Indoor high-precision positioning system and method based on UWB technology

Abstract

The invention discloses an indoor high-precision positioning system and method based on a UWB technology, and particularly relates to the technical field of positioning, and the system comprises a region division module which divides an indoor space into N dynamic region units based on the structural layout of a building and the coverage range of UWB anchor nodes; establishing a bidirectional mapping relationship between the region and the UWB tag by taking the key building nodes as boundaries; each area unit is associated with moving track data of the label, a space encoder is introduced to generate an area feature vector, and an original three-dimensional coordinate is obtained to represent the positioning characteristic of the area; according to the method, multi-source data of the UWB signal layer data, the motion sensing layer data and the environment sensing layer data are analyzed and processed, the superposition error of environment reflection and hardware deviation is effectively reduced, and the geometric convergence precision of position calculation can be remarkably improved in a complex space.

Description

Technical Field

[0001] The present invention relates to the technical field of positioning, and more specifically, to an indoor high-precision positioning system and method based on UWB technology. Background Art

[0002] With the rapid development of the Internet of Things and smart buildings, the demand for indoor positioning technology is increasing day by day; UWB technology has the advantages of extremely wide signal bandwidth, high time resolution, strong anti-interference ability, etc., and shows great potential in the field of indoor positioning; therefore, an indoor high-precision positioning system based on UWB technology is needed to meet the growing demand for indoor positioning technology.

[0003] Traditional indoor positioning systems include a signal transmitting module, a signal receiving module, and a positioning module; among them, the signal transmitting module is responsible for transmitting signals for positioning; the signal receiving module is used to receive the signals sent by the signal transmitting module; the positioning module obtains the position of the object or person to be located based on the signal parameters obtained by the signal receiving module.

[0004] However, in actual use, there are still some disadvantages, such as low positioning accuracy. Traditional positioning technologies are easily affected by factors such as multipath effects and signal interference, and the signal strength fluctuates greatly, resulting in an increase in positioning errors and making it difficult to achieve high-precision positioning in complex environments; weak anti-interference ability. The signal frequency band of traditional positioning technologies is relatively narrow, and it is easily interfered by other devices in the same frequency band, as well as the reflection and refraction of obstacles in the indoor environment, resulting in signal distortion and an increase in positioning errors; poor real-time performance. In the process of data acquisition, transmission, and processing of traditional positioning systems, it often takes a long time, resulting in poor real-time performance of the positioning results.

[0005] Therefore, there is an urgent need to provide an indoor high-precision positioning system and method based on UWB technology to solve the problems of low positioning accuracy, weak anti-interference ability, and poor real-time performance of existing indoor positioning systems. Summary of the Invention

[0006] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an indoor high-precision positioning system and method based on UWB technology, through the following solutions, to solve the problems raised in the above background art.

[0007] To achieve the above object, the present invention provides the following technical solutions: An indoor high-precision positioning system and method based on UWB technology, including:

[0008] The area division module divides the indoor space into N dynamic area units based on the structural layout of the building and the coverage range of UWB anchor nodes; takes key building nodes as boundaries to establish a two-way mapping relationship between areas and UWB tags; associates the movement trajectory data of tags for each area unit, and introduces a spatial encoder to generate area feature vectors, obtaining the original three-dimensional coordinates to characterize the positioning characteristics of the area.

[0009] The multi-source data acquisition module constructs an original positioning data set for complex scenarios through heterogeneous sensors deployed in UWB anchor base stations, mobile tags, and environmental perception modules.

[0010] The data processing module calculates indicators by establishing a mathematical model for the original positioning data set collected by the multi-source data acquisition module, obtains the influence coefficients of UWB signal layer data, motion perception layer data, and environmental perception layer data, and constructs three sets of core features of core data.

[0011] The comprehensive analysis module maps multi-source heterogeneous data into a unified positioning credibility index through weighted geometric fusion of the influence coefficients of UWB signal layer data, motion perception layer data, and environmental perception layer data.

