Space, Time, and Interaction: A Taxonomy of Corner Cases in Trajectory Datasets for Automated Driving

TL;DR

This paper introduces a taxonomy of trajectory corner cases in automated driving, categorizing unusual trajectories based on cause and data sources to improve the safety and reliability of highly automated vehicles.

Contribution

It provides a novel taxonomy of trajectory corner cases, linking causes with data sources, to enhance understanding and handling of unusual driving scenarios in automated vehicles.

Findings

Categorization of corner cases by cause and data source

Illustration of complexity between ML models and corner cases

Processing chain model for corner case analysis

Abstract

Trajectory data analysis is an essential component for highly automated driving. Complex models developed with these data predict other road users' movement and behavior patterns. Based on these predictions - and additional contextual information such as the course of the road, (traffic) rules, and interaction with other road users - the highly automated vehicle (HAV) must be able to reliably and safely perform the task assigned to it, e.g., moving from point A to B. Ideally, the HAV moves safely through its environment, just as we would expect a human driver to do. However, if unusual trajectories occur, so-called trajectory corner cases, a human driver can usually cope well, but an HAV can quickly get into trouble. In the definition of trajectory corner cases, which we provide in this work, we will consider the relevance of unusual trajectories with respect to the task at hand. Based on this, we will also present a taxonomy of different trajectory corner cases. The categorization of corner cases into the taxonomy will be shown with examples and is done by cause and required data sources. To illustrate the complexity between the machine learning (ML) model and the corner case cause, we present a general processing chain underlying the taxonomy.