CN117406170A - Positioning method and system based on ultra-wideband - Google Patents
Positioning method and system based on ultra-wideband Download PDFInfo
- Publication number
- CN117406170A CN117406170A CN202311724878.5A CN202311724878A CN117406170A CN 117406170 A CN117406170 A CN 117406170A CN 202311724878 A CN202311724878 A CN 202311724878A CN 117406170 A CN117406170 A CN 117406170A
- Authority
- CN
- China
- Prior art keywords
- ultra
- wideband
- target
- position coordinate
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012549 training Methods 0.000 claims abstract description 38
- 238000005070 sampling Methods 0.000 claims abstract description 14
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/06—Position of source determined by co-ordinating a plurality of position lines defined by path-difference measurements
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/04—Position of source determined by a plurality of spaced direction-finders
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S5/00—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations
- G01S5/02—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves
- G01S5/12—Position-fixing by co-ordinating two or more direction or position line determinations; Position-fixing by co-ordinating two or more distance determinations using radio waves by co-ordinating position lines of different shape, e.g. hyperbolic, circular, elliptical or radial
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0499—Feedforward networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention discloses a positioning method and a system based on ultra-wideband, which relate to the technical field of ultra-wideband positioning, and the method comprises the following steps: when a target vehicle runs, determining a position coordinate set of a target point at a current time point based on ultra-wideband signals of the target point received by a plurality of ultra-wideband positioning tags on the target vehicle at the current time point; inputting the position coordinate set into a coordinate prediction model to obtain the predicted position coordinate of the target point at the current time point; the coordinate prediction model is obtained by training a transducer network by adopting a training set; the training set sample data comprises input data and label data, the input data is a position coordinate set of a target tracking point determined by ultra-wideband signals of a target vehicle at a sampling time point, and the label data is actual position coordinates of the target tracking point at the sampling time point. The invention improves the accuracy of ultra-wideband positioning and reduces the computational complexity.
Description
Technical Field
The invention relates to the technical field of ultra-wideband positioning, in particular to a positioning method and system based on ultra-wideband.
Background
The traditional Ultra Wide Band (UWB) positioning technology has excellent penetrating power and anti-interference capability. At present, the UWB positioning technology cannot meet the high-precision positioning requirement of the navigation positioning of the all-terrain vehicle, and particularly the problems of high computational complexity and large positioning error of the UWB positioning method are commonly existed.
Disclosure of Invention
The invention aims to provide a positioning method and a positioning system based on ultra-wideband, which improve the accuracy of ultra-wideband positioning and reduce the computational complexity.
In order to achieve the above object, the present invention provides the following solutions:
an ultra-wideband based positioning method, comprising:
when a target vehicle runs, determining a position coordinate set of a target point at a current time point based on ultra-wideband signals of the target point received by a plurality of ultra-wideband positioning tags on the target vehicle at the current time point;
inputting the position coordinate set into a coordinate prediction model to obtain the predicted position coordinate of the target point at the current time point; the coordinate prediction model is obtained by training a transducer network by adopting a training set;
the training set sample data comprises input data and label data, the input data is a position coordinate set of a target tracking point determined by ultra-wideband signals of a target vehicle at a sampling time point, and the label data is actual position coordinates of the target tracking point at the sampling time point.
Optionally, the number of ultra-wideband positioning tags on the target vehicle is more than three.
Optionally, when the target vehicle runs, determining the position coordinate set of the target point at the current time point based on the ultra-wideband signals of the target point received by the plurality of ultra-wideband positioning tags on the target vehicle at the current time point specifically includes:
by using the principle of triangulation, a position coordinate of a target point is calculated by using ultra-wideband signals received by every three ultra-wideband positioning labels, and the position coordinate is calculatedPosition coordinates>The location coordinates form the set of location coordinates, and n represents the number of ultra-wideband locating tags on the target vehicle.
Optionally, the transducer network includes an input layer, an encoding layer, a decoding layer and a full connection layer connected in sequence;
the coding layer comprises a plurality of encoders which are sequentially connected in series, and each encoder comprises a first multi-head self-attention layer and a first feedforward neural network layer which are sequentially connected;
the decoding layer comprises a plurality of decoders which are connected in series in sequence, and each decoder comprises a multi-head self-attention layer with a mask, a second multi-head self-attention layer and a second feedforward neural network layer which are connected in sequence.
