CN115585807A - GNSS/INS integrated navigation method based on machine learning - Google Patents
GNSS/INS integrated navigation method based on machine learning Download PDFInfo
- Publication number
- CN115585807A CN115585807A CN202211587677.0A CN202211587677A CN115585807A CN 115585807 A CN115585807 A CN 115585807A CN 202211587677 A CN202211587677 A CN 202211587677A CN 115585807 A CN115585807 A CN 115585807A
- Authority
- CN
- China
- Prior art keywords
- data
- gnss
- machine learning
- ins
- imu
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
- G01C21/165—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation combined with non-inertial navigation instruments
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- 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
- G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement
- G01S19/47—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement the supplementary measurement being an inertial measurement, e.g. tightly coupled inertial
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Networks & Wireless Communication (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The application discloses a GNSS/INS combined navigation method based on machine learning, which comprises the steps of receiving GNSS signals from a GNSS signal source, generating GNSS data, coupling an INS system to a GNSS receiver, generating IMU signals by using an IMU sensor, generating IMU data, integrating the IMU data with the GNSS data, and generating INS data according to the integrated IMU data and the GNSS data; obtaining geographical position data generated by a GNSS receiver and assistance data other than the geographical position data; training a machine learning model with the assistance data to predict a positioning error based on the residual and the satellite direction information; a data representation of the machine learning model representing a trained version of the machine learning model is output. The reliability of application, the reliability of data and the robustness of signal processing are improved, and the GNSS/INS combined navigation service with full time, all directions and all spaces is provided for the user.
Description
Technical Field
The invention relates to the field of computers, in particular to the field of machine learning, and more particularly to a GNSS/INS combined navigation method based on machine learning.
Background
Global navigation satellite system GNSS receivers are widely used to provide autonomous geospatial positioning, and advances in integration have led to GNSS receivers that can be implemented as Integrated Circuits (ICs), for example, as a system on a chip (SOC). Their low cost and widespread availability make GNSS receivers highly universally applicable, not only in professional fields such as navigation positioning, but also in consumer fields such as smart phones, tablets, cameras, etc. Examples of global navigation satellite systems include, but are not limited to, GPS, GLONASS, and Beidou.
However, due to the multipath propagation of the satellites, the GNSS receiver is prone to positioning errors, a phenomenon also known as "multipath reception", when the GNSS receiver tracks multipath signals, such as radio signals emitted by reflections from close-range buildings, the GNSS receiver may estimate the distance to the emitting satellite in an erroneous way. This phenomenon is particularly present in urban environments where the line of sight (LOS) to the satellite may be obstructed and several radio signals received by a GNSS receiver may be multipath signals.
Several technical solutions have been investigated to mitigate the multipath problem, including the design of radio signals that provide better multipath mitigation at the system level, and dedicated signal processing techniques at the receiver side. The main drawbacks of these approaches include increased complexity of the GNSS receiver and thus increased cost.
Machine learning is a widely used artificial intelligence technique, and different equipment parameter combinations lead to different learning effects of a machine learning model when the machine learning model is generated. At present, all model parameter combinations within a certain range are generally searched according to a certain step length, machine learning models respectively corresponding to the model parameter combinations are trained and verified in sequence, namely, the training and verification are carried out in a serial mode, and the optimal model parameter combination is determined according to a verification result.
Disclosure of Invention
The invention aims to solve at least one technical problem mentioned in the background, and provides a GNSS/INS combined navigation method based on machine learning, which can exert the advantages of each positioning system, improve the reliability of application, the reliability of data and the robustness of signal processing, and provide full-time, all-around and full-space GNSS/INS combined navigation service for users.
