Lane change strategy analysis and recognition for intelligent driving systems based on random forest

作者：

Highlights：

• A recognition model of lane change strategy was established based on random forest.

• On-road experiments were executed to collect the three kinds of lane change strategy.

• Recognition accuracy under 3 input parameters was 88.78% with time window as 1.2 s.

• Recognition time and accuracy of the RF model were better than that of GA-SVM model.

摘要

•A recognition model of lane change strategy was established based on random forest.•On-road experiments were executed to collect the three kinds of lane change strategy.•Recognition accuracy under 3 input parameters was 88.78% with time window as 1.2 s.•Recognition time and accuracy of the RF model were better than that of GA-SVM model.

论文关键词：Lane change strategy recognition,Random forest,Support vector machine,Intelligent driving system

论文评审过程：Received 21 February 2020, Revised 6 August 2021, Accepted 14 August 2021, Available online 20 August 2021, Version of Record 23 August 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115781