# Unsupervised Driving Event Discovery Based on Vehicle CAN-data

arXiv: https://arxiv.org/abs/2301.04988 · HTML: https://mlsanity.com/paper/2301.04988/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 12 Jan 2023.

## Builds on (most cited first, 8 of 8)

- [Self-supervised Learning: Generative or Contrastive](https://mlsanity.com/paper/2006.08218/) (2020)
- [Unsupervised Scalable Representation Learning for Multivariate Time Series](https://mlsanity.com/paper/1901.10738/) (2019)
- [Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding](https://mlsanity.com/paper/2106.00750/) (2021)
- [Time Series Change Point Detection with Self-Supervised Contrastive Predictive Coding](https://mlsanity.com/paper/2011.14097/) (2020)
- [Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data](https://mlsanity.com/paper/1706.03161/) (2017)
- [Drive2Vec: Multiscale State-Space Embedding of Vehicular Sensor Data](https://mlsanity.com/paper/1806.04795/) (2018)
- [Deep Learning in the Automotive Industry: Recent Advances and Application Examples](https://mlsanity.com/paper/1906.08834/) (2019)
- [TripMD: Driving patterns investigation via Motif Analysis](https://mlsanity.com/paper/2007.03727/) (2020)

## Built on by (most cited first, 2 of 2)

- [Augmenting Safety-Critical Driving Scenarios while Preserving Similarity to Expert Trajectories](https://mlsanity.com/paper/2404.13347/) (2024)
- [Behavior-Centric Extraction of Scenarios from Highway Traffic Data and their Domain-Knowledge-Guided Clustering using CVQ-VAE](https://mlsanity.com/paper/2603.16964/) (2026)

## Abstract (arXiv)

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.