A GNSS/INS combined navigation method based on machine learning comprises the following steps:
a GNSS receiver configured to receive GNSS signals from a GNSS signal source at an antenna coupled to the GNSS receiver, generate GNSS data in response to the GNSS signals, transmit the GNSS data to the INS system;
an INS system configured to be coupled to a GNSS receiver, to generate IMU signals with an IMU sensor, to generate IMU data in response to the IMU signals, to integrate the IMU data with the GNSS data in a navigation processing unit of the INS system, and to generate INS data from the integrated IMU data and GNSS data;
the machine learning step includes: acquiring geographical position data generated by a GNSS receiver and assistance data in addition to the geographical position data, the assistance data comprising residuals RES associated with satellites, satellite orientation information AZ, EL indicating the orientation of the satellites with respect to the GNSS receiver; training a machine learning model using the assistance data to predict a positioning error based on the residual and the satellite direction information; a data representation of the machine learning model is output that represents a trained version of the machine learning model.
In one embodiment of the integrated navigation method, reference data TP of the GNSS receiver is obtained, wherein the reference data represents a reference geographical position of the GNSS receiver.
In a particular embodiment of the integrated navigation method, for respective instances of the geographical position data and the reference data, a positioning error is determined as a difference between the calculated geographical position and the reference geographical position.
In a particular embodiment of the integrated navigation method, the geographical position data represent a geographical position calculated by a GNSS receiver.
In a particular embodiment of the combined navigation method, the residuals RES are pseudorange residuals or innovative residuals obtained from kalman filtering performed by the GNSS receiver.
In a particular embodiment of the combined navigation method, the satellite direction information comprises the azimuth AZ and the elevation EL of the satellite in the sky at the calculated geographical position.
In a specific embodiment of the combined navigation method, the method comprises representing the azimuth AZ, the elevation EL and the residual RES as data tuples representing the spherical coordinates in a spherical coordinate system.
In one embodiment of the integrated navigation method, the method further comprises converting the spherical coordinates into cartesian coordinates in an earth-centered earth-fixed coordinate system, wherein the cartesian coordinates are used for training of the machine learning model.
In one embodiment of the integrated navigation method, the integrated navigation system further comprises an integration filter coupled to the GNSS receiver and the INS system and configured to integrate the INS data and the GNSS data.
In a specific embodiment of the integrated navigation method, the INS system is further configured to: transmitting the INS data to the GNSS receiver; and integrates the INS data with the GNSS signals to generate GNSS data.
In a particular embodiment of the integrated navigation method, the navigation processing unit is configured to integrate IMU data and GNSS data in the signal domain.
In one embodiment of the integrated navigation method, integration generates a loosely coupled GNSS with INS integration in the IMU processor when the GNSS data is in the location domain.
In one embodiment of the integrated navigation method, the integrated in the IMU processor generates a GNSS tightly coupled to the INS integration while the GNSS data is in the survey domain.
In one embodiment of the integrated navigation method, the integration generates an ultra-tightly coupled GNSS with INS integration in the IMU processor when the GNSS data is in the signal domain.
In one particular embodiment of the combined navigation method, wherein the IMU sensor is configurable to enhance IMU sensor performance (accuracy, dynamics, usability, etc.), particularly for low cost and small size memims.
The GNSS/INS integrated navigation system based on machine learning comprises:
a GNSS receiver configured to receive GNSS signals from a GNSS signal source at an antenna coupled to the GNSS receiver, generate GNSS data in response to the GNSS signals, and transmit the GNSS data to the INS system;
an INS system configured to be coupled to a GNSS receiver, to generate IMU signals with an IMU sensor, to generate IMU data in response to the IMU signals, to integrate the IMU data with the GNSS data in a navigation processing unit of the INS system, and to generate INS data from the integrated IMU data and GNSS data;
an integration filter configured to be coupled to a GNSS receiver and an INS system and capable of integrating the INS data and the GNSS data;
the system is operated to perform the method.
