CN109115231A - A kind of vehicle positioning method, equipment and automatic driving vehicle - Google Patents
A kind of vehicle positioning method, equipment and automatic driving vehicle Download PDFInfo
- Publication number
- CN109115231A CN109115231A CN201810994919.5A CN201810994919A CN109115231A CN 109115231 A CN109115231 A CN 109115231A CN 201810994919 A CN201810994919 A CN 201810994919A CN 109115231 A CN109115231 A CN 109115231A
- Authority
- CN
- China
- Prior art keywords
- characteristic point
- characteristic
- vehicle
- feature set
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Navigation (AREA)
Abstract
The invention discloses a kind of vehicle positioning method, equipment and automatic driving vehicles.The present invention is based on onboard sensors to the accuracy of identification of roadway characteristic, carries out preliminary screening to the roadway characteristic in fisrt feature set, obtains the second feature set being made of first kind roadway characteristic.If the matching degree between second feature set and third feature set is more than the first preset matching degree threshold value, show the roadway characteristic for the characteristic point that onboard sensor detects, it is similar to the high-precision map roadway characteristic of characteristic point on a driving path of getting on the bus, the roadway characteristic successful match of characteristic point, characteristic point based on the successful match obtains the relative position of its absolute position and vehicle and characteristic point, and the more accurate vehicle absolute position of positioning can be obtained.This method obtains the absolute position of characteristic point based on high-precision map, and further obtains the absolute position of vehicle, and compared with the prior art, the accuracy of vehicle location effectively improves.
Description
Technical field
The present invention relates to automobile technical field more particularly to a kind of vehicle positioning methods, equipment and automatic driving vehicle.
Background technique
Nowadays, global positioning system and Beidou satellite navigation system etc. is mostly used to provide positioning and navigation for vehicle user
Service.But it is restricted at present in civil field using the precision of these positioning and navigation system, global positioning system and north
The positioning accuracy for the satellite navigation system that struggles against is ten meters or so, can not be improved the positioning accuracy of vehicle to lane rank.For example, root
The location information detected according to positioning system, the lane information in lane where searching the vehicle that map data base obtains, with vehicle
The lane information in lane is inconsistent where practical.
It can be seen that the vehicle positioning method precision provided in the prior art is too low, caused position error influences certainly
The dynamic path planning for driving vehicle.
Summary of the invention
Based on the above technical problem, the application provides a kind of vehicle positioning method, equipment and automatic driving vehicle, to solve
The too low problem of vehicle location precision.
Present applicant proposes following technical solutions:
For the application in a first aspect, providing a kind of vehicle positioning method, this method is applied to vehicle, includes vehicle on the vehicle
Set sensor;Onboard sensor roadway characteristic for identification;
The described method includes:
The roadway characteristic of characteristic point on vehicle running path is obtained from high-precision map, forms fisrt feature set;
First kind roadway characteristic is screened from the fisrt feature set forms second feature set, the first kind road
Feature is the roadway characteristic that the onboard sensor can identify;
The roadway characteristic of the characteristic point on the vehicle running path is identified using the onboard sensor, obtains third
Characteristic set;
Compare the second feature set and the third feature set, if the second feature set and the third
Matching degree between characteristic set is more than the first preset matching degree threshold value, then obtains the characteristic point using the high-precision map
Absolute position, and obtain from the vehicle positioning system of the vehicle relative position of the vehicle Yu the characteristic point;
According to the absolute position of the characteristic point and the relative position of the vehicle and the characteristic point, described in acquisition
The absolute position of vehicle.
As a kind of possible implementation, the second feature set and the third feature set it
Before, the method also includes:
Characteristic point is screened according to the roadway characteristic of the characteristic point, rejects invalid characteristic point.
It is described that characteristic point is screened according to the roadway characteristic of the characteristic point as a kind of possible implementation, reject nothing
Characteristic point is imitated, is specifically included:
Judging the matching degree on the vehicle running path between the corresponding second feature set of adjacent characteristic point is
It is no more than the second preset matching degree threshold value, if it is, by the adjacent characteristic point vehicle pass through first characteristic point make
For validity feature point, remaining characteristic point in addition to the validity feature point in the adjacent characteristic point is rejected.
It is described that characteristic point is screened according to the roadway characteristic of the characteristic point as a kind of possible implementation, reject nothing
Characteristic point is imitated, is specifically included:
Obtain the confidence level of each roadway characteristic in the third feature set of the characteristic point;The confidence level is at any time
The variable of variation;
According to the confidence level of each roadway characteristic in the third feature set of the characteristic point, setting for the characteristic point is obtained
Reliability;
If the matching degree on the vehicle running path between the corresponding third feature set of adjacent characteristic point is super
Third preset matching degree threshold value is crossed, and the matching degree between the corresponding confidence level of the adjacent characteristic point is more than default confidence
Matching threshold is spent, then using the adjacent characteristic point as similar features point;
It screens confidence level highest in the similar features point and is more than the similar features point of confidence threshold value, described in rejecting
Remaining characteristic point in adjacent characteristic point.
As a kind of possible implementation, each roadway characteristic in the third feature set according to the characteristic point
Confidence level, obtain the confidence level of the characteristic point, specifically include:
Obtain the average confidence of each roadway characteristic within a preset time in the third feature set of the characteristic point;
By the average confidence of each roadway characteristic within a preset time, with the institute obtained from the high-precision map
The confidence level for stating each roadway characteristic is multiplied, and obtains the first confidence level of each roadway characteristic of the characteristic point;
First confidence level of each roadway characteristic of the characteristic point is added, the confidence level of the characteristic point is obtained.
The application second aspect provides a kind of Vehicle Positioning Equipment, the equipment application on vehicle, the vehicle include vehicle
Set sensor;Onboard sensor roadway characteristic for identification;
The Vehicle Positioning Equipment includes: that fisrt feature set obtains module, second feature set obtains module, third spy
Collection closes and obtains module, feature compares and position acquisition module and locating module;
The fisrt feature set obtains module, for obtaining the road of characteristic point on vehicle running path from high-precision map
Road feature forms fisrt feature set;
The second feature set obtains module, for screening first kind roadway characteristic shape from the fisrt feature set
At second feature set, the first kind roadway characteristic is the roadway characteristic that the onboard sensor can identify;
The third feature set obtains module, for identifying the vehicle running path using the onboard sensor
The roadway characteristic of the characteristic point obtains third feature set;
The feature compare with position acquisition module, be used for the second feature set and the third feature collection
It closes, if the matching degree between the second feature set and the third feature set is more than the first preset matching degree threshold value,
It obtains the absolute position of the characteristic point using the high-precision map, and obtains from the vehicle positioning system of the vehicle described
The relative position of vehicle and the characteristic point;
The locating module, for according to the absolute position of the characteristic point and the vehicle and the characteristic point
Relative position obtains the absolute position of the vehicle.
As a kind of possible implementation, the Vehicle Positioning Equipment further include:
Characteristic point screening module rejects invalid characteristic point for screening characteristic point according to the roadway characteristic of the characteristic point.
As a kind of possible implementation, the characteristic point screening module is specifically included:
The first screening unit of characteristic point, for judging adjacent characteristic point corresponding second on the vehicle running path
Whether the matching degree between characteristic set is more than the second preset matching degree threshold value, if it is, by vehicle in the adjacent characteristic point
First characteristic point passed through is used as validity feature point, in the rejecting adjacent characteristic point in addition to the validity feature point
Remaining characteristic point.
As a kind of possible implementation, the characteristic point screening module is specifically included:
Roadway characteristic confidence level acquiring unit, each roadway characteristic in the third feature set for obtaining the characteristic point
Confidence level;The confidence level is the variable changed over time;
Feature pixel confidence acquiring unit, for each roadway characteristic in the third feature set according to the characteristic point
Confidence level obtains the confidence level of the characteristic point;
Similar features point determination unit, if for the corresponding third of characteristic point adjacent on the vehicle running path
Matching degree between characteristic set is more than third preset matching degree threshold value, and the corresponding confidence level of the adjacent characteristic point it
Between matching degree be more than default confidence match threshold value, using the adjacent characteristic point as similar features point;
The second screening unit of characteristic point, for screening confidence level highest in the similar features point and being more than confidence level thresholding
The similar features point of value rejects remaining characteristic point in the adjacent characteristic point.
The application third aspect provides a kind of automatic driving vehicle, which includes that the above-mentioned second aspect of the application provides
Vehicle Positioning Equipment, further includes: automated driving system;
The Vehicle Positioning Equipment, for the absolute position of the vehicle to be sent to the automated driving system;
The automated driving system carries out automatic Pilot for controlling vehicle according to the absolute position of the vehicle.
Compared with prior art, the present invention has at least the following advantages:
Vehicle positioning method provided by the present application, applied to the vehicle configured with the onboard sensor that can identify roadway characteristic
, firstly, obtaining the roadway characteristic of characteristic point on vehicle running path from high-precision map, form fisrt feature set;Thereafter,
First kind roadway characteristic is screened from fisrt feature set and forms second feature set, and first kind roadway characteristic is onboard sensor
The roadway characteristic that can be identified;Then, using the roadway characteristic of characteristic point on onboard sensor identification vehicle running path, the is obtained
Three characteristic sets;Then, compare second feature set and third feature set, if second feature set and third feature set
Between matching degree be more than the first preset matching degree threshold value, the absolute position of characteristic point is obtained using high-precision map, and from vehicle
Vehicle positioning system obtain vehicle and characteristic point relative position;Finally, according to the absolute position of characteristic point and vehicle
With the relative position of characteristic point, the absolute position of vehicle is obtained.
This method based on onboard sensor to the accuracy of identification of roadway characteristic, to the roadway characteristic in fisrt feature set into
Row preliminary screening obtains the second feature set being made of first kind roadway characteristic, by screening, avoids onboard sensor can not
The roadway characteristic of identification influences the accurate match of characteristic point roadway characteristic.If between second feature set and third feature set
Matching degree be more than the first preset matching degree threshold value, that is, show the roadway characteristic for the characteristic point that onboard sensor detects, with height
The roadway characteristic of characteristic point is similar on vehicle running path on precision map, the roadway characteristic successful match of characteristic point, and being based on should
The characteristic point of successful match obtains the relative position of its absolute position and vehicle and characteristic point, and it is more accurate that positioning can be obtained
Vehicle absolute position.This method obtains the absolute position of characteristic point based on high-precision map, and further obtains the absolute of vehicle
Position, compared with the prior art, the accuracy of vehicle location effectively improve.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, 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
The some embodiments recorded in application, for those of ordinary skill in the art, without creative efforts,
It can also be obtained according to these attached drawings other attached drawings.
Fig. 1 is a kind of flow chart for vehicle positioning method that the application first embodiment provides;
Fig. 2 is a kind of flow chart for vehicle positioning method that the application second embodiment provides;
Fig. 3 is a kind of flow chart for vehicle positioning method that the application 3rd embodiment provides;
Fig. 4 is a kind of structural schematic diagram for Vehicle Positioning Equipment that the application fourth embodiment provides;
Fig. 5 is a kind of structural schematic diagram for automatic driving vehicle that the 5th embodiment of the application provides.
Specific embodiment
It is too low to solve aforementioned vehicle positioning accuracy, it is difficult to the problem of meeting the automatic Pilot demand based on map, this Shen
It please provide a kind of vehicle positioning method, equipment and automatic driving vehicle.
It is clearly and completely described below with reference to technical solution of the embodiment and attached drawing to the application, it is clear that described
Embodiment be only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiment in the application, this field
Those of ordinary skill's every other embodiment obtained without making creative work belongs to the application protection
Range.
First embodiment
Referring to Fig. 1, which is a kind of flow chart of vehicle positioning method provided by the embodiments of the present application.Firstly the need of explanation
, it includes the vehicle-mounted biography that can identify roadway characteristic on vehicle that vehicle positioning method provided in this embodiment, which is applied to vehicle,
Sensor.
As shown in Figure 1, vehicle positioning method provided in this embodiment, comprising:
S101: obtaining the roadway characteristic of characteristic point on vehicle running path from high-precision map, forms fisrt feature set.
Vehicle running path can be the driving path determined by the stroke starting point and stroke point of destination of vehicle.In vehicle
On driving path, including at least two characteristic points.In the present embodiment, characteristic point can be various types of crossings and terrestrial reference
Deng, such as crossroad, T-shaped road junction, restaurant, shopping plaza, school, station, bridge etc..
The roadway characteristic of characteristic point includes traffic sign, road surface characteristic, pavement behavior and the traffic condition near characteristic point
Deng.As an example, the roadway characteristic of characteristic point can be with are as follows: crossing stop line, lane curvature, crossing feature, is prohibited at lane line line style
Stop mark, speed(-)limit sign, releases speed(-)limit sign, direction board, signal lamp, left-hand bend, right-hand bend, straight trip, change lane, keep left
Skidding sails, traveling, men working and road, upcoming traffic accident etc. on the right side.
The fisrt feature set of characteristic point, all roadway characteristics comprising this feature point in high-precision map.
It should be noted that being all made of skill provided in this embodiment for each characteristic point on vehicle running path
Art scheme.Each characteristic point corresponds to a fisrt feature set.In the present embodiment, the case where being only with any one characteristic point
It is described as example.
S102: first kind roadway characteristic is screened from the fisrt feature set and forms second feature set.
Onboard sensor is limited for the roadway characteristic accuracy of identification of characteristic point on vehicle running path, it is possible to Wu Fashi
All roadway characteristics for the characteristic point that Chu do not include in fisrt feature set, and be only capable of identifying a part of roadway characteristic therein.
Due to subsequent to realize high accuracy positioning, by the detection recognition result according to onboard sensor to roadway characteristic, high-precision is completed
The matching of map feature point and the characteristic point of onboard sensor detection, therefore, to avoid the unrecognized road of onboard sensor
Feature impacts the accurate match of characteristic point, and from fisrt feature set, filtering out onboard sensor can know this step
Other roadway characteristic, i.e. first kind roadway characteristic constitute second feature set by first kind roadway characteristic.In turn, second feature
The roadway characteristic for including in set is the roadway characteristic that can be identified based on this feature point onboard sensor.
As an example, each roadway characteristic respectively has confidence level, the confidence of each roadway characteristic in fisrt feature set
Degree indicates that the roadway characteristic can be by the degree of onboard sensor reliable recognition.For example, the feature of onboard sensor identifies confidence
Degree threshold value is Tr, in fisrt feature set, confidence level is greater than feature recognition confidence threshold value TrRoadway characteristic as first kind road
Road feature constitutes second feature set by first kind roadway characteristic.
It should be noted that onboard sensor includes but is not limited to following any one or more in the embodiment of the present application
Combination: global position system (Global Navigation Satellite System, GNSS), odometer, lane identification
System, Traffic Sign Recognition System and other roadway characteristic identifying systems.
Wherein, odometer includes but is not limited to following any one or more combination: transmission output shaft revolving speed passes
Sensor, wheel speed sensors and vehicle speed sensor;
The identification content of lane recognition system includes but is not limited to following any one or more combination: lane line class
Type, lane line curvature, the offset based on lane and the course deviation based on lane;
The identification content of Traffic Sign Recognition System includes but is not limited to following any one or more combination: speed limitation board
And traffic sign;
The identification content of other roadway characteristic identifying systems includes but is not limited to: water horse and portal frame.
S103: the roadway characteristic of the characteristic point on the vehicle running path is identified using the onboard sensor, is obtained
Obtain third feature set.
Each roadway characteristic in third feature set is that the practical confidence level recognized of onboard sensor is identified more than feature
Confidence threshold value TrRoadway characteristic.
