Title:
Autonomously learning to visually detect where manipulation will succeed
Autonomously learning to visually detect where manipulation will succeed
| dc.contributor.author | Nguyen, Hai | en_US |
| dc.contributor.author | Kemp, Charles C. | en_US |
| dc.contributor.corporatename | Georgia Institute of Technology. Healthcare Robotics Lab | en_US |
| dc.contributor.corporatename | Georgia Institute of Technology. Institute for Robotics and Intelligent Machines | en_US |
| dc.date.accessioned | 2013-12-19T17:49:07Z | |
| dc.date.available | 2013-12-19T17:49:07Z | |
| dc.date.issued | 2013-09 | |
| dc.description | © The Author(s) 2013. This article is published with open access at Springerlink.com | en_US |
| dc.description | DOI: 10.1007/s10514-013-9363-y | en_US |
| dc.description.abstract | Visual features can help predict if a manipulation behavior will succeed at a given location. For example, the success of a behavior that flips light switches depends on the location of the switch. We present methods that enable a mobile manipulator to autonomously learn a function that takes an RGB image and a registered 3D point cloud as input and returns a 3D location at which a manipulation behavior is likely to succeed. With our methods, robots autonomously train a pair of support vector machine (SVM) classifiers by trying behaviors at locations in the world and observing the results. Our methods require a pair of manipulation behaviors that can change the state of the world between two sets (e.g., light switch up and light switch down), classifiers that detect when each behavior has been successful, and an initial hint as to where one of the behaviors will be successful. When given an image feature vector associated with a 3D location, a trained SVM predicts if the associated manipulation behavior will be successful at the 3D location. To evaluate our approach, we performed experiments with a PR2 robot from Willow Garage in a simulated home using behaviors that flip a light switch, push a rocker-type light switch, and operate a drawer. By using active learning, the robot efficiently learned SVMs that enabled it to consistently succeed at these tasks. After training, the robot also continued to learn in order to adapt in the event of failure. | en_US |
| dc.identifier.citation | Autonomously Learning to Visually Detect Where Manipulation Will Succeed, Hai Nguyen and Charles C. Kemp, Autonomous Robots, September 2013. | en_US |
| dc.identifier.doi | 10.1007/s10514-013-9363-y | |
| dc.identifier.issn | 0929-5593 | |
| dc.identifier.issn | 1573-7527 | |
| dc.identifier.uri | http://hdl.handle.net/1853/49876 | |
| dc.language.iso | en_US | en_US |
| dc.publisher | Georgia Institute of Technology | en_US |
| dc.publisher.original | Springer Verlag | en_US |
| dc.subject | Robot learning | en_US |
| dc.subject | Mobile manipulation | en_US |
| dc.subject | Home robots | en_US |
| dc.subject | Behavior-based systems | en_US |
| dc.subject | Active learning | en_US |
| dc.title | Autonomously learning to visually detect where manipulation will succeed | en_US |
| dc.type | Text | |
| dc.type.genre | Article | |
| dspace.entity.type | Publication | |
| local.contributor.author | Kemp, Charles C. | |
| local.contributor.corporatename | Healthcare Robotics Lab | |
| local.contributor.corporatename | Institute for Robotics and Intelligent Machines (IRIM) | |
| relation.isAuthorOfPublication | e4f743b9-0557-4889-a16e-00afe0715f4c | |
| relation.isOrgUnitOfPublication | c6394b0e-6e8b-42dc-aeed-0e22560bd6f1 | |
| relation.isOrgUnitOfPublication | 66259949-abfd-45c2-9dcc-5a6f2c013bcf |
Files
Original bundle
1 - 1 of 1