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.
@article{arxiv.2206.05158,
title = {MEAT: Maneuver Extraction from Agent Trajectories},
author = {Julian Schmidt and Julian Jordan and David Raba and Tobias Welz and Klaus Dietmayer},
journal= {arXiv preprint arXiv:2206.05158},
year = {2022}
}
Comments
Accepted at IEEE Intelligent Vehicles Symposium (IV) 2022 2nd Workshop on Autonomy@Scale