[0012] The indoor positioning module dynamically allocates multi-anchor ranging weights through the positioning credibility index, and combines a pre-trained residual correction model to achieve robust high-precision positioning and obtain the final coordinates.

[0013] The data interaction module transports the final coordinates, positioning credibility index, and relevant data of the original positioning data set to the user information section.

[0014] Preferably, the original positioning data set includes UWB signal layer data, motion perception layer data, and environmental perception layer data.

[0015] Preferably, the UWB signal layer data includes the peak amplitude of the CIR main path, denoted as A peak , the multi-path energy distribution entropy, denoted as H mp , the delay spread, denoted as τ rms , the clock offset compensation amount, denoted as Δt clock ; the motion perception layer data includes the IMU predicted displacement, denoted as Δd IMU , the UWB ranging displacement, denoted as Δd UWB , the heading angle deviation, denoted as Δθ, and the environmental perception layer data includes the radio frequency noise level, denoted as N rf , the occlusion status code, denoted as O flag , the channel occupancy rate, denoted as R ch .

[0016] Preferably, the UWB signal layer data influence coefficient normalizes the UWB signal characteristics with different dimensions into a reliability index of 0-1 through the product of four parameters: multipath suppression weight, main path strength, delay spread control, and clock synchronization error, reflecting the comprehensive attenuation degree of the signal affected by multipath, hardware errors, and environmental interference. By limiting the influence of over-amplitude signals through the ratio of the measured peak amplitude to the calibrated maximum value, and exponentially punishing the multipath entropy value, the greater the delay spread, the more significant the attenuation of the denominator term to the signal quality for delay spread control. A large coefficient amplifies the negative impact of clock offset. Specifically:

[0017]

[0018] Preferably, the motion perception layer data influence coefficient fuses the kinematic characteristics and the wireless ranging results by the difference between the IMU predicted displacement and the UWB ranging displacement, and superimposing the cosine penalty term of the heading angle deviation, reflecting the consistency of sensor data. By calculating the displacement difference and smoothing the heading deviation with the half-angle cosine function, suppressing outliers in the form of the reciprocal of the displacement difference term, and attenuating the heading deviation through the cosine function. Specifically:

[0019]

[0020] Preferably, the environmental perception layer data influence coefficient quantifies the interference level of the environment on the UWB signal by superimposing the dynamic weights of the radio frequency noise intensity and the occlusion state, and combining the channel occupancy rate to determine the proportion of the noise weight. Normalize the radio frequency noise intensity through noise linear mapping, and then perform dynamic weight allocation and superposition output to merge the noise and occlusion effects. Specifically:

[0021]

[0022] Preferably, the positioning confidence index first performs normalized truncation on the UWB signal layer data influence coefficient, the motion perception layer data influence coefficient, and the environmental perception layer data influence coefficient, and then performs weight allocation according to the exponential weights, and then performs geometric fusion to achieve cross-level dimension normalization, comprehensively reflecting the dynamic reliability of the positioning system. Specifically:

[0023] LCI = SQI 0.4 ·MCI 0.3 ·(1 - EIC) 0.2 。

[0024] Preferably, the specific operation steps of the indoor positioning module are as follows:

[0025] 1. Dynamic weight allocation, calculating the weight corresponding to the positioning confidence index of the ranging value of each dynamic area unit anchor point based on the two-way mapping relationship between the area of the dynamic area unit and the UWB tag and the area feature vector. Specifically:

[0026]

[0027] where LCI i represents the positioning confidence index of the i-th dynamic area unit anchor point, and N represents the total number of dynamic area unit anchor points.

[0028] 2. Based on the weights obtained in step 1 and the weighted positioning calculation of the original three-dimensional coordinates, use the least squares method to model and construct an objective function to obtain the estimated coordinates of the tag, specifically:

[0029]

[0030] where ω i represents the weight of the i-th dynamic area unit anchor point, χ represents the original three-dimensional coordinates (x, y, z), and χ i represents the known three-dimensional coordinates (x i , y i , z i ) of the i-th dynamic area unit anchor point, and d i represents the ranging value between the i-th dynamic area unit anchor point and the tag.

