CN106384540B - Vehicle real-time track prediction technique and forecasting system - Google Patents
Vehicle real-time track prediction technique and forecasting system Download PDFInfo
- Publication number
- CN106384540B CN106384540B CN201610920986.3A CN201610920986A CN106384540B CN 106384540 B CN106384540 B CN 106384540B CN 201610920986 A CN201610920986 A CN 201610920986A CN 106384540 B CN106384540 B CN 106384540B
- Authority
- CN
- China
- Prior art keywords
- time
- vehicle
- real
- rate
- change
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The present invention discloses a kind of based on vehicle real-time track prediction technique and forecasting system, this method comprises: acquiring vehicle real-time parameter from GNSS dynamic data, it wherein include the real-time course angle of vehicle, time and real-time speed in parameter, by the change rate and above-mentioned real-time speed of the course angle in continuous state, vehicle running path radius is obtained；The confidence rate of reaction vehicle running path variable condition is calculated according to above-mentioned parameter, and compare confidence rate and preset confidence rate section, if confidence rate is fallen in confidence rate section, carry out trajectory predictions, if confidence rate not in confidence rate section, terminates the prediction of this data；Subsequent time vehicle driving trace is obtained according to above-mentioned parameter and the vehicle driving radius of acquisition.This programme relies on vehicle itself GNSS dynamic data information to predict subsequent time vehicle driving trace, and without a large amount of mathematical operations, and computational accuracy is higher.
Description
Technical field
The present invention relates to the car networking communication technology, especially a kind of vehicle real-time track prediction technique and forecasting system.
Background technique
Currently, in intelligent transportation system (Intelligent Transport System or Intelligent
Transportation System, abbreviation ITS) in development process, realize that the driving of accurate highly effective and safe is that intelligent transportation is ultimate
Target.Driving primary goal is exactly to realize the tight security of car steering, finds potential safety accident, accurately mentions in time
Early warning and driving auxiliary out, effectively evade accident and planning driving path.
Current vehicle position information is all by Global Navigation Satellite System (Global Navigation
SatelliteSystem, hereinafter referred to as GNSS) provide, the track of vehicle Predicting Technique based on GNSS has more version at present
This, basic principle is exactly to be fitted vehicle driving state according to historical data, and then predict the driving trace of vehicle.
In the process of moving, a large amount of GNSS data record can be used as the source of fitting vehicle driving trace to vehicle, but
It is from the point of view of artificial intelligence angle, a large amount of vehicle GNSS datas can be used as the basis of digging vehicle driving status.It is existing at present
Trajectory predictions technology it is more, such as be based on Markov Chain Method, inertial navigation method, Kalman filtering method, particle filter method, minimum
Square law, gauss hybrid models, neural network, machine learning method, topologic theory and other more complicated trajectory predictions
Method.The above various trajectory predictions methods are present in theory research quality, and the algorithm that can be really used for track of vehicle prediction is less.
Because in embedded systems there is computing resource, GNSS drift, storage resource, actual effect, dependent on geography information, rely on
In the requirement such as other vehicle position informations, above-mentioned algorithm needs to result in waste of resources by a large amount of mathematical operation.
Summary of the invention
The main object of the present invention is to provide a kind of vehicle real-time track prediction technique and forecasting system, it is intended to simplify operation
Process reduces the wasting of resources, and improves the accuracy of prediction.
To achieve the above object, vehicle real-time track prediction technique proposed by the present invention, comprising the following steps:
S1 acquires vehicle real-time parameter, wherein the vehicle real-time parameter includes that vehicle is real-time from GNSS dynamic data
Course angle, the time, real-time speed, the real-time longitude of vehicle, real-time latitude and vehicle driving radian, it is timely according to the course angle
Between, course angular rate of change is obtained, by the change rate and above-mentioned real-time speed of the course angle in continuous state, obtains vehicle
Driving path radius；
S2 calculates the confidence rate of reaction vehicle running path variable condition according to the time and real-time course angle, and compares
The confidence rate and preset confidence rate section；
S3, if confidence rate is fallen in preset confidence rate section, according to the real-time longitude of the vehicle, real-time latitude,
The radian of vehicle driving and the vehicle driving radius of acquisition obtain subsequent time vehicle driving trace.
Preferably, the step S1 the following steps are included:
S1a acquires vehicle real-time parameter according to predeterminated frequency from GNSS dynamic data, wherein the vehicle real-time parameter
Radian including the real-time course angle of vehicle, time, real-time speed, the real-time longitude of vehicle, real-time latitude and vehicle driving；
S1b obtains the real-time course angular rate of change of vehicle by calculating by course angle and time；
S1c is filtered above-mentioned real-time course angular rate of change, to filter out the course angle for being in discontinuous state
Change rate；
S1d obtains vehicle running path half according to above-mentioned course angular rate of change and real-time speed in continuous state
Diameter.
Preferably, it in the step S1c, is filtered using second-order low-pass filter.
Preferably, the step S2 the following steps are included:
S2a calculates the difference value of the course angular rate of change after above-mentioned steps S1c；
S2b selectes confidence rate section, and is closed according to the mapping between the difference value of course angular rate of change and confidence rate section
It is the preset threshold for determining the difference value of course angular rate of change；
S2c, if the difference value of course angular rate of change is less than above-mentioned preset threshold, then it is assumed that in confidence rate interval range
It is interior, then carry out step S3；
If the difference value of course angular rate of change is greater than or equal to preset threshold, then it is assumed that not in confidence rate interval range
It is interior, then terminate the prediction of this data.
