Vehicle State Estimation and Prediction for Autonomous Driving in a Round Intersection

This paper presents methods for vehicle state estimation and prediction for autonomous driving. A round intersection is chosen for application of the methods and to illustrate the results as autonomous vehicles have difficulty in handling round intersections. State estimation based on the unscented Kalman filter (UKF) is presented in the paper and then applied to state estimation of vehicles in a round intersection. The microscopic traffic simulator SUMO (Simulation of Urban Mobility) is used to generate realistic traffic in the round intersection for the simulation experiments. Change point detection-based driving behavior prediction using a multipolicy approach is then introduced and evaluated for the round intersection. Finally, these methods are combined for vehicle trajectory estimation based on UKF and policy prediction and demonstrated using the round intersection.