A probabilistic framework for learning geometry-based robot manipulation skills

dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorAbu-Dakka, Fares J.
dc.contributor.authorHuang, Yanlong
dc.contributor.authorSilvério, João
dc.contributor.authorKyrki, Ville
dc.contributor.departmentIntelligent Robotics
dc.contributor.departmentUniversity of Leeds
dc.contributor.departmentIDIAP Research Institute
dc.contributor.departmentDepartment of Electrical Engineering and Automation
dc.date.accessioned2021-05-12T06:38:30Z
dc.date.available2021-05-12T06:38:30Z
dc.date.issued2021-07
dc.description.abstractProgramming robots to perform complex manipulation tasks is difficult because many tasks require sophisticated controllers that may rely on data such as manipulability ellipsoids, stiffness/damping and inertia matrices. Such data are naturally represented as Symmetric Positive Definite (SPD) matrices to capture specific geometric characteristics of the data, which increases the complexity of hard-coding them. To alleviate this difficulty, the Learning from Demonstration (LfD) paradigm can be used in order to learn robot manipulation skills with specific geometric constraints encapsulated in SPD matrices. Learned skills often need to be adapted when they are applied to new situations. While existing techniques can adapt Cartesian and joint space trajectories described by various desired points, the adaptation of motion skills encapsulated in SPD matrices remains an open problem. In this paper, we introduce a new LfD framework that can learn robot manipulation skills encapsulated in SPD matrices from expert demonstrations and adapt them to new situations defined by new start-, via- and end-matrices. The proposed approach leverages Kernelized Movement Primitives (KMPs) to generate SPD-based robot manipulation skills that smoothly adapt the demonstrations to conform to new constraints. We validate the proposed framework using a couple of simulations in addition to a real experiment scenario.en
dc.description.versionPeer revieweden
dc.format.extent10
dc.format.mimetypeapplication/pdf
dc.identifier.citationAbu-Dakka , F J , Huang , Y , Silvério , J & Kyrki , V 2021 , ' A probabilistic framework for learning geometry-based robot manipulation skills ' , Robotics and Autonomous Systems , vol. 141 , 103761 . https://doi.org/10.1016/j.robot.2021.103761en
dc.identifier.doi10.1016/j.robot.2021.103761
dc.identifier.issn0921-8890
dc.identifier.otherPURE UUID: ebf72464-cb84-4a52-99ef-0d275683f552
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/ebf72464-cb84-4a52-99ef-0d275683f552
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=85104929959&partnerID=8YFLogxK
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/62675663/ELEC_Abu_Dakka_etal_Probabilistic_framework_Robotics_and_Autonomous_Systems_2021_finalpublishedversion.pdf
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/107466
dc.identifier.urnURN:NBN:fi:aalto-202105126730
dc.language.isoenen
dc.publisherElsevier Science Publishers BV
dc.relation.ispartofseriesRobotics and Autonomous Systemsen
dc.relation.ispartofseriesVolume 141en
dc.rightsopenAccessen
dc.subject.keywordLearning from demonstration
dc.subject.keywordVariable impedance
dc.subject.keywordRobot learning
dc.subject.keywordManipulability ellipsoids
dc.subject.keywordRiemannian manifolds
dc.titleA probabilistic framework for learning geometry-based robot manipulation skillsen
dc.typeA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessäfi
dc.type.versionpublishedVersion
Files