CN117782114A - Vehicle positioning correction method, device, computer equipment and storage medium - Google Patents
Vehicle positioning correction method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117782114A CN117782114A CN202410221917.8A CN202410221917A CN117782114A CN 117782114 A CN117782114 A CN 117782114A CN 202410221917 A CN202410221917 A CN 202410221917A CN 117782114 A CN117782114 A CN 117782114A
- Authority
- CN
- China
- Prior art keywords
- positioning information
- correction
- vehicle
- information
- point set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012937 correction Methods 0.000 title claims abstract description 197
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000000007 visual effect Effects 0.000 claims abstract description 51
- 239000011159 matrix material Substances 0.000 claims description 82
- 230000006870 function Effects 0.000 claims description 31
- 238000006243 chemical reaction Methods 0.000 claims description 27
- 238000013519 translation Methods 0.000 claims description 23
- 238000004590 computer program Methods 0.000 claims description 14
- 238000005070 sampling Methods 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 8
- 230000009466 transformation Effects 0.000 description 15
- 238000004422 calculation algorithm Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000003111 delayed effect Effects 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000036962 time dependent Effects 0.000 description 1
Landscapes
- Navigation (AREA)
Abstract
The application provides a vehicle positioning correction method, a vehicle positioning correction device, computer equipment and a storage medium, wherein initial positioning information, high-precision map information and visual lane lines of a vehicle are acquired; determining a map lane line based on the initial positioning information and the high-precision map information; ICP correction is carried out on the initial positioning information based on the visual lane lines and the map lane lines, so that first correction positioning information is obtained; performing time correction on the initial positioning information to obtain second correction positioning information; and determining final positioning information of the vehicle according to the first correction positioning information and the second correction positioning information. The vehicle positioning correction method can accurately correct the positioning information of the vehicle, is more suitable for positioning the real actual coordinates of the vehicle, and can improve the use experience of the user.
Description
Technical Field
The present application relates to the field of autopilot, and in particular, to a vehicle positioning correction method, apparatus, computer device, and storage medium.
Background
In the automatic driving field, when an automobile uses a high-precision Map (HD Map) to navigate an automatic driving vehicle, longitude and latitude coordinates of high-precision Map data need to be converted into coordinates under a vehicle coordinate system, and dynamic vehicle positioning information is used at this time.
However, due to certain errors in the accuracy of positioning information of the GPS of the current vehicle, particularly when the posture of the vehicle body is changed more severely, the positioning error of the vehicle is most serious, the accuracy of vehicle navigation is low due to the large positioning error, and the user experience is poor.
Disclosure of Invention
Based on this, it is necessary to provide a vehicle positioning correction method, apparatus, computer device, and storage medium in view of the above-described technical problems.
In a first aspect, the present application provides a vehicle positioning correction method, the method comprising:
acquiring initial positioning information, high-precision map information and visual lane lines of a vehicle;
determining a map lane line based on the initial positioning information and the high-precision map information;
ICP correction is carried out on the initial positioning information based on the visual lane lines and the map lane lines, so that first correction positioning information is obtained;
performing time correction on the initial positioning information to obtain second correction positioning information;
And determining final positioning information of the vehicle according to the first correction positioning information and the second correction positioning information.
In one embodiment, the performing ICP correction on the initial positioning information based on the visual lane line and the map lane line, and obtaining the first corrected positioning information includes:
sampling each lane line in the visual lane lines to obtain a reference point set;
projecting the reference point set to the map lane line to obtain a projection point set;
determining a conversion matrix according to the reference point set and the projection point set;
and correcting the initial positioning information according to the conversion matrix to obtain first corrected positioning information.
In one embodiment, the determining the transformation matrix according to the reference point set and the projection point set includes:
determining the distance information between each reference point in the reference point set and each projection point in the corresponding projection point set;
establishing a matching relation between the reference point set and the projection point set according to the distance information;
and determining a conversion matrix according to the reference point set and the projection point set after the matching relation is established.
In one embodiment, the determining the transformation matrix according to the reference point set and the projection point set includes:
Acquiring a preset objective function, wherein the objective function is used for determining the rotation angle between the point sets;
substituting the reference point set and the projection point set into an objective function, and determining a rotation angle between the reference point set and the projection point set;
determining a rotation matrix and a translation matrix according to the rotation angle;
and taking the rotation matrix and the translation matrix as conversion matrices.
In one embodiment, the performing time correction on the initial positioning information to obtain second corrected positioning information includes:
acquiring initial positioning time, current time, vehicle speed and vehicle angular speed; the initial positioning time is the time for acquiring initial positioning information;
determining a time difference according to the initial positioning time and the current time;
determining a distance difference and a head direction difference according to the time difference and the vehicle speed of the vehicle;
and carrying out time correction on the initial positioning information according to the distance difference to obtain second correction positioning information.
In one embodiment, the determining the final positioning information of the vehicle according to the first corrected positioning information and the second corrected positioning information includes:
acquiring the inertial navigation data of a vehicle;
Determining the confidence level of the first correction positioning information according to the inertial navigation data;
if the confidence coefficient is larger than a preset threshold value, determining final positioning information of the vehicle according to the first correction positioning information and the second correction positioning information.
In one embodiment, the determining the final positioning information of the vehicle according to the first corrected positioning information and the second corrected positioning information includes:
generating fusion correction information based on the distance difference in the first correction positioning information, the conversion matrix in the second correction positioning information and the initial positioning information;
and carrying out error state Kalman filtering on the fusion correction information to obtain final positioning information.
In a second aspect, the present application also provides a vehicle positioning correction device, the device including:
the acquisition module is used for acquiring initial positioning information, high-precision map information and visual lane lines of the vehicle;
the determining module is used for determining a map lane line based on the initial positioning information and the high-precision map information;
the first correction module is used for carrying out ICP correction on the initial positioning information based on the visual lane lines and the map lane lines to obtain first correction positioning information;
The second correction module is used for carrying out time correction on the initial positioning information to obtain second correction positioning information;
and the positioning determining module is used for determining the final positioning information of the vehicle according to the first correction positioning information and the second correction positioning information.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes a vehicle positioning correction method when executing the computer program:
acquiring initial positioning information, high-precision map information and visual lane lines of a vehicle;
determining a map lane line based on the initial positioning information and the high-precision map information;
ICP correction is carried out on the initial positioning information based on the visual lane lines and the map lane lines, so that first correction positioning information is obtained;
performing time correction on the initial positioning information to obtain second correction positioning information;
and determining final positioning information of the vehicle according to the first correction positioning information and the second correction positioning information.
In a fourth aspect, the present application also provides a computer-readable storage medium. The computer readable storage medium having stored thereon a computer program which when executed by a processor implements a vehicle positioning correction method:
Acquiring initial positioning information, high-precision map information and visual lane lines of a vehicle;
determining a map lane line based on the initial positioning information and the high-precision map information;
ICP correction is carried out on the initial positioning information based on the visual lane lines and the map lane lines, so that first correction positioning information is obtained;
performing time correction on the initial positioning information to obtain second correction positioning information;
and determining final positioning information of the vehicle according to the first correction positioning information and the second correction positioning information.
The vehicle positioning correction method, the vehicle positioning correction device, the computer equipment and the storage medium are used for acquiring initial positioning information, high-precision map information and visual lane lines of a vehicle; determining a map lane line based on the initial positioning information and the high-precision map information; ICP correction is carried out on the initial positioning information based on the visual lane lines and the map lane lines, so that first correction positioning information is obtained; performing time correction on the initial positioning information to obtain second correction positioning information; and determining final positioning information of the vehicle according to the first correction positioning information and the second correction positioning information. The vehicle positioning correction method can accurately correct the positioning information of the vehicle, is more suitable for positioning the real actual coordinates of the vehicle, and can improve the use experience of the user.
Drawings
In order to more clearly illustrate the technical solutions of embodiments or conventional techniques of the present application, the drawings required for the descriptions of the embodiments or conventional techniques will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a diagram of an application environment for a vehicle positioning correction method in one embodiment;
FIG. 2 is a flow chart of a vehicle positioning correction method according to an embodiment of the invention;
FIG. 3 is a schematic diagram of a map border line and a visual lane line before and after correction according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a map and visual lane lines before correction in accordance with one embodiment of the present invention;
FIG. 5 is a schematic diagram of matching point sampling according to an embodiment of the present invention;
FIG. 6 is a schematic diagram showing a specific implementation of a vehicle positioning and lane line correction method according to an embodiment of the present invention;
FIG. 7 is a block diagram showing the construction of a vehicle positioning correction device in one embodiment of the invention;
fig. 8 is an internal structural view of a computer device in one embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.
Real-time reliable pose is a basis for realizing autonomous running of an autonomous vehicle, and is one of hot spots for research in the field of automatic driving.
There are currently various approaches to the problem of autonomous vehicle positioning, whether of the type of sensors used or of the strategy of state estimation. For example, a positioning system GPS which can be used independently is adopted, but is easily influenced by factors such as satellite signal shielding, signal attenuation, multipath transmission and the like, and the provided pose information has poor continuity and sometimes relatively low precision. The inertial navigation system, the odometer and other positioning systems can generally obtain higher local relative positioning precision, but the absolute pose precision is difficult to guarantee due to the problem of long-time error integral accumulation.
In order to improve the accuracy, continuity and robustness of the output pose of the navigation positioning system, the method is realized by adopting a method of fusing multiple sensing information such as a GPS and Inertial Measurement Unit (IMU), an odometer, a speed sensor, a direction sensor and the like. Whichever positioning method is adopted, the sensor has measurement errors, thereby affecting the positioning accuracy of the system, and therefore, various measures are required to be taken to correct the positioning errors. The map matching algorithm is a typical error correction strategy for the structured road environment.
In Geographic Information Systems (GIS), map networks contain absolute position information, and the use of such data to calibrate drift of position estimates is one of the very effective solutions. The most direct mode of realizing position calibration by using map network information is map matching, which is a positioning correction method based on a software technology, and the basic idea is to correlate the running track of a vehicle with road network information in a geographic information system so as to determine the pose of the vehicle in the map network. The application of map matching technology needs to satisfy two preconditions: (1) the vehicle is always running in the road network; (2) The digital map used for matching has a sufficiently high accuracy. Therefore, the map matching algorithm is mainly used for environments with relatively clear road network data, especially structured road environments. At present, a large number of algorithms for realizing map matching range from simple search technology to complex extended Kalman filtering, fuzzy logic, evidence theory and the like.
Taken together, the matching algorithms can be divided into 4 classes: geometric, topological, probabilistic, and other matching methods. Common geometric matching algorithms include point-to-point matching, point-to-line matching, and line-to-line matching, which make use of geometric features of a road network, generally taking into account only shape information of connections, and not the connection of each other. The topology analysis method utilizes the geometric information and the topological relation of the map to realize the map matching algorithm. The probabilistic algorithm requires defining an elliptical or square confidence region around the anchor point provided by the navigation sensor and if multiple road segments are contained within the confidence region, then the candidate road segments are evaluated using criteria such as heading, connectivity, speed, and distance.
