CN107643088A - Navigation of Pilotless Aircraft method, apparatus, unmanned plane and storage medium - Google Patents
Navigation of Pilotless Aircraft method, apparatus, unmanned plane and storage medium Download PDFInfo
- Publication number
- CN107643088A CN107643088A CN201710679998.6A CN201710679998A CN107643088A CN 107643088 A CN107643088 A CN 107643088A CN 201710679998 A CN201710679998 A CN 201710679998A CN 107643088 A CN107643088 A CN 107643088A
- Authority
- CN
- China
- Prior art keywords
- data
- ins
- ins data
- unmanned plane
- train
- 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
Landscapes
- Navigation (AREA)
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The applicable field of computer technology of the present invention, there is provided a kind of Navigation of Pilotless Aircraft method, apparatus, unmanned plane and storage medium, this method include:Pass through the GLONASS on unmanned plane,Inertial navigation system,Gather the satellite location data and INS data of unmanned plane,When detecting that satellite location data interrupts or be abnormal,By in the good inertial navigation forecast model of INS data inputs training in advance,Generate the predicted value of INS data,According to INS data and the predicted value of INS data,Calculate the error of INS data,Kalman filtering is carried out to the error of INS data,According to the INS data errors after Kalman filtering,INS data are calibrated,INS data after calibration are arranged to the navigation data of unmanned plane,So as to aid in Kalman filter by the inertial navigation forecast model trained,Accuracy compensation is carried out to INS data when satellite location data interrupts or be abnormal,Significantly reduce amount of calculation,And then improve the precision and real-time of Navigation of Pilotless Aircraft.
Description
Technical field
The invention belongs to Navigation of Pilotless Aircraft technical field, more particularly to a kind of Navigation of Pilotless Aircraft method, apparatus, unmanned plane and
Storage medium.
Background technology
Along with the introducing of sophisticated machine people's technology, unmanned plane accelerates intelligentized paces of marching toward, and this is that unmanned plane exists
The application of numerous areas creates unlimited possibility.Navigation system is the core apparatus of unmanned plane, by the motion for determining unmanned plane
Parameter realizes the flight control to unmanned plane.
At present, the navigation system for being widely used in unmanned plane mainly has GLONASS (Global
Navigation Satellite System, GNSS), inertial navigation system (Inertial Navigation System,
INS), celestial navigation system etc., wherein, GNSS include american global positioning system (Global Positioning System,
GPS), russian system (GLONASS), the Galileo system (GALILEO) in Europe, the big-dipper satellite of China
Navigation system.GNSS possesses the advantages of positioning precision is high, not by region and time restriction, but navigation information updating frequency is low, dynamic
State property can be insufficient, can not meet the needs of unmanned plane high dynamic controls in real time.INS is short under conditions of primary condition correctly gives
Shi Jingdu is high, and can provide continuous navigation information (posture, position, speed) in real time, but the error navigated is over time
Passage is not short cumulative.Therefore, different navigation system is generally combined navigation according to advantage and disadvantage and main application.
INS/GPS integrated navigation systems are integrated navigation system based on INS, supplemented by GPS, be widely used in aircraft,
On guided weapon, automobile.The integrated navigation system by INS independence is good, strong antijamming capability, precision is high in short-term the advantages that with
The advantages that GPS long-term statics performance is good, global and all weather navigation combines, and compensate for the defects of both work independently.
But when gps signal is blocked or be disturbed missing or the interruption of short time, INS error can be due to that can not obtain school
It is accurate and add up rapidly, cause navigation information to dissipate.
At present, the method for solving the problem includes:One method matched using earth's magnetic field database with geomagnetic sensor is obtained
The latitude and longitude information of unmanned plane position is obtained, to realize the lasting amendment in the case where GPS is invalid to INS errors, this method pair
The calculating platform of unmanned plane requires high and only effective to the error of horizontal level, and gps signal in the height direction is still sent out
Dissipate;Two, using the attitude information implied between geomagnetic field measuring value and estimate, are fed back to nobody by geomagnetic fieldvector error
Machine attitude angular velocity measured value is modified, and restrained effectively the diverging of inertial navigation system attitude information, but this method is only
The diverging of attitude information can be improved, it is limited to the correcting action of speed and position;Three replace using Dempster-Shafer is theoretical
Kalman filtering carries out data fusion, and simulates the pass between INS measured values and INS resolution errors using SVMs
System, obtains the navigation information of higher precision, but the real-time of this method is poor.
The content of the invention
It is an object of the invention to provide a kind of Navigation of Pilotless Aircraft method, apparatus, unmanned plane and storage medium, it is intended to solves
Due in the integrated navigation of prior art GLONASS and inertial navigation system, because GLONASS by
To the abnormal signal that causes GLONASS to receive or during interruption of disturbing or be blocked, high data can not
Effectively calibrated, cause unmanned plane navigation information dissipate the problem of.
