Search

CN-121989954-A - Method for predicting vehicle pose, device for predicting vehicle pose and vehicle

CN121989954ACN 121989954 ACN121989954 ACN 121989954ACN-121989954-A

Abstract

The application provides a method for predicting vehicle pose, a device for predicting vehicle pose and a vehicle, and relates to the technical field of vehicles. The method comprises the steps of obtaining a current environment image and a current yaw rate of a vehicle, predicting a first pose of the vehicle at the next time of the current time based on the current environment image, predicting a second pose of the vehicle at the next time of the current time based on the current yaw rate, adjusting the first pose based on the second pose to obtain an adjusted first pose, and determining the adjusted first pose as a pose corresponding to the vehicle when the vehicle is at a target driving position, wherein the target driving position is a driving position obtained based on the time difference between the current time and the next time of the current time and the current speed of the vehicle. Based on the scheme, the accuracy of the predicted vehicle pose can be improved in the running process of the vehicle.

Inventors

  • LI KEJING

Assignees

  • 毫末智行科技有限公司

Dates

Publication Date
20260508
Application Date
20241106

Claims (10)

  1. 1. A method of predicting vehicle pose, the method comprising: Acquiring a current environment image and a current yaw rate of a vehicle; Predicting a first pose of the vehicle at a time next to a current time based on the current environmental image, and predicting a second pose of the vehicle at the time next to the current time based on the current yaw rate; Adjusting the first pose based on the second pose to obtain an adjusted first pose; And determining the adjusted first pose as a pose corresponding to the vehicle in a target running position, wherein the target running position is a running position obtained based on the time difference between the current moment and the next moment of the current moment and the current speed of the vehicle.
  2. 2. The method according to claim 1, wherein the method further comprises: acquiring a current pose corresponding to the current running position of the vehicle; The predicting, based on the current yaw rate, a second pose of the vehicle at a time next to the current time, includes: Integrating the current yaw rate to obtain a yaw angle at the current moment and a yaw angle at the next moment; And obtaining the second pose based on the yaw angle at the current moment, the yaw angle at the moment next to the current moment and the current pose.
  3. 3. The method of claim 2, wherein the deriving the second pose based on the yaw angle at the current time, the yaw angle at a time next to the current time, and the current pose comprises: Obtaining a first yaw angle difference value of the vehicle based on the yaw angle of the current moment and the yaw angle of the moment next to the current moment; determining a first pose difference of the vehicle based on the first yaw angle difference; And multiplying the first pose difference value by the current pose to obtain the second pose.
  4. 4. The method of claim 2, wherein adjusting the first pose based on the second pose results in an adjusted first pose, comprising: predicting a second yaw angle difference between the current time and a next time of the current time based on the second pose and the current pose; Determining a second pose value corresponding to the second yaw angle difference value; and adjusting the first pose based on the second pose difference value to obtain the adjusted first pose.
  5. 5. The method of claim 4, wherein adjusting the first pose based on the second pose value results in an adjusted first pose, comprising: multiplying the first pose by the second pose difference value to obtain a first product; and determining the first product as the adjusted first pose.
  6. 6. The method according to any one of claims 1 to 5, characterized in that the running position obtained based on the time difference between the current time and the next time of the current time and the current vehicle speed of the vehicle includes: The current vehicle speed is converted into a first vehicle speed, wherein the first vehicle speed is used for representing the vehicle speed corresponding to the current vehicle speed in a world coordinate system; And obtaining the target running position based on the first vehicle speed, the time difference and the current running position of the vehicle.
  7. 7. The method of claim 6, wherein the deriving the target travel position based on the first vehicle speed, the time difference, and a current travel position of the vehicle comprises: Obtaining a second product by multiplying the first vehicle speed by the time difference; And adding the second product and the current running position to obtain the target running position.
  8. 8. The method according to any one of claims 1 to 5, characterized in that the current yaw rate is acquired by a single-axis inertial measurement unit in the vehicle.
  9. 9. An apparatus for predicting a vehicle pose, the apparatus comprising: The acquisition module is used for acquiring a current environment image and a current yaw rate of the vehicle; The prediction module is used for predicting a first pose of the vehicle at the moment next to the current moment based on the current environment image, and predicting a second pose of the vehicle at the moment next to the current moment based on the current yaw rate; the adjusting module is used for adjusting the first pose based on the second pose to obtain an adjusted first pose; and the determining module is used for determining the adjusted first pose as the corresponding pose of the vehicle at a target running position, wherein the target running position is a running position obtained based on the time difference between the current moment and the next moment of the current moment and the current speed of the vehicle.
  10. 10. A vehicle, characterized in that the vehicle comprises: A memory for storing executable program code; A processor for calling and running the executable program code from the memory, causing the vehicle to perform the method of any one of claims 1 to 8.