Preferably, in the step S3, from the parameter obtained in step S1 include the real-time longitude of vehicle, real-time latitude,
The radian of vehicle driving, according to the vehicle driving that longitude, real-time latitude, the radian of vehicle driving and step S1 are obtained in real time
Radius obtains subsequent time vehicle driving trace.
The present invention also provides a kind of vehicle real-time track forecasting systems, comprising:
Radius obtains module, vehicle real-time parameter is acquired from GNSS dynamic data, wherein the vehicle real-time parameter packet
The radian for including the real-time course angle of vehicle, time, real-time speed, the real-time longitude of vehicle, real-time latitude and vehicle driving, according to described
Course angle and time obtain course angular rate of change, by the course angular rate of change and above-mentioned parameter in continuous state
Real-time speed obtains vehicle running path radius；
Confidence rate screening module calculates reaction vehicle running path according to the real-time course angle of the vehicle and time and changes shape
The confidence rate of state, and the confidence rate and preset confidence rate section；
The trajectory prediction module obtains the institute of module input according to radius if confidence rate is fallen in confidence rate section
The vehicle driving radius for stating the real-time longitude of vehicle, real-time latitude, the radian of vehicle driving and acquisition obtains subsequent time
Vehicle driving trace.
Preferably, the radius acquisition module includes:
Acquisition unit acquires vehicle real-time parameter according to predeterminated frequency from GNSS dynamic data, wherein the vehicle is real
When parameter include the real-time course angle of vehicle, time, real-time speed, the real-time longitude of vehicle, real-time latitude and vehicle driving radian；
Converting unit obtains the real-time course angular rate of change of vehicle by calculating by the course angle and time；
Filter element is filtered above-mentioned real-time course angular rate of change, is in discontinuous state to filter out
Course angular rate of change；
Computing unit obtains vehicle according to above-mentioned course angular rate of change and the real-time speed in continuous state
Driving path radius.
Preferably, the filter element is filtered using second-order low-pass filter.
Preferably, the confidence rate screening module includes:
Confidence rate acquiring unit is counted to by the difference value of the filtered course angular rate of change of above-mentioned filter element
It calculates；And current course angle change rate is determined according to the mapping relations between the difference value of course angular rate of change and confidence rate section
Difference value corresponding confidence rate section；
Threshold module, select confidence rate section, according to the difference value of selected confidence rate section and course angular rate of change with
The preset threshold of mapping relations between the confidence rate section difference value of vectoring angular rate of change really；
Screening unit, if the difference value of course angular rate of change is less than above-mentioned preset threshold, then it is assumed that in selected confidence
In rate interval range, then inputted using above-mentioned vehicle running path radius as radius signal to trajectory prediction module；If course
The difference value of angular rate of change is greater than or equal to preset threshold, then it is assumed that not in confidence rate interval range；Then not to the track
Prediction module input radius signal is obtained, the prediction of this data is terminated.
Preferably, the confidence rate section selected in the threshold module is between 50%~100%.
In technical solution of the present invention, vehicle travels on earth, earth approximate spheres, and the driving trace of vehicle approximate can be used
One section of arc representation assumes that the driving trace of vehicle is one section of circular arc, the collecting vehicle first from GNSS dynamic data in this programme
Real-time parameter, include in these parameters the real-time course angle of vehicle, time and the real-time longitude of real-time speed vehicle, real-time latitude,
The radian of vehicle driving；First according to course angle and time, course angular rate of change is obtained, by the course for being in continuous state
The change rate and real-time speed at angle, can obtain vehicle running path radius；Again by time parameter and the institute in continuous state
State course angle change rate can calculate reaction vehicle running path variable condition confidence rate, and the confidence rate with
Preset confidence rate section；If confidence rate is fallen in preset confidence rate section, real-time according to the vehicle in above-mentioned parameter
Longitude, real-time latitude, the radian of vehicle driving and the vehicle driving radius of acquisition obtain subsequent time vehicle driving rail
Mark.This programme relies on vehicle itself GNSS dynamic data information to predict the vehicle driving trace of subsequent time, relatively existing skill
Art does not have to consider the factors such as GNSS drift, actual effect, therefore without excessive without other vehicle geographical location information are relied on
The mathematical operation of amount, has saved computer and storage resource；And in the application the step of radius prediction in, due to using place
In the change rate of the course angle of continuous state, i.e., the course angular data that course angular rate of change is in discontinuous state is considered
By the data that the factors such as equipment, road conditions or operation are affected, if will lead to prediction radius distortion if, to improve prediction
Accuracy, therefore these data are not as radius prediction data；Meanwhile confidence rate concept is introduced, for the traveling road of vehicle
Diameter variable condition in consideration, it is pre- to improve if confidence rate, which in predetermined interval, assert that vehicle is in, stablizes driving status
The accuracy of survey filters out the data in unstable driving status；By to the filtering of prediction data, improving prediction essence twice
Degree.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
The structure shown according to these attached drawings obtains other attached drawings.