On the one hand, the invention provides a kind of Navigation of Pilotless Aircraft method, methods described to comprise the steps:
By default GLONASS, default inertial navigation system on unmanned plane, the unmanned plane is gathered
Satellite location data and INS data;
When detecting that the satellite location data interrupts or be abnormal, by good used of the INS data inputs training in advance
Property navigation forecast model in, generate the predicted values of the INS data;
According to the INS data and the predicted value of the INS data, the error of the INS data is calculated, to the INS
The error of data carries out Kalman filtering;
According to the INS data errors after the Kalman filtering, the INS data are calibrated, after the calibration
INS data be arranged to the navigation data of the unmanned plane.
On the other hand, the invention provides a kind of Navigation of Pilotless Aircraft device, described device to include:
Data acquisition unit, for passing through default GLONASS, default inertial navigation system on unmanned plane
System, gather the satellite location data and INS data of the unmanned plane;
Inertia forecasting unit, it is for when detecting that the satellite location data interrupts or be abnormal, the INS data are defeated
Enter in the good inertial navigation forecast model of training in advance, generate the predicted value of the INS data;
First filter unit, for the predicted value according to the INS data and the INS data, calculate the INS data
Error, Kalman filtering is carried out to the errors of the INS data;And
Navigation elements are calibrated, for according to the INS data errors after the Kalman filtering, being carried out to the INS data
Calibration, the INS data after the calibration are arranged to the navigation data of the unmanned plane.
On the other hand, present invention also offers a kind of unmanned plane, including memory, processor and it is stored in the storage
In device and the computer program that can run on the processor, realized as above during computer program described in the computing device
State the step described in Navigation of Pilotless Aircraft method.
On the other hand, present invention also offers a kind of computer-readable recording medium, the computer-readable recording medium
Computer program is stored with, the step as described in above-mentioned Navigation of Pilotless Aircraft method is realized when the computer program is executed by processor
Suddenly.
The present invention gathers defending for unmanned plane by default GLONASS, inertial navigation system on unmanned plane
Star location data and INS data, when collecting satellite location data and interrupting or be abnormal, INS data inputs are trained used
Property navigation forecast model in, generate the predicted value of INS data, according to INS data and the predicted value of INS data, calculate INS data
Error, and to the error carry out Kalman filtering, according to the error after Kalman filtering, INS data are calibrated, high-ranking officers
INS data after standard are arranged to the navigation data of unmanned plane, so as to aid in karr by the inertial navigation forecast model trained
Graceful wave filter, accuracy compensation is carried out to INS data when satellite location data interrupts or be abnormal, effectively reduces INS data
Error, and significantly reduce amount of calculation, and then improve the precision and real-time of Navigation of Pilotless Aircraft.
Brief description of the drawings
Fig. 1 is the implementation process figure for the Navigation of Pilotless Aircraft method that the embodiment of the present invention one provides;
Fig. 2 is the reality of inertial navigation forecast model training process in the Navigation of Pilotless Aircraft method that the embodiment of the present invention two provides
Existing flow chart;
Fig. 3 is the structural representation for the Navigation of Pilotless Aircraft device that the embodiment of the present invention three provides;
Fig. 4 is the preferred structure schematic diagram for the Navigation of Pilotless Aircraft device that the embodiment of the present invention three provides;And
Fig. 5 is the structural representation for the unmanned plane that the embodiment of the present invention four provides.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
It is described in detail below in conjunction with specific implementation of the specific embodiment to the present invention:
Embodiment one:
Fig. 1 shows the implementation process for the Navigation of Pilotless Aircraft method that the embodiment of the present invention one provides, for convenience of description, only
The part related to the embodiment of the present invention is shown, details are as follows:
In step S101, by default GLONASS, default inertial navigation system on unmanned plane, adopt
Collect the satellite location data and INS data of unmanned plane.
In embodiments of the present invention, GLONASS and inertial navigation system are pre-set on unmanned plane
(INS), GLONASS with being navigated by way of inertial navigation system integrated navigation to unmanned plane.It can pass through
GLONASS receives the current satellite location data of unmanned plane, current by inertial navigation system collection unmanned plane
INS data.Satellite location data resolve and can obtain the current position of unmanned plane, velocity information.In inertial navigation system
Bag barometertic altimeter, accelerometer, gyroscope and magnetometer, the height and unmanned plane of unmanned plane present position can be obtained
The 3-axis acceleration of motion state, dimensionally tri-axis angular rate, magnetic vector parameter, the INS data that these data are formed are carried out
Resolving can obtain the information such as the current speed of unmanned plane, yaw angle and position.
In step s 102, it is when detecting that satellite location data interrupts or be abnormal, INS data inputs training in advance is good
Inertial navigation forecast model in, generate INS data predicted value.
In embodiments of the present invention, when detecting that satellite location data interrupts or be abnormal, INS data are resolved,
The good inertial navigation forecast model of position that INS data calculations are obtained, speed data input training in advance, generates INS data
Predicted value.Wherein, inertial navigation forecast model satellite location data do not occur interrupt or it is abnormal when train to obtain, in detail
Thin training process can refer to the description of each step in embodiment two.
