Show simple item record

dc.contributor.advisorAlberto Rodriguez.en_US
dc.contributor.authorFazeli, Nima.en_US
dc.contributor.otherMassachusetts Institute of Technology. Department of Mechanical Engineering.en_US
dc.date.accessioned2020-02-10T21:43:18Z
dc.date.available2020-02-10T21:43:18Z
dc.date.copyright2019en_US
dc.date.issued2019en_US
dc.identifier.urihttps://hdl.handle.net/1721.1/123769
dc.descriptionThesis: Ph. D., Massachusetts Institute of Technology, Department of Mechanical Engineering, 2019en_US
dc.descriptionCataloged from PDF version of thesis.en_US
dc.descriptionIncludes bibliographical references (pages 139-146).en_US
dc.description.abstractIn this thesis, we explore a spectrum of inference and modeling approaches for robotic manipulation. Particularly, we investigate the broad class of rigid-bodies undergoing frictional interactions. We begin by deriving a contact-implicit system identification formulation for articulated rigid-bodies. Assuming we have a physical model of the system, the objective is to derive system parameters and contact forces for articulated rigid-bodies without enumerating and inferring contact formations. We then ground this approach by investigating the fidelity of rigid-body contact models and their identification. We evaluate the fidelity of the contact models by empirically studying their predictive performance and parameter identification properties in a planar impact task. Next, we address one approach to augmenting these contact models with data. The objective here is to improve model fidelity through an optimization of model parameters and residual error learning for systems with prior physics models. We conclude the thesis by building models from data for tasks with rich latent structure and no prior physics models. Here, the objective is to learn data-efficient hierarchical models of physics that incorporate force and tactile sensory modalities and are amenable to inference, controls, and planning.en_US
dc.description.statementofresponsibilityby Nima Fazeli.en_US
dc.format.extent146 pagesen_US
dc.language.isoengen_US
dc.publisherMassachusetts Institute of Technologyen_US
dc.rightsMIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission.en_US
dc.rights.urihttp://dspace.mit.edu/handle/1721.1/7582en_US
dc.subjectMechanical Engineering.en_US
dc.titleInference and learning for rigid-body models of manipulationen_US
dc.typeThesisen_US
dc.description.degreePh. D.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Mechanical Engineeringen_US
dc.identifier.oclc1139337545en_US
dc.description.collectionPh.D. Massachusetts Institute of Technology, Department of Mechanical Engineeringen_US
dspace.imported2020-02-10T21:43:17Zen_US
mit.thesis.degreeDoctoralen_US
mit.thesis.departmentMechEen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record