S104: the second feature set and the third feature set, if the second feature set and institute
Stating the matching degree between third feature set is more than the first preset matching degree threshold value, obtains the spy using the high-precision map
The absolute position of point is levied, and obtains the relative position of the vehicle Yu the characteristic point from the vehicle positioning system of vehicle.
For determine characteristic point second feature set and third feature set whether successful match will in the embodiment of the present application
The matching degree of the corresponding second feature set of characteristic point and third feature set and the first preset matching degree threshold value comparison.If institute
Stating the matching degree between second feature set and the third feature set is more than the first preset matching degree threshold value, that is, shows feature
Second feature set and third feature the sets match success of point, the roadway characteristic of the characteristic point of onboard sensor detection, with height
The roadway characteristic of characteristic point on precision map on vehicle running path is similar, i.e. roadway characteristic successful match.
It should be noted that the second feature set that determines characteristic point and third feature set whether successful match when,
The consistency of the sequence of roadway characteristic in second feature set and third feature set is not required.
As an example, the second feature collection of characteristic point is combined into { L1, L2, L3, L4 }, third feature collection be combined into L3, L1,
L4 }, L1, L2, L3 and L4 respectively represent different types of roadway characteristic of this feature point.In this example, the first preset matching
Spending threshold value is 72%, since the roadway characteristic for the identical type for including in second feature set and third feature set occupies second
The 75% of all roadway characteristic types in characteristic set, therefore between characteristic point second feature set and third feature set
With degree 75% more than the first preset matching degree threshold value.Also, since the confidence level of each roadway characteristic in third feature set is super
The feature recognition confidence threshold value for crossing onboard sensor, hence, it can be determined that second feature set is similar to third feature set.
The second feature set of characteristic point is similar to third feature set, indicates the second feature set and third of characteristic point
Roadway characteristic in characteristic set is mutually matched success, and this feature point can be used for realizing the high accuracy positioning of vehicle.As an example,
Obtain absolute position P of the characteristic point J in high-precision mapJ, and pass through the vehicle positioning system such as global positioning system of vehicle
The position for the characteristic point J that system (Global Positioning System, GPS) obtains not is PJ, and then it is found that due to vehicle
Positioning System deficiency is carried, error is only certainly existed by the position vehicle W that vehicle positioning system obtains.To overcome pair
The position error of vehicle W, this step also obtain the relative position Δ P of vehicle W and this feature point J from vehicle positioning systemWJ, Δ
PWJIt can be used for obtaining the absolute position of vehicle W.
S105: it according to the absolute position of the characteristic point and the relative position of the vehicle and the characteristic point, obtains
The absolute position of the vehicle.
As a kind of optional implementation, S105 be can specifically include:
S1051: the relative position is converted under the coordinate system of the absolute position of the characteristic point, is obtained described
First relative position of vehicle and the characteristic point.
S1052: by mobile first relative position in the absolute position of the characteristic point, the absolute position of the vehicle is obtained
It sets, the absolute position of the vehicle includes the longitudinal coordinate, lateral coordinate and course of the vehicle.
Continue to use the example in S104, the relative position Δ P of vehicle W and characteristic point JWJIn the absolute position P of characteristic point JJ's
It is converted under coordinate system, has obtained the first relative position Δ P ' of vehicle W Yu characteristic point JWJ;By the absolute position of characteristic point J
PJMobile first relative position Δ P 'WJ, obtain the absolute position P of vehicle WW.The vehicle directly obtained relative to vehicle positioning system
The position of W, the vehicle W absolute position P obtained using vehicle positioning method provided by the embodiments of the present applicationWPrecision improvement.
The above are vehicle positioning methods provided by the embodiments of the present application.This method is based on onboard sensor to roadway characteristic
Accuracy of identification carries out preliminary screening to the roadway characteristic in fisrt feature set, obtain being made of first kind roadway characteristic the
Two characteristic sets avoid the unrecognized roadway characteristic of onboard sensor from influencing the accurate of characteristic point roadway characteristic by screening
Matching.If the matching degree between second feature set and third feature set is more than the first preset matching degree threshold value, that is, show
The roadway characteristic for the characteristic point that onboard sensor detects, it is special with the high-precision map road of characteristic point on a driving path of getting on the bus
Levy similar, the roadway characteristic successful match of characteristic point, the characteristic point based on the successful match obtains its absolute position and vehicle
With the relative position of characteristic point, the more accurate vehicle absolute position of positioning can be obtained.This method is obtained based on high-precision map
The absolute position of characteristic point, and the absolute position of vehicle is further obtained, compared with the prior art, the accuracy of vehicle location obtains
To effectively improving.
Since there may be continuous adjacent and the similar several characteristic points of roadway characteristic height on vehicle running path.These
The similar characteristic point of adjacent and roadway characteristic height may be directed to same feature to second feature set and third feature set
The roadway characteristic matching of point interferes.For example, successively there is adjacent characteristic point K and characteristic point F on vehicle running path,
Characteristic point K second feature roll-in altitude corresponding with characteristic point F is similar, characteristic point K and the corresponding third of characteristic point F
Characteristic set height is similar.If the second feature set of characteristic point K is similar to the third feature roll-in altitude of characteristic point F,
The characteristic point F for being likely to recognize onboard sensor is considered as the characteristic point K that high-precision map is got on the bus on a driving path, in turn
Influence the positioning accuracy of vehicle.
To avoid the above problem, the application still further provides another vehicle positioning method.Below with reference to embodiment
It is described in detail with specific embodiment of the attached drawing to the vehicle positioning method.
Second embodiment
Referring to fig. 2, which is a kind of flow chart of vehicle positioning method provided in this embodiment.
As shown in Fig. 2, vehicle positioning method provided in this embodiment, comprising:
S201: obtaining the roadway characteristic of characteristic point on vehicle running path from high-precision map, forms fisrt feature set.
S202: first kind roadway characteristic is screened from the fisrt feature set and forms second feature set.
S203: the roadway characteristic of the characteristic point on the vehicle running path is identified using the onboard sensor, is obtained
Obtain third feature set.
In the present embodiment, the implementation of S201 to the S203 implementation with S101 in previous embodiment to S103 respectively
Identical, the detailed description about S201 to S203 can be found in previous embodiment, will no longer repeat in the present embodiment.
S204: characteristic point is screened according to the roadway characteristic of the characteristic point, rejects invalid characteristic point.
This step is screened and is rejected to adjacent characteristic point according to the matching degree of the roadway characteristic of adjacent characteristic point.It needs
It is noted that adjacent characteristic point can be two adjacent characteristic points in the present embodiment, it is also possible to that there is adjacent pass two-by-two
More than two characteristic points of system.
It can include the angle of the roadway characteristic matching degree of characteristic point from high-precision map as the first implementation,
Adjacent characteristic point is screened and rejected.It is specific as follows:
Judging the matching degree on the vehicle running path between the corresponding second feature set of adjacent characteristic point is
It is no more than the second preset matching degree threshold value, if it is, by the adjacent characteristic point vehicle pass through first characteristic point make
For validity feature point, remaining characteristic point in the adjacent characteristic point in addition to validity feature point is rejected.
In the present embodiment, if the matching degree between the corresponding second feature set of adjacent characteristic point is more than second pre-
If matching degree threshold value, then show the adjacent characteristic point similar adjacent characteristic point of roadway characteristic height each other.As an example, second is pre-
If matching degree threshold value can be 90%.
As an example, the corresponding second feature set of characteristic point K and characteristic point F adjacent on vehicle running path it
Between matching degree be greater than the second preset matching degree threshold value, i.e. in characteristic point K second feature set corresponding with characteristic point F,
Roadway characteristic height is similar, and first characteristic point K that vehicle is passed through continues to execute following S205 extremely as validity feature point
S206;And characteristic point F will be removed as invalid characteristic point, no longer execute following S205 to S206.