Fig. 1 is the flow chart schematic diagram for the vehicle real-time track prediction technique that one embodiment of the invention provides；
Fig. 2 is the functional block diagram for the vehicle real-time track forecasting system that one embodiment of the invention provides；
Fig. 3 is the driving trace schematic diagram of vehicle in vehicle real-time track prediction technique provided by the invention.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiment is only a part of the embodiments of the present invention, instead of all the embodiments.Base
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts it is all its
His embodiment, shall fall within the protection scope of the present invention.
It is to be appreciated that the directional instruction (such as up, down, left, right, before and after ...) of institute is only used in the embodiment of the present invention
In explaining in relative positional relationship, the motion conditions etc. under a certain particular pose (as shown in the picture) between each component, if should
When particular pose changes, then directionality instruction also correspondingly changes correspondingly.
In addition, the description for being such as related to " first ", " second " in the present invention is used for description purposes only, and should not be understood as
Its relative importance of indication or suggestion or the quantity for implicitly indicating indicated technical characteristic.Define as a result, " first ",
The feature of " second " can explicitly or implicitly include at least one of the features.In the description of the present invention, " multiple " contain
Justice is at least two, such as two, three etc., unless otherwise specifically defined.
In the present invention unless specifically defined or limited otherwise, term " connection ", " fixation " etc. shall be understood in a broad sense,
For example, " fixation " may be a fixed connection, it may be a detachable connection, or integral；It can be mechanical connection, be also possible to
Electrical connection；It can be directly connected, the connection inside two elements or two can also be can be indirectly connected through an intermediary
The interaction relationship of a element, unless otherwise restricted clearly.It for the ordinary skill in the art, can basis
Concrete condition understands the concrete meaning of above-mentioned term in the present invention.
It in addition, the technical solution between each embodiment of the present invention can be combined with each other, but must be general with this field
Based on logical technical staff can be realized, it will be understood that when the combination of technical solution appearance is conflicting or cannot achieve this
The combination of technical solution is not present, also not the present invention claims protection scope within.
The present invention proposes a kind of vehicle real-time track prediction technique.
In instantaneous state, track of vehicle variation can be indicated with one section of arc length, be changed according in instantaneous time course angle
And velocity variations, the radius of the instantaneous driving trace of vehicle can be calculated, Fig. 1, Fig. 3 are please referred to, in one embodiment of the invention
In, method includes the following steps:
S1 predicts vehicle running path radius；Vehicle real-time parameter is specifically acquired from GNSS dynamic data, wherein described
Vehicle real-time parameter includes the real-time course angle of vehicle, time, real-time speed, the real-time longitude of vehicle, real-time latitude and vehicle driving
Radian, according in parameter course angle and the time, course angular rate of change is obtained, by the course angle in continuous state
Change rate and above-mentioned real-time speed obtain vehicle running path radius；
S2, according to the confidence of time and real-time course angle calculating reaction vehicle running path variable condition in above-mentioned parameter
Rate, and the confidence rate and preset confidence rate section；
S3, if confidence rate is fallen in preset confidence rate section, according to the real-time longitude, real-time latitude, vehicle
Subsequent time vehicle driving trace is obtained by calculating around the radian of traveling and above-mentioned vehicle driving radius.
Technical solution of the present invention, speed, acceleration, course angle, curvature and vehicle driving based on GNSS data
Radian, rapidly variation track confidence interval establish the vehicle driving trace that model judges vehicle next moment, and the model is only
The current and history GNSS data information of itself is only relied upon to predict the vehicle driving trace at next moment, relative to existing
(embedded system depends on other vehicle position informations to technology, and there is computing resource, GNSS drift, storage resources, actual effect
Deng requirement), above-mentioned algorithm saves computer data without a large amount of mathematical operation, and computational accuracy is higher.
Further, the step S1 the following steps are included:
S1a acquires vehicle real-time parameter according to predeterminated frequency from GNSS dynamic data, wherein the vehicle real-time parameter
Radian including the real-time course angle of vehicle, time, real-time speed, the real-time longitude of vehicle, real-time latitude and vehicle driving；Acquisition frequency
Rate can be set as needed, and frequency acquisition is 10Hz in the present embodiment；The parameter of acquisition is configured according to specific needs,
Parameter in the present embodiment includes the real-time course angle λ of vehicle, speed ν, longitude and latitude；
S1b obtains the real-time course angular rate of change α of vehicle by calculating by course angle λ and time t；
By:Obtain course angular rate of change α；Wherein λ 1 is the course angle at t1 moment；λ 2 is the boat at t2 moment
To angle；
The sample point that the real-time course angle of multiple vehicles is obtained from GNSS dynamic data is obtained by these sample point analogs
Being able to the time is abscissa, using course angle as the function of ordinate, carries out derivation to the function against time and obtains the time as cross
Coordinate, using vehicle course angular rate of change as the function of ordinate, each moment vehicle instantaneous course angular rate of change passes through substitution
It is obtained in the function.
