Show simple item record

Files in this item

Thumbnail

Item metadata

dc.contributor.authorAbdulrahim Kadi, Halid
dc.contributor.authorTerzić, Kasim
dc.date.accessioned2024-03-07T15:30:01Z
dc.date.available2024-03-07T15:30:01Z
dc.date.issued2024-02-09
dc.identifier296126784
dc.identifierbe8fd08b-53e6-42f0-beac-d402c6127fe7
dc.identifier85186264734
dc.identifier.citationAbdulrahim Kadi , H & Terzić , K 2024 , PlaNet-ClothPick : effective fabric flattening based on latent dynamic planning . in 2024 IEEE/SICE International Symposium on System Integration (SII) . , 10417545 , IEEE/SICE International Symposium on System Integration (SII) , IEEE , pp. 972-979 , 2024 16th IEEE/SICE International Symposium on System Integration , Ha Long , Vietnam , 8/01/24 . https://doi.org/10.1109/SII58957.2024.10417545en
dc.identifier.citationconferenceen
dc.identifier.isbn9798350312089
dc.identifier.isbn9798350312072
dc.identifier.issn2474-2317
dc.identifier.urihttps://hdl.handle.net/10023/29457
dc.description.abstractWhy do Recurrent State Space Models such as PlaNet fail at cloth manipulation tasks? Recent work has attributed this to the blurry prediction of the observation, which makes it difficult to plan directly in the latent space. This paper explores the reasons behind this by applying PlaNet in the pick-and-place fabric-flattening domain. We find that the sharp discontinuity of the transition function on the contour of the fabric makes it difficult to learn an accurate latent dynamic model, causing the MPC planner to produce pick actions slightly outside of the article. By limiting picking space on the cloth mask and training on specially engineered trajectories, our mesh-free PlaNet-ClothPick surpasses visual planning and policy learning methods on principal metrics in simulation, achieving similar performance as state-of-the-art mesh-based planning approaches. Notably, our model exhibits a faster action inference and requires fewer transitional model parameters than the state-of-the-art robotic systems in this domain. Other supplementary materials are available at: https://sites.google.com/view/planet-clothpick.
dc.format.extent1638418
dc.language.isoeng
dc.publisherIEEE
dc.relation.ispartof2024 IEEE/SICE International Symposium on System Integration (SII)en
dc.relation.ispartofseriesIEEE/SICE International Symposium on System Integration (SII)en
dc.subjectQA75 Electronic computers. Computer scienceen
dc.subjectNSen
dc.subject.lccQA75en
dc.titlePlaNet-ClothPick : effective fabric flattening based on latent dynamic planningen
dc.typeConference itemen
dc.contributor.institutionUniversity of St Andrews. School of Computer Scienceen
dc.contributor.institutionUniversity of St Andrews. Centre for Research into Ecological & Environmental Modellingen
dc.contributor.institutionUniversity of St Andrews. Coastal Resources Management Groupen
dc.identifier.doi10.1109/SII58957.2024.10417545
dc.date.embargoedUntil2024-03-07


This item appears in the following Collection(s)

Show simple item record