It, can be from the roadway characteristic matching degree of the practical characteristic point identified of onboard sensor as second of implementation
Angle is screened and is rejected to adjacent characteristic point.It is specific as follows:
Judging the matching degree on the vehicle running path between the corresponding third feature set of adjacent characteristic point is
It is no more than the second preset matching degree threshold value, if it is, by the adjacent characteristic point vehicle pass through first characteristic point make
For validity feature point, remaining characteristic point in the adjacent characteristic point in addition to validity feature point is rejected.
If the matching degree between the corresponding third feature set of adjacent characteristic point is more than the second preset matching degree threshold
Value then shows the adjacent characteristic point similar adjacent characteristic point of roadway characteristic height each other.As an example, the second preset matching degree threshold
Value can be 90%.
As an example, the corresponding third feature set of characteristic point M and characteristic point N adjacent on vehicle running path it
Between matching degree be greater than the second preset matching degree threshold value, i.e. in characteristic point M third feature set corresponding with characteristic point N,
Roadway characteristic height is similar.First characteristic point M that vehicle is passed through continues to execute following S205 extremely as validity feature point
S206;And characteristic point N will be removed as invalid characteristic point, no longer execute following S205 to S206.
It is understood that S204 can be combined with above two implementation, adjacent characteristic point is screened and picked
It removes.That is, can include the angle and onboard sensor reality of the roadway characteristic matching degree of characteristic point from high-precision map
The angle of the roadway characteristic matching degree of the characteristic point of border identification, is screened and is rejected to adjacent characteristic point.Herein, no longer to this
Implementation is repeated, reference can be made to the description in two kinds of implementations of aforementioned S204.
S205: the second feature set and the third feature set, if the second feature set and institute
Stating the matching degree between third feature set is more than the first preset matching degree threshold value, obtains the spy using the high-precision map
The absolute position of point is levied, and obtains the relative position of the vehicle Yu the characteristic point from the vehicle positioning system of vehicle.
S206: it according to the absolute position of the characteristic point and the relative position of the vehicle and the characteristic point, obtains
The absolute position of the vehicle.
In the present embodiment, the implementation of S205 and the S206 implementation with S104 in previous embodiment to S105 respectively
Identical, the detailed description about S205 to S206 can be found in previous embodiment, will no longer repeat in the present embodiment.
The above are a kind of vehicle positioning methods provided in this embodiment.This method during realizing high accuracy positioning,
Characteristic point is screened according to the roadway characteristic of the characteristic point, rejects invalid characteristic point.Specifically, by between second feature set
It is more than second pre- with spending more than matching degree between the adjacent characteristic point and/or third feature set of the second preset matching degree threshold value
If the adjacent characteristic point of matching degree threshold value is screened, retain first characteristic point that vehicle passes through in adjacent characteristic point, rejects
Remaining characteristic point in adjacent characteristic point in addition to validity feature point.First feature in adjacent characteristic point has been filtered out as a result,
After point and in the second feature set roadway characteristic similar characteristic point of height and/or adjacent characteristic point of first characteristic point
With the similar characteristic point of third feature set roadway characteristic height of first characteristic point after first characteristic point, feature is avoided
The roadway characteristic erroneous matching of point second feature set and third feature set.Therefore, it is special to improve characteristic point second for this method
The matched accuracy of roadway characteristic with third feature set is closed in collection, and then avoids Feature Points Matching fault, is further protected
The precision of vehicle location is demonstrate,proved.
Since there may be the more similar several characteristic points of adjacent and roadway characteristic on vehicle running path.These features
Point may be directed to same spy to second feature set and third feature set since position is close and roadway characteristic is more similar
The roadway characteristic matching of sign point interferes.
To avoid the above problem, guarantee that the precision of vehicle location, the application have been still further provided in a kind of vehicle location side
Method.It is described in detail below with reference to specific embodiment of the embodiment and attached drawing to the vehicle positioning method.
3rd embodiment
Referring to Fig. 3, which is a kind of flow chart of vehicle positioning method provided in this embodiment.
As shown in figure 3, vehicle positioning method provided in this embodiment, comprising:
S301: obtaining the roadway characteristic of characteristic point on vehicle running path from high-precision map, forms fisrt feature set.
S302: first kind roadway characteristic is screened from the fisrt feature set and forms second feature set.
S303: the roadway characteristic of the characteristic point on the vehicle running path is identified using the onboard sensor, is obtained
Obtain third feature set.
In the present embodiment, the implementation of S301 to the S303 implementation with S101 in previous embodiment to S103 respectively
Identical, the detailed description about S301 to S303 can be found in previous embodiment, will no longer repeat in the present embodiment.
S304: the confidence level of each roadway characteristic in the third feature set of the characteristic point is obtained.
It is available each when as a specific implementation manner, by the roadway characteristic of onboard sensor identification feature point
The confidence level of a roadway characteristic.It is understood that vehicle is by during characteristic point, each roadway characteristic of characteristic point with
The distance of onboard sensor constantly changes, and therefore, the confidence level of each roadway characteristic identified changes over time
Variable.
The confidence level of each roadway characteristic in third feature set, indicate third feature set in each roadway characteristic can
Letter degree.The higher roadway characteristic of confidence level, credibility are higher.
Certainly, the confidence level of each roadway characteristic can also be by certain parameter processings of roadway characteristic in third feature set
And it is calculated.Here, not being defined to the specific acquisition modes of the confidence level of roadway characteristic each in third feature.
S305: according to the confidence level of each roadway characteristic in the third feature set of the characteristic point, the feature is obtained
The confidence level of point.
To be screened to adjacent on the vehicle running path and similar characteristic point of third feature set, needed in the present embodiment
The confidence of characteristic point corresponding to third feature set is calculated using the confidence level of each roadway characteristic in third feature set
Degree.This step can specifically obtain the confidence level of characteristic point as follows:
S3051: it obtains being averaged within a preset time of each roadway characteristic in the third feature set of the characteristic point and sets
Reliability.
As an example, the roadway characteristic of onboard sensor identification feature point, obtains in the third feature set of characteristic point m
The confidence level of roadway characteristic is respectively fc1(t), fc2(t), fc3(t)…fcm(t), in preset time T m roadway characteristic it is flat
Equal confidence level is respectively fca1, fca2, fca3…fcam。
S3052: the average confidence of each roadway characteristic within a preset time is obtained with from the high-precision map
The confidence level of each roadway characteristic arrived is multiplied, and obtains the first confidence level of each roadway characteristic of the characteristic point.
As an example, the confidence level of the above-mentioned m roadway characteristic of the characteristic point obtained from high-precision map is respectively f1, f2,
f3…fm。
The first confidence level of m roadway characteristic of this feature point can be acquired using formula (1).
fj1=fj*fcajFormula (1)
In formula (1), j indicates that j-th of roadway characteristic in m roadway characteristic of characteristic point, m are the integer greater than 1, and j is
Any integer in [1, m], fjIndicate confidence level of j-th of roadway characteristic on high-precision map, fcajFor in preset time T
The average confidence of interior j-th of roadway characteristic, fj1Indicate first confidence level of j-th of roadway characteristic.
S3053: the first confidence level of each roadway characteristic of the characteristic point is added, the confidence of the characteristic point is obtained
Degree.
The example in S3052 is continued to use, the confidence level of characteristic point can be indicated by formula (2).
In formula (2), j indicates j-th of roadway characteristic in m roadway characteristic of characteristic point, fj1Indicate j-th of roadway characteristic
The first confidence level, F indicate characteristic point confidence level.
S306: if the matching on the vehicle running path between the corresponding third feature set of adjacent characteristic point
Degree is more than third preset matching degree threshold value, and the matching degree between the corresponding confidence level of the adjacent characteristic point is more than default
Confidence match threshold value, then using the adjacent characteristic point as similar features point.
In the present embodiment, if the matching degree between the corresponding third feature set of adjacent characteristic point is more than third
Preset matching degree threshold value then shows that the corresponding third feature set roadway characteristic of adjacent characteristic point is similar.As an example, the
Three preset matching degree threshold values can be 70%.