In addition to the 3 algorithms described above, many scholars in recent years have implemented map matching using algorithms such as kalman filtering, extended kalman filtering, D-S evidence theory, state space model, particle filtering, interactive multi-model, fuzzy logic model, and bayesian reasoning.
The embodiment of the application provides a vehicle positioning correction method, which can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be located on a cloud or other network server. The user makes a current behavior on the terminal 102, the terminal 102 transmits current behavior data to the server 104, and the server 104 acquires initial positioning information, high-precision map information and visual lane lines of the vehicle; determining a map lane line based on the initial positioning information and the high-precision map information; ICP correction is carried out on the initial positioning information based on the visual lane lines and the map lane lines, so that first correction positioning information is obtained; performing time correction on the initial positioning information to obtain second correction positioning information; and determining final positioning information of the vehicle according to the first correction positioning information and the second correction positioning information. The server 104 may be implemented as a stand-alone server or as a server cluster of multiple servers.
In one embodiment, as shown in fig. 2, a vehicle positioning correction method is provided, where the method is applied to a terminal to illustrate the method, it is understood that the method may also be applied to a server, and may also be applied to a system including the terminal and the server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the steps of:
step S201, acquiring initial positioning information, high-precision map information and visual lane lines of a vehicle.
Specifically, the initial positioning information refers to initial positioning data with errors, which is acquired by an uncorrected vehicle positioning system, where the initial positioning information includes, for example, longitude and latitude of a vehicle position, a province area where the vehicle position is located, a street name, a positioning time when the vehicle position is acquired, a vehicle speed, and the like, which are not described in detail herein.
The high-precision map information refers to map road network information in a Geographic Information System (GIS).
The visual lane line is a lane line which is acquired by the vehicle acquisition system and takes the vehicle lens as a visual center, namely a visual lane line perceived by a front-mounted camera of the vehicle.
Step S202, determining a map lane line based on the initial positioning information and the high-precision map information.
Specifically, the map lane line refers to a lane line on a map determined based on initial positioning information of the vehicle in the high-precision map information.
And step S203, performing ICP correction on the initial positioning information based on the visual lane lines and the map lane lines to obtain first corrected positioning information.
Specifically, the ICP algorithm is essentially an optimal registration method based on the least squares method. And repeatedly selecting corresponding relation point pairs, and calculating the optimal rigid body transformation [ R, T ] until the convergence accuracy requirement of correct registration is met. The purpose is to find a rotation matrix R and a translation matrix T between the point cloud data to be registered and the reference cloud data, so that the two points meet the optimal matching under a certain measurement criterion. And performing ICP correction on the initial positioning information, namely correcting the initial positioning information according to the rotation matrix R and the translation matrix T to obtain first corrected positioning information.
Step S204, time correction is carried out on the initial positioning information to obtain second correction positioning information.
In particular, the time correction is also time-dependent, wherein the time compensation is to compensate for a delayed positioning deviation according to the vehicle motion state if the time stamp of the received initial positioning information is delayed. Namely, the time correction is carried out on the initial positioning information through the current time and the time for acquiring the initial positioning information, so as to obtain second corrected positioning information.
Step S205, determining final positioning information of the vehicle according to the first corrected positioning information and the second corrected positioning information.
Specifically, the first correction positioning information and the second correction positioning information are comprehensively considered, and finally accurate final positioning information is obtained.
The vehicle positioning correction method, the vehicle positioning correction device, the computer equipment and the storage medium are used for acquiring initial positioning information, high-precision map information and visual lane lines of a vehicle; determining a map lane line based on the initial positioning information and the high-precision map information; ICP correction is carried out on the initial positioning information based on the visual lane lines and the map lane lines, so that first correction positioning information is obtained; performing time correction on the initial positioning information to obtain second correction positioning information; and determining final positioning information of the vehicle according to the first correction positioning information and the second correction positioning information. The vehicle positioning correction method can accurately correct the positioning information of the vehicle, is more suitable for positioning the real actual coordinates of the vehicle, and can improve the use experience of the user.
In one embodiment, the performing ICP correction on the initial positioning information based on the visual lane line and the map lane line, and obtaining the first corrected positioning information includes:
Sampling each lane line in the visual lane lines to obtain a reference point set;
projecting the reference point set to the map lane line to obtain a projection point set;
determining a conversion matrix according to the reference point set and the projection point set;
and correcting the initial positioning information according to the conversion matrix to obtain first corrected positioning information.
Specifically, when each of the visual lane lines is sampled, the sampling point is not too far away from the vehicle body, so that the effective length can be limited for sampling during actual sampling, accurate sampling is realized, and a reference point set is acquired.
Specifically, the reference point set is projected to the map lane line, the projection point set is obtained by using the reference point set on the visual lane line to find the projection points at the same position on the map lane line, the reference point set and the projection point set are in one-to-one matching correspondence, and a corresponding matching relationship exists, and based on the reference point set, the projection point set and the corresponding matching relationship, the conversion matrix can be finally determined. Wherein the transformation matrix [ R, T ] comprises a rotation matrix R and a translation matrix T.
Specifically, the initial positioning information is corrected based on the rotation torque matrix R and the translation matrix T in the conversion matrix [ R, T ], and then the first corrected positioning information is accurately obtained.
For example, in practical application, 4 visual lane lines near the lane line of the vehicle, such as a left lane line, a right lane line, and a left lane line, may be traversed, and sampling is performed within the effective length of the visual lane lines, so as to obtain 4 groups of reference point sets. The effective length refers to a lane length that affects the running of the vehicle, and is not too long, and can be determined according to actual situations, which is not described in detail herein. The sampling interval is generally 5-10 meters, and the closer the distance from the vehicle is, the higher the confidence of the lane line is, and the more dense the sampling is. The matching weight of the left lane line and the right lane line is greater than that of the left lane line and the right lane line.
And then, using the points of the reference point set to find corresponding projection points on each map lane line as the projection point set. When finding the corresponding projection point, it is necessary to consider that the distance between the reference point and the projection point is smaller than the threshold value, and the projection point can be listed in the candidate projection point set. After each map lane line is traversed, the average distance between each set of reference points and each set of projection points can be used to determine the matching relationship, and 4 sets of reference points and each set of projection points can be placed in the final set of matching points.
In the above embodiment, the projection point set is obtained based on the reference point set, and then the matching relationship is determined based on the average distance between the reference point set and the projection point set, so as to accurately determine the conversion matrix.
In one embodiment, the determining the transformation matrix according to the reference point set and the projection point set includes:
determining the distance information between each reference point in the reference point set and each projection point in the corresponding projection point set;
establishing a matching relation between the reference point set and the projection point set according to the distance information;
and determining a conversion matrix according to the reference point set and the projection point set after the matching relation is established.
Specifically, determining the distance information of each reference point in the reference point set and each projection point in the corresponding projection point set refers to determining an average distance between the reference point set and the projection point set; since it is not possible to determine which point set is the projection point set that truly corresponds to the reference point from among the plurality of point sets on the acquired map when the projection point set is actually determined based on the reference point set, it is necessary to introduce an average distance for calculation.
And calculating the average distance by using the plurality of point sets and the reference point set on the acquired map, wherein the point set with the minimum average distance, namely the projection point set, is adopted.
It can be understood that, the reference point set is used as a fixed point set, a unique projection point set is accurately determined according to the determined matching relationship, and the conversion matrix can be accurately determined by using the related ICP function algorithm.
In the embodiment, the average distance between the reference point set and the projection point set is used for determining the matching relation, so that the accuracy of matching calculation is improved.
In one embodiment, the determining the transformation matrix according to the reference point set and the projection point set includes:
acquiring a preset objective function, wherein the objective function is used for determining the rotation angle between the point sets;
substituting the reference point set and the projection point set into an objective function, and determining a rotation angle between the reference point set and the projection point set;
determining a rotation matrix and a translation matrix according to the rotation angle;
and taking the rotation matrix and the translation matrix as conversion matrices.
Specifically, substituting the reference point set and the projection point set into an objective function, determining a rotation angle between the reference point set and the projection point set, and determining a rotation matrix and a translation matrix according to the rotation angle; the rotation matrix and the translation matrix are used as a conversion matrix, and the calculation process is as follows:
First, an initial first function is determined.
Assuming that a is a reference point set and B is a projection point set, that is, a is a point set perceived by the vehicle device, that is, the reference point set, and B is a point set on the map, that is, the projection point set, the initial first function is as follows:
wherein D (R, T), i.e. the initial unmodified first function, wherein A i Representing the coordinates of each point in the set of points A, B i The coordinates of each point in the set of points B are represented, R is the rotation matrix initially calculated, and T is the translation matrix initially calculated.
Step two, simplifying the first function to obtain an objective function, wherein the specific calculation process is as follows:
two variables exist in the first function, and each point A in the A point set can be calculated through normalization calculation i To their center A mean Deviation a of (2) i And each point B in the point B set i To their center B mean Deviation b of (2) i 。
Wherein D (R, T), i.e. the initial unmodified first function, wherein A i Representing the coordinates of each point in the set of points A, B i Representing the coordinates of each point in the B point set, R is the rotation matrix of the initial calculation, T is the translation matrix of the initial calculation, a i Is each point A in the point A set i To the collection center A mean Coordinate deviation of b i Is each point B in the B point set i To collection center B mean Is a coordinate deviation of (a).
Wherein, after eliminating the influence of the translation matrix, the first function is simplified as:
wherein a is i Is each point A in the point A set i To the collection center A mean Coordinate deviation of b i Is each point B in the B point set i To collection center B mean R is the rotation matrix initially calculated.
Continuing to decompose the above functions can result in:
the D (R, T) function is maximized to a simplified objective function G:
and thirdly, solving a transformation matrix.
Taking a rotation matrix R and a translation matrix T,the angle delta x and delta y are distances to be translated when the point sets are overlapped.
Substituting the above parameters into the objective function G:
wherein a is X i Refer to each point A in the point A set i To the collection center A mean Coordinate deviation on X-axis of (a), a Y i Refer to each point A in the point A set i To the collection center A mean Coordinate deviation on the Y-axis of (2); b X i Refer to each point B in the B point set i To collection center B mean Coordinate deviation on X-axis of (b) Y i Refer to each point B in the B point set i To collection center B mean Coordinate deviation on the Y-axis of (c).
The objective function G is performedThe extremum is calculated, and the derivative is 0, and then:
Only the following are required:
the rotation angle can be determinedFind +.>The rotation matrix R can be obtained, and then the translation matrix T is obtained according to the rotation matrix R.
Wherein A is X mean Refers to the point ACentralizing the average position of all points in X direction, A y mean Mean position of all points in the point A set in the Y direction, R is a rotation matrix, and T is a translation matrix.
And then iterating continuously, and finally outputting to obtain a final transformation matrix.
In the above embodiment, the objective function calculation in the ICP algorithm is used to iterate continuously, so as to more accurately determine the result of the transformation matrix.
In one embodiment, the performing time correction on the initial positioning information to obtain second corrected positioning information includes:
acquiring initial positioning time, current time, vehicle speed and vehicle angular speed; the initial positioning time is the time for acquiring initial positioning information;
determining a time difference according to the initial positioning time and the current time;
determining a distance difference and a head direction difference according to the time difference and the vehicle speed of the vehicle;
and carrying out time correction on the initial positioning information according to the distance difference to obtain second correction positioning information.
