MEAT: Maneuver Extraction from Agent Trajectories

TL;DR

This paper introduces an automated method to extract maneuvers from agent trajectories in large datasets, enabling detailed analysis and maneuver-specific evaluation of trajectory prediction models, which enhances understanding beyond average metrics.

Contribution

The paper presents a novel automated approach for maneuver extraction from trajectories, facilitating in-depth dataset analysis and model evaluation based on agent dynamics.

Findings

The methodology successfully extracts maneuvers like lane changes and turns.

Maneuver-specific evaluation reveals differences in model performance.

Dataset analysis uncovers insights into agent behavior and dataset characteristics.

Abstract

Advances in learning-based trajectory prediction are enabled by large-scale datasets. However, in-depth analysis of such datasets is limited. Moreover, the evaluation of prediction models is limited to metrics averaged over all samples in the dataset. We propose an automated methodology that allows to extract maneuvers (e.g., left turn, lane change) from agent trajectories in such datasets. The methodology considers information about the agent dynamics and information about the lane segments the agent traveled along. Although it is possible to use the resulting maneuvers for training classification networks, we exemplary use them for extensive trajectory dataset analysis and maneuver-specific evaluation of multiple state-of-the-art trajectory prediction models. Additionally, an analysis of the datasets and an evaluation of the prediction models based on the agent dynamics is provided.