[0031] 3. Input the positioning residual into the pre-trained LSTM network to output the coordinate compensation amount Δχ, and correct the final coordinates according to the coordinate compensation amount Δχ and the tag estimated coordinates obtained in S2.

[0032] The positioning residual includes a positioning residual vector and an environmental feature vector.

[0033] The positioning residual vector is specifically:

[0034] r = [r1, r2,..., r N ,

[0035] where

[0036]

[0037] The environmental feature vector is specifically:

[0038] e = [SQI, EIC, MCI],

[0039] The coordinate compensation amount Δx is obtained by importing the positioning residual vector and the environmental feature vector into the residual input model, specifically:

[0040] Δx = LSTM(r, e),

[0041] The corrected final coordinates are obtained by adding the coordinate compensation amount and the tag estimated coordinates, specifically:

[0042]

[0043] Preferably, an indoor high-precision positioning method based on UWB technology includes the following steps:

[0044] S1. Area division: Based on the structural layout of the building and the coverage range of UWB anchor nodes, the indoor space is divided into N dynamic area units; taking key building nodes as boundaries, a two-way mapping relationship between areas and UWB tags is established; the movement trajectory data of the tags associated with each area unit is collected, and a spatial encoder is introduced to generate area feature vectors, obtaining the original three-dimensional coordinates to characterize the positioning characteristics of the area.

[0045] S2. Multi-source data acquisition: By deploying heterogeneous sensors in UWB anchor base stations, mobile tags, and environmental perception modules, a positioning original data set for complex scenarios is constructed.

[0046] S3. Data processing: By establishing a mathematical model for the positioning original data set collected in S2 to calculate indicators, the influence coefficients of UWB signal layer data, motion perception layer data, and environmental perception layer data are obtained, and three groups of core data core features are constructed.

[0047] S4. Comprehensive analysis: Through the weighted geometric fusion of the influence coefficients of UWB signal layer data, motion perception layer data, and environmental perception layer data, multi-source heterogeneous data is mapped into a unified positioning credibility index.

[0048] S5. Indoor positioning: By dynamically allocating multi-anchor ranging weights according to the positioning credibility index and combining a pre-trained residual correction model, robust high-precision positioning is achieved to obtain the final coordinates.

[0049] S6. Data interaction: The final coordinates, positioning credibility index, and relevant data of the positioning original data set are transmitted to the user information segment.

[0050] The technical effects and advantages of the present invention are as follows:

[0051] 1. By analyzing and processing multi-source data of UWB signal layer data, motion perception layer data, and environmental perception layer data, the present invention effectively reduces the superimposed error of environmental reflection and hardware deviation, and can significantly improve the accuracy of position calculation in complex spaces.

[0052] 2. By analyzing the radio frequency noise and physical occlusion status in real time through the built-in environmental perception module and using the multi-sensor data cross-validation mechanism, the present invention can automatically isolate abnormal signals in strong electromagnetic interference or sudden occlusion scenarios, ensuring positioning continuity and anti-interference ability.

[0053] 3. Through the real-time detection and dynamic adjustment of multi-source data, the present invention calculates the analysis and judgment of the positioning credibility index, and ensures high-frequency position updates through the real-time nature of positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a schematic diagram of the overall structure of the present invention.

[0055] Figure 2 It is a schematic diagram of the method structure of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0056] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0057] As shown in the attached Figure 1 An indoor high-precision positioning system based on UWB technology includes:

[0058] A region division module divides the indoor space into N dynamic region units based on the structural layout of the building and the coverage range of UWB anchor nodes; a bidirectional mapping relationship between the region and the UWB tag is established with key building nodes as boundaries; the movement trajectory data of the tags associated with each region unit is introduced, and a spatial encoder is used to generate a region feature vector to obtain the original three-dimensional coordinates to characterize the positioning characteristics of the region.

[0059] A multi-source data acquisition module constructs an original positioning data set for complex scenarios through heterogeneous sensors deployed in UWB anchor base stations, mobile tags, and environmental perception modules.