As an example, in the present embodiment, can according in the third feature set of adjacent characteristic point, the quantity of roadway characteristic and
Type determines whether the third feature set of adjacent characteristic point is similar.For example, third preset matching degree threshold value Ts is preset,
There are adjacent characteristic point A and B, corresponding third feature set is respectively LA3={ L1, L2, L3, L4 }, LB3=L1, L2,
L5, L3 }.According to LA3With LB3It is found that the quantity of roadway characteristic is identical in the third feature set of adjacent characteristic point A and B, and every
The quantity of same link feature occupies the 75% of roadway characteristic total quantity in a third feature set, thereby determines that adjacent characteristic point
Matching degree between the corresponding third feature set of A and B is 75%.By the similarity of adjacent characteristic point A and B be 75% with
Third preset matching degree threshold value Ts is compared, if can determine the third feature set phase of adjacent characteristic point A and B more than Ts
Seemingly.
In the present embodiment, default confidence match threshold value is to determine the unmatched maximum matching of the confidence level of adjacent characteristic point
Degree.If the matching degree between the corresponding confidence level of adjacent characteristic point is more than preset value confidence match threshold value, that is, show
The corresponding confidence level of characteristic point is mutually matched, and the corresponding confidence level of adjacent characteristic point is similar.
In the present embodiment, the confidence level of adjacent characteristic point can be done difference and taken absolute value, obtained numerical value is as adjacent
The matching degree of the confidence level of characteristic point.For example, the confidence level of adjacent characteristic point is done difference and is taken absolute value, and by absolute value knot
Fruit and preset confidence match threshold value TFIt is compared, it is whether similar with the confidence level of the adjacent characteristic point of determination.For example, phase
The confidence level of adjacent characteristic point A and B is respectively 78% and 91%, and the absolute value result of the confidence level difference of adjacent characteristic point A and B is
13%, by the absolute value result 13% of the confidence level difference of adjacent characteristic point A and B and confidence match threshold value TFIt is compared,
If absolute value result is more than TF, that is, can determine that adjacent characteristic point A is similar with the confidence level of B.
It is understood that the corresponding third feature sets match degree of the adjacent characteristic point of the determination of above-mentioned offer, with
And the method for the corresponding confidence match degree of the adjacent characteristic point of determination is merely illustrative.In specific implementation, it can be used
His mode determines the matching degree of the corresponding third feature set of adjacent characteristic point, and determines that adjacent characteristic point respectively corresponds
Confidence match degree.Here, not to the corresponding third feature sets match degree of the adjacent characteristic point of determination, and determine phase
The specific implementation of the corresponding confidence match degree of adjacent characteristic point is defined.
S307: confidence level highest and the similar features point more than confidence threshold value in the similar features point are screened, is picked
Except remaining characteristic point in the adjacent characteristic point.
As an example, the present embodiment has preset confidence threshold value Fthre=83%.Four adjacent features if it exists
Point A, B, C and D, and characteristic point A, B, C and D similar features point each other.The confidence level F of characteristic point AA=78%, characteristic point B's
Confidence level FBThe confidence level F of=91%, characteristic point CCThe confidence level F of=79%, characteristic point DD=85%.Wherein, confidence level highest
It and is more than confidence threshold value FthreSimilar features point be characterized point B, therefore only keeping characteristics point B will be in adjacent characteristic point
Remaining characteristic point A, C and D are rejected.
For the characteristic point B of reservation, following S308 to S309 are continued to execute;And characteristic point A, C and D will be as invalid spies
Sign point is removed, and no longer executes following S308 to S309.
S308: the second feature set and the third feature set, if the second feature set and institute
Stating the matching degree between third feature set is more than the first preset matching degree threshold value, obtains the spy using the high-precision map
The absolute position of point is levied, and obtains the relative position of the vehicle Yu the characteristic point from the vehicle positioning system of vehicle.
S309: it according to the absolute position of the characteristic point and the relative position of the vehicle and the characteristic point, obtains
The absolute position of the vehicle.
In the present embodiment, the implementation of S308 and the S309 implementation with S104 in previous embodiment to S105 respectively
Identical, the detailed description about S308 to S309 can be found in previous embodiment, will no longer repeat in the present embodiment.
The above are a kind of vehicle positioning methods provided in this embodiment.This method during realizing high accuracy positioning,
According to the matching degree and the corresponding confidence of adjacent characteristic point of the corresponding third feature set of the adjacent characteristic point
The matching degree of degree determines whether adjacent characteristic point is similar features point;Thereafter, by the corresponding confidence level of similar features point with
Confidence threshold value is compared, only by confidence level highest in similar features point and more than the similar features point of confidence threshold value
It remains.It is thus achieved that the screening to similar features point on vehicle running path.Avoid characteristic point second feature set with
The roadway characteristic erroneous matching of third feature set.Therefore, this method also improves characteristic point second feature set and third is special
The matched accuracy of roadway characteristic closed is collected, and then avoids Feature Points Matching fault, further ensures vehicle location
Precision.
It is understood that since the confidence level of the characteristic point of onboard sensor identification is the variable changed over time, because
This present embodiment can be set feature pixel confidence and update interval t when screening the similar features point in adjacent characteristic pointS, often
Cross tSTime interval, calculating is updated to the confidence level of characteristic point.In turn, so that vehicle location side provided in this embodiment
The vehicle precision of method positioning has higher real-time.
To solve aforementioned technical problem, embodiment of the application based on preceding method additionally provides a kind of vehicle location and sets
It is standby.The Vehicle Positioning Equipment is described in detail with reference to the accompanying drawings and examples.
Fourth embodiment
Referring to fig. 4, which is the structural schematic diagram of Vehicle Positioning Equipment provided by the embodiments of the present application.It needs to illustrate
It is that Vehicle Positioning Equipment provided in this embodiment is applied to vehicle, includes the vehicle-mounted sensing that can identify roadway characteristic on vehicle
Device.
As shown in figure 4, Vehicle Positioning Equipment 40 provided in this embodiment, comprising:
Fisrt feature set obtains module 401, second feature set obtains module 402, third feature set obtains module
403, feature compares and position acquisition module 404 and locating module 405.
Wherein, the fisrt feature set obtains module 401, special on vehicle running path for obtaining from high-precision map
The roadway characteristic for levying point, forms fisrt feature set;
The second feature set obtains module 402, special for screening first kind road from the fisrt feature set
Sign forms second feature set, and the first kind roadway characteristic is the roadway characteristic that the onboard sensor can identify;
The third feature set obtains module 403, for identifying the vehicle driving road using the onboard sensor
The roadway characteristic of the characteristic point on diameter obtains third feature set;
The feature compare with position acquisition module 404, be used for the second feature set and the third feature
Set, if the matching degree between the second feature set and the third feature set is more than the first preset matching degree threshold
Value, obtains the absolute position of the characteristic point using the high-precision map, and obtains from the vehicle positioning system of vehicle described
The relative position of vehicle and the characteristic point;
The locating module 405, for according to the absolute position of the characteristic point and the vehicle and the characteristic point
Relative position, obtain the absolute position of the vehicle.
The above are Vehicle Positioning Equipments provided by the embodiments of the present application.The equipment is based on onboard sensor to roadway characteristic
Accuracy of identification carries out preliminary screening to the roadway characteristic in fisrt feature set, obtain being made of first kind roadway characteristic the
Two characteristic sets avoid the unrecognized roadway characteristic of onboard sensor from influencing the accurate of characteristic point roadway characteristic by screening
Matching.If the matching degree between second feature set and third feature set is more than the first preset matching degree threshold value, that is, show
The roadway characteristic for the characteristic point that onboard sensor detects, it is special with the high-precision map road of characteristic point on a driving path of getting on the bus
Levy similar, the roadway characteristic successful match of characteristic point, the characteristic point based on the successful match obtains its absolute position and vehicle
With the relative position of characteristic point, the more accurate vehicle absolute position of positioning can be obtained.The Vehicle Positioning Equipment is based on high-precision
Map obtains the absolute position of characteristic point, and further obtains the absolute position of vehicle, compared with the prior art, vehicle location
Accuracy effectively improves.
