Search

CN-116091855-B - Vehicle parking position determining method and device and vehicle

CN116091855BCN 116091855 BCN116091855 BCN 116091855BCN-116091855-B

Abstract

The application provides a method for determining a parking position of a vehicle, which comprises the steps of determining a target area according to a target position of the vehicle, wherein the maximum distance between the target area and the target position is smaller than a distance threshold value, acquiring real-time road condition information of the target area at the current moment, wherein the real-time road condition information comprises at least one road element, and determining the parking position of the vehicle at the target area at the current moment according to the real-time road condition information and a target machine learning model. The application can lead the vehicle to stop at the determined stop position, and lead the user to get on or off the vehicle at the determined stop position more conveniently and safely.

Inventors

  • LI CHENGYANG

Assignees

  • 华为技术有限公司

Dates

Publication Date
20260508
Application Date
20211102

Claims (12)

  1. 1. A method of determining a parking position of a vehicle, the method comprising: Determining a target area according to a target position of a vehicle, wherein the maximum distance between the target area and the target position is smaller than a distance threshold; acquiring real-time road condition information of the target area at the current moment, wherein the real-time road condition information comprises at least one road element; Determining the parking position of the vehicle in the target area at the current moment according to the real-time road condition information and a target machine learning model; The method further comprises the steps of: acquiring map information of the target area at the current moment, wherein the map information comprises at least one road element; the determining, according to the real-time road condition information and the target machine learning model, the parking position of the vehicle in the target area at the current moment includes: determining the parking position according to the real-time road condition information, the map information and the target machine learning model; The target area includes a plurality of candidate locations, and determining the parking location according to the real-time road condition information, the map information and the target machine learning model includes: Determining initial candidate position sets respectively corresponding to road elements in the real-time road condition information and the map information, wherein the initial candidate position sets comprise at least one candidate position in the plurality of candidate positions; Combining the initial candidate position sets respectively corresponding to all road elements in the real-time road condition information and the map information to obtain a candidate position set; obtaining data sets respectively corresponding to candidate positions in the candidate position set according to road elements respectively corresponding to the candidate positions in the real-time road condition information and the candidate position set in the map information, wherein the data set corresponding to any candidate position in the candidate position set is used for indicating the road elements corresponding to any candidate position in the real-time road condition information and the map information; and inputting the data sets corresponding to the candidate positions in the candidate position set into the target machine learning model to obtain the parking positions output by the target machine learning model.
  2. 2. The method of claim 1, wherein the real-time traffic information comprises at least one road element selected from the group consisting of a travelable area, a vehicle, a roadblock, a pedestrian, a railing, a water accumulation area, a silt area, and a pothole area.
  3. 3. The method according to claim 1, wherein the method further comprises: updating the map information by using the real-time road condition information to obtain updated map information, wherein the updated map information comprises road elements in the real-time road condition information; The determining the parking position according to the real-time road condition information, the map information and the target machine learning model includes: And determining the parking position according to the updated map information and the target machine learning model.
  4. 4. A method according to any one of claims 1 to 3, further comprising: Cyclically performing a parking position determination process until the vehicle stops running; The dock location determination process includes: acquiring real-time road condition information of the target area at the current moment; And determining the parking position of the vehicle in the target area at the current moment according to the real-time road condition information and the target machine learning model.
  5. 5. A parking position determining apparatus of a vehicle, characterized by comprising: The first determining module is used for determining a target area according to a target position of the vehicle, and the maximum distance between the target area and the target position is smaller than a distance threshold; The first acquisition module is used for acquiring real-time road condition information of the target area at the current moment, wherein the real-time road condition information comprises at least one road element; The second determining module is used for determining the parking position of the vehicle in the target area at the current moment according to the real-time road condition information and the target machine learning model; The apparatus further comprises: The second acquisition module is used for acquiring map information of the target area at the current moment, wherein the map information comprises at least one road element; The target area comprises a plurality of candidate positions, the second determining module comprises a determining unit and a parking position obtaining unit, wherein the determining unit is used for determining initial candidate position sets corresponding to road elements in the real-time road condition information and the map information respectively, the initial candidate position sets comprise at least one candidate position in the plurality of candidate positions, merging the initial candidate position sets corresponding to all road elements in the real-time road condition information and the map information respectively to obtain the candidate position sets, obtaining data sets corresponding to candidate positions in the candidate position sets according to the road elements corresponding to candidate positions in the real-time road condition information and the map information respectively, and inputting the data sets corresponding to the candidate positions in the candidate position sets into the target machine learning model to obtain the parking position output by the target machine learning model.
  6. 6. The apparatus of claim 5, wherein the real-time traffic information comprises at least one road element selected from the group consisting of a travelable area, a vehicle, a roadblock, a pedestrian, a railing, a water accumulation area, a silt area, and a pothole area.
  7. 7. The apparatus of claim 5, wherein the apparatus further comprises: The updating module is used for updating the map information by utilizing the real-time road condition information to obtain updated map information, wherein the updated map information comprises road elements in the real-time road condition information; The determining unit is specifically configured to determine the parking position according to the updated map information and the target machine learning model.
  8. 8. The apparatus according to any one of claims 5 to 7, further comprising: A circulation module configured to circulate execution of a stop position determination process until the vehicle stops traveling; The dock location determination process includes: acquiring real-time road condition information of the target area at the current moment; And determining the parking position of the vehicle in the target area at the current moment according to the real-time road condition information and the target machine learning model.
  9. 9. A parking position determining apparatus of a vehicle, characterized by comprising: One or more processors; A memory for storing one or more computer programs or instructions; When executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1 to 4.
  10. 10. A computer readable storage medium comprising a computer program or instructions which, when executed on a computer, cause the computer to perform the method of any of claims 1 to 4.
  11. 11. A computer program product, characterized in that the computer program product comprises computer program code which, when run on a computer, causes the computer to perform the method of any of claims 1 to 4.
  12. 12. A vehicle, characterized in that the vehicle comprises a control system and a parking position determining apparatus of the vehicle according to any one of claims 5 to 8; the vehicle parking position determining device is used for determining the parking position of the vehicle in a target area; The control system is configured to control the vehicle to park based on the determined parking position.

Description

Vehicle parking position determining method and device and vehicle Technical Field The embodiment of the application relates to the field of automatic driving, in particular to a vehicle parking position determining method and device and a vehicle. Background With the development of computer technology, the application of autopilot technology is becoming more and more widespread. In an autopilot scenario, the vehicle may automatically park to get the user on and off. In the existing scheme, when a user needs to get on or off the vehicle, a driving instruction carrying a target position can be sent to the vehicle, and the vehicle determines the target position according to the received driving instruction. The vehicle then travels to the destination location and stops at the destination location to enable the user to get on and off the vehicle at the destination location. However, the destination location may have an obstacle or the road surface condition of the destination location is poor (for example, there is water accumulation, silt or a deep pothole area), so that the vehicle cannot be parked or the convenience of a user to get on or off the vehicle after parking is poor. Disclosure of Invention The application provides a method and a device for determining the parking position of a vehicle, and the vehicle, so that the vehicle can park at the determined parking position and a user can get on or off the vehicle at the determined parking position more conveniently and safely. The application provides a method for determining a parking position of a vehicle, which comprises the steps of determining a target area according to a target position of the vehicle, wherein the maximum distance between the target area and the target position is smaller than a distance threshold value, acquiring real-time road condition information of the target area at the current moment, wherein the real-time road condition information comprises at least one road element, and determining the parking position of the vehicle in the target area at the current moment according to the real-time road condition information and a target machine learning model. According to the method, the parking position of the vehicle in the target area at the current moment is determined according to the real-time road condition information and the target machine learning model, and the change condition of the road condition is considered in the process of determining the parking position, so that the vehicle can park at the determined parking position, and a user can get on or off the vehicle at the determined parking position more conveniently and safely. The target machine learning model is obtained by training data and obtaining rules and essence of the data by using an algorithm. Real-time traffic information generally includes a large variety of road elements, and the amount of information is complex. The target machine learning model is capable of processing a wide variety of road elements to accurately and efficiently determine an optimal stop position from among a plurality of candidate positions. Specifically, the target machine learning model can adaptively obtain the importance of various road elements in a plurality of road elements and the redundancy among the plurality of road elements according to training labels in the training process. The target machine learning model obtained through training can accurately obtain the importance of various road elements corresponding to each candidate position and the redundancy among the various road elements, and therefore the optimal parking position can be determined and output from the plurality of candidate positions according to the importance of the various road elements corresponding to each candidate position and the redundancy among the various road elements. The target machine learning model may include at least one of a visual transformation (Vision Transformers) model, a convolutional neural network (Convolutional Neural Networks, CNN) model, a graph transformation (Graph Transformers) model, and a graph neural network (Graph Neural Network, GNN) model, among others. The target area is a vicinity of the destination location, and may or may not include the destination location. The target area may be a circular area or a rectangular area or the like centered on the destination location as an example. The destination location may be determined by the vehicle based on the received driving instructions. The user may send the driving instruction through an application running on a peripheral device or a terminal device (e.g., a mobile phone, a computer, a bracelet, etc.). In one possible implementation, the real-time road condition information includes at least one road element selected from the group consisting of a drivable area, a vehicle, a roadblock, a pedestrian, a railing, a water accumulation area, a silt area, and a hollow area. The road elements included in the real-time traffi