[0060] In this embodiment, it should be specifically noted that the original positioning data set includes UWB signal layer data, motion perception layer data, and environmental perception layer data.

[0061] In this embodiment, it should be specifically noted that the UWB signal layer data includes the peak amplitude of the CIR main path, denoted as A peak , the multi-path energy distribution entropy, denoted as H mp , the delay spread, denoted as τ rms , the clock offset compensation amount, denoted as Δt clock ; the motion perception layer data includes the IMU predicted displacement, denoted as Δd IMU , the UWB ranging displacement, denoted as Δd UWB , the heading angle deviation, denoted as Δθ, and the environmental perception layer data includes the radio frequency noise level, denoted as N rf, Occlusion status code, denoted as O flag , Channel occupancy rate, denoted as R ch .

[0062] In this embodiment, specifically, the CIR main path peak amplitude is obtained by the UWB anchor base station enabling the high-speed ADC sampling mode to receive the UWB pulse signal transmitted by the tag, capturing the complete channel impulse response waveform within the time window, recording the time-domain signal sequence, applying the sliding window peak detection algorithm, traversing the CIR time-domain signal sequence and identifying the main path signal point with the largest amplitude, so as to obtain the CIR main path peak amplitude. Specifically:

[0063] A peak = max(|s(t)|),

[0064] where s(t) represents the original CIR time-domain signal sequence.

[0065] In this embodiment, specifically, the multipath energy distribution entropy is obtained by performing wavelet decomposition on the CIR time-domain signal sequence, separating the direct path and multipath components, calculating the energy proportion of each multipath component, and then quantifying the randomness of the multipath energy distribution based on the Shannon entropy formula. Specifically:

[0066]

[0067] where N1 represents the number of detected multipath components, p i represents the energy proportion of the i-th path.

[0068] In this embodiment, specifically, the delay spread is obtained by recording the time offset of each detected multipath component relative to the main path, and calculating the root mean square value of the delay with the energy of each path as the weight. Specifically:

[0069]

[0070] where τ i represents the delay of the i-th path, N1 represents the number of detected multipath components, τ represents the average delay, and E i represents the path energy of the i-th path.

[0071] In this embodiment, specifically, the clock offset compensation amount is calculated based on the two-way ranging protocol for the signal propagation time. The tag and the anchor base station perform a three-way handshake. The tag sends a Poll message and records the sending time. After the anchor receives it, it replies with a Response message to obtain the recorded reception time and the recorded reply time. The tag receives the Response message and records the time. The frequency drift is eliminated by linear regression to estimate the relative clock offset. Specifically:

[0072]

[0073] Among them, t1 represents the record sending time, t2 represents the record receiving time, t3 represents the record reply time, t4 represents the record time, and f tag represents the local clock frequency of the tag, and f anchor represents the local clock frequency of the base station.

[0074] In this embodiment, it should be specifically noted that the predicted displacement of the IMU is obtained by integrating an IMU sensor at the mobile tag end, using the SPI interface to collect the three-axis acceleration output by the IMU in real time, and then performing double integration, accumulating the displacement components, and calculating the total displacement. Specifically:

[0075]

[0076] a x [k] represents the x-axis acceleration at the kth sampling point, and a y [k] represents the y-axis acceleration at the kth sampling point, and Δt represents the sampling time interval.

[0077] In this embodiment, it should be specifically noted that the UWB ranging displacement is obtained by integrating an IMU sensor at the mobile tag end, using the SPI interface to collect the UWB ranging displacement in real time, and calculating the distance change amount of each anchor point by recording the UWB ranging values at adjacent moments. Specifically:

[0078]

[0079] where d i t represents the ranging value of the ith anchor point at time t, and d i t-1 represents the ranging value of the ith anchor point at time t - 1, and N2 represents the number of anchor points participating in the calculation.