In step s 103, according to INS data and the predicted value of INS data, the error of calculating INS data, to INS data
Error carry out Kalman filtering.
In embodiments of the present invention, the difference of the predicted value of the INS data after resolving and INS data is calculated, to obtain INS
The error of data, processing is filtered to the error of INS data by default Kalman filter.
In step S104, according to the INS data errors after Kalman filtering, INS data are calibrated, after calibration
INS data be arranged to the navigation data of unmanned plane.
In embodiments of the present invention, according to the INS data errors after Kalman filtering, the INS data after resolving are carried out
Calibration, the INS data after calibration can be as the navigation data of unmanned plane.
Preferably, when the satellite location data that GLONASS receives is normal, to satellite location data and
INS data are resolved, and are calculated the difference of the satellite location data after resolving and the INS data after resolving, are filtered by Kalman
Ripple device carries out Kalman filtering to the difference, according to the difference after Kalman filtering, INS data is calibrated, after calibration
INS data be arranged to the navigation data of unmanned plane, so as to when satellite location data is normal, realize that unmanned plane worldwide navigation is defended
The integrated navigation of star system and inertial navigation system.
Preferably, GPS is global positioning system, and satellite location data is gps data, so as to ensure
The stability and accuracy of location data.
In embodiments of the present invention, by the GLONASS on unmanned plane, inertial navigation system, nobody is gathered
The satellite location data and INS data of machine, when detecting that satellite location data interrupts or be abnormal, INS data inputs are trained
In good inertial navigation forecast model, the predicted value of INS data is generated, according to INS data and the predicted value of INS data, is calculated
The error of INS data, according to the INS data errors after Kalman filtering, INS data are calibrated, by the INS numbers after calibration
According to the navigation data for being arranged to unmanned plane, so that Kalman filter is aided in by the inertial navigation forecast model trained,
Accuracy compensation is carried out to INS data when satellite location data interrupts or be abnormal, effectively reduces the error of INS data, and entirely
The combination of ball navigational satellite system and inertial navigation system is pine combination, significantly reduces amount of calculation, and then improve
The precision and real-time of Navigation of Pilotless Aircraft.
Embodiment two:
Fig. 2 shows inertial navigation forecast model training process in the Navigation of Pilotless Aircraft method that the embodiment of the present invention two provides
Implementation process, for convenience of description, illustrate only the part related to the embodiment of the present invention, details are as follows:
In step s 201, BP neural network model is built, BP neural network model is initialized.
In embodiments of the present invention, BP neural network model is built, the weights of BP neural network model can be carried out random
Initialization, and the parameter such as learning rate, learning objective and maximum iteration to BP neural network model initializes.
In step S202, it is used for what is trained by what GLONASS and inertial navigation system gathered unmanned plane
Satellite location data and the INS data for training.
In step S203, satellite location data and the difference of the INS data for training for training are calculated, to difference
Value carries out Kalman filtering, obtains the error of the INS data for training.
In embodiments of the present invention, to collect the satellite location data for being used to train, INS data solve respectively
Calculate, calculate satellite location data and the difference of INS data after resolving, and Kalman filtering is carried out to difference, obtain being used to train
INS data error.
As illustratively, the error after Kalman filtering is represented by X=[Δ L Δ λ Δ h Δs νEΔνNΔνU], wherein,
Δ L, Δ λ, Δ h are respectively the longitudes of INS data and satellite location data, latitude, the difference of height, Δ vE、ΔvN、ΔvURespectively
For INS data east orientation, north orientation, error from day to translational speed.
In step S204, according to the error of the INS data for training, the INS data for training are calibrated,
According to the INS data for being used to train after calibration and before calibration, BP neural network model is trained, by the BP trained god
Inertial navigation forecast model is arranged to through network model.
In inventive embodiments, INS data (value after resolving) can be entered according to the error of the INS data for training
Row calibration, the INS data before calibration is arranged to the input of BP neural network model, by the computing of BP neural network model,
The INS data of BP neural network model output are obtained, calculate the INS data of BP neural network model output and the INS after calibration
The difference of data, the difference is arranged to the feedback of BP neural network model, repaiied with the weight to BP neural network model
Just, when the frequency of training of BP neural network model reaches maximum iteration or the INS data of BP neural network model output
When reaching the limits of error with the difference of the INS data after calibration, deconditioning simultaneously obtains the BP neural network mould trained
Type, otherwise continue to train BP neural network model.The inertial navigation BP network models trained being arranged in embodiment one
Forecast model.
In embodiments of the present invention, build and initialize BP neural network model, by GLONASS and be used to
Property navigation system collection unmanned plane the satellite location data for being used to train and INS data for training, to satellite digit
Kalman filtering is carried out according to the difference of INS data, according to the difference after Kalman filtering, INS data are calibrated, according to
The front and rear INS data of calibration, are trained to BP neural network model, the BP neural network model trained are arranged into inertia
Navigate forecast model, so as to which when satellite location data is normal, training obtains BP neural network model, to pass through BP neural network
The mode of model-aided Kalman filter, realize when satellite location data interrupts or be abnormal to the accuracy compensations of INS data,
The diverging of INS data is restrained effectively, and the combination of GLONASS and inertial navigation system is pine combination,
Amount of calculation is significantly reduced, improves the precision and real-time of Navigation of Pilotless Aircraft.
Embodiment three:
Fig. 3 shows the structure for the Navigation of Pilotless Aircraft device that the embodiment of the present invention three provides, and for convenience of description, only shows
The part related to the embodiment of the present invention, including:
Data acquisition unit 31, for passing through default GLONASS, default inertial navigation on unmanned plane
System, gather the satellite location data and INS data of unmanned plane.
In embodiments of the present invention, GLONASS and inertial navigation system are pre-set on unmanned plane
(INS), GLONASS with being navigated by way of inertial navigation system integrated navigation to unmanned plane.It can pass through
GLONASS receives the current satellite location data of unmanned plane, current by inertial navigation system collection unmanned plane
INS data.Satellite location data resolve and can obtain the current position of unmanned plane, velocity information.In inertial navigation system
Bag barometertic altimeter, accelerometer, gyroscope and magnetometer, the height and unmanned plane of unmanned plane present position can be obtained
The 3-axis acceleration of motion state, dimensionally tri-axis angular rate, magnetic vector parameter, the INS data that these data are formed are carried out
Resolving can obtain the information such as the current speed of unmanned plane, yaw angle and position.
Inertia forecasting unit 32, for when detect satellite location data interrupt or it is abnormal when, INS data inputs is advance
In the inertial navigation forecast model trained, the predicted value of INS data is generated.
In embodiments of the present invention, when detecting that satellite location data interrupts or be abnormal, INS data are resolved,
The good inertial navigation forecast model of position that INS data calculations are obtained, speed data input training in advance, generates INS data
Predicted value.Wherein, inertial navigation forecast model satellite location data do not occur interrupt or it is abnormal when train to obtain.
First filter unit 33, for the predicted value according to INS data and INS data, the error of INS data is calculated, it is right
The error of INS data carries out Kalman filtering.
In embodiments of the present invention, the difference of the predicted value of the INS data after resolving and INS data is calculated, to obtain INS
The error of data, the error of INS data is filtered by default Kalman filter.
Navigation elements 34 are calibrated, for according to the INS data errors after Kalman filtering, calibrating, inciting somebody to action to INS data
INS data after calibration are arranged to the navigation data of unmanned plane.
In embodiments of the present invention, according to the INS data errors after Kalman filtering, the INS data after resolving are carried out
Calibration, the INS data after calibration can be as the navigation data of unmanned plane.
Preferably, as shown in figure 4, Navigation of Pilotless Aircraft device also includes model construction unit 41, collecting training data unit
42nd, the second filter unit 43 and model training unit 44, wherein:
Model construction unit 41, for building BP neural network model, BP neural network model is initialized.
In embodiments of the present invention, BP neural network model is built, the weights of BP neural network model can be carried out random
Initialization, and the parameter such as learning rate, learning objective and maximum iteration to BP neural network model initializes.
Collecting training data unit 42, for gathering unmanned plane by GLONASS and inertial navigation system
Satellite location data for training and the INS data for training.
Second filter unit 43, for calculating the difference for the satellite location data trained and the INS data for training
Value, Kalman filtering is carried out to difference, obtains the error of the INS data for training.
In embodiments of the present invention, to collect the satellite location data for being used to train, INS data solve respectively
Calculate, calculate satellite location data and the difference of INS data after resolving, and Kalman filtering is carried out to difference, obtain being used to train
INS data error.
Model training unit 44, for the error according to the INS data for being used to train, the INS data for training are entered
Row calibration, according to the INS data for being used to train after calibration and before calibration, BP neural network model is trained, will be trained
Good BP neural network model is arranged to inertial navigation forecast model.
In inventive embodiments, INS data (value after resolving) can be entered according to the error of the INS data for training
INS data before calibration, can be arranged to the input of BP neural network model, by the fortune of BP neural network model by row calibration
Calculate, obtain the INS data of BP neural network model output, after the INS data and the calibration that calculate the output of BP neural network model
The difference of INS data, the difference is arranged to the feedback of BP neural network model, to be carried out to the weight of BP neural network model
Amendment, when the frequency of training of BP neural network model reaches the INS numbers of maximum iteration or the output of BP neural network model
When reaching the limits of error according to the difference with the INS data after calibration, deconditioning simultaneously obtains the BP neural network trained
Model, otherwise continue to train BP neural network model.The inertia that the BP network models trained are arranged in embodiment one is led
Navigate forecast model.
Preferably, model training unit 44 includes mode input unit 441 and model feedback unit 442, wherein:
Mode input unit 441, for the INS data for being used to train before calibration to be arranged into BP neural network model
Input, obtain the INS data of BP neural network model output;And
Model feedback unit 442, for by the INS data of output with calibration after be used for train INS data difference
The feedback of BP neural network model is arranged to, is modified with the weight to BP neural network model.
Preferably, when the satellite location data that GLONASS receives is normal, to satellite location data and
INS data are resolved, and are calculated the difference of the satellite location data after resolving and the INS data after resolving, are filtered by Kalman
Ripple device carries out Kalman filtering to the difference, according to the difference after Kalman filtering, INS data is calibrated, after calibration
INS data be arranged to the navigation data of unmanned plane, so as to when satellite location data is normal, realize that unmanned plane worldwide navigation is defended
The integrated navigation of star system and inertial navigation system.
Preferably, GPS is global positioning system, and satellite location data is gps data, so as to ensure
The stability and accuracy of location data.
In embodiments of the present invention, by the GLONASS on unmanned plane, inertial navigation system, nobody is gathered
The satellite location data and INS data of machine, when detecting that satellite location data interrupts or be abnormal, INS data inputs are trained
In good inertial navigation forecast model, the predicted value of INS data is generated, according to INS data and the predicted value of INS data, is calculated
The error of INS data, Kalman filtering is carried out to the error of INS data, it is right according to the INS data errors after Kalman filtering
INS data are calibrated, and the INS data after calibration are arranged to the navigation data of unmanned plane, so as to pass through the inertia trained
The forecast model that navigates aids in Kalman filter, and accuracy compensation is carried out to INS data when satellite location data interrupts or be abnormal,
The error of INS data is effectively reduced, and the combination of GLONASS and inertial navigation system is pine combination,
Amount of calculation is significantly reduced, and then improves the precision and real-time of Navigation of Pilotless Aircraft.
In embodiments of the present invention, each unit of Navigation of Pilotless Aircraft device can be realized by corresponding hardware or software unit,
Each unit can be independent soft and hardware unit, can also be integrated into a soft and hardware unit, herein not limiting this hair
It is bright.
Example IV:
Fig. 5 shows the structure for the unmanned plane that the embodiment of the present invention four provides, and for convenience of description, illustrate only and this hair
The related part of bright embodiment.
The unmanned plane 5 of the embodiment of the present invention includes processor 50, memory 51 and is stored in memory 51 and can be
The computer program 52 run on processor 50.The processor 50 realizes that above-mentioned each method is implemented when performing computer program 52
Step in example, such as the step S101 to S104 shown in Fig. 1.Or realized during the execution computer program 52 of processor 50
State the function of each unit in device embodiment, such as the function of unit 31 to 34 shown in Fig. 3.
In embodiments of the present invention, default GLONASS, inertial navigation system on unmanned plane, collection are passed through
The satellite location data and INS data of unmanned plane, when collect satellite location data interrupt or it is abnormal when, by INS data inputs
In the good inertial navigation forecast model of training in advance, the predicted value of INS data is generated, according to the prediction of INS data and INS data
Value, the error of INS data is calculated, and Kalman filtering is carried out to the error, according to the error after Kalman filtering, to INS numbers
According to being calibrated, the INS data after calibration are arranged to the navigation data of unmanned plane, so as to pre- by the inertial navigation trained
Model-aided Kalman filter is surveyed, accuracy compensation is carried out to INS data when satellite location data interrupts or be abnormal, effectively
Reduce the error of INS data, and the combination of GLONASS and inertial navigation system is pine combination, effectively
Amount of calculation is reduced, and then improves the precision and real-time of Navigation of Pilotless Aircraft.
Embodiment five:
In embodiments of the present invention, there is provided a kind of computer-readable recording medium, the computer-readable recording medium are deposited
Computer program is contained, the computer program realizes the step in above-mentioned each embodiment of the method when being executed by processor, for example,
Step S101 to S104 shown in Fig. 1.Or the computer program realize when being executed by processor it is each in said apparatus embodiment
The function of unit, such as the function of unit 31 to 34 shown in Fig. 3.
In embodiments of the present invention, default GLONASS, inertial navigation system on unmanned plane, collection are passed through
The satellite location data and INS data of unmanned plane, when collect satellite location data interrupt or it is abnormal when, by INS data inputs
In the good inertial navigation forecast model of training in advance, the predicted value of INS data is generated, according to the prediction of INS data and INS data
Value, the error of INS data is calculated, and Kalman filtering is carried out to the error, according to the error after Kalman filtering, to INS numbers
According to being calibrated, the INS data after calibration are arranged to the navigation data of unmanned plane, so as to pre- by the inertial navigation trained
Model-aided Kalman filter is surveyed, accuracy compensation is carried out to INS data when satellite location data interrupts or be abnormal, effectively
Reduce the error of INS data, and the combination of GLONASS and inertial navigation system is pine combination, effectively
Amount of calculation is reduced, and then improves the precision and real-time of Navigation of Pilotless Aircraft.
