A method for establishing a lane-changing decision model for automatic driving in a hybrid driving environment

Abstract

The invention discloses a method for establishing a lane-changing decision model for automatic driving in a mixed driving environment, establishes a multi-step dynamic game lane-changing model of an automatic driving vehicle LV and a human-driven vehicle RV in a mixed driving environment, and designs a lane-changing model for the automatic driving vehicle nested game algorithm. The present invention first establishes a multi-step dynamic game framework, and the vehicles of both parties will decide the next action according to the opponent's strategy selection, and define the potential conflict points between the lane-changing vehicle and the vehicle behind the target lane, and based on the vehicle's initial information, strategy and game step Then, the two vehicles use their respective strategies and acceleration selection methods to conduct a dynamic game until the termination condition of lane change is met, so that the self-driving vehicle can It can also create lane-changing space by playing games with human-driven vehicles, and realize safe lane-changing.

Description

technical field [0001] The invention relates to a method for establishing a lane-changing decision model for automatic driving in a mixed driving environment. Background technique [0002] In recent years, autonomous driving technology has received more and more attention worldwide, and is considered to be an emerging technology that can subvert traditional transportation and plays an important role in solving traffic safety and traffic congestion problems. However, the transition from all human-driven vehicles on the current road to fully autonomous driving is bound to be a long-term process. During this process, the traffic environment is a mixed environment of human-driven and autonomous vehicles. Self-driving vehicles not only need to complete safe and efficient driving in a fully automatic driving environment, but also need to adapt to a mixed driving environment. [0003] According to the existing research on lane-changing decision-making for autonomous driving, the c...

AI Technical Summary

Problems solved by technology

[0006] At present, although there has been related research on this issue, this research cannot adjust its own strategy according to the actual strategy selection of human-driven vehicles, but only makes assumptions about the behavior of RVs by evaluating the aggressiveness of RV vehicles. , in the case of an error in the aggressiveness estimate, it may cause the LV to change lanes when the RV does not avoid, thus causing safety hazards

Images