Title:
Effective robot task learning by focusing on task-relevant objects
Effective robot task learning by focusing on task-relevant objects
dc.contributor.author | Lee, Kyu Hwa | en_US |
dc.contributor.author | Lee, Jinhan | en_US |
dc.contributor.author | Thomaz, Andrea L. | en_US |
dc.contributor.author | Bobick, Aaron F. | en_US |
dc.contributor.corporatename | Georgia Institute of Technology. Center for Robotics and Intelligent Machines | en_US |
dc.date.accessioned | 2013-02-15T17:50:05Z | |
dc.date.available | 2013-02-15T17:50:05Z | |
dc.date.issued | 2009-10 | |
dc.description | ©2009 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. | |
dc.description | Presented at IROS 2009, the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems, October 11-15, 2009; St. Louis, MO, USA. | |
dc.description | DOI: 10.1109/IROS.2009.5353979 | |
dc.description.abstract | In a robot learning from demonstration framework involving environments with many objects, one of the key problems is to decide which objects are relevant to a given task. In this paper, we analyze this problem and propose a biologically-inspired computational model that enables the robot to focus on the task-relevant objects. To filter out incompatible task models, we compute a task relevance value (TRV) for each object, which shows a human demonstrator's implicit indication of the relevance to the task. By combining an intentional action representation with `motionese', our model exhibits recognition capabilities compatible with the way that humans demonstrate. We evaluate the system on demonstrations from five different human subjects, showing its ability to correctly focus on the appropriate objects in these demonstrations. | en_US |
dc.identifier.citation | Kyu Hwa Lee, Jinhan Lee, A. L. Thomaz, and A. Bobick, "Effective robot task learning by focusing on task-relevant objects," Proceedings of the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2009, 2551-2556. | en_US |
dc.identifier.doi | 10.1109/IROS.2009.5353979 | |
dc.identifier.isbn | 978-1-4244-3803-7 | |
dc.identifier.uri | http://hdl.handle.net/1853/46200 | |
dc.language.iso | en_US | en_US |
dc.publisher | Georgia Institute of Technology | en_US |
dc.publisher.original | Institute of Electrical and Electronics Engineers | en_US |
dc.subject | Learning from demonstration | en_US |
dc.subject | Task relevant value | en_US |
dc.subject | Biologically-inspired computational models | en_US |
dc.title | Effective robot task learning by focusing on task-relevant objects | en_US |
dc.type | Text | |
dc.type.genre | Proceedings | |
dc.type.genre | Post-print | |
dspace.entity.type | Publication | |
local.contributor.corporatename | College of Computing | |
local.contributor.corporatename | Socially Intelligent Machines Lab | |
local.contributor.corporatename | Institute for Robotics and Intelligent Machines (IRIM) | |
relation.isOrgUnitOfPublication | c8892b3c-8db6-4b7b-a33a-1b67f7db2021 | |
relation.isOrgUnitOfPublication | 57e47d4b-8e04-4c68-a99e-2cb4580b4844 | |
relation.isOrgUnitOfPublication | 66259949-abfd-45c2-9dcc-5a6f2c013bcf |
Files
Original bundle
1 - 1 of 1