Behavior-Aware Online Prediction of Obstacle Occupancy using Zonotopes

TL;DR

This paper introduces an online method for predicting vehicle occupancy in autonomous driving by combining Kalman filtering, LP, and reachability analysis to produce accurate, compact predictions without prior data.

Contribution

It presents a novel two-stage approach using zonotopes and reachability analysis for real-time occupancy prediction based solely on motion observations.

Findings

Accurate occupancy predictions demonstrated in urban simulations.

Method produces compact sets without prior training.

Effective in unstructured driving environments.

Abstract

Predicting the motion of surrounding vehicles is key to safe autonomous driving, especially in unstructured environments without prior information. This paper proposes a novel online method to accurately predict the occupancy sets of surrounding vehicles based solely on motion observations. The approach is divided into two stages: first, an Extended Kalman Filter and a Linear Programming (LP) problem are used to estimate a compact zonotopic set of control actions; then, a reachability analysis propagates this set to predict future occupancy. The effectiveness of the method has been validated through simulations in an urban environment, showing accurate and compact predictions without relying on prior assumptions or prior training data.