Predicting human-driving behavior to help driverless vehicles drive: random intercept Bayesian additive regression trees

The development of driverless vehicles has spurred the need to predict human driving behavior to facilitate interaction between driverless and human-driven vehicles. This interaction is possible when both driverless and human-driven vehicles are connected through vehicle-to-vehicle communication. Predicting human driving movements can be challenging, and poor prediction models can lead to accidents between the driverless and human-driven vehicles. We used the vehicle speed obtained from a naturalistic driving dataset to predict whether a human-driven vehicle would stop before executing a left turn. To handle the possible non-linear effects and interactions, we used Bayesian additive regression trees (BART). However, BART assumes independent observations, but our dataset consists of multiple observations clustered by driver. Although methods extending BART to clustered or longitudinal data are available, they lack readily available software and can only be applied to clustered continuous outcomes. We extend BART to handle correlated binary observations by adding a random intercept and used a simulation study to investigate its properties. We then successfully implemented our proposed model to our clustered dataset and found substantial improvements in prediction performance compared to BART, BART adjusted for driver level effects, random intercept linear logistic regression, and linear logistic regression.

Keywords

Bayesian additive regression trees, classification and regression trees, driverless vehicles, hierarchical models, longitudinal prediction, transportation statistics

Full Text (PDF format)

This work was supported jointly by Dr. Michael Elliott and an ATLAS Research Excellence Program project awarded to Dr. Carol Flannagan. This work was also funded in part by the Toyota Class Action Settlement Safety Research and Education Program.

Published 19 September 2018