Hydrodynamic modeling of a robotic surface vehicle using representation learning for long-term prediction

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 76
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorJang, Junwooko
dc.contributor.authorKim, Jinwhanko
dc.date.accessioned2023-02-28T02:01:02Z-
dc.date.available2023-02-28T02:01:02Z-
dc.date.created2023-02-28-
dc.date.issued2023-02-
dc.identifier.citationOCEAN ENGINEERING, v.270-
dc.identifier.issn0029-8018-
dc.identifier.urihttp://hdl.handle.net/10203/305381-
dc.description.abstractThe hydrodynamic modeling of a surface vehicle in an aquatic environment is known to be a challenging problem. In particular, it is difficult to calculate the hydrodynamic forces due to the intricate coupling of the vehicle with water. In recent years, deep dynamics models have been utilized to improve the accuracy of dynamics modeling precision. However, it is well known that data-driven approaches do not extrapolate well and are vulnerable to out-of-distribution data. In this paper, we argue that the naive use of neural networks may reduce the accuracy of long-term predictions. In order to address this issue, we employ representation learning techniques that facilitate the learning of the valid data space, so that long-term predictions can be made within the valid data space. In addition, hallucinated replay is incorporated into the prediction network to further improve the accuracy of long-term predictions. We validate the proposed method on experimental data using a robotic surface vehicle and demonstrate its application to path tracking control.-
dc.languageEnglish-
dc.publisherPERGAMON-ELSEVIER SCIENCE LTD-
dc.titleHydrodynamic modeling of a robotic surface vehicle using representation learning for long-term prediction-
dc.typeArticle-
dc.identifier.wosid000924394400001-
dc.identifier.scopusid2-s2.0-85146466106-
dc.type.rimsART-
dc.citation.volume270-
dc.citation.publicationnameOCEAN ENGINEERING-
dc.identifier.doi10.1016/j.oceaneng.2023.113620-
dc.contributor.localauthorKim, Jinwhan-
dc.description.isOpenAccessN-
dc.type.journalArticleArticle-
dc.subject.keywordAuthorMachine learning for modeling-
dc.subject.keywordAuthorMarine robotics-
dc.subject.keywordAuthorModel learning for control-
dc.subject.keywordPlusQUADROTOR-
Appears in Collection
ME-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0