[0080] In this embodiment, it should be specifically noted that the heading angle deviation is obtained by integrating an IMU sensor at the mobile tag end, using the SPI interface to collect the heading angle of the IMU by fusing the magnetometer and accelerometer in real time, calculating the UWB heading angle based on the continuous position coordinates, and taking the absolute difference between the two. Specifically:

[0081] Δθ = |θ mag -θ UWB |,

[0082] where θmag represents the IMU heading angle, and θ UWB represents the UWB heading angle.

[0083] In this embodiment, it should be specifically noted that the radio frequency noise level measures the background noise power spectral density through the spectrum analyzer module built into the anchor base station, and integrates the noise energy within the UWB signal bandwidth of 500 MHz. Specifically:

[0084]

[0085] Where f c represents the UWB center frequency, B represents the signal bandwidth, and P(f) represents the background noise power spectral density.

[0086] In this embodiment, it should be specifically noted that the occlusion status code obtains the reflected point cloud data by the base station carrying a radar to scan the tag direction, and counts the number of reflection points per unit area. Specifically:

[0087]

[0088] Where

[0089]

[0090] Where N points represents the number of reflection points detected by the radar, A scan represents the radar scanning area, and ρ thresh represents the reflection point cloud density occlusion threshold.

[0091] In this embodiment, it should be specifically noted that the channel occupancy rate counts the time when the channel power exceeds the threshold, and calculates the occupancy rate within the period. Specifically:

[0092]

[0093] Where T busy represents the cumulative time when the channel is occupied, and T total represents the total statistical time.

[0094] The data processing module calculates the indicators by establishing a mathematical model for the original positioning data set collected by the multi-source data acquisition module, obtains the UWB signal layer data influence coefficient, the motion perception layer data influence coefficient, and the environment perception layer data influence coefficient, and constructs the core features of three groups of kernel data.

[0095] In this embodiment, it should be specifically noted that the UWB signal layer data influence coefficient is the product of four parameters: multipath suppression weight, main path strength, delay spread control, and clock synchronization error. It normalizes the UWB signal characteristics with different dimensions into a reliability index of 0-1, reflecting the comprehensive attenuation degree of the signal affected by multipath, hardware errors, and environmental interference. By the ratio of the measured peak amplitude to the calibrated maximum value, it restricts the influence of over-amplitude signals, and the exponential function penalizes the multipath entropy value. The greater the delay spread, the more significant the attenuation of the denominator term on the signal quality for delay spread control. The large coefficient amplifies the negative impact of clock offset. Specifically:

[0096]

[0097] In this embodiment, it should be specifically noted that the motion perception layer data influence coefficient fuses the kinematic characteristics and the wireless ranging result by the difference degree between the IMU predicted displacement and the UWB ranging displacement, and superimposes the cosine penalty term of the heading angle deviation, reflecting the consistency of sensor data. By calculating the displacement difference and smoothing the heading deviation with the half-angle cosine function, the displacement difference term suppresses outliers in the form of a reciprocal, and the heading deviation is attenuated by the cosine function. Specifically:

[0098]

[0099] In this embodiment, it should be specifically noted that the environmental perception layer data influence coefficient quantifies the interference level of the environment on the UWB signal by superimposing the dynamic weights of the radio frequency noise intensity and the occlusion state, and combining the channel occupancy rate to determine the proportion of the noise weight. It normalizes the radio frequency noise intensity through noise linear mapping, and then performs dynamic weight allocation and superposition output, combining the influence of noise and occlusion. Specifically:

[0100]

[0101] The comprehensive analysis module maps the multi-source heterogeneous data into a unified positioning credibility index through the weighted geometric fusion of the UWB signal layer data influence coefficient, the motion perception layer data influence coefficient, and the environmental perception layer data influence coefficient.

[0102] In this embodiment, it should be specifically noted that the positioning credibility index first normalizes and truncates the UWB signal layer data influence coefficient, the motion perception layer data influence coefficient, and the environmental perception layer data influence coefficient, and then performs weight allocation according to the exponential weight, and then performs geometric fusion to achieve cross-level dimension normalization, comprehensively reflecting the dynamic reliability of the positioning system. Specifically:

[0103] LCI = SQI 0.4 ·MCI 0.3 ·(1 - EIC) 0.2 。

[0104] The indoor positioning module dynamically allocates the ranging weights of multiple anchors through the positioning credibility index, and combines the pre-trained residual correction model to achieve robust high-precision positioning and obtain the final coordinates.