Optionally, the input layer is configured to perform linear projection on an input position coordinate set, and convert a dimension of the position coordinate set into a set hidden dimension.
Alternatively, a mean square error loss function is used as the loss function when training the Transformer network using the training set.
Alternatively, when training a Transformer network with a training set, the Transformer network is trained with a random gradient descent optimizer.
The invention discloses a positioning system based on ultra-wideband, comprising:
the system comprises a position coordinate set determining module, a target vehicle detecting module and a target vehicle detecting module, wherein the position coordinate set determining module is used for determining a position coordinate set of a target point at a current time point based on ultra-wideband signals of the target point received by a plurality of ultra-wideband positioning tags on the target vehicle at the current time point when the target vehicle runs;
the predicted position coordinate determining module is used for inputting the position coordinate set into a coordinate prediction model to obtain the predicted position coordinate of the target point at the current time point; the coordinate prediction model is obtained by training a transducer network by adopting a training set;
the training set sample data comprises input data and label data, the input data is a position coordinate set of a target tracking point determined by ultra-wideband signals of a target vehicle at a sampling time point, and the label data is actual position coordinates of the target tracking point at the sampling time point.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects:
when the target vehicle runs, the method and the device adopt the ultra-wideband signal to determine the position coordinate set of the target point, input the position coordinate set of the target point into the trained transducer network, obtain the predicted position coordinate of the target point at the current time point, realize the correction of the position coordinate determined by the ultra-wideband signal through the transducer network, improve the positioning accuracy and robustness, simplify the calculation process and reduce the calculation complexity.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a positioning method based on ultra wideband according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a coordinate prediction model construction flow provided in an embodiment of the present invention;
FIG. 3 is a schematic diagram of a transducer network according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a transform network training process according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention aims to provide a positioning method and a positioning system based on ultra-wideband, which improve the accuracy of ultra-wideband positioning and reduce the computational complexity.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Example 1
As shown in fig. 1, the positioning method based on the ultra-wideband provided in this embodiment includes the following steps.
Step 101: and when the target vehicle runs, determining a position coordinate set of the target point at the current time point based on ultra-wideband signals of the target point received by a plurality of ultra-wideband positioning tags on the target vehicle at the current time point.
Step 102: inputting the position coordinate set into a coordinate prediction model to obtain the predicted position coordinate of the target point at the current time point; the coordinate prediction model is obtained by training a transducer network by adopting a training set.
In step 101, n ultra-wideband positioning tags are disposed at the front end of the target vehicle, and an ultra-wideband base station is disposed on each ultra-wideband positioning tag.
The number of ultra-wideband positioning labels on the target vehicle is more than three.
The step 101 specifically includes:
by using the principle of triangulation, a position coordinate of a target point is calculated by using ultra-wideband signals received by every three ultra-wideband positioning labels, and the position coordinate is calculatedPosition coordinates>The location coordinates form the set of location coordinates, and n represents the number of ultra-wideband locating tags on the target vehicle. More specifically, for each ultra-wideband signal, the time of flight of the ultra-wideband signal is calculated, the initial distance and azimuth between the target vehicle and the target point are obtained, and the initial distance and azimuth are converted into three-dimensional coordinates in the world coordinate system, wherein the intersection between each three ultra-wideband base stations and the range circle of the ultra-wideband tag signal can be calculated into a three-dimensional coordinate S_m (the intersection of the three circles may be a space due to the relationship of the error of the UWB itself), wherein m is equal to->. I.e. the coordinate set in which the ultra wideband tag signal detected at each time point t may be located is x_t= [ s_1, s_2, …, s_m]。
In the process of the transform network training, a time mark is located at a real coordinate Y_t of a world coordinate system at each time point t, and the obtained data X_t and Y_t are divided into a training set, a testing set and a verification set through a large number of real measurement and collection of X_t and Y_t.
The training set sample data comprises input data and label data, the input data is a position coordinate set of a target tracking point determined by ultra-wideband signals of a target vehicle at a sampling time point, and the label data is actual position coordinates of the target tracking point at the sampling time point.
