Show simple item record

dc.contributor.authorZhang, Yunboen_US
dc.contributor.authorClegg, Alexanderen_US
dc.contributor.authorHa, Sehoonen_US
dc.contributor.authorTurk, Gregen_US
dc.contributor.authorYe, Yutingen_US
dc.contributor.editorMyszkowski, Karolen_US
dc.contributor.editorNiessner, Matthiasen_US
dc.date.accessioned2023-05-03T06:09:23Z
dc.date.available2023-05-03T06:09:23Z
dc.date.issued2023
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.14741
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14741
dc.description.abstractIn-hand object manipulation is challenging to simulate due to complex contact dynamics, non-repetitive finger gaits, and the need to indirectly control unactuated objects. Further adapting a successful manipulation skill to new objects with different shapes and physical properties is a similarly challenging problem. In this work, we show that natural and robust in-hand manipulation of simple objects in a dynamic simulation can be learned from a high quality motion capture example via deep reinforcement learning with careful designs of the imitation learning problem. We apply our approach on both single-handed and two-handed dexterous manipulations of diverse object shapes and motions. We then demonstrate further adaptation of the example motion to a more complex shape through curriculum learning on intermediate shapes morphed between the source and target object. While a naive curriculum of progressive morphs often falls short, we propose a simple greedy curriculum search algorithm that can successfully apply to a range of objects such as a teapot, bunny, bottle, train, and elephant.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies -> Physical simulation; Motion capture; Reinforcement learning; Learning from demonstrations
dc.subjectComputing methodologies
dc.subjectPhysical simulation
dc.subjectMotion capture
dc.subjectReinforcement learning
dc.subjectLearning from demonstrations
dc.titleLearning to Transfer In-Hand Manipulations Using a Greedy Shape Curriculumen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersHuman Object Interaction
dc.description.volume42
dc.description.number2
dc.identifier.doi10.1111/cgf.14741
dc.identifier.pages25-36
dc.identifier.pages12 pages


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

Show simple item record