CN111856527B - Indoor positioning method based on pseudolite space signal spectrum - Google Patents
Indoor positioning method based on pseudolite space signal spectrum Download PDFInfo
- Publication number
- CN111856527B CN111856527B CN202010788744.XA CN202010788744A CN111856527B CN 111856527 B CN111856527 B CN 111856527B CN 202010788744 A CN202010788744 A CN 202010788744A CN 111856527 B CN111856527 B CN 111856527B
- Authority
- CN
- China
- Prior art keywords
- pseudolite
- neural network
- indoor
- positioning
- indoor positioning
- 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.)
- Active
Links
Images
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
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/01—Satellite radio beacon positioning systems transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/13—Receivers
- G01S19/35—Constructional details or hardware or software details of the signal processing chain
- G01S19/37—Hardware or software details of the signal processing chain
-
- 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
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Abstract
The invention discloses an indoor positioning method based on a pseudolite space signal spectrum, and belongs to the technical field of pseudolite indoor positioning. The method comprises two stages of offline data set construction and online positioning. In an off-line stage, constructing an electromagnetic signal spectrum in a space environment by utilizing the carrier noise spectral density ratio and indoor space position information in the received pseudolite original observation data; the method comprises the steps of learning deep signal features in a signal map through a deep convolutional neural network, and constructing an indoor positioning model; and realizing real-time indoor position estimation by using the constructed model. The method avoids solving the whole-cycle ambiguity and realizes the indoor absolute positioning of the meter level.
Description
Technical Field
The invention relates to the technical field of pseudolite indoor positioning navigation, in particular to an indoor positioning method based on a pseudolite space signal map.
Background
At present, a positioning mode based on navigation satellites basically meets the navigation of people in an outdoor environment. However, in indoor environments, GNSS signals cannot provide accurate positioning information due to occlusion. Therefore, research and development of indoor positioning navigation technology is attracting more and more attention. The pseudolite positioning system has the capability of transmitting the same signals as the astronomical satellites, can provide stable and reliable satellite signals for indoor environments, and enables indoor and outdoor seamless positioning and navigation to be possible based on the existing smart phone hardware conditions, so that the pseudolite positioning system becomes a research hot spot in the indoor positioning field.
However, in the existing pseudo-satellite indoor positioning technology, the position resolving technology based on pseudo-range or carrier phase smoothing pseudo-range faces the technical problems of resolving integer ambiguity, near-far effect and the like, and the indoor positioning based on pseudo-satellites is difficult to be widely applied due to the fact that the influence of indoor multipath signals on the method is large.
Disclosure of Invention
In view of the above, the invention provides an indoor positioning method based on a pseudolite space signal spectrum, which is simple and easy to implement and has higher robustness.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
an indoor positioning method based on a pseudolite space signal spectrum comprises the following steps:
(1) Constructing a signal map of the pseudolite signal in the indoor space environment in an off-line manner;
(2) Constructing a deep convolutional neural network, inputting the signal spectrum obtained in the step (1) into the neural network so as to train the neural network, and obtaining a trained neural network; the output of the neural network is a spatial position coordinate;
(3) And inputting the pseudolite data received by the receiver into a trained neural network, and positioning the receiver in real time.
Further, the specific mode of the step (1) is as follows:
(101) Setting up a multichannel pseudolite positioning system in an indoor positioning area, connecting each channel with a transmitting antenna, and arranging and installing the pseudolite antenna;
(102) Dividing an indoor positioning area into grids with equal sizes, taking corner points of the grids as sampling points, placing receivers at all sampling points, and calibrating the positions of all receivers and the positions of all pseudo satellite antennas by using a total station;
(103) For each sampling point, collecting the carrier noise spectrum density ratio of each pseudo satellite antenna at the point, arranging the carrier noise spectrum density ratios into a line, and attaching the horizontal and vertical coordinates of the corresponding sampling point after the line so as to form a complete line of data; arranging the row data of each sampling point up and down to form a data set;
(104) Preprocessing a data set, and reconstructing each row of data into a single-channel image of M multiplied by M pixels, wherein the M value is larger than the maximum value of the transverse coordinates and the longitudinal coordinates of all the pseudo satellite antenna positions; after pretreatment, each auxiliary image is formed into a signal map in a (a, M, M, 1) format, wherein a is the number of sampling points.
Further, the neural network comprises a convolution layer, a pooling layer and a full connection layer.