The beneficial effects of the invention include: the GNSS/INS combined navigation method based on machine learning is provided, the current GNSS/INS integration in an IMU sensor is expanded, so that the INS integration is carried out in an IMU signal domain, a new process of multi-sensor integration with INS and GNSS is realized, and a system integrating the GNSS/INS can improve the performances of the IMU sensor and a GNSS receiver. Thus, as two complementary positioning techniques, GNSS/INS integration can take advantage of each positioning system, INS bias can be calibrated by GNSS signals, GNSS navigation signal disruptions can be mitigated by INS, meaning not only including increased availability, including but not limited to across GNSS navigation signal disruptions, reliability of rejecting data with outliers, and robustness of signal processing. The novel positioning and navigation application service system based on the machine learning model improves the dynamic characteristic and the anti-interference performance of the GNSS receiver, improves the satellite tracking capability of the GNSS receiver in a resource-limited environment, is favorable for simultaneously improving the calibration of the INS system, the air alignment of the inertial navigation system, the stability of a high channel of the inertial navigation system and other levels, effectively improves the performance and the precision of the inertial navigation system, and provides full-time, all-round and full-space GNSS/INS combined navigation service for users.
Drawings
The accompanying drawings, which are included to provide a further understanding of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the principles of the disclosure.
FIG. 1 is a flow chart of the training and validation operations of a machine learning model in an embodiment of the present application.
Detailed Description
Example 1:
the GNSS/INS combined navigation system based on machine learning is provided, and is characterized by comprising:
a GNSS receiver configured to receive GNSS signals from a GNSS signal source at an antenna coupled to the GNSS receiver, generate GNSS data in response to the GNSS signals, transmit the GNSS data to the INS system;
an INS system configured to be coupled to a GNSS receiver, to generate IMU signals with an IMU sensor, to generate IMU data in response to the IMU signals, a navigation processing unit of the INS system to integrate IMU data with GNSS data in a signal domain, and to generate INS data from the integrated IMU data and GNSS data; is further configured to communicate the INS data to the GNSS receiver and integrate the INS data with the GNSS signals to generate GNSS data
An integration filter configured to be coupled to a GNSS receiver and an INS system and capable of integrating the INS data and the GNSS data.
When the GNSS data is in the location domain, the integration generates a loosely coupled GNSS with INS integration in the IMU processor.
In the integrated navigation system, when GNSS data is in the survey domain, the integrated in IMU processor generates a GNSS that is tightly coupled with the INS integration.
In the integrated navigation system, when GNSS data is in the signal domain, integration generates an ultra-tightly coupled GNSS with INS integration in the IMU processor.
In the integrated navigation system, wherein the IMU sensors are configurable to enhance IMU sensor performance (accuracy, dynamics, usability, etc.), particularly for low cost and small size memims.
Example 2:
on the basis of the foregoing embodiments, a method for GNSS/INS combined navigation based on machine learning is provided, which specifically includes the following steps.
Reference data TP of the GNSS receiver is obtained, wherein the reference data represents a reference geographical position of the GNSS receiver.
A positioning error is determined as a difference between the calculated geographic position and the reference geographic position.
The geographical position data represents a geographical position calculated by the GNSS receiver.
The residuals RES are pseudorange residuals or innovative residuals obtained from kalman filtering performed by the GNSS receiver.
The satellite orientation information includes an azimuth AZ and an elevation EL of the satellite in the sky at the calculated geographic position.
The method comprises representing the azimuth AZ, the elevation EL and the residual RES as data tuples representing the spherical coordinates in a spherical coordinate system. The training data may comprise data tuples, each consisting of azimuth AZ, elevation EL and residual RES, which in turn may be considered to represent coordinates or vectors in a spherical coordinate system. That is, elevation and azimuth may indicate direction to the satellite in units of degrees, while the residual may indicate pseudorange error in direction to the satellite in units of meters, indicating magnitude toward or away from the satellite.
Further comprising converting the spherical coordinates to cartesian coordinates in an earth-centered earth-fixed coordinate system, wherein the cartesian coordinates are used for training of the machine learning model. For training, the acquisition of the azimuth AZ, the elevation EL and the residual RES is beneficial, wherein the data elements represented have the same physical meaning. Such a representation may be obtained by converting the azimuth, elevation and residual into earth-centered cartesian coordinates, whereas if represented in an earth-fixed (ECEF) coordinate system, such as the XYZ coordinate system, all elements in this case may have the same physical meaning, such as meters, kilometers, etc.
