A lane-changing decision-making method, device, storage medium and intelligent vehicle for an intelligent vehicle

Abstract

The embodiment of the present application relates to a smart car lane change decision method, device, storage medium and smart car. The intelligent vehicle lane change decision method includes: determining the current environment information of the intelligent vehicle, the environmental information including trajectory information and lane information; based on the first decision rule and the environmental information, generating a first lane change decision; Describe the first lane-changing decision and the second decision-making rule to generate the second lane-changing decision. Based on this smart vehicle lane-changing decision method, different lane-changing decisions are coupled, and the decision rules between different lane-changing decisions are decoupled, thereby reducing decision rules and avoiding a decrease in decision-making efficiency; at the same time, different lane-changing decisions handle different Improve the rationality of lane changing for smart vehicles.

Description

technical field [0001] The embodiment of the present application relates to the technical field of automatic driving, and specifically relates to a method, device, storage medium and smart car for making a lane change decision for a smart car. Background technique [0002] With the development of vehicle intelligent technology, intelligent vehicle automatic driving technology has gradually become a hot spot in the field of vehicle research. Smart cars need to face complex road environments during driving. How to make reasonable lane-changing decisions in complex and changeable environments has always been a difficult problem in the field of smart car technology. [0003] The existing lane-changing decision-making methods for intelligent vehicles can be roughly divided into two categories: rule-based lane-changing decision-making and learning-based lane-changing decision-making. Rule-based lane-changing decisions generally formulate lane-changing rules based on traffic rules...

AI Technical Summary

Problems solved by technology

This type of method has good stability and is easy to implement, but due to the need to consider various environmental factors, the number of rules formulated will become larger and larger, all states will be coupled together, and the finite state machine will become more and more bloated, which will lead to a decrease in decision-making efficiency; At the same time, due to the functional correlation or similarity between some lane-changing decisions, frequent lane-changing may occur

Images