MEAT: Maneuver Extraction from Agent Trajectories
This work provides a tool for in-depth analysis of trajectory datasets and more nuanced evaluation of prediction models, which is incremental but useful for researchers in autonomous driving and robotics.
The authors tackled the problem of limited analysis and evaluation in trajectory prediction datasets by proposing an automated method to extract maneuvers from agent trajectories, enabling detailed dataset analysis and maneuver-specific model evaluation.
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.