The computer-readable recording medium of the embodiment of the present invention can include that any of computer program code can be carried
Entity or device, recording medium, for example, the memory such as ROM/RAM, disk, CD, flash memory.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should be included in the scope of the protection.
Claims (10)
- A kind of 1. Navigation of Pilotless Aircraft method, it is characterised in that methods described comprises the steps:By default GLONASS, default inertial navigation system on unmanned plane, defending for the unmanned plane is gathered Star location data and INS data;When detecting that the satellite location data interrupts or be abnormal, the good inertia of the INS data inputs training in advance is led In boat forecast model, the predicted value of the INS data is generated;According to the INS data and the predicted value of the INS data, the error of the INS data is calculated, to the INS data Error carry out Kalman filtering;According to the INS data errors after the Kalman filtering, the INS data are calibrated, by the INS after the calibration Data are arranged to the navigation data of the unmanned plane.
- 2. the method as described in claim 1, it is characterised in that by default GLONASS on unmanned plane, pre- If inertial navigation system, before the step of gathering the satellite location data and INS data of the unmanned plane, methods described is also wrapped Include:BP neural network model is built, the BP neural network model is initialized;The satellite for being used to train of the unmanned plane is gathered by the GLONASS and the inertial navigation system Location data and the INS data for training;The satellite location data for being used to train and the difference of the INS data for being used to train are calculated, the difference is entered Row Kalman filtering, obtain the error of the INS data for being used to train;According to the error of the INS data for being used to train, the INS data for being used to train are calibrated, according to calibration Afterwards with before calibration described in be used for train INS data, the BP neural network model is trained, described in training BP neural network model is arranged to the inertial navigation forecast model.
- 3. method as claimed in claim 2, it is characterised in that according to after calibration and calibration before described in be used for train INS Data, the step of being trained to the BP neural network model, including:The INS data for being used to train before the calibration are arranged to the input of the BP neural network model, obtain the BP The INS data of neural network model output;The difference of the INS data for being used to train after the INS data of the output and the calibration is arranged to the BP nerves The feedback of network model, it is modified with the weight to the BP neural network model.
- 4. the method as described in claim 1, it is characterised in that gather the satellite location data and INS data of the unmanned plane The step of after, before the step in the good inertial navigation forecast model of the INS data inputs training in advance, methods described Also include:When detecting that the satellite location data is normal, the difference of the satellite location data and the INS data is calculated, it is right The difference of the satellite location data and the INS data carries out Kalman filtering;According to the satellite location data after the Kalman filtering and the difference of the INS data, the INS data are entered Row calibration, the INS data after the calibration are arranged to the navigation data of the unmanned plane.
- 5. the method as described in claim 1, it is characterised in that the GLONASS is global positioning system, institute It is gps data to state satellite location data.
- 6. a kind of Navigation of Pilotless Aircraft device, it is characterised in that described device includes:Data acquisition unit, for by default GLONASS, default inertial navigation system on unmanned plane, adopting Collect the satellite location data and INS data of the unmanned plane;Inertia forecasting unit, it is for when detecting that the satellite location data interrupts or be abnormal, the INS data inputs is pre- In the inertial navigation forecast model first trained, the predicted value of the INS data is generated;First filter unit, for the predicted value according to the INS data and the INS data, calculate the mistake of the INS data Difference, Kalman filtering is carried out to the error of the INS data;AndNavigation elements are calibrated, for according to the INS data errors after the Kalman filtering, being calibrated to the INS data, INS data after the calibration are arranged to the navigation data of the unmanned plane.
- 7. device as claimed in claim 6, it is characterised in that described device also includes:Model construction unit, for building BP neural network model, BP neural network model is initialized;Collecting training data unit, for gathering the nothing by the GLONASS and the inertial navigation system The man-machine satellite location data for being used to train and the INS data for training;Second filter unit, for calculating the satellite location data for being used to train and the INS data for being used to train Difference, Kalman filtering is carried out to the difference, obtain the error of the INS data for being used to train;AndModel training unit, for the error according to the INS data for being used to train, to the INS data for being used to train Calibrated, according to after calibration and calibration before described in be used for train INS data, the BP neural network model is instructed Practice, the BP neural network model trained is arranged to the inertial navigation forecast model.
- 8. device as claimed in claim 7, it is characterised in that the model training unit includes:Mode input unit, for the INS data for being used to train before the calibration to be arranged into the BP neural network model Input, obtain the INS data of BP neural network model output;AndModel feedback unit, for by the difference of the INS data for being used to train after the INS data of the output and the calibration The feedback of the BP neural network model is arranged to, is modified with the weight to the BP neural network model.
- 9. a kind of unmanned plane, including memory, processor and it is stored in the memory and can transports on the processor Capable computer program, it is characterised in that realize such as claim 1 to 5 times described in the computing device during computer program The step of one methods described.
