Toward Unified Practices in Trajectory Prediction Research on Bird's-Eye-View Datasets
(2025) 36th IEEE Intelligent Vehicles Symposium, IV 2025 In IEEE Intelligent Vehicles Symposium, Proceedings p.83-89- Abstract
The availability of high-quality datasets is crucial for developing 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... (More)
The availability of high-quality datasets is crucial for developing 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.
(Less)
- author
- Westny, Theodor ; Olofsson, Björn LU and Frisk, Erik
- organization
- publishing date
- 2025
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- IV 2025 - 36th IEEE Intelligent Vehicles Symposium
- series title
- IEEE Intelligent Vehicles Symposium, Proceedings
- pages
- 7 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 36th IEEE Intelligent Vehicles Symposium, IV 2025
- conference location
- Cluj-Napoca, Romania
- conference dates
- 2025-06-22 - 2025-06-25
- external identifiers
-
- scopus:105014242174
- ISSN
- 1931-0587
- 2642-7214
- ISBN
- 9798331538033
- DOI
- 10.1109/IV64158.2025.11097573
- project
- ELLIIT B14: Autonomous Force-Aware Swift Motion Control
- RobotLab LTH
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © 2025 IEEE.
- id
- 539c42be-8b7a-492c-a2d2-4e07ea73c801
- alternative location
- https://arxiv.org/abs/2405.00604
- date added to LUP
- 2025-09-08 18:14:31
- date last changed
- 2025-09-09 14:22:32
@inproceedings{539c42be-8b7a-492c-a2d2-4e07ea73c801, abstract = {{<p>The availability of high-quality datasets is crucial for developing 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.</p>}}, author = {{Westny, Theodor and Olofsson, Björn and Frisk, Erik}}, booktitle = {{IV 2025 - 36th IEEE Intelligent Vehicles Symposium}}, isbn = {{9798331538033}}, issn = {{1931-0587}}, language = {{eng}}, pages = {{83--89}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, series = {{IEEE Intelligent Vehicles Symposium, Proceedings}}, title = {{Toward Unified Practices in Trajectory Prediction Research on Bird's-Eye-View Datasets}}, url = {{http://dx.doi.org/10.1109/IV64158.2025.11097573}}, doi = {{10.1109/IV64158.2025.11097573}}, year = {{2025}}, }