Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and device for correcting vehicle pose

A vehicle and pose technology, applied in the field of automatic driving, can solve problems such as the inability to automatically drive vehicle positioning, and achieve the effect of improving robustness

Active Publication Date: 2022-05-13
BEIJING MOMENTA TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present invention discloses a method and device for correcting the pose of a vehicle, which solves the problem that the self-driving vehicle cannot be positioned when the perception model information is missing, and improves the robustness of the positioning system

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and device for correcting vehicle pose
  • Method and device for correcting vehicle pose
  • Method and device for correcting vehicle pose

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0070] see Figure 1a , Figure 1a It is a schematic flowchart of a vehicle pose correction method provided by an embodiment of the present invention. This method is applied to automatic driving, and is typically applied to scenarios where the automatic driving vehicle cannot be positioned due to lack of perception model information. The method can be performed by a method device for correcting vehicle pose, which can be realized by means of software and / or hardware, and can generally be integrated in vehicle-mounted terminals such as a vehicle-mounted computer and a vehicle-mounted industrial personal computer (IPC). The present invention implements Examples are not limited. like Figure 1a As shown, the pose correction process provided by the embodiment of the present invention occurs after the high-precision map is initialized, from the vehicle entering the map positioning algorithm to leaving the map positioning algorithm. , pitch angle, roll angle and heading correction r...

Embodiment 2

[0085] see Figure 2a , Figure 2a It is a schematic flow chart of a method for correcting vehicle heading provided by an embodiment of the present invention. This embodiment is optimized on the basis of the above embodiments, and further corrects the heading of the vehicle. like Figure 2a As shown, the method includes:

[0086] 210. According to the current position of the vehicle provided by the preset positioning device, filter out the first lane line in the lane where the vehicle is currently located and the current position within a set distance range.

[0087] 220 . Select a second lane line whose direction is consistent with the driving direction of the vehicle from the first lane line.

[0088] In this embodiment, when the vehicle is driving on a road section of the high-precision map, it usually travels along the lane line, so the track direction of the lane line can be used to correct the heading of the vehicle. Generally, when the vehicle is turning or changin...

Embodiment 3

[0098] Figure 3a A schematic flow chart of a vehicle body elevation correction method provided by an embodiment of the present invention, as Figure 3a As shown, the correction methods for the height of the vehicle body include:

[0099] 310. According to the current position of the vehicle provided by the preset positioning device, filter out the first lane line in the lane in which the vehicle is currently located and the current position within a set distance range.

[0100] When the vehicle passes through the main and auxiliary roads, elevated roads and other special circumstances, there may be multiple layers of road sections at the same location, so it needs to be distinguished, the current road section where the vehicle is located is filtered out, and the first lane within a certain range of the current location of the vehicle is cut out Wire.

[0101] 320. Based on the preset navigation map, determine the average value of the elevation of the first lane line.

[01...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The embodiment of the present invention discloses a method and device for correcting vehicle pose. The method includes: according to the current position of the vehicle provided by the preset positioning device, filter out the first vehicle in the lane where the vehicle is currently located and the current position that meet the set distance range. Lane line; discretize the first lane line to obtain a plurality of discrete points of the lane line, and fit the ground plane where the vehicle at the current position is based on the plurality of discrete points of the lane line; use the normal vector of the ground plane as the vehicle body The actual normal vector is used to correct the roll angle and pitch angle of the vehicle body by using the difference between the actual normal vector and the current vehicle body normal vector. By adopting the above-mentioned technical solution, the problem that the self-driving vehicle cannot be positioned when the perception model information is missing is solved, and the robustness of the positioning system is improved.

Description

technical field [0001] The invention relates to the technical field of automatic driving, in particular to a method and device for correcting vehicle pose. Background technique [0002] In the field of autonomous driving, high-precision positioning is crucial. In recent years, the achievements of deep learning and other technologies have greatly promoted the development of image semantic segmentation and image recognition, which provides a solid foundation for high-precision maps and high-precision positioning. [0003] In the usual unmanned positioning scheme, the use of high-precision maps generally relies on the perception model provided by deep learning, and the location of the vehicle is determined by matching and checking the perception model information and high-precision map information. That is, the high-precision map information is projected to the image plane through the pinhole camera model and compared with the information provided by the deep learning percepti...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G01C21/00G01C21/28G01C25/00
CPCG01C25/00G01C21/005G01C21/28G01C21/00G05D1/02G01C21/30
Inventor 侯政华杜志颖管守奎
Owner BEIJING MOMENTA TECH CO LTD