Acquiring geographical position data generated by a GNSS receiver and assistance data in addition to the geographical position data, the assistance data comprising residuals RES associated with satellites, satellite orientation information AZ, EL indicating the orientation of the satellites with respect to the GNSS receiver; training a machine learning model using the assistance data to predict a positioning error based on the residual and the satellite direction information; a data representation of the machine learning model is output that represents a trained version of the machine learning model.
The machine-learned model may be used to correct the output of the GNSS receiver during operation, more specifically to correct the calculated geographical position by applying the machine-learned model to the assistance data to obtain a positioning error of the calculated geographical position, which may be used as a correction term for the calculated geographical position and may be applied to the calculated geographical position to produce a corrected geographical position, which may be more accurate than the initially calculated geographical position in the sense that the geographical position is less deviated from the actual geographical position, i.e. has a smaller positioning error with respect to the actual geographical position.
As shown in fig. 1, the further optimization scheme further comprises the following steps.
The machine learning model is generated by: an optimal combination of model parameters corresponding to the machine learning model to be generated is determined based on the validation scores, and a machine learning pattern corresponding to the optimal combination of model parameters is generated.
Some optional modes of the machine learning model further include: the method comprises the steps of executing training and verification operations by using a Map task in a Map-Reduce model of a Hadoop distributed computing framework, and executing model generation operations by using a Reduce task in a MapReduce mode of the Hadoop distributed computing framework.
Training and validation of the machine learning model may be performed using the Map-Reduce model of the Hadoop distributed computing framework. The training and validation operations may be performed using the Map task in Hadoop, and the Reduce task execution model generation operations in Hadoop.
Determining an optimal combination of model parameters corresponding to the machine learning model to be generated comprises: calculating an average parameter value of a plurality of verification scores respectively corresponding to the machine learning model after training and verifying the machine model respectively corresponding to the model parameters for a plurality of times; using the average parameter value as a reference model parameter value; and determining an optimal model parameter combination corresponding to the machine learning model to be generated based on the reference model parameter values. For example, when a user sends a request to generate a machine learning model to a server through a terminal and then trains and verifies the machine learning model in parallel, the server returns a reference model parameter value, i.e., an average value of verification scores corresponding to model parameter combinations, to the user terminal, and the user determines an optimal model parameter combination corresponding to the machine learning model to be generated from the reference model parameter value.
The novel positioning and navigation application service system based on the machine learning model is provided, the dynamic characteristic and the anti-interference performance of a GNSS receiver are improved, the satellite tracking capability of the GNSS receiver in a resource-limited environment is improved, the levels of calibration of an inertial navigation system, air alignment of the inertial navigation system, stability of a height channel of the inertial navigation system and the like are improved, the performance and the precision of the inertial navigation system are effectively improved, and the full-time, all-directional and full-space GNSS/INS combined navigation service is provided for a user.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
The invention is not the best known technology.
Claims (10)
1. The GNSS/INS integrated navigation method based on machine learning is characterized by comprising the following steps:
a GNSS receiver and an INS system that receives GNSS signals from a GNSS signal source at an antenna coupled to the GNSS receiver, generates GNSS data in response to the GNSS signals, and transmits the GNSS data to the INS system; the INS system is configured to be coupled to a GNSS receiver, generate IMU signals with an IMU sensor, generate IMU data in response to the IMU signals, integrate the IMU data with GNSS data in a navigation processing unit of the INS system, and generate INS data from the integrated IMU data and GNSS data;
the combined navigation method performs the following machine learning steps: acquiring geographical position data generated by a GNSS receiver and assistance data in addition to the geographical position data, the assistance data comprising residuals RES associated with satellites, satellite orientation information AZ, EL indicating the orientation of the satellites with respect to the GNSS receiver; training a machine learning model using the assistance data to predict a positioning error based on the residual and the satellite direction information; a data representation of the machine learning model representing a trained version of the machine learning model is output.
