Exploring the Potential of World Models for Anomaly Detection in Autonomous Driving

TL;DR

This paper explores how world models, used in reinforcement learning, can be applied to detect anomalies in autonomous driving, especially in unexpected situations where traditional systems struggle.

Contribution

It provides an overview and characterization of world models for anomaly detection in autonomous driving, linking components to prior anomaly detection research.

Findings

Framework for leveraging world models in anomaly detection

Relation of world model components to existing anomaly detection methods

Facilitation of further research in autonomous driving safety

Abstract

In recent years there have been remarkable advancements in autonomous driving. While autonomous vehicles demonstrate high performance in closed-set conditions, they encounter difficulties when confronted with unexpected situations. At the same time, world models emerged in the field of model-based reinforcement learning as a way to enable agents to predict the future depending on potential actions. This led to outstanding results in sparse reward and complex control tasks. This work provides an overview of how world models can be leveraged to perform anomaly detection in the domain of autonomous driving. We provide a characterization of world models and relate individual components to previous works in anomaly detection to facilitate further research in the field.