Further, the training method for the neural network in the step (2) is as follows:
dividing all signal patterns into a plurality of different training sets and test sets, training the neural network by using the training sets, testing the trained neural network by using the test sets, performing parameter tuning on the neural network according to test results, and repeatedly training and testing to obtain the trained neural network.
Compared with the prior art, the invention has the following beneficial effects:
(1) The invention provides a method for constructing a pseudolite electromagnetic signal spectrum in an indoor environment by using a pseudolite carrier noise spectrum density ratio and space position information, which can realize effective utilization of the space distribution characteristics of pseudolite signals.
(2) The invention provides an indoor positioning method based on a deep convolutional neural network model by combining a constructed pseudo satellite signal map, wherein a positioning model is trained by learning deep features through multi-layer convolutional processing, and the positioning model can be used for indoor real-time positioning.
(3) Compared with the traditional indoor pseudo satellite positioning method, the method does not need to solve the integer ambiguity, and reduces the computational complexity. In addition, the pseudo-satellite information such as pseudo-range and carrier wave is not utilized in the method, so that the influence of indoor multipath on positioning accuracy is reduced, and the method has high robustness.
Drawings
Fig. 1 is a flowchart of a positioning method according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a positioning system according to an embodiment of the invention.
Fig. 3 is a schematic diagram of a format of a data set according to an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the drawings and detailed description.
An indoor positioning method based on a pseudolite space signal spectrum comprises two stages of offline data set construction and online positioning. In the method, the pseudolite base station can send navigation signals with unique C/A codes, is compatible with GPS L1 codes and BDS B1 codes, and generates channel signals by 1PPS at the same time, so that a commercial GNSS receiver can receive the pseudolite signals. In the off-line stage, the carrier noise spectral density ratio C/N in the received pseudolite original observation data is utilized 0 And constructing an electromagnetic signal map in the space environment by the indoor space position information; learning deep signal features in a pseudo satellite signal map through a deep convolutional neural network, and constructing an indoor positioning model; in the online positioning stage, real-time indoor position estimation is realized by using the constructed model, and the flow of the method is shown in figure 1.
The method specifically comprises the following steps:
step 1: and setting up a multichannel pseudolite positioning system in the indoor positioning area, wherein each channel is connected with a transmitting antenna, and the pseudolite antennas are deployed and installed at different indoor positions.
As shown in fig. 2, the multi-channel pseudolite indoor positioning system comprises a multi-channel signal transmitter, an antenna, a receiver and an intelligent terminal, wherein the multi-channel signal transmitter transmits navigation signals through various transmitting antennas, each pseudolite transmitting antenna in the antenna corresponds to one pseudolite channel of the multi-channel signal transmitter, the signals of each pseudolite channel have unique C/a codes, the pseudolite channels are modulated by the L1 codes of a GPS and the B1 codes of a BDS, and the channel signals are generated by 1PPS at the same time; the receiver comprises a GNSS receiving chip and a receiving antenna.
Step 2: and (2) establishing a coordinate system in the positioning area in the step (1), dividing grids of the indoor area at equal intervals according to positioning requirements, wherein the corner points of each grid are used as sampling points, as shown in fig. 2. The receiver is placed at each sampling point, and the position u of the receiver is calibrated by using the total station i (i=1, 2, …, a), a being the number of sampling points, and the position p of each antenna j (j=1, 2, …, b), b being the number of satellite antennas.
Step 3: collecting carrier noise spectrum density ratio C/N of each antenna of pseudolite at all sampling point positions 0 And the corresponding sampling point position u i The data set dataset constituting row a and column (b+2) is shown in fig. 3, where x and y represent the horizontal and vertical coordinates of the corresponding sampling points.
Step 4: preprocessing the dataset described in step 3, reconstructing each row of data into a single-channel image of m×m pixels, wherein the determination of the M value depends on the coordinate position p of the pseudolite antenna, i.e. the M value is larger than the maximum value of the transverse/longitudinal coordinates of all antenna positions. After pretreatment, each auxiliary image is formed into a signal map radio in the format of (a, M, M, 1).
Step 5: the method comprises the steps of constructing a multi-layer convolutional neural network model consisting of a convolutional layer, a pooling layer and a full-connection layer, wherein the input of the multi-layer convolutional neural network model is a preprocessed pseudolite signal spectrum, and the output of the multi-layer convolutional neural network model is a space position coordinate.
