning coordinates;
[0161] The details are shown in Table 1:
[0162] Table 1 Experimental record table
[0163]
[0164]
[0165] Different numbers of 5G base stations were used in the experiment to test the impact of the number of base stations on positioning accuracy;
[0166] Changes in received signal strength at different power levels;
[0167] Reflects the attenuation of the signal in the environment;
[0168] It shows the accuracy of positioning using Beidou satellite signals alone;
[0169] The accuracy of ultra-wideband technology in positioning was evaluated;
[0170] The errors between the predicted coordinates and the actual coordinates are compared, showing the accuracy of the method;
[0171] By comparing the experimental results, it can be seen that the present invention has obvious advantages in positioning accuracy, especially in complex environments. Compared with the existing technology, it can provide more accurate positioning results. In addition, through multi-sensor data fusion and advanced prediction models, the present invention also shows significant improvements in positioning stability and reliability.
[0172] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.
Claims
1. A Beidou satellite-assisted positioning method based on 5G network, characterized in that: include, Build multiple groups of 5G base stations in the positioning area to form a 5G network platform with positioning function; The inspection robot detects and locates in the 5G base station area, obtains positioning data, and processes the positioning data; Building a prediction coordinate model based on the processed positioning data, applying the processed positioning data to the prediction coordinate model, performing hybrid calculation on the positioning data, and obtaining the prediction positioning coordinates; Based on the predicted positioning coordinates, a loss function is constructed to minimize the error between the predicted coordinates and the true coordinates to obtain the error positioning coordinates; Obtain the optimal positioning result in the error positioning coordinates and output the optimal positioning result.
2. The Beidou satellite-assisted positioning method based on the 5G network as claimed in claim 1, characterized in that: Build multiple groups of 5G base stations in the positioning area to form a 5G network platform with positioning function. The specific steps are as follows: Based on the positioning accuracy requirements and base station signal coverage, the number of required 5G base stations is calculated as follows: Where N represents the number of 5G base stations required, A represents the area to be covered in the positioning area, R represents the maximum effective coverage radius of each base station, and π represents pi; The distance, signal frequency and speed of light between each base station are collected to construct the path loss function, which is expressed as: Where L(d) represents the path loss, which indicates the degree to which the signal strength attenuates as the distance increases, f represents the signal frequency, d represents the distance, c represents the speed of light, log 10 represents the logarithmic function with base 10; Based on the path loss function, the signal strength attenuation model is used to calculate the strength of the base station signal at different distances. The expression is: P r (d)=P t +G t +G r -L(d)-η; Among them, P r (d) represents the function of the received signal strength changing with the distance d, i.e., the signal strength information, P t Indicates the base station transmission power, G t represents the base station antenna gain, G r represents the receiving antenna gain, L(d) represents the path loss function, and η represents a random variable; Based on the number N of 5G base stations and signal strength information P r (d) Install 5G base stations in selected areas to provide positioning, receive BeiDou satellite signals and perform positioning calculations; The positioning data processing module is integrated inside the base station, which can clean and standardize the received signals; transmitting the positioning data from the base station to the central processing system according to the transmission protocol; Integrate all base stations and central processing systems to build a 5G network platform.
3. The Beidou satellite-assisted positioning method based on the 5G network as claimed in claim 2, characterized in that: The inspection robot in the 5G base station area performs detection and positioning, obtains positioning data, and processes the positioning data. The specific steps are as follows: The robot patrols the 5G base station area to receive signal strength information, Beidou satellite positioning data, ultra-wideband positioning data, and inertial measurement unit data; Use LiDAR to obtain environmental information around 5G base stations, and use SLAM to convert environmental information into obstacle locations on the map; Standardize the collected Beidou satellite positioning data, inertial measurement unit data, ultra-wideband positioning data and signal strength information; Set the signal strength information after normalization as P st (d); The multi-sensor data fusion algorithm is used to fuse the standardized signal strength information, Beidou satellite positioning data, ultra-wideband positioning data and inertial measurement unit data. The expression is: x f =K(P st (d),GPS,IMU,UWB); Among them, x f represents the fused positioning coordinates, K represents the fusion algorithm, GPS represents the Beidou satellite positioning data, IMU represents the inertial measurement unit data, and UWB represents the ultra-wideband positioning data.
4. The Beidou satellite-assisted positioning method based on the 5G network as claimed in claim 3, characterized in that: Fusion algorithm, the expression is: Among them, K represents the fusion algorithm, that is, the positioning coordinates after fusion, i represents the index of sensor data, and w i represents the weight of the i-th sensor, H i represents the Jacobian matrix of the i-th sensor, R i represents the covariance matrix of the i-th sensor, z i represents the actual observation value of the i-th sensor; The random tree RRT algorithm is used to find the path from the starting point to the end point while avoiding obstacles; Set the starting point to q s , the end point is q g ; Randomly select a point q in the configuration space r ; Find the distance q in the tree r The nearest node q n ; From q n To q r Move a certain distance δ to generate a new node qne w ; Check from q n to q new Whether the path passes through any obstacles; When no obstacles are crossed, q new Add to number and connect it to q n ; Set the number of iterations and the threshold PP. When the distance between the target node and the current node is less than PP, it means q new Close enough to the end point q new , then stop generating new nodes; When the distance between the target node and the current node is greater than or equal to PP, it means q new If there is still some distance to go, the path from the starting point to the end point is searched repeatedly until the set number of iterations is reached; Use smoothing algorithm to optimize the path and get the best path.
