Unsupervised Driving Event Discovery Based on Vehicle CAN-data

TL;DR

This paper introduces an unsupervised method using self-supervised learning to identify and segment common driving events from vehicle CAN-data, demonstrated on Tesla Model 3 data.

Contribution

It presents a novel unsupervised clustering and segmentation approach leveraging SSL techniques for vehicle CAN-data analysis.

Findings

Contrastive SSL approaches perform similarly to generative SSL methods.

The method effectively identifies driving events in real vehicle data.

Unsupervised learning reduces the need for manual annotation in vehicle data analysis.

Abstract

The data collected from a vehicle's Controller Area Network (CAN) can quickly exceed human analysis or annotation capabilities when considering fleets of vehicles, which stresses the importance of unsupervised machine learning methods. This work presents a simultaneous clustering and segmentation approach for vehicle CAN-data that identifies common driving events in an unsupervised manner. The approach builds on self-supervised learning (SSL) for multivariate time series to distinguish different driving events in the learned latent space. We evaluate our approach with a dataset of real Tesla Model 3 vehicle CAN-data and a two-hour driving session that we annotated with different driving events. With our approach, we evaluate the applicability of recent time series-related contrastive and generative SSL techniques to learn representations that distinguish driving events. Compared to state-of-the-art (SOTA) generative SSL methods for driving event discovery, we find that contrastive learning approaches reach similar performance.