[0105] In this embodiment, it should be specifically noted that the specific operation steps of the indoor positioning module are as follows:

[0106] 1. Dynamic weight allocation: Calculate the weights corresponding to the ranging values of the anchors of each dynamic region unit based on the bidirectional mapping relationship between the regions of the dynamic region unit and the UWB tag and the region feature vector. Specifically:

[0107]

[0108] where LCI i represents the positioning credibility index of the i-th dynamic region unit anchor, and N represents the total number of dynamic region unit anchors.

[0109] 2. Based on the weights obtained in step 1 and the weighted positioning calculation of the original three-dimensional coordinates, use the least squares method to model and construct the objective function to obtain the tag estimated coordinates. Specifically:

[0110]

[0111] where the ω i represents the weight of the i-th dynamic region unit anchor, χ represents the original three-dimensional coordinates (x, y, z), and χ i represents the known three-dimensional coordinates of the i-th dynamic region unit anchor (x i , y i , z i ), and d i represents the ranging value between the i-th dynamic region unit anchor and the tag.

[0112] 3. Input the positioning residual into the pre-trained LSTM network, output the coordinate compensation amount Δχ, and correct the final coordinates according to the coordinate compensation amount Δχ and the tag estimated coordinates obtained in S2.

[0113] where the positioning residual includes the positioning residual vector and the environmental feature vector.

[0114] where the positioning residual vector is specifically:

[0115] r = [r1, r2,..., r N ,

[0116] where

[0117]

[0118] where the environmental feature vector is specifically:

[0119] e = [SQI, EIC, MCI],

[0120] where the coordinate compensation amount Δx is obtained by introducing the positioning residual vector and the environmental feature vector into the residual input model, specifically:

[0121] Δx = LSTm(r, e),

[0122] where the corrected final coordinate is obtained by adding the coordinate compensation amount and the label estimated coordinate, specifically:

[0123]

[0124] The data interaction module transports the final coordinate, the positioning confidence index, and the data related to the original positioning data set to the user information segment.

[0125] Reference Figure 2 , in this embodiment, it should be specifically noted that the present invention provides an indoor high-precision positioning method based on UWB technology, including the following steps:

[0126] S1. Region division: Based on the structural layout of the building and the coverage range of UWB anchor nodes, the indoor space is divided into N dynamic regional units; taking key building nodes as boundaries, a two-way mapping relationship between the regions and UWB tags is established; the movement trajectory data of the tags associated with each regional unit is introduced, and a spatial encoder is used to generate regional feature vectors to obtain the original three-dimensional coordinates to characterize the positioning characteristics of the region;

[0127] S2. Multi-source data acquisition: By deploying heterogeneous sensors in UWB anchor base stations, mobile tags, and environmental perception modules, a positioning original data set for complex scenarios is constructed;

[0128] S3. Data processing: By establishing a mathematical model for the positioning original data set collected in S2 for index calculation, the influence coefficients of UWB signal layer data, motion perception layer data, and environmental perception layer data are obtained, and three groups of core data core features are constructed;

[0129] S4. Comprehensive analysis: Through the weighted geometric fusion of the influence coefficients of UWB signal layer data, motion perception layer data, and environmental perception layer data, the multi-source heterogeneous data is mapped to a unified positioning confidence index;

[0130] S5. Indoor positioning: By dynamically allocating multi-anchor ranging weights according to the positioning confidence index and combining with a pre-trained residual correction model, robust high-precision positioning is achieved to obtain the final coordinate;

[0131] S6. Data interaction: The final coordinate, the positioning confidence index, and the data related to the original positioning data set are transported to the user information segment.

[0132] Secondly, in the attached drawings of the disclosed embodiments of the present invention, only the structures related to the disclosed embodiments are involved. For other structures, reference can be made to the general design. Without conflict, the same embodiment and different embodiments of the present invention can be combined with each other;

[0133] Finally, the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An indoor high-precision positioning system based on UWB technology, characterized in that, Including: A region division module that divides the indoor space into N dynamic region units based on the structural layout of the building and the coverage range of UWB anchor nodes; Taking key building nodes as boundaries, establishing a two-way mapping relationship between regions and UWB tags; associating the movement trajectory data of tags for each region unit, and introducing a spatial encoder to generate region feature vectors and obtain the original three-dimensional coordinates to characterize the positioning characteristics of the region. A multi-source data acquisition module that constructs an original positioning dataset for complex scenarios through heterogeneous sensors deployed in UWB anchor base stations, mobile tags, and environmental perception modules. A data processing module that calculates metrics by establishing a mathematical model for the original positioning dataset collected by the multi-source data acquisition module, obtains the UWB signal layer data influence coefficient, the motion perception layer data influence coefficient, and the environmental perception layer data influence coefficient, and constructs three sets of core features of core data. A comprehensive analysis module that maps multi-source heterogeneous data to a unified positioning credibility index through weighted geometric fusion of the UWB signal layer data influence coefficient, the motion perception layer data influence coefficient, and the environmental perception layer data influence coefficient. An indoor positioning module that dynamically assigns multi-anchor ranging weights through the positioning credibility index, combines a pre-trained residual correction model, and achieves robust high-precision positioning to obtain the final coordinates. A data interaction module that transmits the final coordinates, the positioning credibility index, and data related to the original positioning dataset to the user information section.

2. The indoor high-precision positioning system based on UWB technology according to claim 1, wherein: The original positioning dataset includes UWB signal layer data, motion perception layer data, and environmental perception layer data.

3. An indoor high-precision positioning system based on UWB technology according to claim 1, characterized in that: The UWB signal layer data includes the peak amplitude of the CIR main path, denoted as A peak , the entropy of the multipath energy distribution, denoted as H mp , the delay spread, denoted as τ rms , the clock offset compensation amount, denoted as Δt clock ; The motion perception layer data includes the IMU predicted displacement, denoted as Δd IMU , the UWB ranging displacement, denoted as Δd UWB , the heading angle deviation, denoted as Δθ, and the environmental perception layer data includes the radio frequency noise level, denoted as N rf , the occlusion status code, denoted as O flag , the channel occupancy rate, denoted as R ch .

4. An indoor high-precision positioning system based on UWB technology according to claim 1, characterized in that: The UWB signal layer data influence coefficient is obtained by multiplying four parameters: multipath suppression weight, main path strength, delay spread control, and clock synchronization error. It normalizes UWB signal characteristics with different dimensions into a reliability index of 0-1, reflecting the comprehensive attenuation degree of the signal affected by multipath, hardware errors, and environmental interference. By the ratio of the measured peak amplitude to the calibrated maximum value, it limits the influence of over-amplitude signals, and uses an exponential function to penalize the multipath entropy value. The greater the delay spread, the more significant the attenuation of the denominator term on the signal quality for delay spread control. A large coefficient amplifies the negative impact of clock offset. Specifically:

5. An indoor high-precision positioning system based on UWB technology according to claim 1, characterized in that: The motion perception layer data influence coefficient fuses kinematic features and wireless ranging results by the difference between the IMU predicted displacement and the UWB ranging displacement, and superimposes a cosine penalty term for the heading angle deviation, reflecting the consistency of sensor data. It smooths the heading deviation through displacement difference calculation and the half-angle cosine function, suppresses outliers in the form of the reciprocal of the displacement difference term, and attenuates the heading deviation through the cosine function. Specifically:

6. The indoor high-precision positioning system based on UWB technology according to claim 1, characterized in that: The environmental perception layer data influence coefficient quantifies the interference level of the environment on the UWB signal by dynamically superimposing the weights of radio frequency noise intensity and occlusion status, and combining the channel occupancy rate to determine the proportion of the noise weight. It normalizes the radio frequency noise intensity through noise linear mapping, and then performs dynamic weight allocation and superposition output to combine the effects of noise and occlusion. Specifically:

