Self-driving vehicle self-adaptive lane changing track planning method

Abstract

The invention discloses a self-driving vehicle self-adaptive lane changing track planning method. Firstly, a section of longitudinal lane changing track is added before an original lane changing track, a vehicle is allowed to adjust own speed and the relative position between the vehicle and a target lane on the longitudinal track, then, transverse lane changing movement is carried out, and the safety and the efficiency of lane change of the current vehicle are guaranteed; secondly, a lane changing return track is added in the model; considering that when the lane changing condition of the vehicle does not meet the safety constraint in the lane changing process, a track for the vehicle to return to the current lane is planned; and thirdly, a new vehicle lane change collision avoidance algorithm is introduced into the model, according to the influence of the change of the body posture of the self-driving vehicle on the safety in the lane changing process, the concept of a vehicle conflict area is further provided, and the safety constraint after the vehicle completes lane change is guaranteed. Compared with the prior art, the method has the advantages that automatic adjustment of the self-driving vehicle to the change of the traffic environment in the lane changing process is achieved, and the lane changing efficiency and safety are improved.

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