Since there may be continuous adjacents on vehicle running path, and roadway characteristic height is similar or more similar several
Characteristic point.These are adjacent, and roadway characteristic height is similar or more similar characteristic point, may be to second feature set and the
Three characteristic sets are interfered for the roadway characteristic matching of same characteristic point, and then influence the positioning accuracy of vehicle.
In order to solve the above problem, Vehicle Positioning Equipment provided in this embodiment can also include:
Characteristic point screening module 406 rejects invalid feature for screening characteristic point according to the roadway characteristic of the characteristic point
Point.
As a kind of implementation, characteristic point screening module 406 can be specifically included:
The first screening unit of characteristic point 4061, for judging that adjacent characteristic point is corresponding on the vehicle running path
Whether the matching degree between second feature set is more than the second preset matching degree threshold value, if it is, by the adjacent characteristic point
First characteristic point that middle vehicle passes through is used as validity feature point, in the rejecting adjacent characteristic point in addition to validity feature point
Remaining characteristic point.
It is more than the adjacent feature of the second preset matching degree threshold value by matching degree between second feature set in the implementation
Point is screened, and first characteristic point that vehicle passes through in adjacent characteristic point is retained, and is rejected in adjacent characteristic point except validity feature
Remaining characteristic point except point has filtered out in adjacent characteristic point the with first characteristic point after first characteristic point as a result,
The similar characteristic point of two characteristic set roadway characteristic height, avoids the road of characteristic point second feature set Yu third feature set
Characteristic error matching.Therefore, equipment lifting characteristic point second feature set is matched with the roadway characteristic of third feature set
Accuracy, and then avoid Feature Points Matching fault, further ensure the precision of vehicle location.
As another implementation, characteristic point screening module 406 can be specifically included: roadway characteristic confidence level obtains single
Member 4062, feature pixel confidence acquiring unit 4063, similar features point determination unit 4064 and the second screening unit of characteristic point
4065。
Wherein, roadway characteristic confidence level acquiring unit 4062, it is each in the third feature set for obtaining the characteristic point
The confidence level of a roadway characteristic;The confidence level is the variable changed over time;
Feature pixel confidence acquiring unit 4063, it is special for road each in the third feature set according to the characteristic point
The confidence level of sign obtains the confidence level of the characteristic point;
Similar features point determination unit 4064, if corresponding for adjacent characteristic point on the vehicle running path
Matching degree between third feature set is more than third preset matching degree threshold value, and the corresponding confidence of the adjacent characteristic point
Matching degree between degree is more than default confidence match threshold value, using the adjacent characteristic point as similar features point;
The second screening unit of characteristic point 4065, for screening confidence level highest in the similar features point and being more than confidence level
The similar features point of threshold value rejects remaining characteristic point in the adjacent characteristic point.
In the implementation, according to the matching degree of the corresponding third feature set of the adjacent characteristic point and adjacent
The matching degree of the corresponding confidence level of characteristic point determines whether adjacent characteristic point is similar features point, by similar features point minute
Not corresponding confidence level is compared with confidence threshold value, only by confidence level highest in similar features point and more than confidence level door
The similar features point of limit value remains.It is thus achieved that the screening to similar features point on vehicle running path.It avoids to spy
Sign point second feature set is matched with the roadway characteristic of third feature set to be interfered.Therefore, which is also able to ascend
The matched accuracy of roadway characteristic of characteristic point second feature set and third feature set, and then avoid Feature Points Matching mistake
Accidentally, the precision of vehicle location is further ensured.
Based on the Vehicle Positioning Equipment that previous embodiment provides, the application furthermore provides a kind of automatic driving vehicle.
The specific implementation of the vehicle is described with reference to the accompanying drawings and examples.
5th embodiment
Referring to Fig. 5, which is a kind of structural schematic diagram of automatic driving vehicle provided by the embodiments of the present application.
As shown in figure 5, automatic driving vehicle 50 provided in this embodiment, comprising:
The Vehicle Positioning Equipment 40 and automated driving system 501 that fourth embodiment provides.
Wherein, Vehicle Positioning Equipment 40, for the absolute position of the vehicle to be sent to the automated driving system;
The automated driving system 501 carries out automatic Pilot for controlling vehicle according to the absolute position of the vehicle.
The above are automatic driving vehicles 50 provided by the embodiments of the present application.Wherein, Vehicle Positioning Equipment 40 is based on vehicle-mounted biography
Sensor carries out preliminary screening to the roadway characteristic in fisrt feature set, obtains by the first kind to the accuracy of identification of roadway characteristic
The second feature set that roadway characteristic is constituted avoids the unrecognized roadway characteristic of onboard sensor from influencing feature by screening
The accurate match of point roadway characteristic.If the matching degree between second feature set and third feature set is more than first default
With degree threshold value, that is, show the roadway characteristic for the characteristic point that onboard sensor detects, gets on the bus a driving path with high-precision map
The roadway characteristic of upper characteristic point is similar, and the roadway characteristic successful match of characteristic point, the characteristic point based on the successful match obtains it
The more accurate vehicle absolute position of positioning can be obtained in the relative position of absolute position and vehicle and characteristic point.The vehicle is fixed
Position equipment 40 obtains the absolute position of characteristic point based on high-precision map, and further obtains the absolute position of vehicle, compared to
The accuracy of the prior art, vehicle location effectively improves.
In the automatic driving vehicle 50, automatic Pilot vehicle that automated driving system 501 is obtained according to Vehicle Positioning Equipment 40
50 absolute position, control vehicle carry out automatic Pilot.Since the absolute positional accuracy of vehicle and accuracy improve, from
Dynamic control loop 501 can obtain accurate location of the vehicle in lane, this be conducive to Vehicular automatic driving path planning and
Operate decision.
It should be appreciated that in this application, " at least one (item) " refers to one or more, and " multiple " refer to two or two
More than a."and/or" indicates may exist three kinds of relationships, for example, " A and/or B " for describing the incidence relation of affiliated partner
It can indicate: only exist A, only exist B and exist simultaneously tri- kinds of situations of A and B, wherein A, B can be odd number or plural number.Word
Symbol "/" typicallys represent the relationship that forward-backward correlation object is a kind of "or"." at least one of following (a) " or its similar expression, refers to
Any combination in these, any combination including individual event (a) or complex item (a).At least one of for example, in a, b or c
(a) can indicate: a, b, c, " a and b ", " a and c ", " b and c ", or " a and b and c ", and wherein a, b, c can be individually, can also
To be multiple.
The above described is only a preferred embodiment of the present invention, being not intended to limit the present invention in any form.Though
So the present invention has been disclosed as a preferred embodiment, and however, it is not intended to limit the invention.It is any to be familiar with those skilled in the art
Member, without departing from the scope of the technical proposal of the invention, all using the methods and technical content of the disclosure above to the present invention
Technical solution makes many possible changes and modifications or equivalent example modified to equivalent change.Therefore, it is all without departing from
The content of technical solution of the present invention, according to the technical essence of the invention any simple modification made to the above embodiment, equivalent
Variation and modification, all of which are still within the scope of protection of the technical scheme of the invention.
Claims (10)
1. a kind of vehicle positioning method, which is characterized in that be applied to vehicle, include onboard sensor on the vehicle;The vehicle
Set sensor roadway characteristic for identification;
The roadway characteristic of characteristic point on vehicle running path is obtained from high-precision map, forms fisrt feature set;
First kind roadway characteristic is screened from the fisrt feature set forms second feature set, the first kind roadway characteristic
The roadway characteristic that can be identified for the onboard sensor;
The roadway characteristic of the characteristic point on the vehicle running path is identified using the onboard sensor, obtains third feature
Set;
Compare the second feature set and the third feature set, if the second feature set and the third feature
Matching degree between set is more than the first preset matching degree threshold value, then obtains the exhausted of the characteristic point using the high-precision map
To position, and obtain from the vehicle positioning system of the vehicle relative position of the vehicle Yu the characteristic point;
According to the absolute position of the characteristic point and the relative position of the vehicle and the characteristic point, the vehicle is obtained
Absolute position.