S1c is filtered above-mentioned real-time course angular rate of change, to filter out the course angle for being in discontinuous state
Change rate；
Because there are road noises (complicated condition of road surface influences the output of GNSS sensing data), sensor noise (itself
Drift) and driver's driving behavior noise (complicated driving behavior), prediction radius can be had an impact, be needed at this time pair
The course angular rate of change calculated in real time is filtered to prevent discrete course angular rate of change acutely changed from making
It obtains for input signal from positive and negative value, infinitely great radius value；It thus will have a direct impact on the calculated result of radius, if half
Diameter calculates mistake, and the trajectory predictions that can directly result in vehicle deviate vehicle lower a moment actual path, in order to avoid this special feelings
Data under condition carry out trajectory predictions as input data, it is therefore desirable to pass through this step acutely changing discontinuous state
Course angular rate of change filters out；
It is specifically filtered using second-order low-pass filter, the second-order low-pass filter expression formula meets:
Following relationship is obtained after discrete to above-mentioned expression formula (1) progress:
Wherein initialization condition is chosen are as follows: y1=u1, y2=u2；ω0=2 π f0, f0For cutoff frequency, ζ is damped coefficient,
Ts is the sampling time, and y is the difference value of course angular rate of change, and u is course angle, wherein n >=3；In 0.32Hz≤f0≤ 0.34Hz,
0≤ζ≤2,100ms≤Ts≤400ms.F in the present embodiment0Preferably 0.33Hz, ζ are preferably that 1, Ts is preferably 100ms.It is above-mentioned
Formula and Parameters in Formula choose the course angular rate of change that can effectively filter out discontinuous state, and filter effect is more preferably.
S1d obtains vehicle according to above-mentioned course angular rate of change α and real-time speed ν in continuous state referring to Fig. 3
Driving path radius R:
According to formula: R=v/ α andIt can obtain:
R is traveling radius, and v is the car speed obtained from GNSS, and α is course angular rate of change；λ 1 is the course at t1 moment
Angle；λ 2 is the course angle at t2 moment.
The vehicle driving radius of prediction is carried out filtering out noise:
By course angle angular speed (i.e. the unit of α, α are angle degrees second) and vehicle speed (i.e. the unit of v, v be rice/
Second) traveling radius can be obtained:
R=v/ α；
And by(unit of angular speed is converted to radian per second by angle degrees second) obtains curvature:
Wherein l is the angular speed of course angle, and unit is radian per second, and speed v minimum value is not zero.
Above-mentioned curvature is through second-order low-pass filter transmission function:
Vehicle original curvature ρ is obtained after filtering；
ByFiltered vehicle driving radius R is obtained, if vehicle radius is greater than critical value, then it is assumed that vehicle road
Diameter is straight line.
Step S1 calculating is effective for vehicle stabilization state traveling, but in driving condition acute variation, is calculated
Prediction radius can give a discount.Thus need the confidence of a response prediction radius authenticity when violent driving condition changes
Rate.Confidence rate height then indicates that vehicle is in and stablizes driving status, and what can be trusted predicts the side of radius using the calculating of previous step
Method.Conversely, then abandoning the prediction radius calculated.
Calculate the confidence rate of the vehicle driving radius of prediction:
The angular speed (i.e. the unit of α, α are angle degrees second) of course angle is through second-order low-pass filter transmission function:
It takes absolute value after filtering, checks that the second difference score value of course angle and confidence rate parameter comparison table obtain
Confidence rate.
Further, the step S2 is specifically included:
S2a calculates the difference value of the course angular rate of change after above-mentioned steps S1c；
Here the difference value of course angular rate of change refers to the secondary derivation to course angle relative time function, reacts course
The state of angular rate of change, if the difference value of course angular rate of change is constant always, indicate course angle variation be it is stable, at vehicle
In stablizing driving status；The size of variation can be judged that this threshold value is according to by multiple by preset threshold value
What experimental data obtained.If the difference value of course angular rate of change is less than preset threshold, then it is assumed that the traveling radius confidence of vehicle
Rate is high, can adopt；If instead the difference value of course angular rate of change is greater than or equal to preset threshold, then it is assumed that the traveling of vehicle
Radius confidence rate is low；It abandons, not adopts, terminate the prediction of this data；
Preferably, in the step S2a difference value (i.e. course angle second difference score value) of course angular rate of change meet it is following
Expression formula:
Wherein initialization condition is chosen are as follows: y1=0, y2=0；ω'0=2 π f0', f0' be confidence rate cutoff frequency, ζ ' is
Confidence rate damped coefficient, T 'sFor the discrete sampling time for calculating confidence rate, y is course angle second difference score value, and u is course angle.
Wherein 0.33Hz≤f0'≤1Hz, 0≤ζ '≤2,100ms≤T 's≤400ms；Further, f0' it is preferably 1Hz, ζ ' is preferably
1, T 'sPreferably 100ms.Parameter in above-mentioned formula and formula, which is chosen, enables to course angle second difference score value and confidence rate
Mapping relations become apparent, reaction confidence rate that can be more accurate by course angle second difference score value, that is, have reacted vehicle row
Sail state.