The process of constructing the coordinate prediction model is shown in fig. 2.
The transducer network consists of an Encoder (Encoder) and a Decoder (Decoder). The input layer is used for processing the input X_t and transmitting the input X_t to the encoder, the encoder performs feature extraction and encoding on the input sequence X_t through the multi-layer stacked self-attention layer and the feedforward neural network layer, the decoder transmits the output of the encoder to the multi-layer stacked masked self-attention layer, the common attention layer and the feedforward neural network layer to generate corresponding prediction coordinates, and the prediction coordinates are transmitted to the full-connection layer to generate corresponding prediction position coordinates Y_t.
As shown in fig. 3, the converter network includes an input layer, an encoding layer, a decoding layer, and a full connection layer, which are sequentially connected.
The coding layer comprises a plurality of encoders which are sequentially connected in series, each encoder comprises a first multi-head self-attention layer and a first feedforward neural network layer which are sequentially connected, and r in fig. 3 represents the number of the encoders.
The decoding layer comprises a plurality of decoders which are connected in series in sequence, each decoder comprises a multi-head self-attention layer with a mask, a second multi-head self-attention layer and a second feedforward neural network layer which are connected in sequence, and m represents the number of the decoders.
The input layer is used for linearly projecting an input position coordinate set, and converting the dimension of the position coordinate set into a set hidden dimension (hidden_dim). The dimension of the set of location coordinates is the number of elements in the set of location coordinates.
In a transform network, the output of the decoder layer is passed to the fully connected layer, which maps the hidden state of the last time step (the last layer in the decoded layer) to the predicted y_t coordinate.
As shown in fig. 4, the mean square error loss function is used as the loss function when training the Transformer network using the training set. The mean square error loss function is used for measuring the difference between the predicted value and the true value, and the expression is as follows: mse= (1/N) ×Σ (y_p-y_t), where MSE represents the mean square error, y_p is the predicted value, y_t is the true value, and N is the number of samples.
When a training set is adopted to train a transducer network, a random gradient descent optimizer is adopted to train the transducer network, super parameters are adjusted in the training process to optimize the performance of the model, and the model with the optimal effect is stored.
The Transformer network is trained using the training set. In each training step, x_t is input to the encoding layer, and a corresponding coordinate prediction is generated by the decoding layer. The predicted value is compared with the true value Y _ t and the loss is calculated. The loss is reduced step by back-propagating and updating the weights of the model using random gradient descent.
Prediction and verification of a coordinate prediction model: and predicting and verifying the coordinate prediction model by using the verification set. By inputting the input X_t into the trained transducer network, a corresponding Y_t coordinate prediction result is obtained and compared with a true value.
Deploying a coordinate prediction model: deploying the coordinate prediction model to the cloud end to calculate the corrected real coordinates of the tag vehicle to realize accurate navigation and positioning of the UWB on the target and obtain accurate position information.
Compared with the prior art, the invention has the following advantages:
high-precision positioning: the UWB positioning model based on the transducer can provide accurate unmanned vehicle position information, and positioning accuracy is improved.
The anti-interference capability is strong: the self-attention mechanism of the transducer can effectively process multipath effect and interference in UWB signals, and positioning robustness is improved.
The real-time performance is high: because the transducer is adopted, the method has higher calculation efficiency and response speed, and can meet the requirements of real-time navigation and positioning.
Example 2
The invention discloses a positioning system based on ultra-wideband, comprising:
and the position coordinate set determining module is used for determining a position coordinate set of the target point at the current time point based on ultra-wideband signals of the target point received by a plurality of ultra-wideband positioning tags on the target vehicle at the current time point when the target vehicle runs.
The predicted position coordinate determining module is used for inputting the position coordinate set into a coordinate prediction model to obtain the predicted position coordinate of the target point at the current time point; the coordinate prediction model is obtained by training a transducer network by adopting a training set.
