A Lane Keeping Method Based on Machine Learning

A technology of lane keeping and machine learning, applied in the field of lane keeping based on machine learning, it can solve the problem of inability to realize the personalized design of the car owner, and achieve the effect of better accuracy and reducing the following error.

Active Publication Date: 2022-04-29
英博超算(南京)科技有限公司
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Existing vision-guided intelligent vehicles control the lateral movement of the lane according to a stereotyped control model during the automatic driving process. This stereotyped control model formulated according to traffic rules is relatively mature, but it cannot realize the personalized design of the driving behavior of the car owner.

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
  • A Lane Keeping Method Based on Machine Learning
  • A Lane Keeping Method Based on Machine Learning
  • A Lane Keeping Method Based on Machine Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention will be described in further detail below in conjunction with the accompanying drawings and embodiments.

[0039] refer to figure 1 , image 3 As shown, a machine learning-based lane keeping method in this embodiment provides a visual detection system, a steering execution system, and a lateral controller. The controller includes a feedforward controller and a feedback controller.

[0040] The lane keeping method includes a model building step and an automatic lateral control step. refer to image 3 , Figure 4 As shown, the model building steps include:

[0041] S10, the visual inspection system collects driving data of the car owner to construct a driving behavior habit database when the car owner is driving the vehicle, and the car owner's driving data is data representing the driving behavior and driving habits of the car owner driving the vehicle.

[0042] S20, the lateral controller constructs a mathematical model of driving behavior ha...

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 invention discloses a lane keeping method based on machine learning, and the key points of the technical scheme include a model building step and an automatic lateral control step. The model building steps include: S10, the vision detection system collects the driving data of the car owner to build a driving behavior habit database when the car owner is driving the vehicle; S20, the lateral controller builds a driving behavior habit mathematical model through machine learning according to the driving behavior habit database. The automatic lateral control steps include: S30, the visual detection system collects vehicle driving data in real time when the vehicle is automatically driven, and the lateral controller obtains the vehicle's expected corner angle according to the vehicle driving data and the mathematical model of driving behavior habits; S40, the steering execution system according to the vehicle's expected corner angle Lateral motion control for smart vehicles. The method can control the intelligent vehicle to imitate the driving behavior of the owner during the automatic driving process, and accurately, stably and smoothly realize the lane lateral motion control of the intelligent vehicle.

Description

technical field [0001] The present invention relates to the technical field of intelligent vehicle automatic driving, and more specifically relates to a lane keeping method based on machine learning. Background technique [0002] With the development of science and technology, self-driving cars have become an important development direction of future cars. Self-driving cars rely on artificial intelligence, visual computing, radar, monitoring devices, and global positioning systems to work together to allow computers to automatically and safely operate motor vehicles without any active human intervention. Self-driving vehicles can not only help improve people's travel convenience and travel experience, but also greatly improve the efficiency of people's travel. [0003] Existing vision-guided intelligent vehicles perform lane lateral motion control according to a stereotyped control model in the process of automatic driving. This stereotyped control model formulated accordin...

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): B60W60/00B60W30/12B60W50/00G06N20/00
CPCB60W60/0016B60W60/0013B60W30/12B60W50/00G06N20/00B60W2050/0029B60W2520/06B60W2520/10B60W2710/20
Inventor 枚元元王继贞田锋秦伦宋吉
Owner 英博超算(南京)科技有限公司
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