Cluster Naturalistic Driving Encounters Using Deep Unsupervised Learning

TL;DR

This paper introduces an unsupervised learning approach combining auto-encoders and k-means clustering to categorize naturalistic driving encounters, aiding autonomous vehicles in understanding complex driving scenarios.

Contribution

The paper presents a novel AE-kMC method that effectively clusters naturalistic driving encounters, outperforming traditional k-means clustering.

Findings

AE-kMC outperforms k-means in clustering accuracy

Validated on 10,000 real-world driving encounters

Improves decision-making in autonomous driving systems

Abstract

Learning knowledge from driving encounters could help self-driving cars make appropriate decisions when driving in complex settings with nearby vehicles engaged. This paper develops an unsupervised classifier to group naturalistic driving encounters into distinguishable clusters by combining an auto-encoder with k-means clustering (AE-kMC). The effectiveness of AE-kMC was validated using the data of 10,000 naturalistic driving encounters which were collected by the University of Michigan, Ann Arbor in the past five years. We compare our developed method with the $k$-means clustering methods and experimental results demonstrate that the AE-kMC method outperforms the original k-means clustering method.