Turn prediction at generalized intersections

Abstract

Navigating a car at intersections is one of the most challenging parts of urban driving. Successful navigation needs predicting of intention of other traffic participants at the intersection. Such prediction is an important component for both Advanced Driver Assistance Systems (ADAS) and Autonomous Driving (AD) Systems. In this paper, we present a driver intention prediction model for general intersections. Our model incorporates lane-level maps of an intersection and makes a prediction based on past position and movement of the vehicle. We create a real-world dataset of 375 turning tracks at a variety of intersections. We present turn prediction results based on Hidden Markov Model (HMM), Support Vector Machine (SVM), and Dynamic Bayesian Network (DBN). SVM and DBN models give higher accuracy compared to HMM models. We get over 90% turn prediction accuracy 1.6 seconds before the intersection. Our work advances the state of art in ADAS/AD systems with a turn prediction model for general intersections.