How to choose features to improve prediction performance in lane-changing intention: A meta-analysis

TL;DR

This paper conducts a meta-analysis to evaluate how different feature categories affect the accuracy of predicting lane-changing intentions, highlighting vehicle features as most effective.

Contribution

It systematically assesses the effectiveness of various feature combinations in lane-changing intention prediction through meta-analysis, providing insights for future research.

Findings

Vehicle input features outperform environment and driver features.

Combining multiple feature types can improve prediction accuracy.

Meta-analysis reveals heterogeneity and publication bias in existing studies.

Abstract

Lane-change is a fundamental driving behavior and highly associated with various types of collisions, such as rear-end collisions, sideswipe collisions, and angle collisions and the increased risk of a traffic crash. This study investigates effectiveness of different features categories combination in lane-changing intention prediction. Studies related to lane-changing intention prediction have been selected followed by strict standards. Then the meta-analysis was employed to not only evaluate the effectiveness of different features categories combination in lane-changing intention but also capture heterogeneity, effect size combination, and publication bias. According to the meta-analysis and reviewed research papers, results indicate that using input features from different types can lead to different performances. And vehicle input type has a better performance in lane-changing intention, prediction, compared with environment or even driver combination input type. Finally, some potential future research directions are proposed based on the findings of the paper.