2. vehicle positioning method according to claim 1, which is characterized in that the second feature set and institute
Before stating third feature set, the method also includes:
Characteristic point is screened according to the roadway characteristic of the characteristic point, rejects invalid characteristic point.
3. vehicle positioning method according to claim 2, which is characterized in that the roadway characteristic according to the characteristic point
Characteristic point is screened, invalid characteristic point is rejected, specifically includes:
Judge whether the matching degree on the vehicle running path between the corresponding second feature set of adjacent characteristic point surpasses
The second preset matching degree threshold value is crossed, if it is, first characteristic point that vehicle in the adjacent characteristic point is passed through is as having
Characteristic point is imitated, remaining characteristic point in addition to the validity feature point in the adjacent characteristic point is rejected.
4. vehicle positioning method according to claim 2, which is characterized in that the roadway characteristic according to the characteristic point
Characteristic point is screened, invalid characteristic point is rejected, specifically includes:
Obtain the confidence level of each roadway characteristic in the third feature set of the characteristic point;The confidence level is to change over time
Variable;
According to the confidence level of each roadway characteristic in the third feature set of the characteristic point, the confidence of the characteristic point is obtained
Degree;
If the matching degree on the vehicle running path between the corresponding third feature set of adjacent characteristic point is more than the
Three preset matching degree threshold values, and the matching degree between the corresponding confidence level of the adjacent characteristic point is more than default confidence level
With threshold value, then using the adjacent characteristic point as similar features point;
Confidence level highest and the similar features point more than confidence threshold value in the similar features point are screened, is rejected described adjacent
Remaining characteristic point in characteristic point.
5. vehicle positioning method according to claim 4, which is characterized in that the third feature according to the characteristic point
The confidence level of each roadway characteristic in set, obtains the confidence level of the characteristic point, specifically includes:
Obtain the average confidence of each roadway characteristic within a preset time in the third feature set of the characteristic point;
By the average confidence of each roadway characteristic within a preset time, with obtained from the high-precision map it is described each
The confidence level of a roadway characteristic is multiplied, and obtains the first confidence level of each roadway characteristic of the characteristic point;
First confidence level of each roadway characteristic of the characteristic point is added, the confidence level of the characteristic point is obtained.
6. a kind of Vehicle Positioning Equipment, which is characterized in that be applied to vehicle, include onboard sensor on the vehicle;The vehicle
Set sensor roadway characteristic for identification;The Vehicle Positioning Equipment includes: that fisrt feature set obtains module, second feature collection
It closes and obtains module, third feature set obtains module, feature compares and position acquisition module and locating module;
The fisrt feature set obtains module, and the road for obtaining characteristic point on vehicle running path from high-precision map is special
Sign forms fisrt feature set;
The second feature set obtains module, forms for screening first kind roadway characteristic from the fisrt feature set
Two characteristic sets, the first kind roadway characteristic are the roadway characteristic that the onboard sensor can identify;
The third feature set obtains module, described on the vehicle running path for being identified using the onboard sensor
The roadway characteristic of characteristic point obtains third feature set;
The feature compare with position acquisition module, be used for the second feature set and the third feature set, such as
Matching degree between second feature set described in fruit and the third feature set is more than the first preset matching degree threshold value, utilizes institute
State the absolute position that high-precision map obtains the characteristic point, and from the vehicle positioning system of the vehicle obtain the vehicle with
The relative position of the characteristic point;
The locating module, for opposite with the characteristic point according to the absolute position and the vehicle of the characteristic point
Position obtains the absolute position of the vehicle.
7. Vehicle Positioning Equipment according to claim 6, which is characterized in that the Vehicle Positioning Equipment further include:
Characteristic point screening module rejects invalid characteristic point for screening characteristic point according to the roadway characteristic of the characteristic point.
8. Vehicle Positioning Equipment according to claim 7, which is characterized in that the characteristic point screening module specifically includes:
The first screening unit of characteristic point, for judging the corresponding second feature of adjacent characteristic point on the vehicle running path
Whether the matching degree between set is more than the second preset matching degree threshold value, if it is, vehicle in the adjacent characteristic point is passed through
First characteristic point crossed rejects its in addition to the validity feature point in the adjacent characteristic point as validity feature point
Remaining characteristic point.
9. Vehicle Positioning Equipment according to claim 7, which is characterized in that the characteristic point screening module specifically includes:
Roadway characteristic confidence level acquiring unit, each roadway characteristic sets in the third feature set for obtaining the characteristic point
Reliability;The confidence level is the variable changed over time;
Feature pixel confidence acquiring unit, the confidence for each roadway characteristic in the third feature set according to the characteristic point
Degree, obtains the confidence level of the characteristic point;
Similar features point determination unit, if for the corresponding third feature of characteristic point adjacent on the vehicle running path
Matching degree between set is more than third preset matching degree threshold value, and between the corresponding confidence level of the adjacent characteristic point
Matching degree is more than default confidence match threshold value, using the adjacent characteristic point as similar features point;
The second screening unit of characteristic point, for screening confidence level highest in the similar features point and being more than confidence threshold value
Similar features point rejects remaining characteristic point in the adjacent characteristic point.
10. a kind of automatic driving vehicle, which is characterized in that including the described in any item Vehicle Positioning Equipments of claim 6-9, also
It include: automated driving system;
The Vehicle Positioning Equipment, for the absolute position of the vehicle to be sent to the automated driving system;
The automated driving system carries out automatic Pilot for controlling vehicle according to the absolute position of the vehicle.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810994919.5A CN109115231B (en) | 2018-08-29 | 2018-08-29 | Vehicle positioning method and device and automatic driving vehicle |
PCT/CN2019/084539 WO2020042642A1 (en) | 2018-08-29 | 2019-04-26 | Vehicle positioning method and device, and autonomous vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810994919.5A CN109115231B (en) | 2018-08-29 | 2018-08-29 | Vehicle positioning method and device and automatic driving vehicle |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109115231A true CN109115231A (en) | 2019-01-01 |
CN109115231B CN109115231B (en) | 2020-09-11 |
Family
ID=64861217
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810994919.5A Active CN109115231B (en) | 2018-08-29 | 2018-08-29 | Vehicle positioning method and device and automatic driving vehicle |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN109115231B (en) |
WO (1) | WO2020042642A1 (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110068830A (en) * | 2019-03-27 | 2019-07-30 | 东软睿驰汽车技术(沈阳)有限公司 | A kind of method and device of vehicle location |
