Hybrid Approach for Vehicle Trajectory Prediction Using Weighted Integration of Multiple Models
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Gihoon | - |
dc.contributor.author | Kim, Dongchan | - |
dc.contributor.author | Ahn, Yoonyong | - |
dc.contributor.author | Huh, Kunsoo | - |
dc.date.accessioned | 2022-07-06T17:19:58Z | - |
dc.date.available | 2022-07-06T17:19:58Z | - |
dc.date.created | 2021-07-14 | - |
dc.date.issued | 2021-06 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/141781 | - |
dc.description.abstract | Prediction of surrounding vehicles accurately is an essential prerequisite for safe autonomous driving. Trajectory prediction methods can be classified into physics-, maneuver-, or learning-based methods. Learning-based methods have been studied extensively in recent years because it effectively exploits the road information and interactions among vehicles. However, learning-based methods perform poorly in unseen environments that were not considered during training and provide unreasonable results such as inconsistent trajectories according to road geometry. In this paper, to address this problem, a hybrid model that combines a learning-based model with physics-and maneuver-based models according to their uncertainties is proposed. The deep ensemble technique is also used to estimate the uncertainty of the learning-based method. Because the deep ensemble tends to show a large variance in unseen environments, this method is used to determine whether to use a hybrid model. The proposed method is trained and validated using the Lyft l5 dataset, the real environment vehicle driving data containing several types of intersections. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Hybrid Approach for Vehicle Trajectory Prediction Using Weighted Integration of Multiple Models | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Huh, Kunsoo | - |
dc.identifier.doi | 10.1109/ACCESS.2021.3083918 | - |
dc.identifier.scopusid | 2-s2.0-85113241603 | - |
dc.identifier.wosid | 000673801800001 | - |
dc.identifier.bibliographicCitation | IEEE Access, v.9, pp.78715 - 78723 | - |
dc.relation.isPartOf | IEEE Access | - |
dc.citation.title | IEEE Access | - |
dc.citation.volume | 9 | - |
dc.citation.startPage | 78715 | - |
dc.citation.endPage | 78723 | - |
dc.type.rims | ART | - |
dc.type.docType | Article in Press | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | Y | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordPlus | PATH | - |
dc.subject.keywordAuthor | deep ensemble | - |
dc.subject.keywordAuthor | Learning systems | - |
dc.subject.keywordAuthor | Licenses | - |
dc.subject.keywordAuthor | maneuver-based model | - |
dc.subject.keywordAuthor | Mathematical model | - |
dc.subject.keywordAuthor | physics-based model | - |
dc.subject.keywordAuthor | Predictive models | - |
dc.subject.keywordAuthor | Roads | - |
dc.subject.keywordAuthor | Trajectory | - |
dc.subject.keywordAuthor | trajectory prediction | - |
dc.subject.keywordAuthor | uncertainty | - |
dc.subject.keywordAuthor | Uncertainty | - |
dc.subject.keywordAuthor | weighted integrated model | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9441017 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.