CN109115231B - Vehicle positioning method and device and automatic driving vehicle - Google Patents
Vehicle positioning method and device and automatic driving vehicle Download PDFInfo
- Publication number
- CN109115231B CN109115231B CN201810994919.5A CN201810994919A CN109115231B CN 109115231 B CN109115231 B CN 109115231B CN 201810994919 A CN201810994919 A CN 201810994919A CN 109115231 B CN109115231 B CN 109115231B
- Authority
- CN
- China
- Prior art keywords
- feature
- vehicle
- points
- road
- feature points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- 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 vehicle positioning method and device and an automatic driving vehicle. The method is based on the recognition accuracy of the vehicle-mounted sensor on the road characteristics, and the road characteristics in the first characteristic set are preliminarily screened to obtain a second characteristic set formed by the first type of road characteristics. If the matching degree between the second feature set and the third feature set exceeds a first preset matching degree threshold value, the road features of the feature points detected by the vehicle-mounted sensor are similar to the road features of the feature points on the vehicle driving path on the high-precision map, the road features of the feature points are successfully matched, the absolute positions of the feature points and the relative positions of the vehicle and the feature points are obtained based on the feature points which are successfully matched, and the absolute position of the vehicle which is more accurate in positioning can be obtained. The method obtains the absolute position of the feature point based on the high-precision map, further obtains the absolute position of the vehicle, and effectively improves the accuracy of vehicle positioning compared with the prior art.
Description
Technical Field
The invention relates to the technical field of automobiles, in particular to a vehicle positioning method and device and an automatic driving vehicle.
Background
Nowadays, a global positioning system, a Beidou satellite navigation system and the like are mostly adopted to provide positioning and navigation services for vehicle users. However, the accuracy of the positioning and navigation systems applied in the civil field is limited at present, the positioning accuracy of the global positioning system and the Beidou satellite navigation system is about ten meters, and the positioning accuracy of the vehicle cannot be improved to the lane level. For example, according to the position information detected by the positioning system, the lane information of the lane where the vehicle is located, which is obtained by searching the map database, is inconsistent with the lane information of the lane where the vehicle is actually located.
Therefore, the vehicle positioning method provided by the prior art has low precision, and the positioning error caused by the method influences the path planning of the automatic driving vehicle.
Disclosure of Invention
Based on the technical problems, the application provides a vehicle positioning method, equipment and an automatic driving vehicle so as to solve the problem that the vehicle positioning accuracy is too low.
The application provides the following technical scheme:
in a first aspect of the application, a vehicle positioning method is provided, and the method is applied to a vehicle, wherein the vehicle comprises an on-board sensor; the vehicle-mounted sensor is used for identifying road characteristics;
the method comprises the following steps:
acquiring road characteristics of characteristic points on a vehicle driving path from a high-precision map to form a first characteristic set;
screening first road features from the first feature set to form a second feature set, wherein the first road features are road features which can be identified by the vehicle-mounted sensor;
identifying road characteristics of the characteristic points on the vehicle running path by using the vehicle-mounted sensor to obtain a third characteristic set;
comparing the second feature set with the third feature set, if the matching degree between the second feature set and the third feature set exceeds a first preset matching degree threshold value, obtaining the absolute position of the feature point by using the high-precision map, and obtaining the relative position of the vehicle and the feature point from an on-board positioning system of the vehicle;
and obtaining the absolute position of the vehicle according to the absolute position of the characteristic point and the relative position of the vehicle and the characteristic point.
As a possible implementation manner, before the comparing the second feature set and the third feature set, the method further includes:
and screening the characteristic points according to the road characteristics of the characteristic points, and removing the invalid characteristic points.
As a possible implementation manner, the screening of the feature points according to the road features of the feature points and the elimination of the invalid feature points specifically include:
and judging whether the matching degree between second feature sets respectively corresponding to adjacent feature points on the vehicle running path exceeds a second preset matching degree threshold value, if so, taking a first feature point passed by a vehicle in the adjacent feature points as an effective feature point, and rejecting the rest feature points except the effective feature point in the adjacent feature points.
As a possible implementation manner, the screening of the feature points according to the road features of the feature points and the elimination of the invalid feature points specifically include:
obtaining the confidence of each road feature in the third feature set of the feature points; the confidence is a variable that varies over time;
obtaining the confidence coefficient of the feature point according to the confidence coefficient of each road feature in the third feature set of the feature point;
if the matching degree between the third feature sets respectively corresponding to the adjacent feature points on the vehicle running path exceeds a third preset matching degree threshold value, and the matching degree between the confidence degrees respectively corresponding to the adjacent feature points exceeds a preset confidence degree matching threshold value, taking the adjacent feature points as similar feature points;
and screening the similar characteristic points with the highest confidence level and exceeding a confidence level threshold value from the similar characteristic points, and rejecting the rest characteristic points from the adjacent characteristic points.
As a possible implementation manner, the obtaining the confidence level of the feature point according to the confidence level of each road feature in the third feature set of the feature point specifically includes:
obtaining the average confidence of each road characteristic in the third characteristic set of the characteristic points in a preset time;
multiplying the average confidence coefficient of each road characteristic in preset time by the confidence coefficient of each road characteristic obtained from the high-precision map to obtain a first confidence coefficient of each road characteristic of the characteristic point;
and adding the first confidence degrees of the road characteristics of the characteristic points to obtain the confidence degree of the characteristic points.
In a second aspect of the application, a vehicle positioning device is provided, which is applied to a vehicle, wherein the vehicle comprises an on-board sensor; the vehicle-mounted sensor is used for identifying road characteristics;
the vehicle positioning apparatus includes: the system comprises a first feature set acquisition module, a second feature set acquisition module, a third feature set acquisition module, a feature comparison and position acquisition module and a positioning module;
the first feature set acquisition module is used for acquiring road features of feature points on a vehicle driving path from a high-precision map to form a first feature set;
the second feature set acquisition module is used for screening a first type of road features from the first feature set to form a second feature set, wherein the first type of road features are road features which can be identified by the vehicle-mounted sensor;
the third feature set acquisition module is used for identifying the road features of the feature points on the vehicle running path by using the vehicle-mounted sensor to acquire a third feature set;
the feature comparison and position acquisition module is used for comparing the second feature set with the third feature set, if the matching degree between the second feature set and the third feature set exceeds a first preset matching degree threshold value, acquiring the absolute position of the feature point by using the high-precision map, and acquiring the relative position of the vehicle and the feature point from a vehicle-mounted positioning system of the vehicle;
and the positioning module is used for obtaining the absolute position of the vehicle according to the absolute position of the characteristic point and the relative position of the vehicle and the characteristic point.
As a possible implementation, the vehicle positioning apparatus further includes:
and the characteristic point screening module is used for screening the characteristic points according to the road characteristics of the characteristic points and eliminating invalid characteristic points.
