Toward Unified Practices in Trajectory Prediction Research on Bird's-Eye-View Datasets

TL;DR

This paper proposes standardized datasets, tools, and practices for trajectory prediction research in autonomous vehicles, aiming to improve comparability and reproducibility across studies.

Contribution

It introduces an open-source toolbox with standardized preprocessing, visualization, and evaluation methods for bird's-eye-view trajectory prediction datasets.

Findings

Provides a comprehensive review of current literature

Offers a set of standardized preprocessing and evaluation protocols

Facilitates comparison of results across different studies

Abstract

The availability of high-quality datasets is crucial for the development of behavior prediction algorithms in autonomous vehicles. This paper highlights the need to standardize the use of certain datasets for motion forecasting research to simplify comparative analysis and proposes a set of tools and practices to achieve this. Drawing on extensive experience and a comprehensive review of current literature, we summarize our proposals for preprocessing, visualization, and evaluation in the form of an open-sourced toolbox designed for researchers working on trajectory prediction problems. The clear specification of necessary preprocessing steps and evaluation metrics is intended to alleviate development efforts and facilitate the comparison of results across different studies. The toolbox is available at: https://github.com/westny/dronalize.