The training set sample data comprises input data and label data, the input data is a position coordinate set of a target tracking point determined by ultra-wideband signals of a target vehicle at a sampling time point, and the label data is actual position coordinates of the target tracking point at the sampling time point.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (8)
1. An ultra-wideband based positioning method, comprising:
when a target vehicle runs, determining a position coordinate set of a target point at a current time point based on ultra-wideband signals of the target point received by a plurality of ultra-wideband positioning tags on the target vehicle at the current time point;
inputting the position coordinate set into a coordinate prediction model to obtain the predicted position coordinate of the target point at the current time point; the coordinate prediction model is obtained by training a transducer network by adopting a training set;
the training set sample data comprises input data and label data, the input data is a position coordinate set of a target tracking point determined by an ultra-wideband signal at a sampling time point of a target vehicle, and the label data is an actual position coordinate of the target tracking point at the sampling time point.
2. The ultra-wideband based positioning method of claim 1, wherein the number of ultra-wideband positioning tags on the target vehicle is more than three.
3. The positioning method based on ultra wideband according to claim 2, wherein determining the set of position coordinates of the target point at the current time point based on ultra wideband signals of the target point received by the plurality of ultra wideband positioning tags at the current time point on the target vehicle when the target vehicle is traveling, specifically comprises:
by using the principle of triangulation, a position coordinate of a target point is calculated by using ultra-wideband signals received by every three ultra-wideband positioning labels, and the position coordinate is calculatedPosition coordinates>The location coordinates form the set of location coordinates, and n represents the number of ultra-wideband locating tags on the target vehicle.
4. The ultra-wideband based positioning method of claim 1, wherein the Transformer network comprises an input layer, an encoding layer, a decoding layer and a full connection layer connected in sequence;
the coding layer comprises a plurality of encoders which are sequentially connected in series, and each encoder comprises a first multi-head self-attention layer and a first feedforward neural network layer which are sequentially connected;
the decoding layer comprises a plurality of decoders which are connected in series in sequence, and each decoder comprises a multi-head self-attention layer with a mask, a second multi-head self-attention layer and a second feedforward neural network layer which are connected in sequence.
5. The ultra-wideband based positioning method of claim 4, wherein the input layer is configured to linearly project an input set of position coordinates, and convert dimensions of the set of position coordinates to set hidden dimensions.
6. The ultra-wideband based positioning method of claim 1, wherein a mean square error loss function is used as the loss function when training the fransformer network using the training set.
7. The ultra-wideband based positioning method of claim 1, wherein the Transformer network is trained using a random gradient descent optimizer when training the Transformer network using a training set.
8. An ultra-wideband based positioning system, comprising:
the system comprises a position coordinate set determining module, a target vehicle detecting module and a target vehicle detecting module, wherein the position coordinate set determining module is used for determining a position coordinate set of a target point at a current time point based on ultra-wideband signals of the target point received by a plurality of ultra-wideband positioning tags on the target vehicle at the current time point when the target vehicle runs;
the predicted position coordinate determining module is used for inputting the position coordinate set into a coordinate prediction model to obtain the predicted position coordinate of the target point at the current time point; the coordinate prediction model is obtained by training a transducer network by adopting a training set;