As a possible implementation manner, the feature point screening module specifically includes:
and the feature point first screening unit is used for judging whether the matching degree between second feature sets respectively corresponding to adjacent feature points on the vehicle running path exceeds a second preset matching degree threshold value, if so, taking a first feature point passed by a vehicle in the adjacent feature points as an effective feature point, and rejecting other feature points except the effective feature point in the adjacent feature points.
As a possible implementation manner, the feature point screening module specifically includes:
a road feature confidence coefficient obtaining unit, configured to obtain a confidence coefficient of each road feature in a third feature set of the feature points; the confidence is a variable that varies over time;
a feature point confidence coefficient obtaining unit, configured to obtain a confidence coefficient of the feature point according to a confidence coefficient of each road feature in a third feature set of the feature point;
a similar feature point determining unit, configured to, if a matching degree between third feature sets respectively corresponding to adjacent feature points on the vehicle travel path exceeds a third preset matching degree threshold, and a matching degree between confidence degrees respectively corresponding to the adjacent feature points exceeds a preset confidence degree matching threshold, take the adjacent feature points as similar feature points;
and the second feature point screening unit is used for screening the similar feature points with the highest confidence level and exceeding a confidence level threshold value from the similar feature points and rejecting other feature points in the adjacent feature points.
In a third aspect of the present application, there is provided an autonomous vehicle comprising the vehicle positioning apparatus provided in the second aspect of the present application, further comprising: an automatic driving system;
the vehicle positioning device is used for sending the absolute position of the vehicle to the automatic driving system;
and the automatic driving system is used for controlling the vehicle to automatically drive according to the absolute position of the vehicle.
Compared with the prior art, the invention has at least the following advantages:
the vehicle positioning method is applied to a vehicle provided with a vehicle-mounted sensor capable of identifying road characteristics, and comprises the steps of firstly, acquiring the road characteristics of characteristic points on a vehicle driving path from a high-precision map to form a first characteristic set; then, screening first road characteristics from the first characteristic set to form a second characteristic set, wherein the first road characteristics are road characteristics which can be identified by the vehicle-mounted sensor; then, recognizing road characteristics of characteristic points on a vehicle running path by using a vehicle-mounted sensor to obtain a third characteristic set; then, comparing the second feature set with the third feature set, if the matching degree between the second feature set and the third feature set exceeds a first preset matching degree threshold value, obtaining the absolute position of the feature point by using a high-precision map, and obtaining the relative position of the vehicle and the feature point from a vehicle-mounted positioning system of the vehicle; finally, the absolute position of the vehicle is obtained according to the absolute position of the feature point and the relative positions of the vehicle and the feature point.
The method includes the steps that road features in a first feature set are preliminarily screened based on the recognition accuracy of a vehicle-mounted sensor on the road features, a second feature set formed by the first type of road features is obtained, and the road features which cannot be recognized by the vehicle-mounted sensor are prevented from influencing accurate matching of the road features of feature points through screening. If the matching degree between the second feature set and the third feature set exceeds a first preset matching degree threshold value, the road features of the feature points detected by the vehicle-mounted sensor are similar to the road features of the feature points on the vehicle driving path on the high-precision map, the road features of the feature points are successfully matched, the absolute positions of the feature points and the relative positions of the vehicle and the feature points are obtained based on the feature points which are successfully matched, and the absolute position of the vehicle which is more accurate in positioning can be obtained. The method obtains the absolute position of the feature point based on the high-precision map, further obtains the absolute position of the vehicle, and effectively improves the accuracy of vehicle positioning compared with the prior art.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a vehicle locating method according to a first embodiment of the present application;
FIG. 2 is a flow chart of a vehicle locating method according to a second embodiment of the present application;
FIG. 3 is a flow chart of a vehicle locating method according to a third embodiment of the present application;
FIG. 4 is a schematic structural diagram of a vehicle positioning apparatus according to a fourth embodiment of the present application;
fig. 5 is a schematic structural diagram of an autonomous vehicle according to a fifth embodiment of the present application.
Detailed Description
In order to solve the problem that the positioning accuracy of the vehicle is too low and the automatic driving requirement based on a map is difficult to meet, the application provides a vehicle positioning method and equipment and an automatic driving vehicle.
The technical solutions of the present application will be described clearly and completely with reference to the following embodiments and the accompanying drawings, and it is to be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
First embodiment
Referring to fig. 1, the figure is a flowchart of a vehicle positioning method provided in an embodiment of the present application. First, it should be noted that the vehicle positioning method provided by the present embodiment is applied to a vehicle, and the vehicle includes an on-vehicle sensor capable of identifying a road characteristic.
As shown in fig. 1, the vehicle positioning method provided in this embodiment includes:
s101: and acquiring road characteristics of the characteristic points on the vehicle driving path from the high-precision map to form a first characteristic set.
The vehicle travel path may be a travel path determined from a trip start point and a trip destination point of the vehicle. On the vehicle driving path, at least two characteristic points are included. In this embodiment, the feature points may be various types of intersections, landmarks, and the like, such as intersections, t-junctions, restaurants, shopping malls, schools, stations, bridges, and the like.
The road characteristics of the feature points include traffic signs, road surface characteristics, road surface conditions, traffic conditions, and the like in the vicinity of the feature points. As an example, the road feature of the feature point may be: stop line of intersection, line type of lane line, curvature of lane, intersection feature, stop prohibition sign, speed limit release sign, signal lamp, left turn, right turn, straight going, lane change, left side going, right side going, front construction, merging, front traffic accident, etc.
And the first feature set of the feature points comprises all road features of the feature points in the high-precision map.
It should be noted that the technical solution provided by the present embodiment is adopted for each feature point on the vehicle travel path. Each feature point corresponds to a first set of features. In the present embodiment, a case of any one feature point is described as an example only.
S102: and screening a first type of road features from the first feature set to form a second feature set.
The accuracy of identifying the road features of the feature points on the vehicle travel path by the vehicle-mounted sensor is limited, and all the road features of the feature points included in the first feature set may not be identified, and only a part of the road features may be identified. In order to realize high-precision positioning, the matching between the high-precision map feature points and the feature points detected by the vehicle-mounted sensor is completed according to the detection and identification results of the vehicle-mounted sensor on the road features, so that the influence of the road features which cannot be identified by the vehicle-mounted sensor on the accurate matching of the feature points is avoided, the step screens out the road features which can be identified by the vehicle-mounted sensor, namely the first road features from the first feature set, and the first road features form a second feature set. Furthermore, the road features included in the second feature set are all road features that can be identified based on the feature point vehicle-mounted sensor.
