trajdata: A Unified Interface to Multiple Human Trajectory Datasets

TL;DR

trajdata offers a unified, easy-to-use interface for multiple human trajectory datasets, simplifying research and enabling comprehensive evaluation of existing data for autonomous vehicle and pedestrian motion forecasting.

Contribution

It introduces a standardized API and data format for diverse trajectory datasets, facilitating cross-dataset analysis and research in the field.

Findings

Comprehensive empirical evaluation of existing datasets.

Insights and suggestions for future dataset development.

Enhanced understanding of data used in motion forecasting.

Abstract

The field of trajectory forecasting has grown significantly in recent years, partially owing to the release of numerous large-scale, real-world human trajectory datasets for autonomous vehicles (AVs) and pedestrian motion tracking. While such datasets have been a boon for the community, they each use custom and unique data formats and APIs, making it cumbersome for researchers to train and evaluate methods across multiple datasets. To remedy this, we present trajdata: a unified interface to multiple human trajectory datasets. At its core, trajdata provides a simple, uniform, and efficient representation and API for trajectory and map data. As a demonstration of its capabilities, in this work we conduct a comprehensive empirical evaluation of existing trajectory datasets, providing users with a rich understanding of the data underpinning much of current pedestrian and AV motion forecasting research, and proposing suggestions for future datasets from these insights. trajdata is permissively licensed (Apache 2.0) and can be accessed online at https://github.com/NVlabs/trajdata