S2b selectes confidence rate section, and is closed according to the mapping between the difference value of course angular rate of change and confidence rate section
System determines the preset threshold of the difference value of course angular rate of change (referring to following table one)；
In the present embodiment, confidence rate section A is selected to be greater than 50%, and selected confidence rate section can be obtained by experiment,
Mapping relations between the difference value and confidence rate section of course angular rate of change are also to be obtained by experiment, are set by selected
Letter rate section and table one, the corresponding preset threshold of difference value that can obtain course angular rate of change is 2.5, i.e., when course angle two
When secondary difference value is less than 2.5, corresponding confidence rate section meets 50% < A≤100%；
Wherein the second difference score value of course angle and confidence rate parameter comparison are referring to table one:
S2c, if the difference value of course angular rate of change i.e. when course angle second difference score value be less than preset threshold 2.5 when,
Think to meet 50% < A≤100% in selected range in confidence rate, then carrying out step S3；
If the difference value of course angular rate of change is greater than or equal to preset threshold 2.5, then it is assumed that confidence rate is not in confidence
50% < A≤100% is unsatisfactory in rate interval range；Then terminate the prediction of this data.
Threshold value in step S2c is 2.5, i.e., when course angle second difference score value is less than 2.5, corresponding confidence rate is greater than 50%
When, it is believed that course angle variation be it is stable, vehicle be in stablizes driving status, when course angle second difference score value be greater than 2.5 when, it is right
When answering confidence rate less than 50%, it is believed that course angle variation be it is unstable, vehicle is in unstable driving status, abandons last
The corresponding track of vehicle prediction of the vehicle driving radius obtained is calculated, invalid data are thought in other words, not as this subslot
Prediction input.To realize to track of vehicle Accurate Prediction, to reduce vehicle safety event such as vehicle rear-end collision, bad weather circumstances
The generation of lower vehicle collision etc..
Referring to Fig. 3, show that vehicle will travel always with this radius, it can by the real-time longitude of vehicle, latitude
Judge that the location of vehicle, θ are the radian of vehicle driving, can be obtained by GNSS dynamic data, according to geometrical relationship: S=
θ * R, R are vehicle driving radius, can approximation obtain vehicle prediction locus S.
The scene that road is straight situation is distinguished at this time, is obtained by experimental data, if the traveling radius of vehicle is greater than
At 2000 meters, then it is assumed that road is straight, if the traveling radius of vehicle is less than or equal to 2000 meters, then it is assumed that vehicle driving rail
Mark is circular arc.
One embodiment of the invention provides a kind of vehicle real-time track forecasting system, which includes: that radius obtains module, sets
Letter rate screening module and trajectory prediction module 3；
Radius obtains module, vehicle real-time parameter is acquired from GNSS dynamic data, wherein the vehicle real-time parameter packet
The radian for including the real-time course angle of vehicle, time, real-time speed, the real-time longitude of vehicle, real-time latitude and vehicle driving, according to parameter
In course angle and the time, obtain course angular rate of change, by be in continuous state the course angular rate of change and above-mentioned parameter
In real-time speed, obtain vehicle running path radius；
Confidence rate screening module, according in above-mentioned parameter time and real-time course angle calculate reaction vehicle running path become
The confidence rate of change state, and the confidence rate and preset confidence rate section；
Trajectory prediction module 3, if confidence rate is fallen in confidence rate section, using above-mentioned vehicle running path radius as
Radius signal obtains module 3 to track and inputs；The above-mentioned parameter of module input is obtained according to radius and above-mentioned radius signal obtains
Obtain subsequent time vehicle driving trace；If confidence rate not in confidence rate section, does not obtain module 3 to the track and inputs
Radius signal terminates the prediction of this data.
The present invention is that the accurate early warning of vehicle safety event on the basis of DSRC V2X communication and multisensor syste is special
Sub- patent implementation in benefit, i.e., the track of vehicle prediction algorithm of vehicle-mounted GNSS data are proposed based on current and history
The path locus at GNSS data prediction vehicle next moment.
In the process of moving, a large amount of GNSS data record can be used as the source of fitting vehicle driving trace to vehicle, greatly
Amount vehicle GNSS data can be used as the basis of digging vehicle driving status；The present invention is a kind of based on GNSS data by proposing
Speed, acceleration, course angle, curvature and rapidly variation track confidence interval establishes model, when judging that vehicle is next
The vehicle driving trace at quarter, algorithm is more simple compared with the existing technology, has saved a large amount of calculation resources.