As an example, each road feature in the first feature set may have a confidence level, and the confidence level of each road feature indicates that the road feature can be reliably identified by the vehicle-mounted sensorTo other extents. For example, the feature recognition confidence threshold for an on-board sensor is TrIn the first feature set, the confidence coefficient is greater than the feature recognition confidence coefficient threshold value TrThe road characteristics of (1) are taken as first-class road characteristics, and a second characteristic set is formed by the first-class road characteristics.
It should be noted that, in the embodiment of the present application, the vehicle-mounted sensor includes, but is not limited to, any one or more of the following in combination: satellite positioning systems (GNSS), odometers, lane recognition systems, traffic sign recognition systems, and other road feature recognition systems.
Wherein the odometer includes, but is not limited to, any one or combination of more of the following: the device comprises a transmission system output shaft rotating speed sensor, a wheel speed sensor and a vehicle speed sensor;
the identification content of the lane identification system includes, but is not limited to, any one or combination of more of the following: lane line type, lane line curvature, lane-based offset, and lane-based heading bias;
the identification content of the traffic sign identification system includes, but is not limited to, any one or combination of more of the following: speed limit boards and traffic signs;
other road feature identification system identification content includes but is not limited to: water horse and portal frame.
S103: and identifying the road characteristics of the characteristic points on the vehicle running path by using the vehicle-mounted sensor to obtain a third characteristic set.
The confidence coefficient actually recognized by the vehicle-mounted sensor exceeds the feature recognition confidence coefficient threshold T for each road feature in the third feature setrThe road characteristic of (1).
S104: and comparing the second feature set with the third feature set, if the matching degree between the second feature set and the third feature set exceeds a first preset matching degree threshold value, obtaining the absolute position of the feature point by using the high-precision map, and obtaining the relative position of the vehicle and the feature point from a vehicle-mounted positioning system of the vehicle.
In order to determine whether the second feature set and the third feature set of the feature point are successfully matched, in this embodiment of the application, the matching degree of the second feature set and the third feature set corresponding to the feature point is compared with a first preset matching degree threshold. If the matching degree between the second feature set and the third feature set exceeds a first preset matching degree threshold value, that is, the second feature set and the third feature set of the feature points are successfully matched, the road features of the feature points detected by the vehicle-mounted sensor are similar to the road features of the feature points on the vehicle driving path on the high-precision map, that is, the road features are successfully matched.
When determining whether the second feature set and the third feature set of the feature points are successfully matched, no requirement is made on the consistency of the order of the road features in the second feature set and the third feature set.
As an example, the second feature set of the feature point is { L1, L2, L3, L4}, the third feature set is { L3, L1, L4}, and L1, L2, L3, and L4 represent different kinds of road features of the feature point, respectively. In the present example, the first preset matching degree threshold is 72%, and since the road features of the same category included in the second feature set and the third feature set occupy 75% of all the road feature categories in the second feature set, the matching degree between the feature point second feature set and the third feature set, which is 75%, exceeds the first preset matching degree threshold. And since the confidence of each road feature in the third feature set exceeds the feature recognition confidence threshold of the vehicle-mounted sensor, it can be determined that the second feature set is similar to the third feature set.
The second feature set of the feature points is similar to the third feature set, and the second feature set and the third feature set representing the feature points are successfully matched with the road features in the third feature set, and the feature points can be used for realizing high-precision positioning of the vehicle. As an example, the absolute position P of the feature point J in the high-precision map is acquiredJOn the other hand, the position of the feature point J obtained by an on-vehicle Positioning System of the vehicle, for example, a Global Positioning System (GPS) is not PJFurthermore, it can be seen that the vehicle obtained only by the on-vehicle positioning system is insufficient in positioning accuracy by the on-vehicle positioning systemThe vehicle W position must have an error. In order to overcome the positioning error of the vehicle W, the step also obtains the relative position delta P of the vehicle W and the characteristic point J from the vehicle-mounted positioning systemWJ，ΔPWJMay be used to acquire the absolute position of the vehicle W.
S105: and obtaining the absolute position of the vehicle according to the absolute position of the characteristic point and the relative position of the vehicle and the characteristic point.
As an optional implementation manner, S105 may specifically include:
s1051: and converting the relative position in a coordinate system of the absolute position of the characteristic point to obtain a first relative position of the vehicle and the characteristic point.
S1052: and moving the absolute position of the characteristic point to the first relative position to obtain the absolute position of the vehicle, wherein the absolute position of the vehicle comprises the longitudinal coordinate, the lateral coordinate and the heading of the vehicle.
Following the example in S104, the relative position Δ P of the vehicle W to the feature point JWJAbsolute position P at feature point JJIs converted to obtain a first relative position delta P 'of the vehicle W and the characteristic point J'WJ(ii) a The absolute position P of the feature point JJMoving a first relative position Δ P'WJObtaining an absolute position P of the vehicle WW. Relative to the position of the vehicle W directly obtained by the vehicle-mounted positioning system, the absolute position P of the vehicle W obtained by the vehicle positioning method provided by the embodiment of the applicationWThe precision is improved.
The vehicle positioning method provided by the embodiment of the application is provided above. The method includes the steps that road features in a first feature set are preliminarily screened based on the recognition accuracy of a vehicle-mounted sensor on the road features, a second feature set formed by the first type of road features is obtained, and the road features which cannot be recognized by the vehicle-mounted sensor are prevented from influencing accurate matching of the road features of feature points through screening. If the matching degree between the second feature set and the third feature set exceeds a first preset matching degree threshold value, the road features of the feature points detected by the vehicle-mounted sensor are similar to the road features of the feature points on the vehicle driving path on the high-precision map, the road features of the feature points are successfully matched, the absolute positions of the feature points and the relative positions of the vehicle and the feature points are obtained based on the feature points which are successfully matched, and the absolute position of the vehicle which is more accurate in positioning can be obtained. The method obtains the absolute position of the feature point based on the high-precision map, further obtains the absolute position of the vehicle, and effectively improves the accuracy of vehicle positioning compared with the prior art.
Because there may be several feature points on the vehicle travel path that are continuously adjacent and have highly similar road features. These neighboring feature points with highly similar road features may interfere with the road feature matching of the second feature set and the third feature set for the same feature point. For example, adjacent feature points K and F exist in sequence on the vehicle driving path, second feature sets corresponding to the feature points K and F are highly similar, and third feature sets corresponding to the feature points K and F are highly similar. If the second feature set of the feature point K is highly similar to the third feature set of the feature point F, the feature point F identified by the vehicle-mounted sensor is likely to be regarded as the feature point K on the vehicle driving path on the high-precision map, and the positioning precision of the vehicle is further influenced.
In order to avoid the problems, the application further provides another vehicle positioning method. The following describes in detail a specific embodiment of the vehicle positioning method with reference to the embodiments and the drawings.
Second embodiment
Referring to fig. 2, the figure is a flowchart of a vehicle positioning method provided in this embodiment.
As shown in fig. 2, the vehicle positioning method provided in this embodiment includes:
s201: and acquiring road characteristics of the characteristic points on the vehicle driving path from the high-precision map to form a first characteristic set.
S202: and screening a first type of road features from the first feature set to form a second feature set.
S203: and identifying the road characteristics of the characteristic points on the vehicle running path by using the vehicle-mounted sensor to obtain a third characteristic set.
In this embodiment, the implementation manners of S201 to S203 are respectively the same as the implementation manners of S101 to S103 in the foregoing embodiment, and for the detailed description of S201 to S203, reference may be made to the foregoing embodiment, which will not be repeated in this embodiment.
S204: and screening the characteristic points according to the road characteristics of the characteristic points, and removing the invalid characteristic points.
In the step, the adjacent feature points are screened and removed according to the matching degree of the road features of the adjacent feature points. It should be noted that, in this embodiment, the adjacent feature points may be two adjacent feature points, or two or more feature points having an adjacent relationship.
As a first implementation manner, adjacent feature points may be screened and eliminated from the perspective of road feature matching degree of the high-precision map including the feature points. The method comprises the following specific steps:
and judging whether the matching degree between second feature sets respectively corresponding to adjacent feature points on the vehicle running path exceeds a second preset matching degree threshold value, if so, taking a first feature point passed by the vehicle in the adjacent feature points as an effective feature point, and rejecting the rest feature points except the effective feature point in the adjacent feature points.
In this embodiment, if the matching degree between the second feature sets respectively corresponding to the adjacent feature points exceeds a second preset matching degree threshold, it indicates that the adjacent feature points are adjacent feature points with highly similar road features. As an example, the second preset matching degree threshold may be 90%.
As an example, the matching degree between the second feature sets respectively corresponding to the feature points K and F adjacent to each other on the vehicle driving path is greater than a second preset matching degree threshold, that is, the road features in the second feature sets respectively corresponding to the feature points K and F are highly similar, the first feature point K where the vehicle passes is taken as an effective feature point, and the following steps S205 to S206 are continuously executed; the feature point F is eliminated as an invalid feature point, and S205 to S206 described below are not executed.
As a second implementation manner, adjacent feature points may be screened and rejected from the perspective of the road feature matching degree of the feature points actually recognized by the vehicle-mounted sensor. The method comprises the following specific steps:
and judging whether the matching degree between the third feature sets respectively corresponding to the adjacent feature points on the vehicle running path exceeds a second preset matching degree threshold value, if so, taking the first feature point passed by the vehicle in the adjacent feature points as an effective feature point, and rejecting the rest feature points except the effective feature point in the adjacent feature points.
And if the matching degree between the third feature sets respectively corresponding to the adjacent feature points exceeds a second preset matching degree threshold value, indicating that the adjacent feature points are mutually adjacent feature points with highly similar road features. As an example, the second preset matching degree threshold may be 90%.
As an example, the matching degree between the third feature sets respectively corresponding to the feature points M and N adjacent to each other on the vehicle driving path is greater than a second preset matching degree threshold, that is, the road features in the third feature sets respectively corresponding to the feature points M and N are highly similar. Taking the first characteristic point M passed by the vehicle as an effective characteristic point, and continuing to execute the following S205 to S206; the feature point N is eliminated as an invalid feature point, and the following S205 to S206 are not executed.
It is understood that S204 may also combine the above two implementation manners to screen and reject adjacent feature points. That is, adjacent feature points may be screened and rejected from the perspective of the road feature matching degree of the feature points included in the high-precision map and the perspective of the road feature matching degree of the feature points actually recognized by the in-vehicle sensor. Here, the description of this implementation is omitted, and reference may be made to the description in the foregoing two implementations of S204.
S205: and comparing the second feature set with the third feature set, if the matching degree between the second feature set and the third feature set exceeds a first preset matching degree threshold value, obtaining the absolute position of the feature point by using the high-precision map, and obtaining the relative position of the vehicle and the feature point from a vehicle-mounted positioning system of the vehicle.
S206: and obtaining the absolute position of the vehicle according to the absolute position of the characteristic point and the relative position of the vehicle and the characteristic point.
In this embodiment, the implementation manners of S205 and S206 are respectively the same as the implementation manners of S104 to S105 in the foregoing embodiment, and for the detailed description of S205 to S206, reference may be made to the foregoing embodiment, which will not be repeated in this embodiment.
The vehicle positioning method provided by the embodiment is described above. In the process of realizing high-precision positioning, the method screens the feature points according to the road features of the feature points and eliminates invalid feature points. Specifically, adjacent feature points with the matching degree between the second feature sets exceeding a second preset matching degree threshold value and/or adjacent feature points with the matching degree between the third feature sets exceeding the second preset matching degree threshold value are screened, a first feature point, through which a vehicle passes, in the adjacent feature points is reserved, and other feature points except for effective feature points in the adjacent feature points are removed. Therefore, the feature points with the height similar to the road feature of the second feature set of the first feature point after the first feature point in the adjacent feature points and/or the feature points with the height similar to the road feature of the third feature set of the first feature point after the first feature point in the adjacent feature points are filtered out, and the road feature mismatching between the second feature set of the feature points and the road feature of the third feature set is avoided. Therefore, the method improves the accuracy of the road characteristic matching of the second characteristic set and the third characteristic set of the characteristic points, further avoids the matching error of the characteristic points, and further ensures the accuracy of vehicle positioning.
Since there may be several feature points on the vehicle travel path that are adjacent and have similar road features. The feature points are close in position and similar in road features, and may interfere with road feature matching of the second feature set and the third feature set for the same feature point.
In order to avoid the problems and ensure the precision of vehicle positioning, the application further provides a vehicle positioning method. The following describes in detail a specific embodiment of the vehicle positioning method with reference to the embodiments and the drawings.
Third embodiment
Referring to fig. 3, it is a flowchart of a vehicle positioning method provided in this embodiment.
As shown in fig. 3, the vehicle positioning method provided in this embodiment includes:
s301: and acquiring road characteristics of the characteristic points on the vehicle driving path from the high-precision map to form a first characteristic set.
S302: and screening a first type of road features from the first feature set to form a second feature set.
S303: and identifying the road characteristics of the characteristic points on the vehicle running path by using the vehicle-mounted sensor to obtain a third characteristic set.
In this embodiment, the implementation manners of S301 to S303 are respectively the same as the implementation manners of S101 to S103 in the foregoing embodiment, and for the detailed description of S301 to S303, reference may be made to the foregoing embodiment, which will not be repeated in this embodiment.
S304: and obtaining the confidence of each road feature in the third feature set of the feature points.