WO2020042642A1 (en) * | 2018-08-29 | 2020-03-05 | 东软睿驰汽车技术(沈阳)有限公司 | Vehicle positioning method and device, and autonomous vehicle |
CN110979346A (en) * | 2019-11-29 | 2020-04-10 | 北京百度网讯科技有限公司 | Method, device and equipment for determining lane where vehicle is located |
CN111489455A (en) * | 2020-03-27 | 2020-08-04 | 中科车港(深圳)实业股份有限公司 | Fuse trinity on-vehicle unit of big dipper ETC active radio frequency identification |
WO2021017213A1 (en) * | 2019-07-26 | 2021-02-04 | 魔门塔(苏州)科技有限公司 | Visual positioning effect self-detection method, and vehicle-mounted terminal |
CN112966059A (en) * | 2021-03-02 | 2021-06-15 | 北京百度网讯科技有限公司 | Data processing method and device for positioning data, electronic equipment and medium |
CN113419258A (en) * | 2021-07-07 | 2021-09-21 | 东软集团股份有限公司 | Positioning abnormity detection method and related equipment thereof |
WO2022041971A1 (en) * | 2020-08-29 | 2022-03-03 | 华为技术有限公司 | Positioning reliability test method and related device |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1841023A (en) * | 2005-01-28 | 2006-10-04 | 爱信艾达株式会社 | Vehicle position recognizing device and vehicle position recognizing method |
DE102009060600A1 (en) * | 2009-12-23 | 2011-06-30 | Volkswagen AG, 38440 | Method for assigning driving strip of road to car, involves compensating marking characteristics that are extracted from digital map and determined by image processing device using classifier to find driving path regarding actual position |
CN102208011A (en) * | 2010-03-31 | 2011-10-05 | 爱信艾达株式会社 | Image processing system and vehicle control system |
CN103954275A (en) * | 2014-04-01 | 2014-07-30 | 西安交通大学 | Lane line detection and GIS map information development-based vision navigation method |
CN105783936A (en) * | 2016-03-08 | 2016-07-20 | 武汉光庭信息技术股份有限公司 | Road sign drawing and vehicle positioning method and system for automatic drive |
CN107328411A (en) * | 2017-06-30 | 2017-11-07 | 百度在线网络技术(北京)有限公司 | Vehicle positioning system and automatic driving vehicle |
CN107339996A (en) * | 2017-06-30 | 2017-11-10 | 百度在线网络技术(北京)有限公司 | Vehicle method for self-locating, device, equipment and storage medium |
CN108303721A (en) * | 2018-02-12 | 2018-07-20 | 北京经纬恒润科技有限公司 | A kind of vehicle positioning method and system |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9719801B1 (en) * | 2013-07-23 | 2017-08-01 | Waymo Llc | Methods and systems for calibrating sensors using road map data |
EP3032221B1 (en) * | 2014-12-09 | 2022-03-30 | Volvo Car Corporation | Method and system for improving accuracy of digital map data utilized by a vehicle |
CN106548651A (en) * | 2017-01-17 | 2017-03-29 | 吉林大学 | A kind of On-line testing method of vehicle traveling road ahead fine information |
CN107957266B (en) * | 2017-11-16 | 2020-09-01 | 北京小米移动软件有限公司 | Positioning method, positioning device and storage medium |
CN109115231B (en) * | 2018-08-29 | 2020-09-11 | 东软睿驰汽车技术(沈阳)有限公司 | Vehicle positioning method and device and automatic driving vehicle |
-
2018
- 2018-08-29 CN CN201810994919.5A patent/CN109115231B/en active Active
-
2019
- 2019-04-26 WO PCT/CN2019/084539 patent/WO2020042642A1/en active Application Filing
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1841023A (en) * | 2005-01-28 | 2006-10-04 | 爱信艾达株式会社 | Vehicle position recognizing device and vehicle position recognizing method |
DE102009060600A1 (en) * | 2009-12-23 | 2011-06-30 | Volkswagen AG, 38440 | Method for assigning driving strip of road to car, involves compensating marking characteristics that are extracted from digital map and determined by image processing device using classifier to find driving path regarding actual position |
CN102208011A (en) * | 2010-03-31 | 2011-10-05 | 爱信艾达株式会社 | Image processing system and vehicle control system |
CN103954275A (en) * | 2014-04-01 | 2014-07-30 | 西安交通大学 | Lane line detection and GIS map information development-based vision navigation method |
CN105783936A (en) * | 2016-03-08 | 2016-07-20 | 武汉光庭信息技术股份有限公司 | Road sign drawing and vehicle positioning method and system for automatic drive |
CN107328411A (en) * | 2017-06-30 | 2017-11-07 | 百度在线网络技术(北京)有限公司 | Vehicle positioning system and automatic driving vehicle |
CN107339996A (en) * | 2017-06-30 | 2017-11-10 | 百度在线网络技术(北京)有限公司 | Vehicle method for self-locating, device, equipment and storage medium |
CN108303721A (en) * | 2018-02-12 | 2018-07-20 | 北京经纬恒润科技有限公司 | A kind of vehicle positioning method and system |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2020042642A1 (en) * | 2018-08-29 | 2020-03-05 | 东软睿驰汽车技术(沈阳)有限公司 | Vehicle positioning method and device, and autonomous vehicle |
CN110068830A (en) * | 2019-03-27 | 2019-07-30 | 东软睿驰汽车技术(沈阳)有限公司 | A kind of method and device of vehicle location |
WO2021017213A1 (en) * | 2019-07-26 | 2021-02-04 | 魔门塔(苏州)科技有限公司 | Visual positioning effect self-detection method, and vehicle-mounted terminal |
CN110979346A (en) * | 2019-11-29 | 2020-04-10 | 北京百度网讯科技有限公司 | Method, device and equipment for determining lane where vehicle is located |
CN110979346B (en) * | 2019-11-29 | 2021-08-31 | 北京百度网讯科技有限公司 | Method, device and equipment for determining lane where vehicle is located |
CN111489455A (en) * | 2020-03-27 | 2020-08-04 | 中科车港(深圳)实业股份有限公司 | Fuse trinity on-vehicle unit of big dipper ETC active radio frequency identification |
CN111489455B (en) * | 2020-03-27 | 2021-09-28 | 中科车港(深圳)实业股份有限公司 | Fuse trinity on-vehicle unit of big dipper ETC active radio frequency identification |
WO2022041971A1 (en) * | 2020-08-29 | 2022-03-03 | 华为技术有限公司 | Positioning reliability test method and related device |
CN112966059A (en) * | 2021-03-02 | 2021-06-15 | 北京百度网讯科技有限公司 | Data processing method and device for positioning data, electronic equipment and medium |
CN112966059B (en) * | 2021-03-02 | 2023-11-24 | 北京百度网讯科技有限公司 | Data processing method and device for positioning data, electronic equipment and medium |
CN113419258A (en) * | 2021-07-07 | 2021-09-21 | 东软集团股份有限公司 | Positioning abnormity detection method and related equipment thereof |
CN113419258B (en) * | 2021-07-07 | 2024-03-01 | 东软集团股份有限公司 | Positioning abnormality detection method and related equipment thereof |
Also Published As
Publication number | Publication date |
---|---|
WO2020042642A1 (en) | 2020-03-05 |
WO2020042642A8 (en) | 2020-04-02 |
CN109115231B (en) | 2020-09-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109115231A (en) | A kind of vehicle positioning method, equipment and automatic driving vehicle | |
JP7009716B2 (en) | Sparse map for autonomous vehicle navigation | |
CN108303103B (en) | Method and device for determining target lane | |
CN111380539B (en) | Vehicle positioning and navigation method and device and related system | |
CN106352867B (en) | Method and device for determining the position of a vehicle | |
CN101246010B (en) | Lane determining device, method, and program | |
US8085984B2 (en) | Image recognizing apparatus and method, and position determining apparatus, vehicle controlling apparatus and navigation apparatus using the image recognizing apparatus or method | |
JP2022535351A (en) | System and method for vehicle navigation | |
JP6729611B2 (en) | Vehicle image data generation device, running trajectory data generation system, section image data generation program and storage medium | |
CN109752741A (en) | Vehicle Positioning Equipment | |
CN111380542B (en) | Vehicle positioning and navigation method and device and related system | |
WO2015087502A1 (en) | Vehicle self-location device | |
CN105807296B (en) | A kind of vehicle positioning method, device and equipment | |
CN110276973B (en) | Automatic intersection traffic rule identification method | |
CN109791698B (en) | Method, device and computer-readable storage medium with instructions for determining the lateral position of a vehicle relative to a lane of a road surface | |
CN112325896B (en) | Navigation method, navigation device, intelligent driving equipment and storage medium | |
CN102208013A (en) | Scene matching reference data generation system and position measurement system | |
CN112009484A (en) | Method and system for determining driving assistance data | |
JP4953012B2 (en) | Image recognition device, program for image recognition device, navigation device using the same, and program for navigation device | |
CN104464375B (en) | It is a kind of to recognize the method that vehicle high-speed is turned | |
JP2011013039A (en) | Lane determination device and navigation system | |
JP2007178271A (en) | Own position recognition system | |
CN104395944A (en) | Carriageway recognition | |
JP6543983B2 (en) | Road information generation device and program | |
CN108351220A (en) | The polymerization of lane information for numerical map service |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |