Rethinking Trajectory Prediction in Real-World Applications: An Online Task-Free Continual Learning Perspective

Yunlong Lin, Zirui Li, Cheng Gong, Qi Liu, Chao Lu, Jianwei Gong*

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Trajectory prediction is essential in improving the safety of automated vehicles (AVs), However, most learning-based models only aim to improve the trajectory prediction accuracy and are tested offline in evaluations. When additional data come from a new environment, the offline models need to be re-trained with both the new and old data to avoid catastrophic forgetting of previously learned knowledge. Moreover, all data from a new environment is assumed to be available simultaneously, conflicting with the online data collection of AVs in the real world. Considering these problems, this paper rethinks the research orientation of trajectory prediction. First, a novel learning paradigm named online task-free continual learning (OTFCL) is proposed, highlighting new goals, including learning online data from new environments efficiently and avoiding catastrophic forgetting without re-training. Then, according to the goals of OTFCL, a testing methodology is designed for a comprehensive evaluation of trajectory prediction. Finally, a state-of-the-art model is evaluated in experiments by applying the proposed testing methodology based on the INTERACTION dataset. Experimental results reveal limitations of the state-of-the-art model in real-world applications, and potential solutions based on OTFCL to overcome these limitations are also discussed.

源语言英语
主期刊名2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023
出版商Institute of Electrical and Electronics Engineers Inc.
5020-5026
页数7
ISBN(电子版)9798350399462
DOI
出版状态已出版 - 2023
活动26th IEEE International Conference on Intelligent Transportation Systems, ITSC 2023 - Bilbao, 西班牙
期限: 24 9月 202328 9月 2023

出版系列

姓名IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
ISSN(印刷版)2153-0009
ISSN(电子版)2153-0017

会议

会议26th IEEE International Conference on Intelligent Transportation Systems, ITSC 2023
国家/地区西班牙
Bilbao
时期24/09/2328/09/23

指纹

探究 'Rethinking Trajectory Prediction in Real-World Applications: An Online Task-Free Continual Learning Perspective' 的科研主题。它们共同构成独一无二的指纹。

引用此

Lin, Y., Li, Z., Gong, C., Liu, Q., Lu, C., & Gong, J. (2023). Rethinking Trajectory Prediction in Real-World Applications: An Online Task-Free Continual Learning Perspective. 在 2023 IEEE 26th International Conference on Intelligent Transportation Systems, ITSC 2023 (页码 5020-5026). (IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ITSC57777.2023.10421951