5. The Beidou satellite-assisted positioning method based on the 5G network as claimed in claim 4, characterized in that: The predicted coordinate model is constructed based on the processed positioning data, the processed positioning data is applied to the predicted coordinate model, and the positioning data is mixed and calculated to obtain the predicted positioning coordinates. The specific steps are as follows: The prediction coordinate model is constructed by combining convolutional neural network CNN and recurrent neural network RNN; The prediction coordinate model structure is set to include input layer, hidden layer, pooling layer, convolution layer and output layer; The fused positioning coordinates x f Input the prediction coordinate model and output the prediction coordinate; The prediction coordinate model is expressed as: Among them, x p represents the predicted positioning coordinates, W out represents the output layer weight matrix, W c Represents the convolutional layer weight matrix, W p represents the pooling layer weight matrix, W h represents the hidden layer weight matrix, W in represents the input layer weight matrix, dΩ represents the tiny volume element in the spatial domain where the convolution kernel acts, represents the weighted sum operation of the four sensor data, w k represents the weight of the kth sensor, z k represents the observed value of the kth sensor, μ k represents the mean of the kth sensor observations, σ k represents the standard deviation of the kth sensor observation, f Ω It represents the integral operation on the spatial domain of the convolution kernel, π represents the circumference of a circle, and e represents the base of the natural logarithm.
6. The Beidou satellite-assisted positioning method based on the 5G network as claimed in claim 5, characterized in that: Based on the predicted positioning coordinates, a loss function is constructed to minimize the error between the predicted coordinates and the true coordinates to obtain the error positioning coordinates. The specific steps are: Construct the loss function L based on weighted square error, mean square error and regularization t , the expression is: Among them, w k represents the weight of the kth sensor, β k Indicates the proportional factor for adjusting the contribution of the x-axis and y-axis prediction errors, x k and k represents the predicted coordinates corresponding to the k-th sensor data, x k t and k t represents the actual coordinates corresponding to the kth sensor, Λ k represents the noise standard deviation of the kth sensor, γ represents the regularization coefficient, N h represents the number of neurons in the hidden layer, w j represents the weight vector of the jth hidden layer neuron; Input the predicted positioning coordinates into the loss function formula, calculate the error between the predicted coordinates and the true value coordinates, and get the error positioning coordinates x fe .
7. The Beidou satellite-assisted positioning method based on the 5G network as claimed in claim 6, characterized in that: Obtain the optimal positioning result in the error positioning coordinates and output the optimal positioning result. The specific steps are: Constructing nonlinear transformation function T(x fe ), the calculation formula is: Among them, exp represents the natural exponential function, α is a positive real number parameter used to adjust the shape of the nonlinear transformation, ln represents the natural logarithm function, and β is a positive real number parameter; The penalty term B based on the Bayesian information criterion is calculated as follows: B=γ·log(N h ); Among them, γ represents the parameter that controls the intensity of the penalty, N h represents the number of hidden layer neurons, and log represents the natural logarithm.
8. The Beidou satellite-assisted positioning method based on the 5G network as claimed in claim 7, characterized in that: Based on the nonlinear transformation function T(x fe ) and the penalty term B of the Bayesian information criterion to construct an optimization function, which is expressed as: Among them, O(x fe ) represents the output of the optimization function, T(x fe ) represents the nonlinear transformation function, σ k represents the standard deviation of the k-th sensor observation, B represents the penalty term based on the Bayesian Information Criterion, μ fe represents the mean of the error positioning coordinates, σ fe represents the standard deviation of the error positioning coordinates, Represents the normal distribution function.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the Beidou satellite-assisted positioning method based on the 5G network as described in any one of claims 1 to 8 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the Beidou satellite-assisted positioning method based on a 5G network as described in any one of claims 1 to 8 are implemented.
Citation Information
Patent Citations
Power grid inspection robot positioning method based on 5G and Beidou
CN113596988A
Indoor positioning method based on convolutional neural network and high-dimensional 5G observation features
CN114189809A
Unmanned aerial vehicle position prediction method and device based on Beidou differential positioning
CN115184970A
Indoor and outdoor fusion positioning method based on 5G and Beidou
CN115802479A
Deep learning assistance-based satellite and inertial integrated positioning method and navigation method
CN116047567A
Cited By
Safety early warning method and system based on Beidou + UWB positioning
CN120544365A
GNSS (Global Navigation Satellite System) and INS (Inertial Navigation System) integrity monitoring method and system based on 5G and multilayer fusion mechanism
CN120602969A
GNSS and INS integrity monitoring method and system based on 5g and multi-layer fusion mechanism
CN120602969B
Beidou satellite and 5G signal fusion positioning method based on number of available satellites
CN120630275A
Vehicle-mounted intelligent module system based on fusion of 5G communication and Beidou navigation
CN121142597A
