2026-09-20T12:40:01Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1431552022-06-16T03:02:24Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Agrawal, Pulkit
Chen, Tao
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2022-06-15T13:00:01Z
2022-06-15T13:00:01Z
2022-02
2022-03-04T20:59:45.193Z
https://hdl.handle.net/1721.1/143155
In-hand object reorientation has been a challenging problem in robotics due to high dimensional actuation space and the frequent change in contact state between the fingers and the objects. We present a simple model-free framework that can learn to reorient objects with both the hand facing upwards and downwards. We demonstrate the capability of reorienting over 2000 geometrically different objects in both cases. The learned policies show strong zero-shot transfer performance on new objects. We provide evidence that these policies are amenable to real-world operation by distilling them to use observations easily available in the real world.
S.M.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright MIT
http://rightsstatements.org/page/InC-EDU/1.0/
A System for General In-Hand Object Re-Orientation
Thesis
application/pdf
Master
Master of Science in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="ef00bf9b-f792-4d78-8ee4-56339318dccf">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>A System for General In-Hand Object Re-Orientation</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2022-02</PublicationDate>
<Authors>
<Author>
<DisplayName>Chen, Tao</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>http://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>In-hand object reorientation has been a challenging problem in robotics due to high dimensional actuation space and the frequent change in contact state between the fingers and the objects. We present a simple model-free framework that can learn to reorient objects with both the hand facing upwards and downwards. We demonstrate the capability of reorienting over 2000 geometrically different objects in both cases. The learned policies show strong zero-shot transfer performance on new objects. We provide evidence that these policies are amenable to real-world operation by distilling them to use observations easily available in the real world.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>