As a specific implementation manner, when the vehicle-mounted sensor identifies the road features of the feature points, the confidence of each road feature may be obtained. It is understood that, during the process that the vehicle passes through the feature points, the distances between the road features of the feature points and the vehicle-mounted sensors are changed continuously, and therefore, the confidence degrees of the identified road features are variable along with the change of time.
And the confidence degree of each road characteristic in the third characteristic set represents the confidence degree of each road characteristic in the third characteristic set. The higher the confidence level of a road feature, the higher its confidence level.
Of course, the confidence of each road feature in the third feature set may also be processed and calculated by some parameters of the road feature. Here, a specific manner of obtaining the confidence of each road feature in the third features is not limited.
S305: and obtaining the confidence coefficient of the feature point according to the confidence coefficient of each road feature in the third feature set of the feature point.
In order to screen feature points that are adjacent to each other on the vehicle travel path and similar to the third feature set, in this embodiment, the confidence level of each road feature in the third feature set needs to be used to calculate the confidence level of the feature point corresponding to the third feature set. The confidence of the feature points can be obtained in the following manner:
s3051: and obtaining the average confidence of each road characteristic in the third characteristic set of the characteristic points in a preset time.
As an example, the vehicle-mounted sensor identifies road features of the feature points, and the confidence degrees of m road features in the third feature set of the feature points are obtained to be fc1(t)，fc2(t)，fc3(t)…fcm(T), the average confidence degrees of the m road characteristics in the preset time T are respectively fca1，fca2，fca3…fcam。
S3052: and multiplying the average confidence coefficient of each road characteristic in preset time by the confidence coefficient of each road characteristic obtained from the high-precision map to obtain a first confidence coefficient of each road characteristic of the characteristic point.
As an example, the confidence levels of the m road features are f respectively for the feature points obtained from the high-precision map1，f2，f3…fm。
The first confidence degrees of the m road characteristics of the characteristic point can be obtained by using the formula (1).
fj1＝fj*fcajFormula (1)
In formula (1), j represents the jth road feature of m road features of the feature point, m is an integer greater than 1, j is [1, m]Any integer of (1), fjRepresenting the confidence of the jth road feature on a high-precision map, fcajIs the average confidence of the jth road feature within a preset time T, fj1Representing a first confidence of the jth road feature.
S3053: and adding the first confidence degrees of the road characteristics of the characteristic points to obtain the confidence degree of the characteristic points.
Following the example in S3052, the confidence of the feature point can be represented by formula (2).
In the formula (2), j represents the jth road feature of the m road features of the feature point, fj1The first confidence of the jth road feature is represented, and F represents the confidence of the feature point.
S306: and if the matching degree between the third feature sets respectively corresponding to the adjacent feature points on the vehicle running path exceeds a third preset matching degree threshold value, and the matching degree between the confidence degrees respectively corresponding to the adjacent feature points exceeds a preset confidence degree matching threshold value, taking the adjacent feature points as similar feature points.
In this embodiment, if the matching degree between the third feature sets respectively corresponding to the adjacent feature points exceeds a third preset matching degree threshold, it indicates that the road features of the third feature sets respectively corresponding to the adjacent feature points are similar. As an example, the third preset matching degree threshold may be 70%.
As an example, in the present embodiment, it may be determined whether the third feature sets of adjacent feature points are similar according to the number and the types of road features in the third feature set of adjacent feature points. For example, a third preset matching degree threshold Ts is preset, adjacent feature points a and B exist, and corresponding third feature sets are L respectivelyA3＝{L1，L2，L3，L4}，LB3L1, L2, L5, L3. According to LA3And LB3It can be known that the number of road features in the third feature sets of the adjacent feature points a and B is the same, and the number of the same road features in each third feature set occupies 75% of the total number of the road features, so that the matching degree between the third feature sets corresponding to the adjacent feature points a and B is determined to be 75%. And comparing the similarity of the adjacent characteristic points A and B, which is 75%, with a third preset matching threshold Ts, and if the similarity exceeds Ts, determining that the third characteristic sets of the adjacent characteristic points A and B are similar.
In this embodiment, the confidence matching threshold is preset as the maximum matching degree for determining the confidence mismatch of adjacent feature points. If the matching degree between the corresponding confidences of the adjacent feature points exceeds a preset confidence matching threshold, the corresponding confidences of the feature points are matched with each other, and the corresponding confidences of the adjacent feature points are similar.
In this embodiment, the confidence degrees of the adjacent feature points may be differentiated and the absolute value may be taken, and the obtained value may be used as the matching degree of the confidence degrees of the adjacent feature points. For example, the confidence degrees of the adjacent feature points are differentiated and the absolute value is taken, and the absolute value result is matched with a preset confidence degree matching threshold TFA comparison is made to determine if the confidence levels of adjacent feature points are similar. For example, the confidence degrees of the adjacent feature points a and B are 78% and 91%, respectively, the absolute value result of the confidence difference between the adjacent feature points a and B is 13%, and the absolute value result of the confidence difference between the adjacent feature points a and B is 13% and the confidence degree matching threshold TFComparing, if the absolute value result exceeds TFIt can be determined that the confidence degrees of the adjacent feature points a and B are similar.
It is to be understood that the above-provided methods for determining the matching degrees of the third feature set corresponding to the adjacent feature points respectively and determining the matching degrees of the confidence degrees corresponding to the adjacent feature points respectively are only examples. In a specific implementation, the matching degree of the third feature set corresponding to the adjacent feature points respectively and the confidence degree matching degree corresponding to the adjacent feature points respectively may be determined in other manners. Here, the specific implementation manner of determining the third feature set matching degree corresponding to each of the adjacent feature points and determining the confidence degree matching degree corresponding to each of the adjacent feature points is not limited.
S307: and screening the similar characteristic points with the highest confidence level and exceeding a confidence level threshold value from the similar characteristic points, and rejecting the rest characteristic points from the adjacent characteristic points.
As an example, the confidence threshold value F is preset in the present embodimentthre83% of the total weight. If there are four adjacent feature points A, B, C and D, and feature points A, B, C and D are mutually similar feature points. Specially for treating diabetesConfidence F of feature point AA78%, confidence F of feature point BB91%, confidence F of feature point CC79%, confidence F of feature point DD85 percent. Wherein, the confidence coefficient is the highest and exceeds a threshold value F of the confidence coefficientthreThe similar feature point of (2) is feature point B, so only feature point B is retained, and the remaining feature points A, C and D in the adjacent feature points are rejected.
For the retained feature point B, the following S308 to S309 are continuously performed; and the feature points A, C and D are eliminated as invalid feature points, and S308 to S309 described below are not executed.
S308: and comparing the second feature set with the third feature set, if the matching degree between the second feature set and the third feature set exceeds a first preset matching degree threshold value, obtaining the absolute position of the feature point by using the high-precision map, and obtaining the relative position of the vehicle and the feature point from a vehicle-mounted positioning system of the vehicle.
S309: and obtaining the absolute position of the vehicle according to the absolute position of the characteristic point and the relative position of the vehicle and the characteristic point.
In this embodiment, the implementation manners of S308 and S309 are respectively the same as the implementation manners of S104 to S105 in the foregoing embodiment, and for the detailed description of S308 to S309, reference may be made to the foregoing embodiment, and no further description will be given in this embodiment.
The vehicle positioning method provided by the embodiment is described above. In the process of realizing high-precision positioning, determining whether the adjacent feature points are similar feature points according to the matching degree of the third feature set corresponding to the adjacent feature points respectively and the matching degree of the confidence degrees corresponding to the adjacent feature points respectively; and then, comparing the confidence degrees corresponding to the similar characteristic points with a confidence degree threshold value, and only keeping the similar characteristic points with the highest confidence degree and exceeding the confidence degree threshold value in the similar characteristic points. Therefore, screening of similar characteristic points on the vehicle driving path is achieved. And avoiding the road characteristic mismatching of the second characteristic set and the third characteristic set of the characteristic points. Therefore, the method also improves the accuracy of the road characteristic matching of the second characteristic set and the third characteristic set of the characteristic points, thereby avoiding the matching error of the characteristic points and further ensuring the accuracy of vehicle positioning.
It is understood that, since the confidence of the feature points identified by the vehicle-mounted sensor is a variable that changes with time, the embodiment may set the feature point confidence update interval t when screening similar feature points in adjacent feature pointsSEvery time t passesSAnd (4) updating and calculating the confidence of the feature points at the time intervals. Furthermore, the vehicle positioning method provided by the embodiment can be used for positioning the vehicle with higher accuracy in real time.
In order to solve the technical problem, the application is based on the embodiment of the method, and further provides a vehicle positioning device. The vehicle positioning apparatus is described in detail below with reference to the accompanying drawings and embodiments.
Fourth embodiment
Referring to fig. 4, the figure is a schematic structural diagram of a vehicle positioning apparatus provided in an embodiment of the present application. It should be noted that the vehicle positioning device provided by the present embodiment is applied to a vehicle, and the vehicle includes an on-vehicle sensor capable of identifying a road characteristic.
As shown in fig. 4, the present embodiment provides a vehicle positioning apparatus 40 including:
a first feature set acquisition module 401, a second feature set acquisition module 402, a third feature set acquisition module 403, a feature comparison and location acquisition module 404, and a location module 405.
The first feature set obtaining module 401 is configured to obtain road features of feature points on a vehicle driving path from a high-precision map to form a first feature set;
the second feature set obtaining module 402 is configured to filter a first type of road features from the first feature set to form a second feature set, where the first type of road features are road features that can be identified by the vehicle-mounted sensor;
the third feature set obtaining module 403 is configured to identify, by using the vehicle-mounted sensor, a road feature of the feature point on the vehicle driving path, and obtain a third feature set;
the feature comparing and position obtaining module 404 is configured to compare the second feature set with the third feature set, obtain an absolute position of the feature point by using the high-precision map if a matching degree between the second feature set and the third feature set exceeds a first preset matching degree threshold, and obtain a relative position between the vehicle and the feature point from a vehicle-mounted positioning system of the vehicle;
the positioning module 405 is configured to obtain an absolute position of the vehicle according to the absolute position of the feature point and the relative position of the vehicle and the feature point.
The vehicle positioning device provided by the embodiment of the application is provided above. The equipment primarily screens the road features in the first feature set based on the identification precision of the vehicle-mounted sensor on the road features to obtain a second feature set formed by the first type of road features, and the road features which cannot be identified by the vehicle-mounted sensor are prevented from influencing the accurate matching of the road features of the feature points through screening. If the matching degree between the second feature set and the third feature set exceeds a first preset matching degree threshold value, the road features of the feature points detected by the vehicle-mounted sensor are similar to the road features of the feature points on the vehicle driving path on the high-precision map, the road features of the feature points are successfully matched, the absolute positions of the feature points and the relative positions of the vehicle and the feature points are obtained based on the feature points which are successfully matched, and the absolute position of the vehicle which is more accurate in positioning can be obtained. The vehicle positioning equipment obtains the absolute position of the characteristic point based on the high-precision map, further obtains the absolute position of the vehicle, and compared with the prior art, the accuracy of vehicle positioning is effectively improved.
Because there may be several feature points that are continuously adjacent and have highly similar or relatively similar road features on the vehicle travel path. These adjacent feature points with highly similar or relatively similar road features may interfere with the road feature matching of the second feature set and the third feature set for the same feature point, thereby affecting the positioning accuracy of the vehicle.
In order to solve the above problem, the vehicle positioning apparatus provided in this embodiment may further include:
and the feature point screening module 406 is configured to screen feature points according to the road features of the feature points, and eliminate invalid feature points.
As an implementation manner, the feature point filtering module 406 may specifically include:
the feature point first screening unit 4061 is configured to determine whether a matching degree between second feature sets respectively corresponding to adjacent feature points on the vehicle travel path exceeds a second preset matching degree threshold, and if so, take a first feature point, through which a vehicle passes, in the adjacent feature points as an effective feature point, and reject other feature points except the effective feature point in the adjacent feature points.
In the implementation mode, adjacent feature points with the matching degree exceeding a second preset matching degree threshold value among the second feature sets are screened, a first feature point, through which a vehicle passes, in the adjacent feature points is reserved, and other feature points except for effective feature points in the adjacent feature points are removed, so that feature points with the height similar to the road feature of the second feature set of the first feature point after the first feature point in the adjacent feature points are filtered, and the road feature mismatching of the second feature set of the feature points and the road feature of the third feature set is avoided. Therefore, the equipment improves the accuracy of the road characteristic matching of the second characteristic set and the third characteristic set of the characteristic points, further avoids the matching error of the characteristic points and further ensures the accuracy of vehicle positioning.
As another implementation manner, the feature point filtering module 406 may specifically include: a road feature confidence degree obtaining unit 4062, a feature point confidence degree obtaining unit 4063, a similar feature point determining unit 4064, and a feature point second screening unit 4065.
The road feature confidence coefficient obtaining unit 4062 is configured to obtain a confidence coefficient of each road feature in the third feature set of the feature points; the confidence is a variable that varies over time;
a feature point confidence coefficient obtaining unit 4063, configured to obtain a confidence coefficient of the feature point according to a confidence coefficient of each road feature in the third feature set of the feature point;
a similar feature point determining unit 4064, configured to, if a matching degree between third feature sets corresponding to adjacent feature points on the vehicle travel path respectively exceeds a third preset matching degree threshold, and a matching degree between confidence degrees corresponding to the adjacent feature points respectively exceeds a preset confidence degree matching threshold, take the adjacent feature points as similar feature points;
the second feature point screening unit 4065 is configured to screen a similar feature point with the highest confidence level and exceeding a threshold value of the confidence level among the similar feature points, and reject other feature points in the adjacent feature points.
In this implementation manner, according to the matching degrees of the third feature set corresponding to the adjacent feature points and the matching degrees of the confidence degrees corresponding to the adjacent feature points, it is determined whether the adjacent feature points are similar feature points, the confidence degrees corresponding to the similar feature points are compared with a confidence threshold value, and only the similar feature points with the highest confidence degree and exceeding the confidence threshold value among the similar feature points are retained. Therefore, screening of similar characteristic points on the vehicle driving path is achieved. And avoiding interference caused by the matching of the road characteristics of the second characteristic set and the third characteristic set of the characteristic points. Therefore, the equipment can also improve the accuracy of the road characteristic matching of the second characteristic set and the third characteristic set of the characteristic points, further avoid the matching error of the characteristic points and further ensure the accuracy of vehicle positioning.
Based on the vehicle positioning device provided by the foregoing embodiment, the present application still further provides an autonomous vehicle. The following describes a specific implementation of the vehicle with reference to the drawings and the embodiments.
Fifth embodiment
Referring to fig. 5, the figure is a schematic structural diagram of an autonomous vehicle according to an embodiment of the present application.
As shown in fig. 5, the present embodiment provides an autonomous vehicle 50 including:
the fourth embodiment provides a vehicle positioning apparatus 40, and an autopilot system 501.
Wherein a vehicle locating device 40 for sending an absolute position of the vehicle to the autonomous driving system;
the automatic driving system 501 is configured to control the vehicle to perform automatic driving according to the absolute position of the vehicle.
The above is the autonomous vehicle 50 provided in the embodiment of the present application. The vehicle positioning device 40 performs preliminary screening on the road features in the first feature set based on the identification precision of the vehicle-mounted sensor on the road features to obtain a second feature set formed by the first type of road features, and avoids the road features which cannot be identified by the vehicle-mounted sensor from influencing the accurate matching of the road features of the feature points through screening. If the matching degree between the second feature set and the third feature set exceeds a first preset matching degree threshold value, the road features of the feature points detected by the vehicle-mounted sensor are similar to the road features of the feature points on the vehicle driving path on the high-precision map, the road features of the feature points are successfully matched, the absolute positions of the feature points and the relative positions of the vehicle and the feature points are obtained based on the feature points which are successfully matched, and the absolute position of the vehicle which is more accurate in positioning can be obtained. The vehicle positioning apparatus 40 obtains the absolute position of the feature point based on the high-precision map, and further obtains the absolute position of the vehicle, and the accuracy of vehicle positioning is effectively improved compared to the prior art.
In the autonomous vehicle 50, the autonomous system 501 controls the vehicle to perform autonomous driving based on the absolute position of the autonomous vehicle 50 obtained by the vehicle positioning device 40. As the absolute position accuracy and precision of the vehicle is improved, the autopilot system 501 is able to derive an accurate position of the vehicle in the lane, which is beneficial to route planning and operational decisions for vehicle autopilot.
It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.
The foregoing is merely a preferred embodiment of the invention and is not intended to limit the invention in any manner. Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make numerous possible variations and modifications to the present teachings, or modify equivalent embodiments to equivalent variations, without departing from the scope of the present teachings, using the methods and techniques disclosed above. Therefore, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention are still within the scope of the protection of the technical solution of the present invention, unless the contents of the technical solution of the present invention are departed.
Claims (4)
1. The vehicle positioning method is characterized by being applied to a vehicle, wherein the vehicle comprises an on-board sensor; the vehicle-mounted sensor is used for identifying road characteristics;
acquiring road characteristics of characteristic points on a vehicle driving path from a high-precision map to form a first characteristic set;
screening first road features from the first feature set to form a second feature set, wherein the first road features are road features which can be identified by the vehicle-mounted sensor;
identifying road characteristics of the characteristic points on the vehicle running path by using the vehicle-mounted sensor to obtain a third characteristic set;
comparing the second feature set with the third feature set, if the matching degree between the second feature set and the third feature set exceeds a first preset matching degree threshold value, obtaining the absolute position of the feature point by using the high-precision map, and obtaining the relative position of the vehicle and the feature point from an on-board positioning system of the vehicle;
obtaining the absolute position of the vehicle according to the absolute position of the characteristic point and the relative position of the vehicle and the characteristic point;
wherein, prior to the comparing the second set of features and the third set of features, the method further comprises:
screening feature points according to the road features of the feature points, and eliminating invalid feature points;
the method comprises the following steps of screening feature points according to road features of the feature points, and eliminating invalid feature points, and specifically comprises the following steps:
judging whether the matching degree between second feature sets respectively corresponding to adjacent feature points on the vehicle running path exceeds a second preset matching degree threshold value, if so, taking a first feature point passed by a vehicle in the adjacent feature points as an effective feature point, and eliminating other feature points except the effective feature point in the adjacent feature points;
or, the screening of the feature points according to the road features of the feature points and the removal of the invalid feature points specifically include:
obtaining the confidence of each road feature in the third feature set of the feature points; the confidence is a variable that varies over time;
obtaining the confidence coefficient of the feature point according to the confidence coefficient of each road feature in the third feature set of the feature point;
if the matching degree between the third feature sets respectively corresponding to the adjacent feature points on the vehicle running path exceeds a third preset matching degree threshold value, and the matching degree between the confidence degrees respectively corresponding to the adjacent feature points exceeds a preset confidence degree matching threshold value, taking the adjacent feature points as similar feature points;
and screening the similar characteristic points with the highest confidence level and exceeding a confidence level threshold value from the similar characteristic points, and rejecting the rest characteristic points from the adjacent characteristic points.
2. The vehicle positioning method according to claim 1, wherein obtaining the confidence level of the feature point according to the confidence level of each road feature in the third feature set of the feature point specifically includes:
obtaining the average confidence of each road characteristic in the third characteristic set of the characteristic points in a preset time;
multiplying the average confidence coefficient of each road characteristic in preset time by the confidence coefficient of each road characteristic obtained from the high-precision map to obtain a first confidence coefficient of each road characteristic of the characteristic point;
and adding the first confidence degrees of the road characteristics of the characteristic points to obtain the confidence degree of the characteristic points.
3. The vehicle positioning device is characterized by being applied to a vehicle, wherein the vehicle comprises an on-board sensor; the vehicle-mounted sensor is used for identifying road characteristics; the vehicle positioning apparatus includes: the system comprises a first feature set acquisition module, a second feature set acquisition module, a third feature set acquisition module, a feature comparison and position acquisition module and a positioning module;
the first feature set acquisition module is used for acquiring road features of feature points on a vehicle driving path from a high-precision map to form a first feature set;
the second feature set acquisition module is used for screening a first type of road features from the first feature set to form a second feature set, wherein the first type of road features are road features which can be identified by the vehicle-mounted sensor;
the third feature set acquisition module is used for identifying the road features of the feature points on the vehicle running path by using the vehicle-mounted sensor to acquire a third feature set;
the feature comparison and position acquisition module is used for comparing the second feature set with the third feature set, if the matching degree between the second feature set and the third feature set exceeds a first preset matching degree threshold value, acquiring the absolute position of the feature point by using the high-precision map, and acquiring the relative position of the vehicle and the feature point from a vehicle-mounted positioning system of the vehicle;
the positioning module is used for obtaining the absolute position of the vehicle according to the absolute position of the characteristic point and the relative position of the vehicle and the characteristic point;
wherein the vehicle positioning apparatus further comprises:
the characteristic point screening module is used for screening characteristic points according to the road characteristics of the characteristic points and eliminating invalid characteristic points;
wherein, the feature point screening module specifically comprises:
the first feature point screening unit is used for judging whether the matching degree between second feature sets respectively corresponding to adjacent feature points on the vehicle running path exceeds a second preset matching degree threshold value, if so, taking a first feature point passed by a vehicle in the adjacent feature points as an effective feature point, and eliminating other feature points except the effective feature point in the adjacent feature points;
or, the feature point screening module specifically includes:
a road feature confidence coefficient obtaining unit, configured to obtain a confidence coefficient of each road feature in a third feature set of the feature points; the confidence is a variable that varies over time;
a feature point confidence coefficient obtaining unit, configured to obtain a confidence coefficient of the feature point according to a confidence coefficient of each road feature in a third feature set of the feature point;
a similar feature point determining unit, configured to, if a matching degree between third feature sets respectively corresponding to adjacent feature points on the vehicle travel path exceeds a third preset matching degree threshold, and a matching degree between confidence degrees respectively corresponding to the adjacent feature points exceeds a preset confidence degree matching threshold, take the adjacent feature points as similar feature points;
and the second feature point screening unit is used for screening the similar feature points with the highest confidence level and exceeding a confidence level threshold value from the similar feature points and rejecting other feature points in the adjacent feature points.
4. An autonomous vehicle comprising the vehicle localization apparatus of claim 3, further comprising: an automatic driving system;
the vehicle positioning device is used for sending the absolute position of the vehicle to the automatic driving system;
and the automatic driving system is used for controlling the vehicle to automatically drive 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 CN109115231A (en) | 2019-01-01 |
| CN109115231B true 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) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| 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 |
| CN112307810B (en) * | 2019-07-26 | 2023-08-04 | 北京魔门塔科技有限公司 | Visual positioning effect self-checking method and vehicle-mounted terminal |
| 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 |
| 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 |
| CN114202574A (en) * | 2020-08-29 | 2022-03-18 | 华为技术有限公司 | Positioning reliability detection method and related equipment |
| 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 |
| 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 |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006208223A (en) * | 2005-01-28 | 2006-08-10 | Aisin Aw Co Ltd | Vehicle position recognition device and vehicle position recognition 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 |
| JP5057184B2 (en) * | 2010-03-31 | 2012-10-24 | アイシン・エィ・ダブリュ株式会社 | Image processing system and vehicle control system |
| US9719801B1 (en) * | 2013-07-23 | 2017-08-01 | Waymo Llc | Methods and systems for calibrating sensors using road map data |
| CN103954275B (en) * | 2014-04-01 | 2017-02-08 | 西安交通大学 | Lane line detection and GIS map information development-based vision navigation method |
| 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 |
| CN105783936B (en) * | 2016-03-08 | 2019-09-24 | 武汉中海庭数据技术有限公司 | For the road markings drawing and vehicle positioning method and system in automatic Pilot |
| 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 |
| 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 |
| CN107328411B (en) * | 2017-06-30 | 2020-07-28 | 百度在线网络技术（北京）有限公司 | Vehicle-mounted positioning system and automatic driving vehicle |
| 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 |
| CN108303721B (en) * | 2018-02-12 | 2020-04-03 | 北京经纬恒润科技有限公司 | Vehicle positioning method and system |
| 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
Also Published As
| Publication number | Publication date |
|---|---|
| CN109115231A (en) | 2019-01-01 |
| WO2020042642A1 (en) | 2020-03-05 |
| WO2020042642A8 (en) | 2020-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109115231B (en) | Vehicle positioning method and device and automatic driving vehicle | |
| EP2012088B1 (en) | Road information generating apparatus, road information generating method and road information generating program | |
| CN111380539B (en) | Vehicle positioning and navigation method and device and related system | |
| US8085984B2 (en) | Image recognizing apparatus and method, and position determining apparatus, vehicle controlling apparatus and navigation apparatus using the image recognizing apparatus or method | |
| EP2244065B1 (en) | Driving assistance apparatus, driving assistance method, and driving assistance program | |
| CN103256937B (en) | The method of route matching and device | |
| CN108445503A (en) | The unmanned path planning algorithm merged with high-precision map based on laser radar | |
| CN104464375B (en) | It is a kind of to recognize the method that vehicle high-speed is turned | |
| CN105270410A (en) | Accurate curvature estimation algorithm for path planning of autonomous driving vehicle | |
| CN109752741A (en) | Vehicle Positioning Equipment | |
| CN102208013A (en) | Scene matching reference data generation system and position measurement system | |
| CN106918342A (en) | Automatic driving vehicle driving path localization method and alignment system | |
| US20090018767A1 (en) | Method for determining the geometry of a route section | |
| US11703347B2 (en) | Method for producing an autonomous navigation map for a vehicle | |
| CN107328423B (en) | Curve identification method and system based on map data | |
| JP4953012B2 (en) | Image recognition device, program for image recognition device, navigation device using the same, and program for navigation device | |
| US20190266419A1 (en) | Method, Device And Computer-Readable Storage Medium With Instructions For Determining The Lateral Position Of A Vehicle Relative To The Lanes Of A Road | |
| CN111051817A (en) | Method for determining the position of a motor vehicle in the environment, control device for a motor vehicle and computing device for operating on a data network | |
| CN104395944A (en) | Carriageway recognition | |
| US20230003531A1 (en) | Matching coordinate systems of multiple maps, based on trajectories | |
| CN104422449A (en) | Vehicle navigation method and vehicle navigation device | |
| CN110647877B (en) | Three-dimensional traffic facility positioning and deviation rectifying method and device based on neural network | |
| CN111832365A (en) | Lane mark determination method and device | |
| US20230236020A1 (en) | System and Method for Map Matching GNSS Positions of a Vehicle | |
| CN110967023A (en) | Automobile positioning method and automobile positioning device |
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 |