In particular, in general, when the running time of the automobile is long, there is a case where information recorded by the vehicle system itself is different from the actual time, and thus time compensation calibration is required.
It can be understood that the positioning information is longitude, latitude and direction of the vehicle, the time compensation is to compensate the distance difference generated by the lag time, the distance difference can be determined by multiplying the current positioning travelling speed of the vehicle by the time difference, and then the time correction is carried out on the initial positioning information according to the distance difference, so as to accurately obtain the second correction positioning information.
In the above embodiment, accurate time compensation is performed on the positioning information based on the time difference, the own vehicle speed and the own vehicle angular velocity.
In one embodiment, determining final positioning information of the vehicle based on the first corrected positioning information and the second corrected positioning information includes:
acquiring inertial navigation data of a vehicle;
determining the confidence level of the first correction positioning information according to the inertial navigation data;
if the confidence coefficient is larger than a preset threshold value, determining final positioning information of the vehicle according to the first correction positioning information and the second correction positioning information.
Specifically, the inertial navigation data refers to data in an IMU (inertial measurement unit) for inertial navigation of the vehicle.
It can be appreciated that the specific calculation process of the confidence coefficient of the first correction positioning information is as follows:
Distance Confidence of the first corrected location information is defined by the following function dis And point Confidence of first corrected positioning information num The Confidence level Confidence of the final output is the product of the two.
Where distance (dis) refers to the average distance of two sets of matching points after transformation, and number of points (num) refers to the number of matching points per set.
In the above embodiment, the confidence coefficient of the first corrected positioning information is accurately calculated by using the inertial navigation data of the vehicle and the first corrected positioning information, and when the confidence coefficient is greater than the preset threshold value, the first corrected positioning information and the second corrected positioning information can be synthesized to determine the final positioning information of the vehicle, and when the confidence coefficient is not greater than the preset threshold value, the corresponding first corrected positioning information is discarded, so that the accuracy of the final positioning information can be improved.
In one embodiment, the determining the final positioning information of the vehicle according to the first corrected positioning information and the second corrected positioning information includes:
generating fusion correction information based on the distance difference in the first correction positioning information, the conversion matrix in the second correction positioning information and the initial positioning information;
And carrying out error state Kalman filtering on the fusion correction information to obtain final positioning information.
In particular, in most IMU systems in existence, an error state kalman filter (Error state Kalman filter, ESKF) is often used instead of the original state kalman filter. And most filter-based LIO or VIO implementations use ESKF as a state estimation method. The advantages of ESKF over traditional KF can be summarized as follows:
1. in the rotating process, the state variables of the ESKF may be expressed with minimized parameters, i.e., using three-dimensional variables to express the increment of rotation. Whereas conventional KF requires the use of quaternion (4-dimensional) or higher-dimensional expressions (rotation matrix, 9-dimensional), or expression with singularities (euler angles).
Eskf is always near the origin, far from the outlier, and also does not create problems that are too far from the working point, resulting in insufficient linearization approximation.
The state quantity of the ESKF is small, and the second-order variable is relatively negligible. While most jacobian matrices become very simple in small quantities and can even be replaced by unit matrices.
In the above embodiment, accurate determination of final positioning information is achieved by means of error state kalman filtering.
In one embodiment, map reference lines in the vehicle coordinate system may also be recalculated based on the final positioning information after the final positioning information is determined.
Referring to fig. 3, fig. 3 is a schematic diagram showing the comparison of map boundary lines and visual lane lines before and after correction.
Illustratively, the following formula is used to correct the vehicle location and recalculate the map reference line in the vehicle coordinate system.
Wherein R is a rotation matrix.
Where H is an initial direction before the vehicle is not corrected, hcor is a direction after the vehicle is corrected, and R is a rotation matrix.
Wherein T is a translation matrix, T comprises [ T (1), T (2) ], and Hcor is the direction of the vehicle after correction.
Wherein the direction of the vehicle after correction is Angle, and the longitude and latitude of the vehicle after correctionAnd。
in one embodiment, after the initial positioning information is obtained, the data may be further processed in advance, which is specifically as follows:
initial positioning information (longitude of vehicle LOC) lon Vehicle latitude LOC lat The host vehicle is directed to Heading), a map reference line (reference point longitude lon, reference point latitude lat) is calculated by the following formula, and a coordinate point (x, y) in the vehicle coordinate system.
Wherein, the meter function in units of latitude, per_lat:111132.954-559.822 Xcos (2 Xphi) +1.175 Xcos (4 Xphi)/where phi is geodetic latitude; a meter function in units of longitude, per_lon: pi×a×cos (phi)/(180×sqrt (1-e train 2×sin train 2 (phi))), e is the eccentricity of the ellipsoid, and a is the equatorial radius.
Referring to fig. 4, fig. 4 is a schematic diagram of a map line and a visual lane line before correction, wherein the map boundary line is a solid dot in the map, and the visual lane line is a broken line in the map, and a significant angle difference exists, and the angle difference is caused by a course angle error of positioning data.
In one embodiment, referring to fig. 5, fig. 5 is a schematic diagram of matching point sampling.
The reference points are sampled on the visual lane lines, only two lane lines are generally considered, and then the projection point of each reference point is found on the map boundary line closest to the two lane lines and is taken as the projection point. And two groups of matching points corresponding to each other one by one are obtained, namely, the hollow circles and asterisks in the figure. And finally, obtaining relative pose relations R and T between two groups of matching points through an ICP algorithm, wherein the translation matrix obtained by the method mainly uses transverse errors to correct positioning because the method is to sample in the longitudinal direction. The angle to be corrected in this example is 0.01328 radians, the lateral error to be corrected is 0.011 meters, and the confidence is 0.96846.
In one embodiment, the vehicle may occasionally generate lane line misalignment and no engagement when the vehicle collects the visual lane line, so that the collected lane line data may also need to be preprocessed.
By way of example, first, by traversing each lane line, finding a point of a lateral position jump, and recording the positions of the lane lines and the jump points; wherein, the transverse position jump points refer to the transverse deviation of two adjacent points exceeding 1.5 meters.
And then searching whether the next section of the other lane lines is closer to the next section of the other lane lines at the jump point, namely, the transverse deviation of two adjacent points is smaller than 1 meter. If so, the next lane line which is closer to the lane line is assigned to the lane line to be spliced. After the operation is finished on all the lane lines, the broken lane lines can be reconnected.
In one embodiment, this method is referred to as iterating the closest point because in a conventional ICP matching task, the target point cloud and the source point cloud are unordered, each time a matching relationship needs to be obtained by traversing the find closest point. However, the visual reference point set and the map source point set are in one-to-one correspondence, and the ith point in the source point set can be considered to correspond to the ith point in the target point set, so that each point does not need to find the closest point. And once the rotation and translation relationship is found, the final result is already obtained in the first iteration. The above embodiment can greatly improve the operation speed.
In one embodiment, referring to FIG. 6, FIG. 6 is a schematic diagram of a specific implementation of a vehicle positioning and lane line correction method.
Step 1, pre-calculating a map boundary line based on positioning information and map information;
the map boundary line is a lane line determined on the map information based on the positioning information.
And 2, inputting the pre-calculated map boundary line and the vision lane line into an ICP correction module in the positioning correction module, and obtaining first correction positioning information, a corresponding transformation matrix and a confidence coefficient.
And 3, judging whether the first correction positioning information is valid.
And when the confidence coefficient meets the requirement of a preset threshold value, the confidence coefficient is determined to be valid.
And step 4, performing time compensation on the positioning information obtained in the step 1 to obtain second correction positioning information.
And step 5, acquiring fused positioning information based on the first corrected positioning information and the second corrected positioning information, and inputting the fused positioning information and the inertial navigation data into an error state Kalman filter to acquire corrected positioning data.
And step 6, calculating a map reference line based on the corrected positioning data and the map information.
It should be understood that, although the steps in the flowcharts related to the embodiments described above are sequentially shown as indicated by arrows, these steps are not necessarily sequentially performed in the order indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in the flowcharts described in the above embodiments may include a plurality of steps or a plurality of stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of the steps or stages is not necessarily performed sequentially, but may be performed alternately or alternately with at least some of the other steps or stages.
Based on the same inventive concept, the embodiment of the application also provides a vehicle positioning correction device for realizing the above-mentioned related vehicle positioning correction device. The implementation of the solution provided by the device is similar to that described in the above method, so the specific limitation of one or more embodiments of the vehicle positioning correction device provided below may refer to the limitation of the vehicle positioning correction method hereinabove, and will not be repeated herein.
In one embodiment, as shown in fig. 7, there is provided a vehicle positioning correction apparatus including: an acquisition module 710, a determination module 720, a first correction module 730, a second correction module 740, and a positioning determination module 750, wherein:
the acquiring module 710 is configured to acquire initial positioning information, high-precision map information, and visual lane lines of a vehicle.
And a determining module 720, configured to determine a map lane line based on the initial positioning information and the high-precision map information.
The first correction module 730 is configured to perform ICP correction on the initial positioning information based on the visual lane line and the map lane line, so as to obtain first corrected positioning information.
The first correction module 730, configured to perform ICP correction on the initial positioning information based on the visual lane line and the map lane line, where obtaining the first corrected positioning information includes:
Sampling each lane line in the visual lane lines to obtain a reference point set;
projecting the reference point set to the map lane line to obtain a projection point set;
determining a conversion matrix according to the reference point set and the projection point set;
and correcting the initial positioning information according to the conversion matrix to obtain first corrected positioning information.
The first correction module 730 is further configured to determine a transformation matrix according to the reference point set and the projection point set, where the determining a transformation matrix includes:
determining the distance information between each reference point in the reference point set and each projection point in the corresponding projection point set;
establishing a matching relation between the reference point set and the projection point set according to the distance information;
and determining a conversion matrix according to the reference point set and the projection point set after the matching relation is established.
The first correction module 730 is further configured to determine a transformation matrix according to the reference point set and the projection point set, where the determining a transformation matrix includes: acquiring a preset objective function, wherein the objective function is used for determining the rotation angle between the point sets; substituting the reference point set and the projection point set into an objective function, and determining a rotation angle between the reference point set and the projection point set; determining a rotation matrix and a translation matrix according to the rotation angle; and taking the rotation matrix and the translation matrix as conversion matrices.
The first correction module 730 is further configured to perform time correction on the initial positioning information, and obtain second corrected positioning information includes:
acquiring initial positioning time, current time, vehicle speed and vehicle angular speed; the initial positioning time is the time for acquiring initial positioning information;
determining a time difference according to the initial positioning time and the current time;
determining a distance difference and a head direction difference according to the time difference and the vehicle speed of the vehicle;
and carrying out time correction on the initial positioning information according to the distance difference to obtain second correction positioning information.
The second correction module 740 performs time correction on the initial positioning information to obtain second corrected positioning information.
The positioning determining module 750 is configured to determine final positioning information of the vehicle according to the first corrected positioning information and the second corrected positioning information.
Determining final positioning information of the vehicle according to the first correction positioning information and the second correction positioning information comprises:
acquiring the inertial navigation data of a vehicle;
determining the confidence level of the first correction positioning information according to the inertial navigation data;
if the confidence coefficient is larger than a preset threshold value, determining final positioning information of the vehicle according to the first correction positioning information and the second correction positioning information.
The positioning determining module 750 is configured to determine final positioning information of the vehicle according to the first corrected positioning information and the second corrected positioning information, where the determining includes:
generating fusion correction information based on the distance difference in the first correction positioning information, the conversion matrix in the second correction positioning information and the initial positioning information;
and carrying out error state Kalman filtering on the fusion correction information to obtain final positioning information.
The respective modules in the above-described vehicle positioning correction apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a terminal, and the internal structure thereof may be as shown in fig. 8. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by a processor to implement a vehicle positioning correction device. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
It will be appreciated by those skilled in the art that the structure shown in fig. 8 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program that when executed implements any of the vehicle positioning correction methods of the above embodiments, illustratively including the steps of:
acquiring initial positioning information, high-precision map information and visual lane lines of a vehicle;
determining a map lane line based on the initial positioning information and the high-precision map information;
ICP correction is carried out on the initial positioning information based on the visual lane lines and the map lane lines, so that first correction positioning information is obtained;
performing time correction on the initial positioning information to obtain second correction positioning information;
and determining final positioning information of the vehicle according to the first correction positioning information and the second correction positioning information.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, the computer program being executed by a processor to perform any of the vehicle positioning correction methods of the above embodiments, illustratively comprising the steps of:
acquiring initial positioning information, high-precision map information and visual lane lines of a vehicle;
determining a map lane line based on the initial positioning information and the high-precision map information;
ICP correction is carried out on the initial positioning information based on the visual lane lines and the map lane lines, so that first correction positioning information is obtained;
performing time correction on the initial positioning information to obtain second correction positioning information;
and determining final positioning information of the vehicle according to the first correction positioning information and the second correction positioning information.
It should be noted that, user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the various embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magnetic random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (Phase Change Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as static random access memory (Static Random Access Memory, SRAM) or dynamic random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the various embodiments provided herein may include at least one of relational databases and non-relational databases. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic units, quantum computing-based data processing logic units, etc., without being limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples only represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the present application. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application shall be subject to the appended claims.
Claims (10)
1. A vehicle positioning correction method, characterized by comprising:
acquiring initial positioning information, high-precision map information and visual lane lines of a vehicle;
determining a map lane line based on the initial positioning information and the high-precision map information;
ICP correction is carried out on the initial positioning information based on the visual lane lines and the map lane lines, so that first correction positioning information is obtained;
Performing time correction on the initial positioning information to obtain second correction positioning information;
and determining final positioning information of the vehicle according to the first correction positioning information and the second correction positioning information.
2. The vehicle positioning correction method according to claim 1, wherein the ICP correction of the initial positioning information based on the visual lane line and the map lane line includes:
sampling each lane line in the visual lane lines to obtain a reference point set;
projecting the reference point set to the map lane line to obtain a projection point set;
determining a conversion matrix according to the reference point set and the projection point set;
and correcting the initial positioning information according to the conversion matrix to obtain first corrected positioning information.
3. The vehicle positioning correction method according to claim 2, wherein the determining a conversion matrix from the reference point set and the projection point set includes:
determining the distance information between each reference point in the reference point set and each projection point in the corresponding projection point set;
establishing a matching relation between the reference point set and the projection point set according to the distance information;
And determining a conversion matrix according to the reference point set and the projection point set after the matching relation is established.
4. The vehicle positioning correction method according to claim 2, wherein the determining a conversion matrix from the reference point set and the projection point set includes:
acquiring a preset objective function, wherein the objective function is used for determining the rotation angle between the point sets;
substituting the reference point set and the projection point set into an objective function, and determining a rotation angle between the reference point set and the projection point set;
determining a rotation matrix and a translation matrix according to the rotation angle;
and taking the rotation matrix and the translation matrix as conversion matrices.
5. The vehicle positioning correction method according to claim 1, wherein the time correcting the initial positioning information to obtain second corrected positioning information includes:
acquiring initial positioning time, current time, vehicle speed and vehicle angular speed; the initial positioning time is the time for acquiring initial positioning information;
determining a time difference according to the initial positioning time and the current time;
determining a distance difference and a head direction difference according to the time difference and the vehicle speed of the vehicle;
And carrying out time correction on the initial positioning information according to the distance difference to obtain second correction positioning information.
6. The vehicle positioning correction method according to claim 1, wherein determining final positioning information of the vehicle based on the first corrected positioning information and the second corrected positioning information includes:
acquiring inertial navigation data of a vehicle;
determining the confidence level of the first correction positioning information according to the inertial navigation data;
if the confidence coefficient is larger than a preset threshold value, determining final positioning information of the vehicle according to the first correction positioning information and the second correction positioning information.
7. The vehicle positioning correction method according to claim 6, wherein the determining final positioning information of the vehicle based on the first corrected positioning information and the second corrected positioning information includes:
generating fusion correction information based on the distance difference in the first correction positioning information, the conversion matrix in the second correction positioning information and the initial positioning information;
and carrying out error state Kalman filtering on the fusion correction information to obtain final positioning information.
8. A vehicle positioning correction apparatus, characterized in that the apparatus comprises:
The acquisition module is used for acquiring initial positioning information, high-precision map information and visual lane lines of the vehicle;
the determining module is used for determining a map lane line based on the initial positioning information and the high-precision map information;
the first correction module is used for carrying out ICP correction on the initial positioning information based on the visual lane lines and the map lane lines to obtain first correction positioning information;
the second correction module is used for carrying out time correction on the initial positioning information to obtain second correction positioning information;
and the positioning determining module is used for determining the final positioning information of the vehicle according to the first correction positioning information and the second correction positioning information.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any one of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410221917.8A CN117782114A (en) | 2024-02-28 | 2024-02-28 | Vehicle positioning correction method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410221917.8A CN117782114A (en) | 2024-02-28 | 2024-02-28 | Vehicle positioning correction method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117782114A true CN117782114A (en) | 2024-03-29 |
Family
ID=90400405
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410221917.8A Pending CN117782114A (en) | 2024-02-28 | 2024-02-28 | Vehicle positioning correction method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117782114A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190271549A1 (en) * | 2018-03-02 | 2019-09-05 | DeepMap Inc. | Camera based localization for autonomous vehicles |
| CN111443327A (en) * | 2019-01-16 | 2020-07-24 | 通用汽车环球科技运作有限责任公司 | Maintaining vehicle position accuracy |
| CN113218389A (en) * | 2021-05-24 | 2021-08-06 | 北京航迹科技有限公司 | Vehicle positioning method, device, storage medium and computer program product |
| CN114034307A (en) * | 2021-11-19 | 2022-02-11 | 智道网联科技(北京)有限公司 | Lane line-based vehicle pose calibration method and device and electronic equipment |
| CN114286762A (en) * | 2019-10-29 | 2022-04-05 | 浩乐行 | Method and control device for operating a virtual reality headset in a vehicle |
| CN115235500A (en) * | 2022-09-15 | 2022-10-25 | 北京智行者科技股份有限公司 | Lane line constraint-based pose correction method and device and all-condition static environment modeling method and device |
| CN116105755A (en) * | 2022-12-27 | 2023-05-12 | 华人运通(上海)自动驾驶科技有限公司 | Vehicle positioning correction method, storage medium and terminal equipment |
-
2024
- 2024-02-28 CN CN202410221917.8A patent/CN117782114A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190271549A1 (en) * | 2018-03-02 | 2019-09-05 | DeepMap Inc. | Camera based localization for autonomous vehicles |
| CN111443327A (en) * | 2019-01-16 | 2020-07-24 | 通用汽车环球科技运作有限责任公司 | Maintaining vehicle position accuracy |
| CN114286762A (en) * | 2019-10-29 | 2022-04-05 | 浩乐行 | Method and control device for operating a virtual reality headset in a vehicle |
| CN113218389A (en) * | 2021-05-24 | 2021-08-06 | 北京航迹科技有限公司 | Vehicle positioning method, device, storage medium and computer program product |
| CN114034307A (en) * | 2021-11-19 | 2022-02-11 | 智道网联科技(北京)有限公司 | Lane line-based vehicle pose calibration method and device and electronic equipment |
| CN115235500A (en) * | 2022-09-15 | 2022-10-25 | 北京智行者科技股份有限公司 | Lane line constraint-based pose correction method and device and all-condition static environment modeling method and device |
| CN116105755A (en) * | 2022-12-27 | 2023-05-12 | 华人运通(上海)自动驾驶科技有限公司 | Vehicle positioning correction method, storage medium and terminal equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109211251B (en) | Instant positioning and map construction method based on laser and two-dimensional code fusion | |
| CN109931944B (en) | AR navigation method, AR navigation device, vehicle-side equipment, server side and medium | |
| CN112268559B (en) | Mobile measurement method for fusing SLAM technology in complex environment | |
| CN113654555A (en) | Automatic driving vehicle high-precision positioning method based on multi-sensor data fusion | |
| CN112444246B (en) | Laser fusion positioning method in high-precision digital twin scene | |
| WO2024027350A1 (en) | Vehicle positioning method and apparatus, computer device and storage medium | |
| CN111241224B (en) | Method, system, computer device and storage medium for target distance estimation | |
| CN111915675B (en) | Particle drift-based particle filtering point cloud positioning method, device and system thereof | |
| Bai et al. | A sensor fusion framework using multiple particle filters for video-based navigation | |
| Ghosh et al. | Multi sensor data fusion for 6D pose estimation and 3D underground mine mapping using autonomous mobile robot | |
| CN110361003B (en) | Information fusion method, apparatus, computer device and computer readable storage medium | |
| CN109916417B (en) | Map establishing method, map establishing device, computer equipment and storage medium thereof | |
| CN114061570A (en) | Vehicle positioning method and device, computer equipment and storage medium | |
| CN114897942B (en) | Point cloud map generation method and device and related storage medium | |
| KR102130687B1 (en) | System for information fusion among multiple sensor platforms | |
| CN116202509A (en) | Passable map generation method for indoor multi-layer building | |
| KR102506411B1 (en) | Method and apparatus for estimation of location and pose on vehicle and record medium for this | |
| Deusch et al. | Improving localization in digital maps with grid maps | |
| CN117782114A (en) | Vehicle positioning correction method, device, computer equipment and storage medium | |
| CN113379915B (en) | Driving scene construction method based on point cloud fusion | |
| CN114088104B (en) | Map generation method under automatic driving scene | |
| CN115585805A (en) | Vehicle positioning method, positioning device, positioning system and vehicle | |
| CN111488419B (en) | Method and device for creating indoor robot map, electronic equipment and storage medium | |
| CN114842224A (en) | Monocular unmanned aerial vehicle absolute vision matching positioning scheme based on geographical base map | |
| CN116858276B (en) | Map-assisted multi-sensor fusion positioning method and computer readable medium |
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 |