Inference and learning for rigid-body models of manipulation
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Mechanical Engineering, 2019
| 1. Verfasser: | |
|---|---|
| Weitere Verfasser: | |
| Format: | Abschlussarbeit |
| Sprache: | eng |
| Veröffentlicht: |
Massachusetts Institute of Technology
2020
|
| Schlagworte: | |
| Online Zugang: | https://hdl.handle.net/1721.1/123769 |
| _version_ | 1826196573883727872 |
|---|---|
| author | Fazeli, Nima. |
| author2 | Alberto Rodriguez. |
| author_facet | Alberto Rodriguez. Fazeli, Nima. |
| author_sort | Fazeli, Nima. |
| collection | MIT |
| description | Thesis: Ph. D., Massachusetts Institute of Technology, Department of Mechanical Engineering, 2019 |
| first_indexed | 2024-09-23T10:29:51Z |
| format | Thesis |
| id | mit-1721.1/123769 |
| institution | Massachusetts Institute of Technology |
| language | eng |
| last_indexed | 2024-09-23T10:29:51Z |
| publishDate | 2020 |
| publisher | Massachusetts Institute of Technology |
| record_format | dspace |
| spelling | mit-1721.1/1237692020-02-11T03:25:06Z Inference and learning for rigid-body models of manipulation Fazeli, Nima. Alberto Rodriguez. Massachusetts Institute of Technology. Department of Mechanical Engineering. Massachusetts Institute of Technology. Department of Mechanical Engineering Mechanical Engineering. Thesis: Ph. D., Massachusetts Institute of Technology, Department of Mechanical Engineering, 2019 Cataloged from PDF version of thesis. Includes bibliographical references (pages 139-146). In 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. by Nima Fazeli. Ph. D. Ph.D. Massachusetts Institute of Technology, Department of Mechanical Engineering 2020-02-10T21:43:18Z 2020-02-10T21:43:18Z 2019 2019 Thesis https://hdl.handle.net/1721.1/123769 1139337545 eng MIT 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. http://dspace.mit.edu/handle/1721.1/7582 146 pages application/pdf Massachusetts Institute of Technology |
| spellingShingle | Mechanical Engineering. Fazeli, Nima. Inference and learning for rigid-body models of manipulation |
| title | Inference and learning for rigid-body models of manipulation |
| title_full | Inference and learning for rigid-body models of manipulation |
| title_fullStr | Inference and learning for rigid-body models of manipulation |
| title_full_unstemmed | Inference and learning for rigid-body models of manipulation |
| title_short | Inference and learning for rigid-body models of manipulation |
| title_sort | inference and learning for rigid body models of manipulation |
| topic | Mechanical Engineering. |
| url | https://hdl.handle.net/1721.1/123769 |
| work_keys_str_mv | AT fazelinima inferenceandlearningforrigidbodymodelsofmanipulation |