Vehicle State Estimation and Prediction

TL;DR

This paper introduces vehicle state estimation and prediction methods using UKF and multi-policy behavior prediction, demonstrated through simulations in a roundabout scenario for autonomous driving.

Contribution

It combines UKF-based state estimation with change point detection for behavior prediction, applied specifically to complex roundabout environments.

Findings

UKF effectively estimates vehicle states in roundabouts

Multi-policy approach predicts driving behavior changes

Combined methods improve vehicle trajectory estimation

Abstract

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