Title:
Improving Multi-Fingered Robot Manipulation by Unifying Learning and Planning

dc.contributor.author Hermans, Tucker
dc.contributor.corporatename Georgia Institute of Technology. Institute for Robotics and Intelligent Machines en_US
dc.contributor.corporatename University of Utah en_US
dc.date.accessioned 2019-10-08T19:07:00Z
dc.date.available 2019-10-08T19:07:00Z
dc.date.issued 2019-09-11
dc.description Presented on September 11th, 2019 at 12:15 p.m.-1:15 p.m. in the Marcus Nanotechnology Building, Rooms 1116-1118, Georgia Tech. en_US
dc.description Tucker Hermans is an assistant professor in the School of Computing at the University of Utah, where he is a founding member of the University of Utah Robotics Center. He was a visiting professor at NVIDIA Research during summer 2019. Hermans is a recipient of the NSF CAREER award and the 3M Non-Tenured Faculty Award. His research has been nominated for multiple conference paper awards, including winning the Best Medical Robotics Paper Award at ICRA 2017. Previously, Hermans was a postdoctoral fellow at TU Darmstadt working with Jan Peters. He attended Georgia Tech from 2009 to 2014, in the School of Interactive Computing where he earned his Ph.D. in Robotics under the supervision of Aaron Bobick and Jim Rehg. At Georgia Tech he earned a M.Sc. in Computer Science. Additionally, Hermans received an A.B. in German and Computer Science from Bowdoin College in 2009. en_US
dc.description Runtime: 58:58 minutes en_US
dc.description.abstract Multi-fingered hands offer autonomous robots increased dexterity, versatility, and stability over simple two-fingered grippers. Naturally, this increased ability comes with increased complexity in planning and executing manipulation actions. As such, I propose combining model-based planning with learned components to improve over purely data-driven or purely-model based approaches to manipulation. This talk examines multi-fingered autonomous manipulation when the robot has only partial knowledge of the object of interest. I will first present results on planning multi-fingered grasps for novel objects using a learned neural network. I will then present our approach to planning in-hand manipulation tasks when dynamic properties of objects are not known. I will conclude with a discussion of our ongoing and future research to further unify these two approaches. en_US
dc.format.extent 58:58 minutes
dc.identifier.uri http://hdl.handle.net/1853/61905
dc.language.iso en_US en_US
dc.publisher Georgia Institute of Technology en_US
dc.relation.ispartofseries IRIM Seminar Series
dc.subject Machine learning en_US
dc.subject Manipulation en_US
dc.subject Robotics en_US
dc.title Improving Multi-Fingered Robot Manipulation by Unifying Learning and Planning en_US
dc.type Moving Image
dc.type.genre Lecture
dspace.entity.type Publication
local.contributor.corporatename Institute for Robotics and Intelligent Machines (IRIM)
local.relation.ispartofseries IRIM Seminar Series
relation.isOrgUnitOfPublication 66259949-abfd-45c2-9dcc-5a6f2c013bcf
relation.isSeriesOfPublication 9bcc24f0-cb07-4df8-9acb-94b7b80c1e46
Files
Original bundle
Now showing 1 - 4 of 4
No Thumbnail Available
Name:
hermans.mp4
Size:
473.64 MB
Format:
MP4 Video file
Description:
Download Video
No Thumbnail Available
Name:
hermans_videostream.html
Size:
1.17 KB
Format:
Hypertext Markup Language
Description:
Streaming Video
No Thumbnail Available
Name:
transcript.txt
Size:
24.05 KB
Format:
Plain Text
Description:
Transcription Text
Thumbnail Image
Name:
thumbnail.jpg
Size:
57.68 KB
Format:
Joint Photographic Experts Group/JPEG File Interchange Format (JFIF)
Description:
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
3.13 KB
Format:
Item-specific license agreed upon to submission
Description:
Collections