An UWB real-time positioning method and system in an obstacle shielding scene

Abstract

The application discloses a kind of UWB real-time positioning method and system under the scene of barrier shelter, method includes: obtaining the real-time signal strength and real-time distance information of mobile label;Through the nonlinear function between signal strength and distance under the state of no barrier shelter pre-fitting, the real-time signal strength and real-time distance information obtained are preprocessed;Real-time signal strength and real-time distance information after pre-processing are input into the sparse auto-encoder and Kmeans two-classification network model pre-trained;According to the output of sparse auto-encoder and Kmeans two-classification network model, mobile label is positioned.The application effectively improves UWB positioning accuracy, guarantees the stability and reliability of UWB positioning in dynamic environment.

Description

Technical Field

[0001] This invention belongs to the field of UWB positioning technology, specifically relating to a UWB real-time positioning method and system in obstacle-occluded scenarios. Background Technology

[0002] With the continuous advancement of science and technology, mobile robots are gradually entering daily production and life. Accurately determining the real-time position of robots is a key technology for mobile robots. UWB (Ultra-Wideband) positioning technology is one of the important methods for low-cost pose estimation. However, because it relies on the straight-line transmission of signals, it is sensitive to object occlusion. Introducing signal data after occlusion will reduce the accuracy of position calculation. Therefore, effectively solving the UWB positioning problem in dynamic occlusion scenarios is both necessary and challenging. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the prior art and provide a UWB real-time positioning method and system in obstacle-occluded scenarios, which can effectively improve UWB positioning accuracy and ensure the stability and reliability of UWB positioning in dynamic environments.

[0004] This invention provides the following technical solution:

[0005] Firstly, a real-time UWB localization method is provided for scenarios with obstacle occlusion, including:

[0006] Obtain real-time signal strength and distance information of the mobile tag;

[0007] The acquired real-time signal strength and real-time distance information are preprocessed by using a pre-fitted nonlinear function between signal strength and distance under unobstructed occlusion conditions.

[0008] The preprocessed real-time signal strength and real-time distance information are input into a pre-trained sparse autoencoder and Kmeans binary classification network model.

[0009] The mobile label is located based on the output of the sparse autoencoder and the Kmeans binary classification network model.

[0010] Furthermore, the real-time signal strength and distance information obtained comes from information collected simultaneously by signal base stations in different locations.

[0011] Furthermore, the fitting method for the nonlinear function between signal strength and distance in an unobstructed state includes: in an unobstructed state, using a single receiver to repeatedly read the signal strength and distance information of the mobile tag at different distances, and fitting a Gaussian distribution function between signal strength and distance based on the read signal strength and distance information, thus obtaining the nonlinear function between signal strength and distance in an unobstructed state; the Gaussian distribution function between signal strength and distance is:

[0012]

[0013] In the formula, f(x) is the signal strength, x is the distance, σ is the standard deviation of the signal strength, and μ is the distance corresponding to the maximum signal strength.

[0014] Furthermore, the preprocessing includes:

[0015] The ideal signal strength under unobstructed conditions is calculated based on the nonlinear function between signal strength and distance under unobstructed conditions and the acquired real-time distance information.

[0016] The ideal signal strength under unobstructed conditions is compared with the acquired real-time signal strength, and real-time signal strength data exceeding the threshold range is removed.

[0017] Furthermore, the preprocessed real-time signal strength and real-time distance information are input into a pre-trained sparse autoencoder and Kmeans binary classification network model to classify the preprocessed real-time signal strength and real-time distance information, remove interference data under obstacle occlusion, and output effective data without obstacle occlusion.

[0018] Furthermore, methods for locating mobile tags include:

[0019] A circle is drawn with the signal base station corresponding to the valid data without obstruction as the center and the distance between the mobile tag and the signal base station as the radius.

[0020] When the number of valid data without obstruction is ≥3, the intersection of multiple circles is taken as the current position of the moving label;

[0021] When there are two valid data points without obstruction, the current position of the moving tag is determined by the intersection of the circles closest to the previous location.

[0022] When the number of valid data points without obstruction is less than 2, the current position of the mobile tag is inferred by the previous positioning position of the mobile tag and the displacement generated during positioning.

[0023] Furthermore, the intersection points of the multiple circles are calculated using the least squares method.

[0024] Secondly, a UWB real-time positioning system for obstacle-occluded scenarios is provided, including:

[0025] The information acquisition module is used to acquire real-time signal strength and real-time distance information of the mobile tag;

[0026] The preprocessing module is used to preprocess the acquired real-time signal strength and real-time distance information by using a pre-fitted nonlinear function between signal strength and distance under unobstructed occlusion conditions.

[0027] The localization module is used to input the pre-processed real-time signal strength and real-time distance information into a pre-trained sparse autoencoder and Kmeans binary classification network model, and to locate the mobile label based on the output of the sparse autoencoder and Kmeans binary classification network model.

[0028] Thirdly, a UWB real-time positioning device for obstacle-occluded scenarios is provided, comprising a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to execute the steps of the method described in the first aspect.

[0029] Fourthly, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in the first aspect.

