Search

CN-122015887-A - Positioning method, positioning device, vehicle, storage medium, and program product

CN122015887ACN 122015887 ACN122015887 ACN 122015887ACN-122015887-A

Abstract

The application relates to the technical field of automobile electronics, and discloses a positioning method, positioning equipment, a vehicle, a storage medium and a program product. The positioning method comprises the steps that the electronic equipment can acquire sensing data of a first moment of a vehicle, wherein the sensing data comprise road section sensing data corresponding to at least one road section. Then, a perceived probability that the vehicle will travel on each road segment at a second time may be determined based on the road segment perceived data and the current pose of the vehicle, where the second time is later than the first time. And, the electronic device may predict a target road segment that the vehicle is traveling at the second time based on the perceived probability of each road segment. Further, at the second time, it may be displayed in the navigation map that the vehicle is traveling on the target road section. Therefore, the road level positioning function can be realized, so that the vehicle is associated with a road section of specific running, the drift phenomenon of the positioning point of the vehicle is avoided, and more accurate navigation decision is provided for the running of the vehicle.

Inventors

  • YIN DING

Assignees

  • 智驾大陆(上海)智能科技有限公司

Dates

Publication Date
20260512
Application Date
20251231

Claims (16)

  1. 1. A positioning method, comprising: Obtaining perception data of a vehicle at a first moment, wherein the perception data comprises road segment perception data corresponding to at least one road segment; based on the road section sensing data and the current pose of the vehicle, determining the sensing probability that the vehicle will travel on each road section at a second moment, wherein the second moment is later than the first moment; predicting a target road segment of the vehicle traveling at the second moment based on the perceived probability of each road segment; at a second time, displaying the road section on which the vehicle runs in the navigation map.
  2. 2. The positioning method of claim 1, wherein the at least one road segment comprises a first road segment, the perceived probability comprises a first perceived probability that the vehicle will travel on the first road segment at a second time, and The determining, based on the road segment awareness data and the current pose of the vehicle, the awareness probability that the vehicle will travel on each road segment at the second moment includes: correcting the current pose of the vehicle based on the road segment awareness data and map data of each road segment in the navigation map; And determining a first perception probability that the vehicle will travel on the first road section at the second moment based on the corrected relative distance and/or relative azimuth angle between the vehicle pose and the first road section in the navigation map.
  3. 3. The positioning method according to claim 2, wherein the correcting the current pose of the vehicle based on the road segment awareness data and map data of each of the road segments in the navigation map includes: determining coordinates of perceived sampling points on each road segment in a vehicle coordinate system based on the road segment perceived data, and determining coordinates of map sampling points on each road segment in the navigation map in a world coordinate system based on the map data; Based on the current pose of the vehicle, converting the coordinate system of the coordinate of the sensing sampling point or the coordinate of the map sampling point to obtain the coordinate of the sensing sampling point and the coordinate of the map sampling point belonging to the same coordinate system; And correcting the pose of the vehicle based on the coordinates of the sensing sampling points and the coordinates of the map sampling points which belong to the same coordinate system and are positioned on the same road feature.
  4. 4. A positioning method according to claim 3, wherein said determining coordinates of perceived sampling points on each of said road segments in a vehicle coordinate system based on said road segment perceived data comprises: Determining a road boundary of the first road section and a road area positioned in the road boundary based on the road section perception data; acquiring coordinates of boundary points on the road boundary under the vehicle coordinate system; And establishing a two-dimensional grid in the road area, and determining the coordinates of the sensing sampling points in each grid of the two-dimensional grid under the vehicle coordinate system based on the coordinates of the boundary points.
  5. 5. A positioning method according to claim 3, wherein said determining coordinates of map sampling points on each of the road segments in the navigation map in a world coordinate system based on the map data comprises: Determining the first road section in the navigation map based on the map data, and determining the road width of the first road section based on a standard road width and the number of lanes in the first road section indicated by the map data; Determining a plurality of sampling centers in the first road section, wherein the adjacent sampling centers have preset sampling distances; And determining a plurality of map sampling points based on the sampling centers and obtaining coordinates of the map sampling points in the world coordinate system, wherein the map sampling points are positioned on a circumference taking the sampling center as a center and taking a first length as a diameter, and the first length is determined according to the road width.
  6. 6. The positioning method of claim 2, wherein the at least one road segment comprises a second road segment, the perceived probability comprising a second perceived probability that the vehicle will travel on the second road segment at a second time; the road section sensing data comprise split point sensing data corresponding to at least one road section split point, and the road section split point is positioned between a road section where the vehicle is positioned at the first moment and the second road section; the determining, based on the road segment awareness data and the current pose of the vehicle, the awareness probability that the vehicle will travel on each road segment at the second moment includes: Determining the position of each road segment split point based on the split point sensing data; And determining a second perception probability that the vehicle will travel on the second road section at a second moment based on the position of each road section split point, the road extension direction of the second road section and the current pose of the vehicle.
  7. 7. The positioning method of claim 6, wherein the at least one road segment further comprises a third road segment, the road segment split point is located between a road segment where the vehicle is located at the first time and the third road segment, and the road segment split point is used to split the vehicle from the road segment where the first time is located to the second road segment and the third road segment; The determining, based on the position of each of the road segment split points, the road extension direction of the second road segment, and the current pose of the vehicle, a second perceived probability that the vehicle will travel on the second road segment at a second moment includes: And determining the second perception probability that the vehicle will travel on the second road section at the second moment through a multi-wheel voting mechanism according to the position of each road section split point, the current pose of the vehicle, the road extending direction of the second road section and the road extending direction of the third road section.
  8. 8. The positioning method according to claim 7, wherein the determining the second perceived probability that the vehicle will travel on the second road segment at the second moment by a multi-wheel voting mechanism based on each of the road segment split point, the current pose of the vehicle, the road extension direction of the second road segment, and the road extension direction of the third road segment includes: Determining that the second road section is a candidate road section corresponding to the first moment based on the current pose of the vehicle, the road extension direction of the second road section and the road extension direction of the third road section; Calculating a first confidence value corresponding to the second road segment at the first moment based on a preset distance and an effective perception distance when the perception data are acquired at the first moment, wherein the preset distance is a distance between a center point position between the road segment split points at the first moment and the vehicle; Determining a total confidence value of the second road segment based on the first confidence value and other confidence values of the second road segment calculated at previous moments; Setting a corresponding second perception probability for the second road section and the third road section in case the number of calculations is larger than a number threshold and/or the total confidence value satisfies a first condition, wherein, And the second perception probability corresponding to the second road section is larger than the second perception probability corresponding to the third road section.
  9. 9. The positioning method of claim 8, wherein the overall confidence value satisfies a first condition, comprising: the total confidence value corresponding to the second road segment is greater than the confidence threshold value, and And the total confidence value corresponding to the second road section is larger than the calculated total confidence value of the third road section at each previous moment.
  10. 10. The positioning method according to claim 6, wherein predicting the target road segment that the vehicle is traveling at the second time based on the perceived probability of each road segment includes: In the navigation map, determining the emission probability that the vehicle will travel on each road section at the second moment based on the relative distance and the relative azimuth angle between the current pose of the vehicle and each road section; In the navigation map, determining a transition probability that the current driving road section of the vehicle at the second moment is to be transitioned to the driving on each road section based on a path connection relation between the current driving road section and each road section of the vehicle at the first moment; and predicting a target road section of the vehicle running at the second moment based on the first perception probability, the second perception probability, the emission probability and the transition probability corresponding to each road section.
  11. 11. The positioning method according to claim 10, wherein predicting the target road section on which the vehicle is traveling at the second time based on the first perceived probability, the second perceived probability, the emission probability, and the transition probability corresponding to each of the road sections includes: Based on the first perceived probability, the second perceived probability and the emission probability corresponding to each road segment, determining a predicted probability that the vehicle will travel on each road segment at a second moment; Predicting a target road section of the vehicle running at the second moment based on the prediction probability and the transition probability corresponding to each road section; The prediction probability corresponding to the target road section meets a prediction probability condition, and the transition probability corresponding to the target road section meets a transition probability condition.
  12. 12. A positioning system, comprising: The sensing data acquisition module is used for acquiring sensing data of a vehicle at a first moment, wherein the sensing data comprises road segment sensing data corresponding to at least one road segment; the perception probability determining module is used for determining the perception probability that the vehicle will travel on each road section at the second moment according to the road section perception data and the current pose of the vehicle; The target road section determining module is used for predicting a target road section of the vehicle running at the second moment according to the perceived probability of each road section; And the navigation display module is used for displaying that the vehicle runs on the target road section in the navigation map at the second moment.
  13. 13. An electronic device comprising at least one memory and at least one processor, the memory coupled to the processor, the memory to store computer program code/instructions that, when executed by the processor, cause the electronic device to perform the positioning method of any of claims 1-11.
  14. 14. A vehicle comprising the electronic device of claim 13.
  15. 15. A readable storage medium having stored thereon instructions that, when executed on an electronic device, cause the electronic device to perform the positioning method of any of claims 1-11.
  16. 16. A computer program product comprising computer instructions which, when run on an electronic device, cause the electronic device to perform the positioning method according to any one of claims 1 to 11.

Description

Positioning method, positioning device, vehicle, storage medium, and program product Technical Field The present application relates to the field of automotive electronics, and in particular, to a positioning method, apparatus, vehicle, storage medium, and program product. Background During the running of the vehicle, the road level locating function can correlate the vehicle position to a specific road segment in the navigation map so as to ensure the reliability of navigation. For example, as shown in fig. 1, on a navigation map with a large number of road segments, vehicle positioning point drift is likely to occur when isolated vehicle coordinates are acquired only by a global navigation satellite system (global navigation SATELLITE SYSTEM, GNSS). For example, in fig. 1, the distance between the road segment a and the road segment B is relatively short, and when the vehicle actually runs on the road segment a, the navigation is performed only by means of the GNSS positioning function, which may cause a drift phenomenon that the navigation map shows that the positioning point of the vehicle jumps back and forth between the adjacent road segment a and road segment B. However, if the electronic device (such as a vehicle machine) associates the vehicle with a specific driving road section through the road level positioning function, the drift phenomenon of the vehicle positioning point can be avoided, and thus a more accurate navigation decision can be provided for the vehicle driving. At present, when the electronic equipment locates the vehicle at the road level, for complex road sections such as a branch road or a ramp entry and exit area, the electronic equipment still cannot accurately associate the vehicle with the road section actually running, and the situation of association errors is easy to occur, such as the situation of error association of the vehicle with the adjacent road of the road section actually running. Disclosure of Invention The application provides a positioning method, positioning equipment, a vehicle, a storage medium and a program product, which are used for improving the accuracy of a road level positioning function. The positioning method comprises the steps of obtaining perception data of a first moment of a vehicle, wherein the perception data comprise road section perception data corresponding to at least one road section, determining perception probability that the vehicle will travel on each road section at a second moment based on the road section perception data and the current pose of the vehicle, wherein the second moment is later than the first moment, predicting a target road section that the vehicle travels on the second moment based on the perception probability of each road section, and displaying that the vehicle travels on the target road section in a navigation map at the second moment. Therefore, the road level positioning function can be realized through the method, so that the vehicle is associated with a road section of specific running, the drift phenomenon of the positioning point of the vehicle is avoided, and more accurate navigation decision is provided for the running of the vehicle. In addition, when the vehicle is positioned, the application can also determine the perception probability of the vehicle running on each road section based on the perception data (such as the environment image data shot by the vehicle-mounted camera) so as to execute the subsequent positioning process based on the perception probability. Therefore, the method for determining the perception probability of each road section by combining the surrounding environment of the vehicle can enable the electronic equipment to accurately correlate the vehicle with the road section actually running on the complex road with a relatively close distance between adjacent road sections (such as bifurcation intersections or ramp roads and the like) and similar direction, and avoid the occurrence of error conditions of correlating the vehicle with the adjacent road section of the road section actually running. In one possible implementation of the first aspect, the at least one road segment includes a first road segment, the perceived probability includes a first perceived probability that the vehicle will travel on the first road segment at a second moment, and the determining the perceived probability that the vehicle will travel on each road segment at the second moment based on the road segment perceived data and the current pose of the vehicle includes correcting the current pose of the vehicle based on the road segment perceived data and map data of each road segment in a navigation map, and determining the first perceived probability that the vehicle will travel on the first road segment at the second moment based on the corrected relative distance and/or relative azimuth between the vehicle pose and the first road segment in the navigation map. Therefore, through registering the per