Traffic flow track generation method, vehicle and transverse control method and system

Abstract

The invention discloses a traffic flow track generation method based on multiple target vehicle positions, a vehicle and a transverse control method and system of an automatic driving vehicle. The method comprises the steps of firstly obtaining a plurality of target vehicles in front according to a front region, then carrying out lane attribute classification on the target vehicles, generating a candidate target vehicle set of each lane after the vehicles are classified according to the lanes, adding the candidate target vehicle set of each lane into the corresponding lane position point set of the previous frame respectively, converting the position point coordinates in the corresponding lane position point set of the previous frame into a current vehicle coordinate system, then judging whether the automatic driving vehicle changes the lane or not, and updating the historical positions of the target vehicles according to the judgment result; and finally, using the positions of the multiple target vehicles in each lane for fitting to generate the traffic flow tracks of each lane. According to the traffic flow track generation method based on the multiple target vehicle positions, the stable transverse control of the automatic driving vehicles can be realized under the conditions of traffic jam, no lane line and the like, the transverse control effect is improved, and the safety is high.

Description

technical field [0001] The invention relates to the technical field of automatic driving control, in particular to a method for generating traffic flow trajectories based on the positions of multiple target vehicles, a lateral control method and system for vehicles and automatic driving vehicles. Background technique [0002] In the automatic driving system, the lateral control of the automatic driving vehicle generally generates the center trajectory line through the lane line, so that the vehicle can drive according to the trajectory to achieve the lateral control effect. It is highly dependent on the lane line for lateral control. When the lane line is not detected in traffic jam conditions, or the quality of the lane line is too poor, it will face the problem of exiting the lateral control, which will affect the automatic driving function. In order to solve the problem caused by no lane line, you can use the track of the vehicle in front to achieve lateral control. The t...

AI Technical Summary

Problems solved by technology

It is highly dependent on lane lines for lateral control. When the lane line is not detected in traffic jam conditions, or the quality of the lane line is too poor, it will face the problem of exiting the lateral control, which will affect the automatic driving function.

In order to solve the problem caused by no lane line, you can use the trajectory of the vehicle in front to achieve lateral control. The traditional technical method of using the trajectory of the vehicle in front to achieve lateral control without lane lines uses the trajectory of the vehicle in front for tracking control. During the process, the trajectory of the vehicle in front is completely controlled by the vehicle in front. If the trajectory of the vehicle in front is unstable or the vehicle in front is not recognized for a short time, the control effect of the vehicle will be seriously affected. What is more serious is that if the current vehicle changes lanes during driving, the vehicle in front will be affected. Cars will also follow and change lanes. Under traffic jam conditions, following the vehicle in front and changing lanes will easily cause traffic accidents and increase traffic pressure

Images