Adaptive lane-changing trajectory planning method for autonomous vehicles

Abstract

The invention discloses a method for planning an adaptive lane-changing trajectory of an automatic driving vehicle. First, a section of longitudinal lane-changing trajectory is added before the original lane-changing trajectory, so that the vehicle can adjust its own speed and the relative position with the target lane on the longitudinal trajectory. Then move laterally to change lanes to ensure the safety and efficiency of the current vehicle lane change; second, the model adds a lane change return trajectory. Considering the vehicle's lane-changing condition does not meet the safety constraints during the lane-changing process, planning the trajectory of the vehicle safely returning to the current lane; The impact of safety during lane changing, and then the concept of vehicle conflict area is proposed to ensure the safety constraints of vehicles after completing lane changing. Compared with the prior art, the positive effect of the present invention is: to realize the automatic adjustment of the automatic driving vehicle to the change of the traffic environment during the lane change process, and improve the efficiency and safety of the lane change.

Description

technical field [0001] The invention relates to a method for planning an adaptive lane-changing trajectory of an automatic driving vehicle. Background technique [0002] In recent years, autonomous driving technology has received widespread attention from the society and is considered to be an important technology to alleviate traffic congestion, reduce traffic accidents and reduce environmental pollution. Among them, vehicle lane change is one of the basic operations of vehicle driving, and it is also an important cause of traffic accidents. According to the report of China Highway Traffic Safety Administration, more than 60% of expressway traffic accidents are related to vehicle lane change. Therefore, the lane-changing trajectory of autonomous driving vehicles is the focus of autonomous driving research, and it is also a technical difficulty to be solved. [0003] Existing research methods for lane-changing trajectories of autonomous vehicles include geometric curve meth...

AI Technical Summary

Problems solved by technology

First, the model has too strong assumptions about the environment of vehicles changing lanes

In the above study, it is assumed that the speed of the surrounding vehicles is constant during the lane change process, which does not match the real driving environment

Second, the lane-changing vehicles in the current research cannot respond to changes in the state of surrounding vehicles in real time, that is, they cannot adjust the speed of vehicles and the distance between vehicles in real time, so these models may fail in real traffic environments

However, the model also has some shortcomings

First of all, the model only considers the impact of the target lane vehicle on the lane-changing vehicle, ignoring the influence of the current lane vehicle on the lane-changing vehicle, which is inconsistent with the actual lane-changing scene; second, the model only studies the lane-changing vehicle from The lateral displacement process from the current lane to the target lane, ignoring the adjustment of the lane-changing vehicle during the lateral displacement process

Third, the collision avoidance model is not perfect. The collision avoidance model in this literature only considers the vehicle lane change completion position, the safety gap between the lane change vehicle and the surrounding vehicles, and ignores the safety of the vehicle during the lane change process.

Images