Vehicle intention prediction method and related device

A technology of intention and vehicle, applied in the field of vehicle intention prediction method and related devices, which can solve the problems of limited representation ability, difficulty in accurately predicting the driving intention of the target vehicle, impractical steering intention, etc., to avoid overlapping, easy to learn, and high prediction accuracy Effect

Active Publication Date: 2022-04-05
HUAWEI TECH CO LTD
View PDF8 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Such methods require artificially designed features, have limited representation capabilities in complex scenes, and output steering intentions are not practical in some complex intersections
[0007] It can be seen that the current prediction method is difficult to accurately predict the driving intention of the target vehicle in some complex intersection situations

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
  • Vehicle intention prediction method and related device
  • Vehicle intention prediction method and related device
  • Vehicle intention prediction method and related device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0121] The embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application.

[0122] The inventor of the present application has found that there are still some problems when training a vehicle intention prediction model by a deep learning-based method in the prior art, such as:

[0123] 1) Low coding efficiency: The above method adopts a non-fixed coordinate system, that is, the position and orientation of the target vehicle at the current moment are used as the coordinate reference, and each frame of data needs to be rasterized separately, which takes a lot of time.

[0124] 2) Insufficient generalization performance: The above method converts the target vehicle intention prediction problem into a twelve-element classification problem. The twelve-element category corresponds to different sectors in the target vehicle coordinate system. In practical applications, the target vehicle exit do...

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 invention provides a vehicle intention prediction method and a related device, and the method comprises the steps: obtaining an intention prediction model which is used for predicting the driving intention of a vehicle in all directions of an intersection; performing rasterization coding on the target driving data to obtain a target image sample, wherein different types of data in the target driving data and data corresponding to different exit directions are respectively coded into different data channels in one image sample; and inputting the target image sample into the intention prediction model to obtain the intention probability of driving of the second vehicle in each direction of the intersection. According to the embodiment of the invention, the intention prediction accuracy of the vehicle in a complex road condition can be improved.

Description

technical field [0001] The invention relates to the technical field of Internet of Vehicles, and in particular, to a vehicle intention prediction method and a related device. Background technique [0002] With the development of intelligent driving technology, intelligent vehicles have become the key research targets of major manufacturers. Intelligent driving includes assisted driving and automatic driving, and the key technologies for its realization are: positioning, perception, prediction, planning control, etc. Vehicle intention prediction refers to predicting the behavior intention of the target vehicle according to the target vehicle state at the current moment and historical moment. For example, in the forward road scene, the vehicle intention can include lane keeping, left lane change, right lane change, etc., in the intersection scene The intent to get off the vehicle may include going straight, turning left, turning right, and U-turn. On urban roads, real-time, ...

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 Applications(China)
IPC IPC(8): G08G1/01G08G1/0967G08G1/0968G08G1/0969G08G1/16G06F16/29G06N3/04G06T9/00G06T11/40
Inventor 范时伟李飞李向旭
Owner HUAWEI TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap