Unsupervised Learning for Detection of Rare Driving Scenarios

TL;DR

This paper presents an unsupervised learning framework using Deep Isolation Forest and t-SNE to detect rare and hazardous driving scenarios from naturalistic driving data, enhancing autonomous vehicle safety.

Contribution

It introduces a novel unsupervised anomaly detection approach combining neural features, Isolation Forests, and dimensionality reduction for identifying complex driving anomalies.

Findings

Effective detection of rare hazardous scenarios

Scalable anomaly detection framework for autonomous driving

Good interpretability through visualization

Abstract

The detection of rare and hazardous driving scenarios is a critical challenge for ensuring the safety and reliability of autonomous systems. This research explores an unsupervised learning framework for detecting rare and extreme driving scenarios using naturalistic driving data (NDD). We leverage the recently proposed Deep Isolation Forest (DIF), an anomaly detection algorithm that combines neural network-based feature representations with Isolation Forests (IFs), to identify non-linear and complex anomalies. Data from perception modules, capturing vehicle dynamics and environmental conditions, is preprocessed into structured statistical features extracted from sliding windows. The framework incorporates t-distributed stochastic neighbor embedding (t-SNE) for dimensionality reduction and visualization, enabling better interpretability of detected anomalies. Evaluation is conducted using a proxy ground truth, combining quantitative metrics with qualitative video frame inspection. Our results demonstrate that the proposed approach effectively identifies rare and hazardous driving scenarios, providing a scalable solution for anomaly detection in autonomous driving systems. Given the study's methodology, it was unavoidable to depend on proxy ground truth and manually defined feature combinations, which do not encompass the full range of real-world driving anomalies or their nuanced contextual dependencies.