Further, referring to fig. 2, it includes acquisition unit 11, converting unit 12, filter element 13 that the radius, which obtains module,
With computing unit 14；Wherein:
Acquisition unit 11 acquires vehicle real-time parameter according to predeterminated frequency from GNSS dynamic data；Specially data are adopted
Storage, acquiring from GNSS dynamic data according to the frequency of setting needs supplemental characteristic to be used；And by the reality in above-mentioned parameter
Shi Hangxiang angular data is sent to converting unit 12, and real-time speed data are sent to computing unit 14, by longitude, latitude and traveling
Radian data be sent to trajectory prediction module；
Converting unit 12,11 obtain the real-time course angle of vehicle, time from acquisition unit, are obtained by course angle by calculating
The real-time course angular rate of change of vehicle；The real-time course angle of vehicle and time are obtained from acquisition unit 11, by setting in a program
Calculation formula obtains course angular rate of change；And input to filter element；
Filter element 13 is filtered above-mentioned real-time course angular rate of change, is in discontinuous state to filter out
Course angular rate of change；It is filtered using second-order low-pass filter；It specifically can be a filter circuit；
Computing unit 14 obtains vehicle real-time speed, according to the above-mentioned course in continuous state from acquisition unit 11
Angular rate of change and real-time speed obtain vehicle running path radius；
Confidence rate screening module includes confidence rate acquiring unit 21, threshold cell 22, screening unit 23, in which: uses two
Rank low-pass filter is filtered；It specifically can be a filter circuit；
Confidence rate acquiring unit 21 is counted to by the difference value of the filtered course angular rate of change of above-mentioned filter element
It calculates；And the mapping relations between the difference value and confidence rate section according to course angular rate of change prestored determine that current course angle becomes
The difference value of rate corresponding confidence rate section；
Threshold cell 22 selectes confidence rate section, according to selected confidence rate section and the difference value of course angular rate of change
The preset threshold of mapping relations between the confidence rate section difference value of vectoring angular rate of change really；
Screening unit 23, if the difference value of course angular rate of change is less than above-mentioned preset threshold, then it is assumed that set in selected
In letter rate interval range, then inputted using above-mentioned vehicle running path radius as radius signal to trajectory prediction module；If boat
It is greater than or equal to preset threshold to the difference value of angular rate of change, then it is assumed that not in confidence rate interval range；Then not to the rail
Mark obtains prediction module input radius signal, terminates the prediction of this data；
Trajectory prediction module 3 is with specific reference to the real-time longitude of above-mentioned vehicle, real-time latitude, the radian of vehicle driving and described
The radius information that vehicle driving radius is characterized in screening unit obtains subsequent time vehicle driving trace.It receives single from acquisition
The real-time longitude of vehicle, real-time latitude, the radian of vehicle driving and the radius information from screening unit 23 of member 11, pass through
Above-mentioned data are calculated according to preset formula, it can subsequent time vehicle driving trace.
Each vehicle itself can periodically send local vehicle GNSS on the basis of short-range communication technique and travel rail
Mark predictive information simultaneously receives surrounding vehicles GNSS driving trace predictive information simultaneously；Local vehicle and remote vehicle are different
Position needs the prediction locus meeting of the GNSS prediction locus and long-range GNSS of local vehicle if safety accident occurs at this time
It is overlapped at a certain moment in the future, when that security incident will occur, warning is generated on local vehicle or remote vehicle.To
Reduce the generation of vehicle collision under vehicle safety event such as vehicle rear-end collision, bad weather circumstances.
The above description is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all at this
Under the inventive concept of invention, using equivalent structure transformation made by description of the invention and accompanying drawing content, or directly/use indirectly
It is included in other related technical areas in scope of patent protection of the invention.
Claims (8)
1. a kind of vehicle real-time track prediction technique, which is characterized in that method includes the following steps:
S1 acquires vehicle real-time parameter, wherein the vehicle real-time parameter includes the real-time course of vehicle from GNSS dynamic data
Angle, the time, real-time speed, the real-time longitude of vehicle, real-time latitude and vehicle driving radian, according to the course angle and time,
Course angular rate of change is obtained, by the change rate and the real-time speed of the course angle in continuous state, obtains vehicle row
Sail path radius；
S2 calculates the confidence rate of reaction vehicle running path variable condition according to the time and real-time course angle, and compares institute
State confidence rate and preset confidence rate section；
S3, if confidence rate is fallen in preset confidence rate section, according to the real-time longitude of the vehicle, real-time latitude, vehicle
The radian of traveling and the vehicle driving radius of acquisition obtain subsequent time vehicle driving trace；
Wherein, the step S2 the following steps are included:
S2a calculates the difference value of course angular rate of change；
S2b selectes confidence rate section, and true according to the mapping relations between the difference value of course angular rate of change and confidence rate section
The preset threshold of the difference value of vectoring angular rate of change；
S2c, if the difference value of course angular rate of change is less than above-mentioned preset threshold, then it is assumed that in confidence rate interval range, then
Carry out step S3；
If the difference value of course angular rate of change is greater than or equal to preset threshold, then it is assumed that not in confidence rate interval range, then
Terminate the prediction of this data.
2. vehicle real-time track prediction technique according to claim 1, which is characterized in that the step S1 includes following step
It is rapid:
S1a acquires vehicle real-time parameter according to predeterminated frequency from GNSS dynamic data, wherein the vehicle real-time parameter includes
The real-time course angle of vehicle, the time, real-time speed, the real-time longitude of vehicle, real-time latitude and vehicle driving radian；
S1b obtains the real-time course angular rate of change of vehicle by calculating by course angle and time；
S1c is filtered above-mentioned real-time course angular rate of change, to filter out the course angle variation for being in discontinuous state
Rate；
S1d obtains vehicle running path radius according to above-mentioned course angular rate of change and real-time speed in continuous state.
3. vehicle real-time track prediction technique according to claim 2, which is characterized in that in the step S1c, using two
Rank low-pass filter is filtered.
4. vehicle real-time track prediction technique according to claim 1 to 3, which is characterized in that in the step S2b,
Selected confidence rate section is between 50%~100%.