- 10. a kind of computer-readable recording medium, the computer-readable recording medium storage has computer program, and its feature exists In when the computer program is executed by processor the step of realization such as any one of claim 1 to 6 methods described.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710679998.6A CN107643088A (en) | 2017-08-10 | 2017-08-10 | Navigation of Pilotless Aircraft method, apparatus, unmanned plane and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710679998.6A CN107643088A (en) | 2017-08-10 | 2017-08-10 | Navigation of Pilotless Aircraft method, apparatus, unmanned plane and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107643088A true CN107643088A (en) | 2018-01-30 |
Family
ID=61110656
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710679998.6A Pending CN107643088A (en) | 2017-08-10 | 2017-08-10 | Navigation of Pilotless Aircraft method, apparatus, unmanned plane and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107643088A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109116398A (en) * | 2018-07-10 | 2019-01-01 | 北京木业邦科技有限公司 | Work data acquisition methods, device, electronic equipment and storage medium |
CN109405827A (en) * | 2018-11-23 | 2019-03-01 | 安徽华米信息科技有限公司 | Method of locating terminal and device |
CN109444928A (en) * | 2018-12-18 | 2019-03-08 | 重庆西部汽车试验场管理有限公司 | A kind of localization method and system |
CN109490931A (en) * | 2018-09-03 | 2019-03-19 | 天津远度科技有限公司 | Flight localization method, device and unmanned plane |
CN111221010A (en) * | 2020-01-08 | 2020-06-02 | 安徽逻根农业科技有限公司 | Method and system for accurately positioning routing inspection node |
RU198994U1 (en) * | 2019-12-10 | 2020-08-06 | федеральное государственное автономное образовательное учреждение высшего образования "Северо-Кавказский федеральный университет" | Device for determining the fact of distortion of the navigation field and identification of interference effects on the receiver of a robotic unmanned aerial vehicle |
EA036815B1 (en) * | 2019-07-03 | 2020-12-23 | федеральное государственное автономное образовательное учреждение высшего образования "Северо-Кавказский федеральный университет" | Method for determining a fact of navigation field distortion and identifying a jamming impact on a receiver of a robot-aided unmanned aircraft |
CN112179375A (en) * | 2020-08-20 | 2021-01-05 | 中国科学院深圳先进技术研究院 | Control method of safety protection device and related device |
CN112214014A (en) * | 2020-09-04 | 2021-01-12 | 东北石油大学 | Automatic driving control method and system for agricultural machinery |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101871782A (en) * | 2010-05-19 | 2010-10-27 | 北京航空航天大学 | Position error forecasting method for GPS (Global Position System)/MEMS-INS (Micro-Electricomechanical Systems-Inertial Navigation System) integrated navigation system based on SET2FNN |
CN202216696U (en) * | 2011-07-07 | 2012-05-09 | 中国矿业大学(北京) | Coal mine disaster relief robot navigation device based on information integration |
CN102768361A (en) * | 2012-07-09 | 2012-11-07 | 东南大学 | GPS/INS combined positioning method based on genetic particle filtering and fuzzy neural network |
CN104898148A (en) * | 2015-06-02 | 2015-09-09 | 北京航空航天大学 | Low-cost INS/GPS seamless navigation method based on data compression and neural network |
CN106327357A (en) * | 2016-08-17 | 2017-01-11 | 深圳先进技术研究院 | Load identification method based on improved probabilistic neural network |
CN106980133A (en) * | 2017-01-18 | 2017-07-25 | 中国南方电网有限责任公司超高压输电公司广州局 | The GPS INS Combinated navigation methods and system for being compensated and being corrected using neural network algorithm |
-
2017
- 2017-08-10 CN CN201710679998.6A patent/CN107643088A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101871782A (en) * | 2010-05-19 | 2010-10-27 | 北京航空航天大学 | Position error forecasting method for GPS (Global Position System)/MEMS-INS (Micro-Electricomechanical Systems-Inertial Navigation System) integrated navigation system based on SET2FNN |
CN202216696U (en) * | 2011-07-07 | 2012-05-09 | 中国矿业大学(北京) | Coal mine disaster relief robot navigation device based on information integration |
CN102768361A (en) * | 2012-07-09 | 2012-11-07 | 东南大学 | GPS/INS combined positioning method based on genetic particle filtering and fuzzy neural network |
CN104898148A (en) * | 2015-06-02 | 2015-09-09 | 北京航空航天大学 | Low-cost INS/GPS seamless navigation method based on data compression and neural network |
CN106327357A (en) * | 2016-08-17 | 2017-01-11 | 深圳先进技术研究院 | Load identification method based on improved probabilistic neural network |
CN106980133A (en) * | 2017-01-18 | 2017-07-25 | 中国南方电网有限责任公司超高压输电公司广州局 | The GPS INS Combinated navigation methods and system for being compensated and being corrected using neural network algorithm |
Non-Patent Citations (2)
Title |
---|
林雪原 等: "利用神经网络预测的GPS/SINS组合导航***算法研究", 《武汉大学学报 信息科学版》 * |
陈鑫鑫 等: "神经网络辅助的GPS/INS组合导航滤波算法研究", 《电子技术应用》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109116398A (en) * | 2018-07-10 | 2019-01-01 | 北京木业邦科技有限公司 | Work data acquisition methods, device, electronic equipment and storage medium |
CN109490931A (en) * | 2018-09-03 | 2019-03-19 | 天津远度科技有限公司 | Flight localization method, device and unmanned plane |
CN109405827A (en) * | 2018-11-23 | 2019-03-01 | 安徽华米信息科技有限公司 | Method of locating terminal and device |
CN109444928A (en) * | 2018-12-18 | 2019-03-08 | 重庆西部汽车试验场管理有限公司 | A kind of localization method and system |
CN109444928B (en) * | 2018-12-18 | 2021-08-06 | 重庆西部汽车试验场管理有限公司 | Positioning method and system |
EA036815B1 (en) * | 2019-07-03 | 2020-12-23 | федеральное государственное автономное образовательное учреждение высшего образования "Северо-Кавказский федеральный университет" | Method for determining a fact of navigation field distortion and identifying a jamming impact on a receiver of a robot-aided unmanned aircraft |
RU198994U1 (en) * | 2019-12-10 | 2020-08-06 | федеральное государственное автономное образовательное учреждение высшего образования "Северо-Кавказский федеральный университет" | Device for determining the fact of distortion of the navigation field and identification of interference effects on the receiver of a robotic unmanned aerial vehicle |
CN111221010A (en) * | 2020-01-08 | 2020-06-02 | 安徽逻根农业科技有限公司 | Method and system for accurately positioning routing inspection node |
CN112179375A (en) * | 2020-08-20 | 2021-01-05 | 中国科学院深圳先进技术研究院 | Control method of safety protection device and related device |
CN112179375B (en) * | 2020-08-20 | 2022-08-09 | 中国科学院深圳先进技术研究院 | Control method of safety protection device and related device |
CN112214014A (en) * | 2020-09-04 | 2021-01-12 | 东北石油大学 | Automatic driving control method and system for agricultural machinery |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107643088A (en) | Navigation of Pilotless Aircraft method, apparatus, unmanned plane and storage medium | |
US11099582B2 (en) | Navigation aids for unmanned aerial systems in a GPS-denied environment | |
CN110196443B (en) | Fault-tolerant integrated navigation method and system of aircraft | |
CN108226980B (en) | Differential GNSS and INS self-adaptive tightly-coupled navigation method based on inertial measurement unit | |
Georgy et al. | Modeling the stochastic drift of a MEMS-based gyroscope in gyro/odometer/GPS integrated navigation | |
CN104406605B (en) | Airborne many navigation sources integrated navigation analogue systems | |
CN101858748B (en) | Fault-tolerance autonomous navigation method of multi-sensor of high-altitude long-endurance unmanned plane | |
CN110095800A (en) | A kind of self-adapted tolerance federated filter Combinated navigation method of multi-source fusion | |
CN106990426A (en) | A kind of air navigation aid and guider | |
CN106932804A (en) | Inertia/the Big Dipper tight integration navigation system and its air navigation aid of astronomy auxiliary | |
CN109937341B (en) | Method and device for estimating the position of a person | |
RU2487419C1 (en) | System for complex processing of information of radio navigation and self-contained navigation equipment for determining real values of aircraft navigation parameters | |
US8560280B2 (en) | Method for calculating a navigation phase in a navigation system involving terrain correlation | |
CN101743453A (en) | The post-mission high accuracy position and azimuth determining system | |
CN106405670A (en) | Gravity anomaly data processing method applicable to strapdown marine gravimeter | |
CN107490378A (en) | A kind of indoor positioning based on MPU6050 and smart mobile phone and the method for navigation | |
CN105371844A (en) | Initialization method for inertial navigation system based on inertial / celestial navigation interdependence | |
CN108981708B (en) | Fault-tolerant integrated navigation method for four-rotor torque model/course gyroscope/magnetic sensor | |
CN108981709B (en) | Four-rotor-wing roll angle and pitch angle fault-tolerant estimation method based on moment model assistance | |
Miller et al. | Sensitivity analysis of a tightly-coupled GPS/INS system for autonomous navigation | |
CN110426032A (en) | A kind of fault-tolerant navigation estimation method of the aircraft of analytic expression redundancy | |
CN110849360B (en) | Distributed relative navigation method for multi-machine collaborative formation flight | |
CN109612459A (en) | The fault-tolerant air navigation aid of quadrotor inertial sensor based on kinetic model | |
CN110332933A (en) | Vehicle positioning method, terminal and computer readable storage medium | |
Miller et al. | Tightly-coupled GPS/INS system design for autonomous urban navigation |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180130 |