Description

Method for predicting vehicle pose, device for predicting vehicle pose and vehicle Technical Field The application relates to the technical field of vehicles, in particular to a method for predicting vehicle pose, a device for predicting vehicle pose and a vehicle in the technical field of vehicles. Background During the running process of the vehicle, the real-time position of the vehicle can be obtained, and the pose of the vehicle can be predicted through the obtained real-time position. And then the position of the vehicle in the environment is obtained through the pose of the vehicle, so that the running safety of the vehicle is ensured. In the related art, the real-time position of the vehicle can be obtained through a global satellite positioning system (Global Positioning System, GPS), but the GPS is easy to be interfered by signal reflection, atmospheric conditions or infrastructure and the like, and the GPS has lower positioning precision, so that the collected real-time position of the vehicle is easy to deviate, and the predicted vehicle pose is caused to deviate in the running process of the vehicle, so that the running safety of the vehicle is reduced. Therefore, how to improve the accuracy of the predicted vehicle pose during the running of the vehicle is a current urgent problem to be solved. Disclosure of Invention The application provides a method for predicting vehicle pose, a device for predicting vehicle pose and a vehicle, the method can improve the accuracy of the predicted vehicle pose in the running process of the vehicle. In a first aspect, the present application provides a method of predicting vehicle pose, the method comprising: The method comprises the steps of obtaining a current environment image and a current yaw rate of a vehicle, predicting a first pose of the vehicle at the next time of the current time based on the current environment image, predicting a second pose of the vehicle at the next time of the current time based on the current yaw rate, adjusting the first pose based on the second pose to obtain an adjusted first pose, and determining the adjusted first pose as a pose corresponding to the vehicle at a target running position, wherein the target running position is a running position obtained based on the time difference between the current time and the next time of the current time and the current speed of the vehicle. In the embodiment of the application, when the current environment image and the current yaw rate of the vehicle are acquired, one pose of the vehicle at the time next to the current time (may be referred to as a "first pose") may be predicted from the current environment image of the vehicle, and the other pose of the vehicle at the time next to the current time (may be referred to as a "second pose") may be predicted from the current yaw rate of the vehicle. When the first pose and the second pose are predicted, the first pose can be adjusted through the second pose, and the adjusted first pose is obtained, namely, the adjusted first pose is obtained after being restrained through the second pose. And compared with the situation that the first pose is directly determined as the vehicle pose at the corresponding running position at the next moment of the current moment, the deviation of the predicted vehicle pose can be reduced, so that the accuracy of the predicted vehicle pose is improved in the running process of the vehicle. With reference to the first aspect, in certain implementations of the first aspect, the method further includes: The method comprises the steps of obtaining a current pose corresponding to a current running position of a vehicle, predicting a second pose of the vehicle at the next time of the current time based on the current yaw rate, and obtaining the second pose based on the yaw angle at the current time, the yaw angle at the next time of the current time and the current pose. In the embodiment of the application, when the current pose corresponding to the current running position of the vehicle is obtained, the second pose of the vehicle is obtained through the current pose of the vehicle, the yaw angle of the vehicle at the current moment and the yaw angle of the vehicle at the next moment of the current moment, so that the predicted second pose of the vehicle is more accurate, and the finally predicted pose of the vehicle at the running position corresponding to the next moment of the current moment is also more accurate on the basis of the more accurate second pose, thereby improving the accuracy of the predicted pose of the vehicle in the running process of the vehicle. With reference to the first aspect and the foregoing implementation manner, in some implementation manners of the first aspect, the obtaining the second pose based on the yaw angle at the current time, the yaw angle at a time next to the current time, and the current pose includes: The method comprises the steps of obtaining a first yaw angle dif