01623751

Component

This paper compares Fuzzy Inference System (FIS), Support Vector Machine (SVM) and MultiLayer Feed-forward neural network (MLF) in the modeling of driver’s decision when making discretionary lane changing move on freeways. The FIS, SVM and MLF models use the same four inputs: the gap (distance) between the subject vehicle and the preceding vehicle in the original lane, the gap between the subject vehicle and the preceding vehicle in the target lane, the gap between the subject vehicle and the following vehicle in the target lane, and the distance between the preceding and following vehicles in the target lane. The models produce a binary “yes, change lane” or “no, do not change lane” decision. The FIS, SVM and MLF models were trained and then tested with the Next Generation SIMulation (NGSIM) vehicle trajectory data. The results of the comparative evaluation have shown that the FIS has the highest accuracies in making correct lane changing decisions. It recommends “yes, change lane” with 82.2% accuracy, and “no, do not change lane” with 99.5% accuracy. These accuracies are also better than the same performance measures given by the TRANSMODELER’s gap acceptance model.

This paper was sponsored by TRB committee AHB45 Standing Committee on Traffic Flow Theory and Characteristics.

01618707

17-00112

English

21p

2017

Transportation Research Board 96th Annual Meeting

Digital/other

Figures; References (22) ; Tables

Automatic headway control; Car following; Decision making; Drivers; Fuzzy algorithms; Mathematical models; Vehicle trajectories

Highways; Safety and Human Factors

Transportation Research Board Annual Meeting 2017 Paper #17-00112

TRIS, TRB, ATRI

Dec 8 2016 9:57AM