[0030] Compared with the prior art, the beneficial effects of the present invention are:

[0031] This invention preprocesses the acquired real-time signal strength and distance information using a pre-fitted nonlinear function relating signal strength and distance under unobstructed conditions, initially filtering out real-time signal strength and distance data under obstructed conditions. Then, it classifies the remaining data using a sparse autoencoder and a K-means binary classification network model, further removing real-time signal strength and distance data under obstructed conditions. This results in a high data filtering success rate, effectively improving UWB positioning accuracy and ensuring the stability and reliability of UWB positioning in dynamic environments. Attached Figure Description

[0032] Figure 1 This is a flowchart illustrating the UWB real-time positioning method in an obstacle occlusion scenario according to an embodiment of the present invention.

[0033] Figure 2 This is a schematic diagram of multi-signal base station UWB positioning in an embodiment of the present invention;

[0034] Figure 3 This is a schematic diagram of multi-signal base station UWB positioning in a pedestrian occlusion scenario according to an embodiment of the present invention;

[0035] Figure 4This is a schematic diagram of the UWB real-time positioning system in an obstacle-occluded scenario according to an embodiment of the present invention. Detailed Implementation

[0036] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention.

[0037] Example 1

[0038] like Figure 1 As shown, this embodiment provides a UWB real-time positioning method in obstacle-occluded scenarios, including the following steps:

[0039] Step 1: Under unobstructed conditions, repeatedly read the signal strength and distance information of the mobile tag at different distances using a single receiver. Fit a Gaussian distribution function relating signal strength and distance based on the read signal strength and distance information, thus obtaining a nonlinear function relating signal strength and distance under unobstructed conditions. The Gaussian distribution function relating signal strength and distance is:

[0040]

[0041] In the formula, f(x) is the signal strength, x is the distance, σ is the standard deviation of the signal strength, and μ is the distance corresponding to the maximum signal strength.

[0042] Step 2: Pre-construct a sparse autoencoder and a K-means binary classification network model, and use the signal strength and distance information of the moving tag read in the unobstructed state in Step 1 to train the sparse autoencoder and K-means binary classification network model.

[0043] Step 3: Obtain the real-time signal strength and real-time distance information of the mobile tag.

[0044] A suitable number of signal base stations are fixed at different locations within the working area of ​​the mobile tag. When the mobile tag moves within the working area, it transmits UWB signals at a certain frequency. The signal base stations simultaneously receive UWB signals at different locations to obtain real-time signal strength and real-time distance information. The real-time distance information is calculated using signal reception time and signal propagation speed.

[0045] by Figure 2 In the example shown, A0, A1, and A2 are signal base stations, and T0 is the location of the mobile tag. The mobile tag transmits a UWB carrier signal at T0, which is captured by the three signal base stations A0, A1, and A2.

[0046] Step 4: Calculate the ideal signal strength under unobstructed occlusion conditions based on the nonlinear function between signal strength and distance pre-fitted in Step 1 and the acquired real-time distance information; compare the ideal signal strength under unobstructed occlusion conditions with the acquired real-time signal strength, and remove signal strength data that exceeds the threshold range.

[0047] Step 5: Input the preprocessed real-time signal strength and real-time distance information into the sparse autoencoder and K-means binary classification network model pre-trained in Step 2. Classify the preprocessed real-time signal strength and real-time distance information, remove interference data caused by obstacles, and output valid data without obstacles. For example... Figure 3 As shown, there is pedestrian obstruction between A1 and T0. After steps four and five, the real-time signal strength and real-time distance information obtained from signal base station A1 will be filtered out.

[0048] Step Six: Localize the mobile label based on the effective data of unobstructed occlusion output from the sparse autoencoder and K-means binary classification network model. Specific steps include:

[0049] Using the signal base station corresponding to the valid data without obstruction as the center, draw a circle with the distance between the mobile tag and the signal base station as the radius. When the number of valid data without obstruction is ≥3, the intersection of the multiple circles is the current position of the mobile tag, which is calculated using the least squares method. When the number of valid data without obstruction is 2, the intersection of the circles closest to the previous positioning position is the current position of the mobile tag. When the number of valid data without obstruction is <2, the current position of the mobile tag is inferred from the previous positioning position of the mobile tag and the displacement generated during positioning.

[0050] Example 2

[0051] This embodiment provides a UWB real-time positioning method in obstacle-occluded scenarios. It adopts the method in Embodiment 1 and outputs 4 sets of valid data without obstacle occlusion after step 5.

[0052] Assume the coordinates of four signal base stations are (x1, y1), (x2, y2), (x3, y3), and (x4, y4), and the times from signal transmission from the mobile tag to signal reception at each base station are t1, t2, t3, and t4, respectively. The signal propagation speed is c. Assume the coordinates of the target location are (x, y). Based on the TOA algorithm principle, construct the following system of equations:

[0053]

[0054] The solution for locating the target can be obtained by using the least squares method:

[0055] X = (A T A) -1 A T B = A -1 B

[0056] In the formula:

[0057]

[0058]

[0059]

[0060] When solving for the intersection of multiple circles, the least squares method is used. After obtaining the preliminary solution, the ranging data with the largest error is removed based on the distance between the current mobile tag position and the signal base station. The least squares solution is then performed again to obtain the final positioning point.

[0061] Example 3

[0062] like Figure 4 As shown, this embodiment provides a UWB real-time positioning system for obstacle-occluded scenarios, including:

[0063] A mobile tag module is used to transmit UWB signals during movement;

[0064] The information acquisition module is used to acquire real-time signal strength and real-time distance information of the mobile tag;

[0065] The preprocessing module is used to preprocess the acquired real-time signal strength and real-time distance information by using a pre-fitted nonlinear function between signal strength and distance under unobstructed occlusion conditions.

[0066] The localization module is used to input the pre-processed real-time signal strength and real-time distance information into a pre-trained sparse autoencoder and Kmeans binary classification network model, and to locate the mobile label based on the output of the sparse autoencoder and Kmeans binary classification network model.

[0067] In some embodiments, the information acquisition module can be configured as a signal base station module.

[0068] In some embodiments, the preprocessing module can be configured as a signal fitting module.

[0069] In some embodiments, the positioning module can be configured as a signal filtering module and a central computing unit module.

[0070] Example 4

[0071] This embodiment provides a UWB real-time positioning device in obstacle-occluded scenarios, including a processor and a storage medium; the storage medium is used to store instructions; the processor is used to perform operations according to the instructions to execute the steps of the method described in Embodiment 1.

[0072] Example 5

[0073] This embodiment provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in Embodiment 1.

[0074] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0075] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0076] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0077] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1The steps of the function specified in one or more boxes.

[0078] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the technical principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A real-time UWB positioning method for obstacle-occluded scenarios, characterized in that, include: Obtain real-time signal strength and distance information of the mobile tag; The acquired real-time signal strength and real-time distance information are preprocessed by using a pre-fitted nonlinear function between signal strength and distance under unobstructed occlusion conditions. The preprocessed real-time signal strength and real-time distance information are input into a pre-trained sparse autoencoder and Kmeans binary classification network model. The mobile label is located based on the output of the sparse autoencoder and the Kmeans binary classification network model; The real-time signal strength and distance information obtained comes from information collected by signal base stations in different directions at the same time. The real-time distance information is calculated by signal reception time and signal propagation speed. The fitting method for the nonlinear function between signal strength and distance in an unobstructed state includes: In an unobstructed state, using a single receiver to repeatedly read the signal strength and distance information of the mobile tag at different distances, and fitting a Gaussian distribution function between signal strength and distance based on the read signal strength and distance information, thus obtaining the nonlinear function between signal strength and distance in an unobstructed state; the Gaussian distribution function between signal strength and distance is: ； In the formula, f ( x () represents signal strength. x For distance, The standard deviation of the signal strength. μ This is the distance corresponding to the maximum signal strength. The preprocessing includes: The ideal signal strength under unobstructed conditions is calculated based on the nonlinear function between signal strength and distance under unobstructed conditions and the acquired real-time distance information. The ideal signal strength under unobstructed conditions is compared with the acquired real-time signal strength, and real-time signal strength data exceeding the threshold range is removed. The preprocessed real-time signal strength and real-time distance information are input into a pre-trained sparse autoencoder and Kmeans binary classification network model to classify the preprocessed real-time signal strength and real-time distance information, remove interference data under obstacle occlusion, and output effective data without obstacle occlusion. Methods for locating mobile tags include: A circle is drawn with the signal base station corresponding to the valid data without obstruction as the center and the distance between the mobile tag and the signal base station as the radius. When the number of valid data without obstruction is ≥3, the intersection of multiple circles is taken as the current position of the moving label; When there are two valid data points without obstruction, the current position of the moving tag is determined by the intersection of the circles closest to the previous location. When the number of valid data points without obstruction is less than 2, the current position of the mobile tag is inferred by the previous positioning position of the mobile tag and the displacement generated during positioning.

2. The UWB real-time positioning method in obstacle-occluded scenarios according to claim 1, characterized in that, The intersection points of the multiple circles were calculated using the least squares method.

3. A UWB real-time positioning system for obstacle-occluded scenarios, characterized in that, The system is used to implement the UWB real-time positioning method in obstacle occlusion scenarios as described in any one of claims 1 to 2, the system comprising: The information acquisition module is used to acquire real-time signal strength and real-time distance information of the mobile tag; The preprocessing module is used to preprocess the acquired real-time signal strength and real-time distance information by using a pre-fitted nonlinear function between signal strength and distance under unobstructed occlusion conditions. The localization module is used to input the pre-processed real-time signal strength and real-time distance information into a pre-trained sparse autoencoder and Kmeans binary classification network model, and to locate the mobile label based on the output of the sparse autoencoder and Kmeans binary classification network model.

4. A UWB real-time positioning device for obstacle-occluded scenarios, characterized in that, It includes a processor and a storage medium; the storage medium is used to store instructions; the processor is used to operate according to the instructions to perform the steps of the method according to any one of claims 1 to 2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method according to any one of claims 1 to 2.

Images