5. a kind of vehicle real-time track forecasting system, which is characterized in that the system includes:
Radius obtains module, vehicle real-time parameter is acquired from GNSS dynamic data, wherein the vehicle real-time parameter includes vehicle
The in real time radian of course angle, time, real-time speed, the real-time longitude of vehicle, real-time latitude and vehicle driving, according to the course
Angle and time obtain course angular rate of change, by real-time in the course angular rate of change and the parameter in continuous state
Speed obtains vehicle running path radius；
Confidence rate screening module calculates reaction vehicle running path variable condition according to the real-time course angle of the vehicle and time
Confidence rate, and the confidence rate and preset confidence rate section；
Trajectory prediction module, if confidence rate is fallen in confidence rate section, the vehicle for obtaining module input according to radius is real
Shi Jingdu, real-time latitude, the radian of vehicle driving and the vehicle driving radius of acquisition obtain subsequent time vehicle driving
Track；
Wherein, the confidence rate screening module includes:
Confidence rate acquiring unit, calculates the difference value of course angular rate of change；And according to the difference value of course angular rate of change
Mapping relations between confidence rate section determine the difference value of current course angle change rate corresponding confidence rate section；
Threshold module selectes confidence rate section, according to selected confidence rate section and the difference value and confidence of course angular rate of change
The preset threshold of mapping relations between the rate section difference value of vectoring angular rate of change really；
Screening unit, if the difference value of course angular rate of change is less than above-mentioned preset threshold, then it is assumed that in selected confidence rate area
Between in range, then inputted using above-mentioned vehicle running path radius as radius signal to trajectory prediction module；If course angle becomes
The difference value of rate is greater than or equal to preset threshold, then it is assumed that not in confidence rate interval range；It is not obtained to the track then pre-
Module input radius signal is surveyed, the prediction of this data is terminated.
6. vehicle real-time track forecasting system according to claim 5, which is characterized in that the radius obtains module packet
It includes:
Acquisition unit acquires vehicle real-time parameter according to predeterminated frequency, wherein the vehicle is joined in real time from GNSS dynamic data
Number includes the radian of the real-time course angle of vehicle, time, real-time speed, the real-time longitude of vehicle, real-time latitude and vehicle driving；
Converting unit obtains the real-time course angular rate of change of vehicle by calculating by the course angle and time；
Filter element is filtered above-mentioned real-time course angular rate of change, to filter out the course for being in discontinuous state
Angular rate of change；
Computing unit obtains vehicle driving according to above-mentioned course angular rate of change and the real-time speed in continuous state
Path radius.
7. vehicle real-time track forecasting system according to claim 6, which is characterized in that the filter element uses second order
Low-pass filter is filtered.
8. according to the described in any item vehicle real-time track forecasting systems of claim 5-7, which is characterized in that the threshold module
In select confidence rate section between 50%~100%.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610920986.3A CN106384540B (en) | 2016-10-20 | 2016-10-20 | Vehicle real-time track prediction technique and forecasting system |
| PCT/CN2017/073558 WO2018072362A1 (en) | 2016-10-20 | 2017-02-15 | Real-time vehicle trajectory prediction method and prediction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610920986.3A CN106384540B (en) | 2016-10-20 | 2016-10-20 | Vehicle real-time track prediction technique and forecasting system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106384540A CN106384540A (en) | 2017-02-08 |
| CN106384540B true CN106384540B (en) | 2019-04-19 |
Family
ID=57958124
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610920986.3A Active CN106384540B (en) | 2016-10-20 | 2016-10-20 | Vehicle real-time track prediction technique and forecasting system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN106384540B (en) |
| WO (1) | WO2018072362A1 (en) |
Families Citing this family (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106384540B (en) * | 2016-10-20 | 2019-04-19 | 深圳市元征科技股份有限公司 | Vehicle real-time track prediction technique and forecasting system |
| CN106875746B (en) * | 2017-02-27 | 2020-09-29 | 山东师范大学 | Automobile safe driving early warning system and method |
| DE102017109731A1 (en) * | 2017-05-05 | 2018-11-08 | Konecranes Global Corporation | Method and system for operating an automatically guided transport vehicle for containers |
| US10649458B2 (en) | 2017-09-07 | 2020-05-12 | Tusimple, Inc. | Data-driven prediction-based system and method for trajectory planning of autonomous vehicles |
| CN108111173B (en) * | 2017-12-27 | 2021-03-26 | 东软集团股份有限公司 | Track compression method and device, storage medium and electronic equipment |
| CN109765886B (en) * | 2018-12-21 | 2022-05-24 | 北京智行者科技有限公司 | Target track identification method followed by vehicle |
| CN109782754B (en) * | 2018-12-25 | 2022-05-06 | 东软睿驰汽车技术（沈阳）有限公司 | Vehicle control method and device |
| CN109922439B (en) * | 2019-03-29 | 2020-10-16 | 重庆长安汽车股份有限公司 | Fusion method of multi-sensor data, and target detection method and system based on V2X |
