Advanced Search
DSpace@MIT

Task-Level Robot Learning

Research and Teaching Output of the MIT Community

Show simple item record

dc.contributor.author Aboaf, Eric W. en_US
dc.date.accessioned 2004-10-20T20:11:45Z
dc.date.available 2004-10-20T20:11:45Z
dc.date.issued 1988-08-01 en_US
dc.identifier.other AITR-1079 en_US
dc.identifier.uri http://hdl.handle.net/1721.1/6972
dc.description.abstract We are investigating how to program robots so that they learn from experience. Our goal is to develop principled methods of learning that can improve a robot's performance of a wide range of dynamic tasks. We have developed task-level learning that successfully improves a robot's performance of two complex tasks, ball-throwing and juggling. With task- level learning, a robot practices a task, monitors its own performance, and uses that experience to adjust its task-level commands. This learning method serves to complement other approaches, such as model calibration, for improving robot performance. en_US
dc.format.extent 9997518 bytes
dc.format.extent 3880924 bytes
dc.format.mimetype application/postscript
dc.format.mimetype application/pdf
dc.language.iso en_US
dc.relation.ispartofseries AITR-1079 en_US
dc.title Task-Level Robot Learning en_US


Files in this item

Name Size Format Description
AITR-1079.ps 9.534Mb Postscript
AITR-1079.pdf 3.701Mb PDF

This item appears in the following Collection(s)

Show simple item record

MIT-Mirage