Step 6: dividing the radio map constructed in the step 4 into different training sets and test sets by using a cross-validation mode, training the constructed multi-layer convolutional neural network model, performing parameter tuning, and storing the trained positioning model.
Step 7: in real-time positioning, the pseudolite data received by the receiver is input into the positioning model in step 6, and the current position coordinates of the receiver are estimated.
According to the method, the electromagnetic signal spectrum of the pseudolite signal in the indoor space environment is built offline, deep signal characteristics are learned by using a deep convolutional neural network, and real-time indoor positioning in an online stage is realized. Wherein, the fakeThe satellite can send navigation signals with unique C/A codes, is compatible with GPS L1 codes and BDS B1 codes, and all channel signals are simultaneously generated by 1 PPS. The signal spectrum is formed by the carrier noise spectrum density ratio C/N in pseudolite original observation data 0 Indoor space position information. The deep convolutional neural network is used as a feature extraction mode to learn the space distribution features of the pseudolite signals and is used for constructing a position estimation model.
In a word, the invention solves the problems of complex time synchronization and ambiguity resolution in the traditional pseudolite indoor positioning method, and provides an indoor positioning method based on a pseudolite indoor signal map. In this method, a multichannel signal transmitter is used to transmit different PRN codes whose signals are compatible with the GPS and BDS signals. Commercial GNSS receivers can receive these signals and build a signal transmission system. By means of the innovative offline data set construction mode, the distribution of the carrier noise spectral density ratio of the pseudolite in the indoor space environment is visualized, the deep representative features are fully learned by combining the deep convolutional neural network model, and the indoor positioning model is obtained through training. Accurate position estimation can be achieved during the real-time positioning phase. The method is verified through experiments, and the results show that the method can provide dynamic and static absolute positioning accuracy of the rice level without the initial position, and compared with the traditional indoor pseudolite ambiguity resolution method, the method reduces the operation complexity of a user and improves the coverage and continuity of the positioning result.
Claims (3)
1. An indoor positioning method based on a pseudolite space signal spectrum is characterized by comprising the following steps:
(1) Constructing a signal map of the pseudolite signal in the indoor space environment in an off-line manner; the specific method is as follows:
(101) Setting up a multichannel pseudolite positioning system in an indoor positioning area, connecting each channel with a transmitting antenna, and arranging and installing the pseudolite antenna;
(102) Dividing an indoor positioning area into grids with equal sizes, taking corner points of the grids as sampling points, placing receivers at all sampling points, and calibrating the positions of all receivers and the positions of all pseudo-satellite antennas by using a total station;
(103) For each sampling point, collecting the carrier noise spectrum density ratio of each pseudolite antenna at the point, arranging the carrier noise spectrum density ratios into a line, and attaching the horizontal and vertical coordinates of the corresponding sampling point after the line so as to form a complete line of data; arranging the row data of each sampling point up and down to form a data set;
(104) Preprocessing a data set, and reconstructing each row of data into a single-channel image of M multiplied by M pixels, wherein the M value is larger than the maximum value of the transverse coordinates and the longitudinal coordinates of all the pseudo satellite antenna positions; after pretreatment, each auxiliary image is formed into a signal map in a (a, M, M, 1) format, wherein a is the number of sampling points;
(2) Constructing a deep convolutional neural network, inputting the signal spectrum obtained in the step (1) into the neural network so as to train the neural network, and obtaining a trained neural network; the output of the neural network is a spatial position coordinate;
(3) And inputting the pseudolite data received by the receiver into a trained neural network, and positioning the receiver in real time.
2. The indoor positioning method based on the pseudolite spatial signal spectrum according to claim 1, wherein the neural network comprises a convolution layer, a pooling layer and a full connection layer.
