Online Monitoring Framework for Automotive Time Series Data using JEPA Embeddings

TL;DR

This paper introduces an online anomaly detection framework for autonomous vehicle data using self-supervised JEPA embeddings, enabling detection of unknown anomalies without labeled data, demonstrated on the nuScenes dataset.

Contribution

It presents a novel self-supervised embedding approach with JEPA for anomaly detection in vehicle data, addressing the challenge of unlabeled, unknown anomalies in real-time systems.

Findings

Effective anomaly detection on nuScenes dataset

Self-supervised JEPA embeddings improve detection accuracy

Framework operates without labeled anomaly data

Abstract

As autonomous vehicles are rolled out, measures must be taken to ensure their safe operation. In order to supervise a system that is already in operation, monitoring frameworks are frequently employed. These run continuously online in the background, supervising the system status and recording anomalies. This work proposes an online monitoring framework to detect anomalies in object state representations. Thereby, a key challenge is creating a framework for anomaly detection without anomaly labels, which are usually unavailable for unknown anomalies. To address this issue, this work applies a self-supervised embedding method to translate object data into a latent representation space. For this, a JEPA-based self-supervised prediction task is constructed, allowing training without anomaly labels and the creation of rich object embeddings. The resulting expressive JEPA embeddings serve as input for established anomaly detection methods, in order to identify anomalies within object state representations. This framework is particularly useful for applications in real-world environments, where new or unknown anomalies may occur during operation for which there are no labels available. Experiments performed on the publicly available, real-world nuScenes dataset illustrate the framework's capabilities.