the training set sample data comprises input data and label data, the input data is a position coordinate set of a target tracking point determined by ultra-wideband signals of a target vehicle at a sampling time point, and the label data is actual position coordinates of the target tracking point at the sampling time point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311724878.5A CN117406170A (en) | 2023-12-15 | 2023-12-15 | Positioning method and system based on ultra-wideband |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311724878.5A CN117406170A (en) | 2023-12-15 | 2023-12-15 | Positioning method and system based on ultra-wideband |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117406170A true CN117406170A (en) | 2024-01-16 |
Family
ID=89500364
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311724878.5A Pending CN117406170A (en) | 2023-12-15 | 2023-12-15 | Positioning method and system based on ultra-wideband |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117406170A (en) |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080039119A1 (en) * | 2004-03-18 | 2008-02-14 | Crawford Jason R | Radiolocation in a wireless network using time difference of arrival |
| CN101403793A (en) * | 2008-11-03 | 2009-04-08 | 华南理工大学 | Distribution type node positioning method for wireless sensor network |
| CN107135541A (en) * | 2017-04-21 | 2017-09-05 | 广东技术师范学院 | UWB indoor localization method based on OPTICS Density Clusterings and BP neural network |
| CN107492113A (en) * | 2017-06-01 | 2017-12-19 | 南京行者易智能交通科技有限公司 | A kind of moving object in video sequences position prediction model training method, position predicting method and trajectory predictions method |
| CN108828519A (en) * | 2018-05-24 | 2018-11-16 | 桂林电子科技大学 | A kind of high-precision indoor visible light localization method based on machine learning |
| CN110385720A (en) * | 2019-07-26 | 2019-10-29 | 南京航空航天大学 | A kind of robot localization error compensating method based on deep neural network |
| CN110536245A (en) * | 2019-08-28 | 2019-12-03 | 杭州电子科技大学 | A kind of indoor wireless positioning method and system based on deep learning |
| CN112069820A (en) * | 2020-09-10 | 2020-12-11 | 杭州中奥科技有限公司 | Model training method, model training device and entity extraction method |
| CN112653991A (en) * | 2020-12-23 | 2021-04-13 | 北京工业大学 | WLAN indoor positioning method of TebNet neural network model based on deep learning |
| CN113068118A (en) * | 2021-03-22 | 2021-07-02 | 深圳市锐迪芯电子有限公司 | NB-IoT positioning accuracy improving method and system |
| WO2022036859A1 (en) * | 2020-08-18 | 2022-02-24 | 浙江吉利控股集团有限公司 | Vehicle-mounted positioning assembly, method, device, and apparatus employing ultra-wideband |
| CN114364015A (en) * | 2021-12-10 | 2022-04-15 | 上海应用技术大学 | UWB positioning method based on deep learning |
| CN114719860A (en) * | 2022-04-25 | 2022-07-08 | 天津大学 | Inertial navigation method based on multi-head attention mechanism |
| CN114924225A (en) * | 2022-04-28 | 2022-08-19 | 合肥工业大学 | High-precision indoor positioning method, device, equipment and medium |
| CN115866517A (en) * | 2022-12-09 | 2023-03-28 | 华东师范大学 | Indoor positioning system based on empirical mode decomposition and spatial autoregressive neural network |
| CN116170744A (en) * | 2023-02-28 | 2023-05-26 | 西南大学 | Indoor cross-region blind spot positioning method and system based on ultra-wideband |
| CN116170746A (en) * | 2023-01-03 | 2023-05-26 | 中国人民解放军63983部队 | Ultra-wideband indoor positioning method based on depth attention mechanism and geometric information |
| CN116744441A (en) * | 2023-05-30 | 2023-09-12 | 网络通信与安全紫金山实验室 | Wireless positioning method, device, equipment and storage medium |
| CN117119377A (en) * | 2023-07-12 | 2023-11-24 | 北京工业大学 | Indoor fingerprint positioning method based on filtering transducer |
-
2023
- 2023-12-15 CN CN202311724878.5A patent/CN117406170A/en active Pending
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080039119A1 (en) * | 2004-03-18 | 2008-02-14 | Crawford Jason R | Radiolocation in a wireless network using time difference of arrival |
| CN101403793A (en) * | 2008-11-03 | 2009-04-08 | 华南理工大学 | Distribution type node positioning method for wireless sensor network |
| CN107135541A (en) * | 2017-04-21 | 2017-09-05 | 广东技术师范学院 | UWB indoor localization method based on OPTICS Density Clusterings and BP neural network |
| CN107492113A (en) * | 2017-06-01 | 2017-12-19 | 南京行者易智能交通科技有限公司 | A kind of moving object in video sequences position prediction model training method, position predicting method and trajectory predictions method |
| CN108828519A (en) * | 2018-05-24 | 2018-11-16 | 桂林电子科技大学 | A kind of high-precision indoor visible light localization method based on machine learning |
