Learning similar tasks from observation and practice

Darrin C. Bentivegna, Christopher G. Atkeson, Gordon Cheng

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

29 Scopus citations

Abstract

This paper presents a case study of learning to select behavioral primitives and generate subgoals from observation and practice. Our approach uses local features to generalize across tasks and global features to learn from practice. We demonstrate this approach applied to the marble maze task. Our robot uses local features to initially learn primitive selection and subgoal generation policies from observing a teacher maneuver a marble through a maze. The robot then uses this information as it tries to traverse another maze, and refines the information during learning from practice.

Original languageEnglish
Title of host publication2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006
Pages2677-2683
Number of pages7
DOIs
StatePublished - 2006
Externally publishedYes
Event2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006 - Beijing, China
Duration: 9 Oct 200615 Oct 2006

Publication series

NameIEEE International Conference on Intelligent Robots and Systems

Conference

Conference2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006
Country/TerritoryChina
CityBeijing
Period9/10/0615/10/06

Fingerprint

Dive into the research topics of 'Learning similar tasks from observation and practice'. Together they form a unique fingerprint.

Cite this