A Lane Keeping Method Based on Machine Learning

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...

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.

Images