Library

eCommons

 

Learning to Manipulate Novel Objects for Assistive Robots

Simple item page
dc.contributor.authorSung, Jaeyong
dc.contributor.chairSaxena, Ashutosh
dc.contributor.committeeMemberSalisbury, J. Kenneth
dc.contributor.committeeMemberSelman, Bart
dc.contributor.committeeMemberGuimbretière, François
dc.contributor.committeeMemberMarschner, Steve
dc.date.accessioned2017-07-07T12:48:41Z
dc.date.available2017-12-08T07:00:46Z
dc.date.issued2017-05-30
dc.description.abstractThe ability to reason about different modalities of information, for the purpose of physical interaction with objects, is a critical skill for assistive robots. For a robot to be able to assist us in our daily lives, it is not feasible to train each robot for a large number of tasks with all instances of objects that exist in human environments. Robots will have to generalize their skills by jointly reasoning with various sensor modalities such as vision, language and haptic feedback. This is an extremely challenging problem because each modality has intrinsically different statistical properties. Moreover, even with expert knowledge, manually designing joint features between such disparate modalities is difficult. In this dissertation, we focus on developing learning algorithms for robots that model tasks involving interactions with various objects in unstructured human environments --- especially on novel objects and scenarios that involve sequences of complicated manipulation. To this end, we develop algorithms that learn shared representations of multimodal data and model full sequences of complex motions. We demonstrate our approach on several different applications: understanding human activities in unstructured environment, synthesizing manipulation sequences for under-specified tasks, manipulating novel appliances, and manipulating objects with haptic feedback.
dc.identifier.doihttps://doi.org/10.7298/X43R0R0W
dc.identifier.otherSung_cornellgrad_0058F_10207
dc.identifier.otherhttp://dissertations.umi.com/cornellgrad:10207
dc.identifier.otherbibid: 9948842
dc.identifier.urihttps://hdl.handle.net/1813/51619
dc.language.isoen_US
dc.subjectmachine learning
dc.subjectMultimodal Data
dc.subjectRobotic Manipulation
dc.subjectRobot Learning
dc.subjectArtificial intelligence
dc.subjectDeep Learning
dc.subjectComputer science
dc.subjectRobotics
dc.titleLearning to Manipulate Novel Objects for Assistive Robots
dc.typedissertation or thesis
dcterms.licensehttps://hdl.handle.net/1813/59810
thesis.degree.disciplineComputer Science
thesis.degree.grantorCornell University
thesis.degree.levelDoctor of Philosophy
thesis.degree.namePh. D., Computer Science

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Sung_cornellgrad_0058F_10207.pdf
Size:
17.5 MB
Format:
Adobe Portable Document Format
Download

Collections

Cornell Theses and Dissertations