A vehicle intelligent driving control method

Abstract

The invention relates to the field of automobile driving safety, in particular to a vehicle intelligent driving control method, which comprises the following steps: in the vehicle driving process, using a laser radar to obtain the reflection point information of the road environment in front of the vehicle; determining a road boundary according to the reflection point information; determining a lane line according to the reflection point information or a road boundary; obtaining the curvature of the lane centerline according to the road boundary and the lane line fitting the lane centerline; calculating a steering wheel rotation angle to be adjusted for driving the vehicle along the lane centerline according to the curvature of the lane centerline. Laser radar is used to collect data and calculate the curvature of the road ahead, and the curvature is used to control the lateral motion of the vehicle. It has the advantages of high reliability and can improve the driving comfort, especially suitable for the automatic driving of the expressway, and can also enhance the existing adaptive cruise system.

Description

technical field [0001] The invention relates to the field of automobile driving safety, in particular to a vehicle intelligent driving control method. Background technique [0002] Traditional adaptive cruise control can only control the speed of the vehicle, but cannot control the direction. At present, vehicles with LKA (Lane Keeping Assistance, Lane Keeping Assistance) are implemented by using cameras to detect lane lines. There are many shortcomings in using cameras to detect lane lines. For example, cameras are sensitive to light. , Lane line wear conditions can not be detected. Even if it can be detected, LKA needs to adjust the direction frequently to ensure that it does not cross the lane line, resulting in poor comfort, and can only achieve hands-off driving for a short time. [0003] At present, there are many methods for calculating the curvature of the road ahead. One is to identify the lane line by computer vision, then fit the lane line, and then use the plan...

AI Technical Summary

Problems solved by technology

[0002] Traditional adaptive cruise control can only control the speed of the vehicle, but cannot control the direction

At present, vehicles with LKA (Lane Keeping Assistance, Lane Keeping Assistance) are implemented by using cameras to detect lane lines. There are many shortcomings in using cameras to detect lane lines. For example, cameras are sensitive to light. , Lane line wear can not be detected

Even if it can be detected, LKA needs to adjust the direction frequently to ensure that it does not cross the lane line, resulting in poor comfort, and can only achieve hands-off driving in a short period of time

[0003] At present, there are many methods for calculating the curvature of the road ahead. One is to identify the lane line by computer vision, then fit the lane line, and then use the plane curve method to find the curvature. This method is highly dependent on the lane line. On the expressway that has been more than 5 years old, the traces of the lane lines are not obvious, and the lane lines are incomplete

Another thing is that computer vision is extremely sensitive to light. It cannot correctly identify the lane line at night, in rainy, snowy and foggy days, and it cannot recognize the lane line when the road is covered with water and snow.

In addition, the effective distance of the vision system is very short. Generally, a 1.3 million-pixel camera needs to achieve an error of less than 5%, and its effective distance is only about 50-60 meters. Identify lane lines

And the vision system is purely flat 2D, which cannot recognize the height change of the road, and the estimation accuracy of the distance is very low. This is the physical limitation of the vision system, and the accuracy of the distance estimation of the vision system cannot be improved by any means.

It can be seen that the reliability of the computer vision system is very low and the practicability is poor

The other is to use the camera or lidar of the self-vehicle to extract the turning features of the vehicle in front to calculate the road curvature. This method has low accuracy and the curvature data must be obtained with the vehicle in front.

Images