UM  > Faculty of Science and Technology
Residential Collegefalse
Status已發表Published
Physics-Informed Trajectory Prediction for Autonomous Driving under Missing Observation
Haicheng Liao1; Chengyue Wang1; Zhenning Li1; Yongkang Li2; Bonan Wang1; Guofa Li3; Chengzhong Xu1
2024
Conference Name33rd International Joint Conference on Artificial Intelligence, IJCAI 2024
Source PublicationProceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Pages6841-6849
Conference Date3-9 August 2024
Conference PlaceJeju, South Korea
CountryRepublic of Korea
PublisherInternational Joint Conferences on Artificial Intelligence
Abstract

This paper introduces a novel trajectory prediction approach for autonomous vehicles (AVs), adeptly addressing the challenges of missing observations and the need for adherence to physical laws in real-world driving environments. This study proposes a hierarchical two-stage trajectory prediction model for AVs. In the first stage we propose the Wavelet Reconstruction Network, an innovative tool expertly crafted for reconstructing missing observations, offering optional integration with state-of-the-art models to enhance their robustness. Additionally, the second stage of the model features the Wave Fusion Encoder, a quantum mechanics-inspired innovation for sophisticated vehicle interaction modeling. By incorporating the Kinematic Bicycle Model, we ensure that our predictions align with realistic vehicular kinematics. Complementing our methodological advancements, we introduce MoCAD-missing, a comprehensive real-world traffic dataset, alongside enhanced versions of the NGSIM and HighD datasets, designed to facilitate rigorous testing in environments with missing observations. Extensive evaluations demonstrate that our approach markedly outperforms existing methods, achieving high accuracy even in scenarios with up to 75% missing observations.

KeywordRobotics Planning And Scheduling Planning Under Uncertainty
DOI10.24963/ijcai.2024/756
Language英語English
Scopus ID2-s2.0-85204296427
Fulltext Access
Citation statistics
Document TypeConference paper
CollectionFaculty of Science and Technology
THE STATE KEY LABORATORY OF INTERNET OF THINGS FOR SMART CITY (UNIVERSITY OF MACAU)
DEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Corresponding AuthorZhenning Li
Affiliation1.University of Macau, Macao
2.UESTC, China
3.Chongqing University, China
First Author AffilicationUniversity of Macau
Corresponding Author AffilicationUniversity of Macau
Recommended Citation
GB/T 7714
Haicheng Liao,Chengyue Wang,Zhenning Li,et al. Physics-Informed Trajectory Prediction for Autonomous Driving under Missing Observation[C]:International Joint Conferences on Artificial Intelligence, 2024, 6841-6849.
APA Haicheng Liao., Chengyue Wang., Zhenning Li., Yongkang Li., Bonan Wang., Guofa Li., & Chengzhong Xu (2024). Physics-Informed Trajectory Prediction for Autonomous Driving under Missing Observation. Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 6841-6849.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Haicheng Liao]'s Articles
[Chengyue Wang]'s Articles
[Zhenning Li]'s Articles
Baidu academic
Similar articles in Baidu academic
[Haicheng Liao]'s Articles
[Chengyue Wang]'s Articles
[Zhenning Li]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Haicheng Liao]'s Articles
[Chengyue Wang]'s Articles
[Zhenning Li]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.