Anomaly Detection in Autonomous Driving: A Survey

TL;DR

This survey reviews various anomaly detection techniques in autonomous driving, highlighting current methods, systematization, and research gaps to improve vehicle safety under unexpected conditions.

Contribution

It provides a comprehensive overview and systematization of anomaly detection approaches across multiple sensor modalities in autonomous driving.

Findings

Summarizes state-of-the-art anomaly detection methods

Identifies key research gaps and challenges

Classifies detection approaches by application and capability

Abstract

Nowadays, there are outstanding strides towards a future with autonomous vehicles on our roads. While the perception of autonomous vehicles performs well under closed-set conditions, they still struggle to handle the unexpected. This survey provides an extensive overview of anomaly detection techniques based on camera, lidar, radar, multimodal and abstract object level data. We provide a systematization including detection approach, corner case level, ability for an online application, and further attributes. We outline the state-of-the-art and point out current research gaps.