Search

US-12624954-B2 - Method and apparatus for predicting success rate of lane changing by vehicle, computer device, and storage medium

US12624954B2US 12624954 B2US12624954 B2US 12624954B2US-12624954-B2

Abstract

A method for predicting a success rate of lane changing by a vehicle, including obtaining lane-group data of the plurality of lane groups, determining feature sets respectively corresponding to a plurality of lane lines of the traveling road, removing a feature subset in the plurality of feature subsets that meets a first preset condition from a feature set corresponding to the feature subset to obtain a remaining feature set, determining a current position offset of a traveling position of the vehicle in the plurality of lane groups during traveling of the vehicle, determining a target position offset of a preset target position of the vehicle in the plurality of lane groups, and predicting a success rate of changing from the first lane to the second lane by the vehicle based on the current position offset, the target position offset, the remaining feature set, and traveling information of the vehicle.

Inventors

  • Ning XIAO

Assignees

  • TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Dates

Publication Date
20260512
Application Date
20240925
Priority Date
20221130

Claims (18)

  1. 1 . A method for predicting a success rate of lane changing by a vehicle located on a traveling road comprising a plurality of lane groups, each lane group comprising lane road segments of a plurality of lanes, the method being performed by a computer device, and the method comprising: obtaining lane-group data of the plurality of lane groups; determining, from the lane-group data of the plurality of lane groups, feature sets respectively corresponding to a plurality of lane lines of the traveling road, the feature sets each comprising a plurality of feature subsets corresponding to the plurality of lane groups, and each feature subset comprising a corresponding lane-line type and a line-segment offset; removing a feature subset in the plurality of feature subsets that meets a first preset condition from a feature set corresponding to the feature subset to obtain a remaining feature set; determining a current position offset of a traveling position of the vehicle in the plurality of lane groups during traveling of the vehicle, the traveling position being located on a first lane of the plurality of lanes; determining a target position offset of a preset target position of the vehicle in the plurality of lane groups, the preset target position being located on a second lane different from the first lane in the plurality of lanes; and predicting a success rate of changing from the first lane to the second lane by the vehicle based on the current position offset, the target position offset, the remaining feature set, and traveling information of the vehicle, wherein the determining, from the lane-group data of the plurality of lane groups, the feature sets respectively corresponding to the plurality of lane lines of the traveling road comprises: reading, from the lane-group data of the plurality of lane groups, lane-line types that respectively correspond to a plurality of lane line segments in the plurality of lane groups and that are of the lane lines, and determining line-segment offsets of the plurality of lane line segments in the lane groups in which the plurality of lane line segments are respectively located; combining, for each lane line segment, the lane-line type and the line-segment offset that correspond to the lane line segment to obtain the feature subset corresponding to each lane line segment; and combining, for each lane line, the feature subsets corresponding to the lane line segments comprised in the lane line to obtain the feature sets respectively corresponding to the lane lines.
  2. 2 . The method according to claim 1 , wherein the reading comprises: determining a plurality of lane-line identifiers from the lane-group data of the plurality of lane groups, wherein the plurality of lane-line identifiers are respectively configured for uniquely identifying one of the plurality of lane lines; and reading, from the lane-group data of the plurality of lane groups, the lane-line types of the lane line segments corresponding to a same lane-line identifier.
  3. 3 . The method according to claim 1 , wherein the lane-group data is obtained by performing lane reconstruction on original lane-group data of the traveling road, and the original lane-group data is data of each original lane group on the traveling road; wherein the performing lane reconstruction on the original lane-group data of the traveling road comprises: determining a quantity of first lanes of a first original lane group in the original lane-group data, and determining a quantity of second lanes of a second original lane group in the original lane-group data, wherein the first original lane group and the second original lane group are lane groups that are adjacent to each other on the traveling road; and adding a virtual lane to the first original lane group to update the original lane-group data when the quantity of first lanes is less than the quantity of second lanes, wherein the virtual lane enables the first original lane group to reach lane alignment with the second original lane group; and wherein the performing lane reconstruction further comprises: configuring, in the original lane-group data, a lane feature for the virtual lane to obtain the lane-group data.
  4. 4 . The method according to claim 3 , wherein the adding comprises: adding, to the first original lane group when the quantity of first lanes is less than the quantity of second lanes and an edge lane road segment in the second original lane group and an edge lane road segment in the first original lane group are not on a same lane, a virtual lane that is aligned with the edge lane road segment in the second original lane group.
  5. 5 . The method according to claim 4 , wherein the configuring comprises: configuring, in the original lane-group data, a first virtual lane width and a first virtual lane line for the virtual lane, wherein the first virtual lane line is a lane line that belongs to a solid-line type and that represents that a lane change is prohibited, and the first virtual lane width is equal to a target width value.
  6. 6 . The method according to claim 3 , wherein the adding comprises: converting a middle lane road segment in the first original lane group into at least two virtual lanes respectively aligned with at least two lane road segments in the second original lane group when the quantity of first lanes is less than the quantity of second lanes and the middle lane road segment in the first original lane group is split into the at least two lane road segments in the second original lane group.
  7. 7 . The method according to claim 6 , wherein the configuring comprises: configuring a second virtual lane line of a dashed-line type between the at least two virtual lanes; and configuring, in the original lane-group data, second virtual lane widths respectively for the at least two virtual lanes, wherein a sum of the second virtual lane widths of the at least two virtual lanes is consistent with a lane width of the middle lane road segment.
  8. 8 . The method according to claim 1 , wherein the lane-group data is obtained by performing lane reconstruction on the original lane-group data of the traveling road, and the original lane-group data is the data of each original lane group on the traveling road; and wherein the performing lane reconstruction on the original lane-group data of the traveling road comprises: obtaining the original lane-group data of the traveling road; and converting the original lane group in the original lane-group data into a lane group of a straight-line type when the original lane group in the original lane-group data is a lane group with a curvature.
  9. 9 . The method according to claim 1 , wherein the removing comprises: searching, in each feature set, a target feature subset meeting the first preset condition; and removing the target feature subset from each feature set, or removing a line-segment offset and a lane-line type from the target feature subset.
  10. 10 . The method according to claim 1 , wherein the predicting comprises: determining a traveling distance of the vehicle based on the traveling information of the vehicle; determining a forward position offset of the vehicle based on the traveling distance and the current position offset; and predicting the success rate of changing from the first lane to the second lane by the vehicle based on the forward position offset, the line-segment offset of each lane line segment in the remaining feature set, and the target position offset.
  11. 11 . The method according to claim 10 , wherein the traveling information of the vehicle comprises a parallel speed and a vertical speed relative to a lane, and the remaining feature set comprises a feature-set subsequence between the first lane and the second lane; wherein the determining the traveling distance of the vehicle based on the traveling information of the vehicle comprises: determining, based on the vertical speed and a lane width, time consumption of crossing each lane in the lane group; and determining the traveling distance of the vehicle based on the time consumption and the parallel speed; and wherein the predicting the success rate of changing from the first lane to the second lane by the vehicle based on the forward position offset, the line-segment offset of each lane line segment in the remaining feature set, and the target position offset comprises: predicting, based on the forward position offset, a line-segment offset of each lane line segment in the feature-set subsequence, and the target position offset, the success rate of changing from the first lane to the second lane by the vehicle.
  12. 12 . The method according to claim 10 , wherein the remaining feature set comprises a feature-set subsequence between the first lane and the second lane; the line-segment offset comprises an end offset, and a quantity of lane lines in the feature-set subsequence is n, and n is a positive integer not less than 1; and wherein the predicting the success rate of changing from the first lane to the second lane by the vehicle based on the forward position offset, the line-segment offset of each lane line segment in the remaining feature set, and the target position offset comprises: traversing, in an i th lane line in the feature-set subsequence, the feature subset of each lane line segment in a traveling direction of the vehicle, to obtain a traversal result; determining that a target feature subset meeting a second preset condition exists in the traversal result, wherein the second preset condition is that the forward position offset is not greater than an end offset of the i th lane line and not greater than the target position offset; and performing increment or decrement processing on i based on a preset step, cyclically performing the foregoing operations until i=n or i=1, and when the target feature subset meeting the second preset condition exists in the traversal result of the i th lane line, determining that the vehicle is capable of changing from the first lane to the second lane.
  13. 13 . The method according to claim 12 , further comprising: based on a determination that the target feature subset meeting the second preset condition does not exist in the traversal result, determining that the vehicle is not capable of changing from the first lane to the second lane.
  14. 14 . The method according to claim 1 , further comprising: displaying a lane-change guide on an electronic map when the vehicle is capable of changing from the first lane to the second lane, wherein the lane-change guide is configured for indicating the vehicle to change lanes based on the lane-change guide.
  15. 15 . The method according to claim 1 , further comprising: re-planning a path to the target position when the vehicle is not capable of changing from the first lane to the second lane; and issuing a new-path prompt, the new-path prompt being configured for instructing the vehicle to travel based on the re-planned path.
  16. 16 . An apparatus for predicting a success rate of lane changing by a vehicle located on a traveling road comprising a plurality of lane groups, each lane group comprising lane road segments of a plurality of lanes, and the apparatus comprising: at least one memory configured to store computer program code; at least one processor configured to read the program code and operate as instructed by the program code, the program code comprising: extraction code configured to cause at least one of the at least one processor to obtain lane-group data of the plurality of lane groups; and determine, from the lane-group data of the plurality of lane groups, feature sets respectively corresponding to a plurality of lane lines of the traveling road, the feature sets each comprising a plurality of feature subsets corresponding to the plurality of lane groups, and each feature subset comprising a corresponding lane-line type and a line-segment offset; processing code configured to cause at least one of the at least one processor to remove a feature subset in the plurality of feature subsets that meets a first preset condition from a feature set corresponding to the feature subset, to obtain a remaining feature set; determining code configured to cause at least one of the at least one processor to determine a current position offset of a traveling position of the vehicle in the plurality of lane groups during traveling of the vehicle, the traveling position being located on a first lane on the plurality of lanes; and determine a target position offset of a preset target position of the vehicle in the plurality of lane groups, the preset target position being located on a second lane different from the first lane in the plurality of lanes; and judging code configured to cause at least one of the at least one processor to predict a success rate of changing from the first lane to the second lane by the vehicle based on the current position offset, the target position offset, the remaining feature set, and traveling information of the vehicle, wherein the extraction code is further configured to cause at least one of the at least one processor to: read, from the lane-group data of the plurality of lane groups, lane-line types that respectively correspond to a plurality of lane line segments in the plurality of lane groups and that are of the lane lines, and determine line-segment offsets of the plurality of lane line segments in the lane groups in which the plurality of lane line segments are respectively located; combine, for each lane line segment, the lane-line type and the line-segment offset that correspond to the lane line segment to obtain the feature subset corresponding to each lane line segment; and combine, for each lane line, the feature subsets corresponding to the lane line segments comprised in the lane line to obtain the feature sets respectively corresponding to the lane lines.
  17. 17 . The apparatus according to claim 16 , wherein the extraction code is further configured to cause at least one of the at least one processor to: determine a plurality of lane-line identifiers from the lane-group data of the plurality of lane groups, wherein the plurality of lane-line identifiers are respectively configured for uniquely identifying one of the plurality of lane lines; and read, from the lane-group data of the plurality of lane groups, the lane-line types of the lane line segments corresponding to a same lane-line identifier.
  18. 18 . A non-transitory computer-readable storage medium storing computer code which, when executed by at least one processor, causes the at least one processor to at least: obtain lane-group data of a plurality of lane groups of a traveling road on which a vehicle is located, each lane group comprising lane road segments of a plurality of lanes; determine, from the lane-group data of the plurality of lane groups, feature sets respectively corresponding to a plurality of lane lines of the traveling road, the feature sets each comprising a plurality of feature subsets corresponding to the plurality of lane groups, and each feature subset comprising a corresponding lane-line type and a line-segment offset; remove a feature subset in the plurality of feature subsets that meets a first preset condition from a feature set corresponding to the feature subset to obtain a remaining feature set determine a current position offset of a traveling position of the vehicle in the plurality of lane groups during traveling of the vehicle, the traveling position being located on a first lane of the plurality of lanes; determine a target position offset of a preset target position of the vehicle in the plurality of lane groups, the preset target position being located on a second lane different from the first lane in the plurality of lanes; and predict a success rate of changing from the first lane to the second lane by the vehicle based on the current position offset, the target position offset, the remaining feature set, and traveling information of the vehicle, wherein the determine, from the lane-group data of the plurality of lane groups, the feature sets respectively corresponding to the plurality of lane lines of the traveling road comprises: reading, from the lane-group data of the plurality of lane groups, lane-line types that respectively correspond to a plurality of lane line segments in the plurality of lane groups and that are of the lane lines, and determining line-segment offsets of the plurality of lane line segments in the lane groups in which the plurality of lane line segments are respectively located; combining, for each lane line segment, the lane-line type and the line-segment offset that correspond to the lane line segment to obtain the feature subset corresponding to each lane line segment; and combining, for each lane line, the feature subsets corresponding to the lane line segments comprised in the lane line to obtain the feature sets respectively corresponding to the lane lines.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application is a continuation application of International Application No. PCT/CN2023/134641 filed on Nov. 28, 2023, which claims priority to Chinese Patent Application No. 202211514504.6, filed with the China National Intellectual Property Administration on Nov. 30, 2022, the disclosures of each being incorporated by reference herein in their entireties. FIELD The disclosure relates to the field of traffic technologies, and in particular, to a method and an apparatus for predicting a success rate of lane changing by a vehicle, a computer device, a storage medium, and a computer program product. BACKGROUND With the development of electronic map technologies, when driving a vehicle to travel, a traveling object may drive through navigation by using an electronic map, or drive in a manner in which an electronic map is combined with assisted driving or unmanned driving technologies. In a process of driving the vehicle in the foregoing driving manner, a success rate of a lane change to a lane on a traveling road generally needs to be predicted, to travel to a destination safely and quickly. However, during actual traveling, prediction of the success rate of the lane change is generally affected by a plurality of factors. As a result, accuracy of a prediction result is low, and a safety hazard is consequently caused to traffic. SUMMARY Some embodiments provide a method for predicting a success rate of lane changing by a vehicle located on a traveling road comprising a plurality of lane groups, each lane group comprising lane road segments of a plurality of lanes, the method being performed by a computer device, and the method including obtaining lane-group data of the plurality of lane groups; determining, from the lane-group data of the plurality of lane groups, feature sets respectively corresponding to a plurality of lane lines of the traveling road, the feature sets each comprising a plurality of feature subsets corresponding to the plurality of lane groups, and each feature subset comprising a corresponding lane-line type and a line-segment offset; removing a feature subset in the plurality of feature subsets that meets a first preset condition from a feature set corresponding to the feature subset to obtain a remaining feature set; determining a current position offset of a traveling position of the vehicle in the plurality of lane groups during traveling of the vehicle, the traveling position being located on a first lane of the plurality of lanes; determining a target position offset of a preset target position of the vehicle in the plurality of lane groups, the preset target position being located on a second lane different from the first lane in the plurality of lanes; and predicting a success rate of changing from the first lane to the second lane by the vehicle based on the current position offset, the target position offset, the remaining feature set, and traveling information of the vehicle. Some embodiments provide an apparatus for predicting a success rate of lane changing by a vehicle located on a traveling road comprising a plurality of lane groups, each lane group comprising lane road segments of a plurality of lanes, and the apparatus including: at least one memory configured to store computer program code; at least one processor configured to read the program code and operate as instructed by the program code, the program code comprising: extraction code configured to cause at least one of the at least one processor to obtain lane-group data of the plurality of lane groups; and determine, from the lane-group data of the plurality of lane groups, feature sets respectively corresponding to a plurality of lane lines of the traveling road, the feature sets each comprising a plurality of feature subsets corresponding to the plurality of lane groups, and each feature subset comprising a corresponding lane-line type and a line-segment offset; processing code configured to cause at least one of the at least one processor to remove a feature subset in the plurality of feature subsets that meets a first preset condition from a feature set corresponding to the feature subset, to obtain a remaining feature set; determining code configured to cause at least one of the at least one processor to determine a current position offset of a traveling position of the vehicle in the plurality of lane groups during traveling of the vehicle, the traveling position being located on a first lane on the plurality of lanes; and determine a target position offset of a preset target position of the vehicle in the plurality of lane groups, the preset target position being located on a second lane different from the first lane in the plurality of lanes; and judging code configured to cause at least one of the at least one processor to predict a success rate of changing from the first lane to the second lane by the vehicle based on the current position offset, the target position