| CN112537296A (en) * | 2019-09-23 | 2021-03-23 | 北京新能源汽车股份有限公司 | Emergency braking device, automobile and braking control method |
| CN111103566B (en) * | 2019-11-28 | 2023-09-05 | 中国科学院上海微系统与信息技术研究所 | Course angle determining method, course angle determining system, electronic equipment and storage medium |
| CN111063210A (en) * | 2019-12-26 | 2020-04-24 | 广东星舆科技有限公司 | Vehicle monitoring method and device based on high-precision positioning |
| CN111693723B (en) * | 2020-05-29 | 2022-04-22 | 阿波罗智联(北京)科技有限公司 | Speed prediction method and device and electronic equipment |
| CN111661061B (en) * | 2020-06-18 | 2022-02-11 | 东软睿驰汽车技术（沈阳）有限公司 | Vehicle driving intention identification method and device |
| CN112714020B (en) * | 2020-12-28 | 2022-10-14 | 青岛海尔科技有限公司 | Method and device for determining validity of data, storage medium and electronic device |
| CN112839855B (en) * | 2020-12-31 | 2022-07-12 | 华为技术有限公司 | Trajectory prediction method and device |
| CN113191672B (en) * | 2021-05-20 | 2022-01-04 | 哈尔滨工业大学 | Village and town garbage classification and transportation planning method and system based on spatial data and VRPTW |
| CN113247000B (en) * | 2021-07-16 | 2021-09-17 | 浙江所托瑞安科技集团有限公司 | Vehicle steering recognition method, device, equipment and storage medium |
| CN113723316B (en) * | 2021-09-01 | 2024-04-16 | 杭州智诚惠通科技有限公司 | Vehicle identification method, device, equipment and storage medium |
| CN113997941B (en) * | 2021-09-14 | 2023-10-13 | 武汉光庭信息技术股份有限公司 | Method and system for analyzing running state of bicycle, electronic equipment and storage medium |
| CN115733867B (en) * | 2022-12-29 | 2024-04-16 | 阿维塔科技(重庆)有限公司 | Vehicle-mounted GPS data uploading method, system and equipment |
| CN116645828B (en) * | 2023-05-26 | 2024-04-16 | 赛马物联科技(宁夏)有限公司 | Logistics vehicle track deviation alarm method and system |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7610146B2 (en) * | 1997-10-22 | 2009-10-27 | Intelligent Technologies International, Inc. | Vehicle position determining system and method |
| US9891054B2 (en) * | 2010-12-03 | 2018-02-13 | Qualcomm Incorporated | Inertial sensor aided heading and positioning for GNSS vehicle navigation |
| CN102542634B (en) * | 2012-01-13 | 2014-05-21 | 北京理工大学 | Measuring system of driving state of target vehicle |
| CN102608641A (en) * | 2012-03-30 | 2012-07-25 | 江苏物联网研究发展中心 | Vehicle-mounted combined navigation system based on single-axis gyroscope and single-axis accelerometer and method |
| KR101535873B1 (en) * | 2013-11-29 | 2015-07-24 | 현대모비스 주식회사 | Car navition system and method merged gnss with dr |
| CN105718750B (en) * | 2016-01-29 | 2018-08-17 | 长沙理工大学 | A kind of prediction technique and system of vehicle driving trace |
| CN106384540B (en) * | 2016-10-20 | 2019-04-19 | 深圳市元征科技股份有限公司 | Vehicle real-time track prediction technique and forecasting system |
-
2016
- 2016-10-20 CN CN201610920986.3A patent/CN106384540B/en active Active
-
2017
- 2017-02-15 WO PCT/CN2017/073558 patent/WO2018072362A1/en active Application Filing
Also Published As
| Publication number | Publication date |
|---|---|
| WO2018072362A1 (en) | 2018-04-26 |
| CN106384540A (en) | 2017-02-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106384540B (en) | Vehicle real-time track prediction technique and forecasting system | |
| Wang et al. | Trajectory planning and safety assessment of autonomous vehicles based on motion prediction and model predictive control | |
| CN109421742B (en) | Method and apparatus for monitoring autonomous vehicles | |
| US10838423B2 (en) | Intelligent vehicle navigation systems, methods, and control logic for deriving road segment speed limits | |
| CN113613980B (en) | Method and system for controlling security of self and social objects | |
| Lytrivis et al. | An advanced cooperative path prediction algorithm for safety applications in vehicular networks | |
| US20230334983A1 (en) | Message broadcasting for vehicles | |
| US10352704B2 (en) | System and method for detection of vehicle lane departure | |
| CN106558219B (en) | Vehicle track prediction method and device | |
| EP3779922A1 (en) | Method for estimating driving road and driving road estimation system | |
| Manogaran et al. | Multi-variate data fusion technique for reducing sensor errors in intelligent transportation systems | |
| US20080243389A1 (en) | Vehicle Collision Avoidance Equipment and Method | |
| CN110398960A (en) | A kind of paths planning method of intelligent driving, device and equipment | |
| KR20190082712A (en) | Method for providing information about a anticipated driving intention of a vehicle | |
| CN113286737A (en) | Steering command limits for safe autonomous vehicle operation | |
| US11946746B2 (en) | Method for satellite-based detection of a vehicle location by means of a motion and location sensor | |
| US11845471B2 (en) | Travel assistance method and travel assistance device | |
| JP4899626B2 (en) | Travel control device | |
| CN109859528B (en) | V2X Internet of vehicles-based method for classifying positions of vehicles at curves | |
| CN113602265A (en) | Processing cooperative lane changing method and system based on vehicle-to-vehicle communication | |
| CN110617815A (en) | Method and device for automatic driving monitoring alarm | |
| CN110398968B (en) | Intelligent vehicle multi-target driving control method and decision system | |
| Wang et al. | Trajectory prediction for turning vehicles at intersections by fusing vehicle dynamics and driver’s future input estimation | |
| CN115218902B (en) | Track planning method, device, equipment and storage medium | |
| Balzer et al. | Epe and speed adaptive extended kalman filter for vehicle position and attitude estimation with low cost gnss and imu sensors |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |