Development of a real-time prediction model of driver behavior at intersections using kinematic time series data

Bayesian additive regression trees and the General BART model

“…We next present another illustration of BART on a real example, but this time with a binary outcome. In the work of Tan et al, 51 the authors were interested in predicting whether a human-driven vehicle would stop at an intersection before making a left turn. Left turns are important in countries with right side driving because most vehicle conflicts including crashes at intersections occur during left turns.…”

“…Accurate predictions about whether a human-driven vehicle would stop before executing a left turn could help driverless vehicles improve decision-making at intersections. More details about this data set can be found in the work of Tan et al 51 In brief, the data comes from the Integrated Vehicle-Based Safety System study conducted by Sayer et al 52 This study collected driving data from 108 licensed drivers in Michigan between April 2009 and April 2010. Each driver drove one of the 16 research vehicles fitted with various recording devices to capture the vehicle dynamics while the subject is driving on public roads for 12 days.…”

“…For this example, we focused on the vehicle speed at 50, 51, … , 56 meters away from the center of an intersection and whether we could utilize this vehicle dynamic to predict whether the driver would stop (vehicle speed < 1 m/s) in the future (0, 1, … , 49 meters from the center of an intersection). Similar to the work of Tan et al, 51 we performed a principal components analysis on the vehicle speeds (50, 51, … , 56 meters) and took the first 3 principal components (PCs) as the predictors. Tan et al 51 took the first 3 PCs as predictors because they found that using the first 3 PCs as predictors improved prediction performance compared to using the original vehicle speeds.…”

A Hybrid Approach for Turning Intention Prediction Based on Time Series Forecasting and Deep Learning

“…We know from the literature that when vehicles approach an intersection, the historical information hidden in the vehicle’s motion parameters often reflects the driver’s turning intention, and previous information often has a considerable impact on the recognition result [ 15 , 40 , 43 ]. Therefore, it is preferred to use a model that considers the behavioral characteristics of the vehicle for an extended period before approaching the intersection to detect the turning behavior.…”

“…When the driver’s destination is unknown, it is difficult to predict the turn behavior, similar to navigation software. However, different drivers have different driving preferences and characteristics, and the effects of their actions on the kinematics of the vehicle often reflect the driver’s intentions [ 15 , 43 ]. We can estimate the driver’s future activity from motion information and trajectory information of the vehicle approaching the intersection for a certain period of time, or recognize the activity in time when the vehicle exhibits early turning behavior characteristics.…”