7. An indoor high-precision positioning system based on UWB technology according to claim 1, characterized in that: The positioning credibility index first normalizes and truncates the data influence coefficients of the UWB signal layer, the motion perception layer, and the environmental perception layer, and then performs weight allocation according to the exponential weights, followed by geometric fusion to achieve cross-level dimension normalization, comprehensively reflecting the dynamic reliability of the positioning system. Specifically: LCI = SQI 0.4 · MCI 0.3 · (1 - EIC) 0.2 。 8. An indoor high-precision positioning system based on UWB technology according to claim 1, characterized in that: The specific operation steps of the indoor positioning module are as follows:

1. Dynamic weight allocation: Based on the bidirectional mapping relationship between the regions of the dynamic region units and the UWB tags and the region feature vectors, calculate the weights corresponding to the ranging values of the anchor points of each dynamic region unit for the positioning credibility index. Specifically: Among them, LCI i represents the positioning confidence index of the i-th dynamic area unit anchor point, and N represents the total number of dynamic area unit anchor points.

2. Weighted positioning calculation based on the weights obtained in step 1 and the original three-dimensional coordinates: Use the least squares method to model and construct an objective function to obtain the estimated coordinates of the tag. Specifically: Among which, ω i represents the weight of the i-th dynamic region unit anchor point, χ represents the original three-dimensional coordinates (x, y, z), and χ i represents the known three-dimensional coordinates (x i , y i , z i ) of the i-th dynamic region unit anchor point, and d i represents the ranging value between the i-th dynamic region unit anchor point and the label.

3. Input the positioning residual into the pre-trained LSTM network, output the coordinate compensation amount Δχ, and correct the final coordinates according to the coordinate compensation amount Δχ and the estimated coordinates of the tag obtained in S2. Among them, the positioning residual includes the positioning residual vector and the environmental feature vector. Among them, the positioning residual vector is specifically: r＝[r1,r2,…,r N ]， Among them Among them, the environmental feature vector is specifically: e = [SQI, EIC, MCI] Among them, the coordinate compensation amount Δx is obtained by importing the positioning residual vector and the environmental feature vector into the residual input model. Specifically: Δx = LSTM(r, e), Among them, the corrected final coordinates are obtained by adding the coordinate compensation amount and the estimated coordinates of the tag. Specifically:

9. An indoor high-precision positioning method based on UWB technology, which is used for an indoor high-precision positioning system based on UWB technology described in any one of claims 1-8 above, and is characterized in that, Include the following steps: S1. Region division: Based on the structural layout of the building and the coverage range of the UWB anchor nodes, divide the indoor space into N dynamic region units; establish a bidirectional mapping relationship between the regions and the UWB tags with key building nodes as the boundaries; associate the movement trajectory data of the tags for each region unit, and introduce a spatial encoder to generate region feature vectors to obtain the original three-dimensional coordinates to characterize the positioning characteristics of the region. S2. Multi-source data collection: Construct a positioning original data set for complex scenarios through heterogeneous sensors deployed in UWB anchor base stations, mobile tags, and environmental perception modules. S3. Data processing: Establish a mathematical model for the positioning original data set collected in S2 to calculate indicators, obtain the data influence coefficients of the UWB signal layer, the motion perception layer, and the environmental perception layer, and construct three groups of core feature data of the core data. S4. Comprehensive analysis: Through the weighted geometric fusion of the data influence coefficients of the UWB signal layer, the motion perception layer, and the environmental perception layer, map the multi-source heterogeneous data to a unified positioning credibility index. S5. Indoor positioning: Dynamically allocate the ranging weights of multiple anchor points through the positioning credibility index, and combine the pre-trained residual correction model to achieve robust high-precision positioning and obtain the final coordinates. S6. Data interaction: Transmit the final coordinates, the positioning credibility index, and the relevant data of the positioning original data set to the user information segment.

Images