3. The indoor positioning method based on pseudolite spatial signal spectrum according to claim 2, wherein the training mode of the neural network in the step (2) is as follows:
dividing all signal patterns into a plurality of different training sets and test sets, training the neural network by using the training sets, testing the trained neural network by using the test sets, performing parameter tuning on the neural network according to test results, and repeatedly training and testing to obtain the trained neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010788744.XA CN111856527B (en) | 2020-08-07 | 2020-08-07 | Indoor positioning method based on pseudolite space signal spectrum |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010788744.XA CN111856527B (en) | 2020-08-07 | 2020-08-07 | Indoor positioning method based on pseudolite space signal spectrum |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111856527A CN111856527A (en) | 2020-10-30 |
| CN111856527B true CN111856527B (en) | 2023-06-20 |
Family
ID=72972278
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010788744.XA Active CN111856527B (en) | 2020-08-07 | 2020-08-07 | Indoor positioning method based on pseudolite space signal spectrum |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111856527B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113267191A (en) * | 2021-05-26 | 2021-08-17 | 中国电子科技集团公司第五十四研究所 | Unmanned navigation system and method based on pseudolite indoor signal map correction |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105182382A (en) * | 2015-08-05 | 2015-12-23 | 中国电子科技集团公司第五十四研究所 | Centimeter-level positioning method of pseudo satellite |
| CN106941718A (en) * | 2017-04-07 | 2017-07-11 | 南京邮电大学 | A kind of mixing indoor orientation method based on signal subspace fingerprint base |
| CN110456307A (en) * | 2019-07-31 | 2019-11-15 | 东南大学 | A kind of method of locating terminal based on indoor Pseudolite signal carrier-to-noise ratio |
| CN110716217A (en) * | 2019-10-29 | 2020-01-21 | 中国电子科技集团公司第五十四研究所 | Array pseudo satellite indoor positioning method and system |
-
2020
- 2020-08-07 CN CN202010788744.XA patent/CN111856527B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105182382A (en) * | 2015-08-05 | 2015-12-23 | 中国电子科技集团公司第五十四研究所 | Centimeter-level positioning method of pseudo satellite |
| CN106941718A (en) * | 2017-04-07 | 2017-07-11 | 南京邮电大学 | A kind of mixing indoor orientation method based on signal subspace fingerprint base |
| CN110456307A (en) * | 2019-07-31 | 2019-11-15 | 东南大学 | A kind of method of locating terminal based on indoor Pseudolite signal carrier-to-noise ratio |
| CN110716217A (en) * | 2019-10-29 | 2020-01-21 | 中国电子科技集团公司第五十四研究所 | Array pseudo satellite indoor positioning method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111856527A (en) | 2020-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101631349B (en) | Method, device and wireless operation maintenance center for positioning terminal | |
| EP3608690B1 (en) | Gnss receiver with an on-board capability to implement an optimal error correction mode | |
| CN100381835C (en) | Radio combined positioning method based on digital broadcasting-television signal | |
| CN107607970B (en) | Indoor positioning information pushing method based on GNSS satellite signals | |
| CN102928860B (en) | Method for improving GPS (Global Positioning System) positioning precision on the basis of local positioning information | |
| CN110515100A (en) | More array element RTK receiver test methods under complex jamming environment | |
| CN106842123A (en) | A kind of indoor orientation method and indoor locating system | |
| CN104735620A (en) | Accurate positioning method based on multiple base stations | |
| CN111856527B (en) | Indoor positioning method based on pseudolite space signal spectrum | |
| CN105629197B (en) | A kind of radiation source localization method based on received signal power information | |
| CN109116385A (en) | A kind of long-range network RTK tropospheric delay estimation method based on BP neural network | |
| CN103096465B (en) | Environment self-adaption multi-target direct locating method | |
| CN113534196B (en) | Indoor two-dimensional high-precision positioning method and system based on virtual GNSS signals | |
| CN205384374U (en) | Combination positioner in environment of city | |
| CN110568458A (en) | ionosphere VTEC closed-loop test system and method based on GNSS | |
| CN111060945B (en) | GNSS/5G tight combination fusion positioning method and device | |
| CN102540225A (en) | Programmable smart mobile phone based CORS (continuous operational reference system) positioning implementing method | |
| CN109901109B (en) | Method, terminal and system for realizing time service based on air interface time delay measurement | |
| CN116106949A (en) | Indoor positioning system and method based on pseudolite | |
| CN109000661B (en) | Indoor navigation method based on pseudolite carrier-to-noise ratio fingerprint | |
| CN101718863A (en) | Signal processing method for active coding radiometric calibration | |
| CN106908757A (en) | A kind of method that single system realizes indoor and outdoor continuous precise positioning on a large scale | |
| CN110456307B (en) | Terminal positioning method based on indoor pseudo satellite signal carrier-to-noise ratio | |
| FI115167B (en) | Method and system for positioning and device | |
| CN112731497A (en) | Method for improving satellite positioning precision by using field vision field analysis |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |