Chaojin Mao
Informative Causality-based Vehicle Trajectory Prediction Architecture for Domain Generalization
Mao, Chaojin; Zhao, Liang; Min, Geyong; Hawbani, Ammar; Al-Dubai, Ahmed Y.; Zomaya, Albert Y.
Authors
Liang Zhao
Geyong Min
Ammar Hawbani
Prof Ahmed Al-Dubai A.Al-Dubai@napier.ac.uk
Professor
Albert Y. Zomaya
Abstract
Vehicle trajectory prediction is a promising technology for improving the performance of Cellular Vehicle-to Everything (C-V2X) applications by providing future road states. Various vehicle trajectory prediction methods have been proposed to increase the accuracy of the predicted trajectory. Although the existing vehicle trajectory prediction methods can accurately predict the future trajectory under the assumption that data comply with the Independent and Identically Distributed (IID), their performance is seriously degraded in practical implementation due to the ubiquitous distribution shifts in vehicle trajectory data. To improve the universality of the vehicle trajectory prediction method, generalizing the method to an environment that never appeared in the training data, namely, the Domain Generalization (DG) task, should be considered. Thus, we propose a plug-and play in FORmaTive caUsality-based vehicle trajectory predictioN architecturE (FORTUNE) to improve the DG capability of vehicle trajectory prediction methods. First, a novel structural causal model (SCM) of vehicle trajectory prediction is established to simulate the causality of the data-generating process. Second, we utilize the principle of mutual information to learn the invariant representation of the SCM. Third, an invariant knowledge transferring module is proposed to increase learning ability without destroying the structure of the original model. The results from simulation experiments demonstrate that the proposed scheme can significantly improve the DG capability of vehicle trajectory prediction methods.
Citation
Mao, C., Zhao, L., Min, G., Hawbani, A., Al-Dubai, A. Y., & Zomaya, A. Y. (2023). Informative Causality-based Vehicle Trajectory Prediction Architecture for Domain Generalization. In GLOBECOM 2023 - 2023 IEEE Global Communications Conference. https://doi.org/10.1109/GLOBECOM54140.2023.10437409
Conference Name | IEEE Global Communications (GLOBECOM) Conference 2023 |
---|---|
Conference Location | Kuala Lumpur, Malaysia |
Start Date | Dec 4, 2023 |
End Date | Dec 8, 2023 |
Acceptance Date | Aug 4, 2023 |
Online Publication Date | Feb 26, 2024 |
Publication Date | 2023 |
Deposit Date | Aug 14, 2023 |
Publicly Available Date | Dec 31, 2023 |
Publisher | Institute of Electrical and Electronics Engineers |
Book Title | GLOBECOM 2023 - 2023 IEEE Global Communications Conference |
ISBN | 9798350310917 |
DOI | https://doi.org/10.1109/GLOBECOM54140.2023.10437409 |
Keywords | Domain Generalization, Structural Causal Model, Mutual Information, Invariant Knowledge-Transferring Module |
Public URL | http://researchrepository.napier.ac.uk/Output/3168668 |
Related Public URLs | https://globecom2023.ieee-globecom.org/ |
Files
Informative Causality-based Vehicle Trajectory Prediction Architecture for Domain Generalization (accepted version)
(386 Kb)
PDF
You might also like
Wireless Power Transfer Technologies, Applications, and Future Trends: A Review
(2024)
Journal Article
Resolving the Decreased Rank Attack in RPL’s IoT Networks
(2023)
Conference Proceeding
Downloadable Citations
About Edinburgh Napier Research Repository
Administrator e-mail: repository@napier.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search