| CN110385720A (en) * | 2019-07-26 | 2019-10-29 | 南京航空航天大学 | A kind of robot localization error compensating method based on deep neural network |
| CN110536245A (en) * | 2019-08-28 | 2019-12-03 | 杭州电子科技大学 | A kind of indoor wireless positioning method and system based on deep learning |
| WO2022036859A1 (en) * | 2020-08-18 | 2022-02-24 | 浙江吉利控股集团有限公司 | Vehicle-mounted positioning assembly, method, device, and apparatus employing ultra-wideband |
| CN112069820A (en) * | 2020-09-10 | 2020-12-11 | 杭州中奥科技有限公司 | Model training method, model training device and entity extraction method |
| CN112653991A (en) * | 2020-12-23 | 2021-04-13 | 北京工业大学 | WLAN indoor positioning method of TebNet neural network model based on deep learning |
| CN113068118A (en) * | 2021-03-22 | 2021-07-02 | 深圳市锐迪芯电子有限公司 | NB-IoT positioning accuracy improving method and system |
| CN114364015A (en) * | 2021-12-10 | 2022-04-15 | 上海应用技术大学 | UWB positioning method based on deep learning |
| CN114719860A (en) * | 2022-04-25 | 2022-07-08 | 天津大学 | Inertial navigation method based on multi-head attention mechanism |
| CN114924225A (en) * | 2022-04-28 | 2022-08-19 | 合肥工业大学 | High-precision indoor positioning method, device, equipment and medium |
| CN115866517A (en) * | 2022-12-09 | 2023-03-28 | 华东师范大学 | Indoor positioning system based on empirical mode decomposition and spatial autoregressive neural network |
| CN116170746A (en) * | 2023-01-03 | 2023-05-26 | 中国人民解放军63983部队 | Ultra-wideband indoor positioning method based on depth attention mechanism and geometric information |
| CN116170744A (en) * | 2023-02-28 | 2023-05-26 | 西南大学 | Indoor cross-region blind spot positioning method and system based on ultra-wideband |
| CN116744441A (en) * | 2023-05-30 | 2023-09-12 | 网络通信与安全紫金山实验室 | Wireless positioning method, device, equipment and storage medium |
| CN117119377A (en) * | 2023-07-12 | 2023-11-24 | 北京工业大学 | Indoor fingerprint positioning method based on filtering transducer |
Non-Patent Citations (1)
| Title |
|---|
| 邱锡鹏: "神经网络与深度学习", vol. 1, 31 July 2020, 机械工业出版社, pages: 388 - 390 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10976410B1 (en) | Generating data using radar observation model based on machine learning | |
| CN111352444A (en) | Unmanned aerial vehicle outdoor mobile platform autonomous landing method and system based on wireless navigation | |
| US20030169943A1 (en) | Methods and arrangements to enhance correlation | |
| CN113962300A (en) | Radar and AIS fused ship accurate association method | |
| CN104820204A (en) | Weighted least square positioning method with reduced deviation | |
| CN110990505A (en) | Loran-C ASF correction method based on neural network | |
| CN110247719A (en) | The playback of 5G time varying channel and emulation mode based on machine learning | |
| CN114241272B (en) | Heterogeneous information fusion positioning method based on deep learning | |
| Cho et al. | Improving TDoA based positioning accuracy using machine learning in a LoRaWan environment | |
| CN113747360A (en) | Indoor positioning method based on mixed visible light and BLE | |
| CN117406170A (en) | Positioning method and system based on ultra-wideband | |
| CN103487784B (en) | A kind of localization method based on time of arrival (toa) | |
| CN101730224B (en) | Wireless sensor network node positioning method based on distributed optimal strategy | |
| CN112130166A (en) | AGV positioning method and device based on reflector network | |
| CN116704304A (en) | Multi-mode fusion target detection method of mixed attention mechanism | |
| Scharf et al. | A semi-automated multi-sensor data labeling process for deep learning in automotive radar environment | |
| CN107994940A (en) | A kind of visible ray localization method based on TABU search | |
| CN115166702A (en) | Automatic calibration method and device of laser radar to vehicle body coordinate system based on high-precision positioning information | |
| CN110471025B (en) | Single-station three-dimensional positioning and speed measuring method | |
| CN113052906A (en) | Indoor robot positioning method based on monocular camera and odometer | |
| CN111856527A (en) | Indoor positioning method based on pseudolite space signal spectrum | |
| Guanli et al. | New algorithms on the solution to drifting problem of GPS positioning | |
| CN113758489B (en) | Navigation positioning method based on multi-source sensor elastic fusion | |
| CN104297745A (en) | Distance measurement device, distance measurement method and positioning method based on radio wave wavelength | |
| CN115696572B (en) | Method and device for generating positioning data and related equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |