CN-121982910-A - Lane recognition method

CN121982910ACN 121982910 ACN121982910 ACN 121982910ACN-121982910-A

Abstract

The embodiment of the application discloses a lane identification method, which belongs to the technical field of vehicles and comprises the steps of determining a lane to be driven based on driving data of a vehicle, determining target driving lane information based on preset lane traffic condition information, the lane to be driven and current time, wherein the target driving lane information is used for indicating a lane which can be driven by the vehicle under the current time, and executing target driving business according to the target driving lane information. The application can improve the accuracy and efficiency of identifying the time-sharing lane.

Inventors

Hou Quanyao
DENG MINGFEI
ZENG JINQUAN

Assignees

广州小鹏自动驾驶科技有限公司

Dates

Publication Date: 20260505
Application Date: 20260325

Claims (10)

1. A lane recognition method, the method comprising: Determining a lane to be driven based on driving data of the vehicle; determining target driving lane information based on preset lane traffic condition information, a lane to be driven and current time, wherein the target driving lane information is used for indicating a lane which can be driven by the vehicle under the current time; and executing the target driving business according to the target driving lane information.
2. The lane recognition method as claimed in claim 1, wherein the determining the target driving lane information based on the preset lane traffic condition information, the lane to be driven, and the current time comprises: acquiring lane traffic condition information of the lane to be driven, wherein the lane to be driven refers to a lane to be driven by the vehicle, the time-sharing traffic data is used for indicating a traffic period in which the lane to be driven allows the vehicle to pass and/or a forbidden period in which the vehicle is not allowed to pass, and the time-sharing traffic data is stored in the vehicle or a server connected with the vehicle; And obtaining target driving lane information according to the lane traffic condition information and the current time, wherein the target driving lane information is also used for indicating whether the vehicle can currently pass through the lane to be driven.
3. The lane recognition method according to claim 2, wherein the acquiring lane traffic condition information of the lane to be driven includes: Acquiring a target map according to the real-time position in the driving data, wherein the target map at least comprises the lane to be driven, and the target map is also used for indicating lane traffic condition information of the lane to be driven; And obtaining the lane traffic condition information of the lane to be driven based on the target map.
4. The lane recognition method as claimed in claim 3, wherein said acquiring a target map based on a real-time position in said traveling data comprises: Determining boundary information according to the real-time position in the driving data, wherein the boundary information is used for indicating the size and/or the shape of an area corresponding to the real-time position and/or the coordinates of boundary points, the boundary information corresponds to a plurality of preset maps, the corresponding scale of each preset map is different, each preset map comprises at least one map tile, and at least one map tile in each map tile comprises the lane to be driven; and acquiring the target map from a plurality of preset maps.
5. The lane recognition method as claimed in claim 4, wherein said acquiring said target map from a plurality of said preset maps comprises: determining target preset maps with the scales matched with the real-time vehicle speed in the driving data from the preset maps; And acquiring a target map tile in the target preset map according to the real-time position in the driving data and the lane to be driven, so as to obtain the target map, wherein the real-time position and the lane to be driven are positioned in a map range indicated by the target map tile.
6. The lane recognition method according to claim 3, wherein the obtaining lane traffic condition information of the lane to be driven based on the target map comprises: Analyzing the target map to obtain the whole marking information and/or lane marking information indicated by the map tiles to be selected in the target map; the whole marking information is used for indicating whether all lanes in the map tile to be selected allow the vehicles to pass in different time periods, and the lane marking information is used for indicating whether all lanes in the map tile to be selected allow the vehicles to pass in different time periods and/or the traffic directions of all lanes in the map tile to be selected allowed in different time periods.
7. The lane recognition method as claimed in claim 6, wherein said obtaining the target traveling lane information based on the lane traffic condition information and the current time in the case where the lane traffic condition information includes at least the overall sign information comprises: according to the whole marking information, determining a first target period in which all lanes in the target map do not allow the vehicle to pass or a second target period in which all lanes in the target map allow the vehicle to pass; Determining that the vehicle is currently able to pass from the lane to be driven if the current time does not satisfy the first target period or the current time satisfies the second target period; Or when the lane traffic condition information includes the whole marking information and the lane marking information, obtaining target driving lane information according to the lane traffic condition information and the current time, including: judging whether each lane corresponding to the lane marking information comprises the lane to be driven or not; If yes, obtaining the target driving lane information according to the lane marking information corresponding to the current time and the lane to be driven; If not, obtaining the target driving lane information according to the current time and the whole mark information.
8. The lane recognition method as claimed in claim 7, wherein said obtaining the target driving lane information from the lane marking information corresponding to the lane to be driven at the current time comprises: According to the lane marking information corresponding to the lane to be driven, determining a third target period in which the lane to be driven does not allow the vehicle to pass or a fourth target period in which the lane to be driven allows the vehicle to pass; and if the current time does not meet the third target period or the current time meets the fourth target period, determining that the vehicle can currently pass through the lane to be driven.
9. The lane recognition method as claimed in claim 7, wherein said obtaining the target driving lane information from the lane marking information corresponding to the lane to be driven at the current time comprises: Acquiring an expected running direction in the running data; determining the allowed passing direction of the lane to be driven in a preset period according to the lane marking information corresponding to the lane to be driven; Judging whether the expected running direction is matched with the allowed running direction or not under the condition that the current time meets the preset time period; If the traffic is matched, determining that the vehicle can currently pass through the lane to be driven; if the traffic is not matched with the traffic lane, determining that the vehicle cannot pass through the traffic lane to be driven currently.
10. The lane recognition method according to any one of claims 1 to 9, wherein the performing a target traffic service according to the target traffic lane information comprises: Controlling the running direction of the vehicle according to the target running lane information; and/or generating and outputting prompt information according to the target driving lane information.

Description

Lane recognition method Technical Field The embodiment of the application relates to the technical field of vehicles, in particular to a lane recognition method. Background Because the traffic flow of urban road sections in different time periods has large difference, such as the traffic flow in the morning and evening peak time is large, some cities are provided with time-sharing roads, such as time-sharing bus lanes which only allow buses to pass in a specific time period, tide lanes or variable lanes which allow different passing directions in different time periods. In the related art, some vehicles are equipped with advanced auxiliary driving functions, and after the advanced auxiliary driving functions are turned on, the vehicles can implement autonomous acceleration and deceleration, lane change, or turning. Under the condition that the vehicle needs to support the working condition of the time-sharing lane, the vehicle needs to request the time-sharing information of the current road to the navigation provider in order to accurately identify whether the vehicle can enter the current lane or not, or obtains the time-sharing information of the current lane by sensing in real time and calling a corresponding large model for semantic speculation, and then judges whether the vehicle can enter the current lane or not according to the obtained time-sharing information. However, the related art schemes are either overly dependent on the accuracy of the navigation provider information or limited by the semantic recognition capabilities of the large model. Accordingly, the related art may have a technical problem in that accuracy of recognizing the time-sharing lane is poor. Disclosure of Invention Therefore, the lane recognition method provided by the embodiment of the application can improve the accuracy and efficiency of recognizing the time-sharing lane. The lane recognition method provided by the embodiment of the application is realized by the following steps: In a first aspect of an embodiment of the present application, there is provided a lane recognition method, including: Determining a lane to be driven based on driving data of the vehicle; determining target driving lane information based on preset lane traffic condition information, a lane to be driven and current time, wherein the target driving lane information is used for indicating a lane which can be driven by the vehicle under the current time; and executing the target driving business according to the target driving lane information. In a second aspect of the embodiment of the present application, there is also provided a lane recognition apparatus, the apparatus including: The first determining module is used for determining a lane to be driven based on driving data of the vehicle; The second determining module is used for determining target driving lane information based on preset lane passing condition information, a lane to be driven and current time, wherein the target driving lane information is used for indicating a lane which can be passed by the vehicle at the current time; and the execution module is used for executing the target driving business according to the target driving lane information. The vehicle provided by the embodiment of the application comprises a memory and a processor, wherein the memory stores a computer program capable of running on the processor, and the processor realizes the method of the embodiment of the application when executing the program. The computer readable storage medium provided by the embodiments of the present application stores a computer program thereon, which when executed by a processor implements the method provided by the embodiments of the present application. The lane recognition method provided by the embodiment of the application determines the lane to be driven by the driving data of the vehicle, determines the target driving lane information based on the preset lane traffic condition information, the lane to be driven and the current time, and executes the target driving business according to the target driving lane information. The lane to be driven is a lane where the vehicle is currently driven, and the target driving lane information is used for indicating a lane where the vehicle can pass at the current time. According to the embodiment, different traffic rules or traffic condition information may be corresponding to different lanes to be driven, so that after the lane to be driven is determined, lane traffic condition information capable of accurately and intuitively indicating the specific traffic rules of the lane to be driven needs to be acquired, and therefore, whether the lane to be driven is allowed to be driven at present can be accurately identified and determined only by comparing or matching the current time with a time period corresponding to the traffic rules indicated by the lane traffic condition information, and the target driving lane information can be rapid