2. The method of claim 1, wherein:
obtaining reference data TP of the GNSS receiver, wherein the reference data represents a reference geographical position of the GNSS receiver;
for respective instances of the geographic location data and the reference data, a positioning error is determined as a difference between the calculated geographic location and the reference geographic location.
3. The method of claim 2, wherein:
the geographical position data represents a geographical position calculated by the GNSS receiver.
4. The method of claim 3, wherein:
the residuals RES are pseudorange residuals or innovative residuals obtained from kalman filtering performed by the GNSS receiver.
5. The method of claim 4, wherein:
the satellite orientation information comprises an azimuth AZ and an elevation EL of the satellite in the sky at the calculated geographical position.
6. The method of claim 5, wherein:
the combined navigation method comprises representing the azimuth AZ, the elevation EL and the residual RES as a data tuple representing a spherical coordinate in a spherical coordinate system.
7. The method of claim 6, wherein:
further comprising converting the spherical coordinates to cartesian coordinates in an earth-centered earth-fixed coordinate system, wherein the cartesian coordinates are used for training of the machine learning model.
8. The method of claim 7, wherein:
further comprising an integration filter coupled to the GNSS receiver and the INS system and configured to integrate the INS data and the GNSS data.
9. The GNSS/INS integrated navigation system based on machine learning is characterized by comprising:
a GNSS receiver configured to receive GNSS signals from a GNSS signal source at an antenna coupled to the GNSS receiver, generate GNSS data in response to the GNSS signals, and transmit the GNSS data to the INS system;
an INS system configured to be coupled to a GNSS receiver, to generate IMU signals with an IMU sensor, to generate IMU data in response to the IMU signals, to integrate the IMU data with the GNSS data in a navigation processing unit of the INS system, and to generate INS data from the integrated IMU data and GNSS data;
an integration filter configured to be coupled to a GNSS receiver and an INS system and capable of integrating the INS data and the GNSS data;
the system when run performs the method of any of claims 1-8.
10. An apparatus, comprising: a processor; and a memory, wherein the memory stores computer readable instructions executable by the processor, when executed, performing a method of generating a machine learning model, the method comprising:
generating a model parameter combination, and generating machine learning models respectively corresponding to the model parameter combination, wherein the model parameters represent the incidence relation between the input vector and the output vector of the machine learning models;
and executing a dividing operation: dividing preset machine learning data into training data and verification data;
performing training and verification operations: training machine learning models in parallel based on training data, respectively; verifying the learning precision of the trained machine learning model according to verification data to obtain verification scores, wherein the verification scores represent the consistency ratio between data types corresponding to output vectors output by the machine learning model based on the verification data, and the data types are verified;
performing a model generation operation: and determining the optimal model parameter combination corresponding to the machine learning model to be generated according to the verification score, and generating the machine learning model corresponding to the optimal model parameter combination.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211587677.0A CN115585807B (en) | 2022-12-12 | 2022-12-12 | GNSS/INS integrated navigation method based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211587677.0A CN115585807B (en) | 2022-12-12 | 2022-12-12 | GNSS/INS integrated navigation method based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115585807A true CN115585807A (en) | 2023-01-10 |
| CN115585807B CN115585807B (en) | 2023-08-15 |
Family
ID=84783346
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211587677.0A Active CN115585807B (en) | 2022-12-12 | 2022-12-12 | GNSS/INS integrated navigation method based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115585807B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100049439A1 (en) * | 2006-11-07 | 2010-02-25 | Electronics And Telecommunications Research Institute | Apparatus for integrated navigation based on multi filter fusion and method for providing navigation information using the same |
| CN105912500A (en) * | 2016-03-30 | 2016-08-31 | 百度在线网络技术（北京）有限公司 | Machine learning model generation method and machine learning model generation device |
| CN109459776A (en) * | 2018-10-08 | 2019-03-12 | 上海交通大学 | GNSS/INS deep integrated navigation method based on the discontinuous tracking of GNSS signal |
| US20200049837A1 (en) * | 2018-08-09 | 2020-02-13 | Apple Inc. | Machine learning assisted satellite based positioning |
| CN111580144A (en) * | 2020-05-07 | 2020-08-25 | 西北工业大学 | Design method of MINS/GPS ultra-tight integrated navigation system |
| CN112595313A (en) * | 2020-11-25 | 2021-04-02 | 北京海达星宇导航技术有限公司 | Vehicle-mounted navigation method and device based on machine learning and computer equipment |
| CN115166804A (en) * | 2022-07-05 | 2022-10-11 | 常熟理工学院 | GNSS/INS tightly-combined positioning method for predicting measurement noise based on machine learning |
-
2022
- 2022-12-12 CN CN202211587677.0A patent/CN115585807B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100049439A1 (en) * | 2006-11-07 | 2010-02-25 | Electronics And Telecommunications Research Institute | Apparatus for integrated navigation based on multi filter fusion and method for providing navigation information using the same |
| CN105912500A (en) * | 2016-03-30 | 2016-08-31 | 百度在线网络技术（北京）有限公司 | Machine learning model generation method and machine learning model generation device |
| US20200049837A1 (en) * | 2018-08-09 | 2020-02-13 | Apple Inc. | Machine learning assisted satellite based positioning |
| CN109459776A (en) * | 2018-10-08 | 2019-03-12 | 上海交通大学 | GNSS/INS deep integrated navigation method based on the discontinuous tracking of GNSS signal |
| CN111580144A (en) * | 2020-05-07 | 2020-08-25 | 西北工业大学 | Design method of MINS/GPS ultra-tight integrated navigation system |
| CN112595313A (en) * | 2020-11-25 | 2021-04-02 | 北京海达星宇导航技术有限公司 | Vehicle-mounted navigation method and device based on machine learning and computer equipment |
| CN115166804A (en) * | 2022-07-05 | 2022-10-11 | 常熟理工学院 | GNSS/INS tightly-combined positioning method for predicting measurement noise based on machine learning |
Non-Patent Citations (1)
| Title |
|---|
| 白军祥等编著, 辽宁科学技术出版社 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115585807B (en) | 2023-08-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11624843B2 (en) | Systems and methods for reduced-outlier satellite positioning | |
| US20220283320A1 (en) | Systems and methods for high-integrity satellite positioning | |
| CN102326092B (en) | Navigation receiver and method for combined use of a standard RTK system and a global carrier-phase differential positioning system | |
| US10989817B2 (en) | Enhanced UWB and GNSS position measurement system | |
| US11624838B2 (en) | System and method for providing GNSS corrections | |
| CN110320536B (en) | Satellite positioning parameter calibration method, device, terminal equipment and storage medium | |
| JP2018520335A (en) | GNSS real-time kinematic dead reckoning receiver for automobile | |
| AU2009322084B2 (en) | A system and method of reference position determination | |
| US20230184956A1 (en) | System and method for correcting satellite observations | |
| Tsakiri et al. | The use of low-cost, single-frequency GNSS receivers in mapping surveys | |
| US20170293032A1 (en) | Up sampling reference station data | |
| US9720071B2 (en) | Mitigating effects of multipath during position computation | |
| US20110199257A1 (en) | Method and system for updating altitude information for a location by using terrain model information to prime altitude sensors | |
| WO2023236643A1 (en) | Positioning method and apparatus, device and storage medium | |
| CN113917509B (en) | Double-difference ambiguity fixing method, device and readable storage medium | |
| CN115585807B (en) | GNSS/INS integrated navigation method based on machine learning | |
| US20190056511A1 (en) | Reliability determination of location updates in multipath environments | |
| CN116018499A (en) | Positioning using orientation aligned with orientation of environmental features | |
| CN114646992B (en) | Positioning method, apparatus, computer device, storage medium and computer program product | |
| CN110531395B (en) | Method, device and equipment for positioning unmanned vehicle | |
| US11550068B2 (en) | Modeling mutable environmental structures | |
| Haosheng | Intelligent shadow matching based on improved multi-classifier for urban positioning | |
| Lin et al. | A New GPS Position Correction Method Based on |
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 |