Discovering Optimal Imitation Strategies

This paper develops a general policy for learning relevant features of an imitation task. We restrict our study to imitation of manipulative tasks or of gestures. The imitation process is modeled as a hierarchical optimization system, which minimizes the discrepancy between two multi- dimensional datasets. To classify across manipulation strategies, we apply a probabilistic analysis to data in Cartesian and joint spaces. We determine a general metric that optimizes the policy of task reproduction, following strategy determination. The model successfully discovers strategies in six different imitative tasks and controls task reproduction by a full body humanoid robot.


Published in:
robotics and autonomous systems, Special Issue: Robot Learning from Demonstration, 47, 2-3, 69-77
Year:
2004
Keywords:
Note:
Sponsor: Swiss National Science Foundation. Top-3 2009 RAS most cited papers for the last five years
Other identifiers:
Laboratories:




 Record created 2005-11-16, last modified 2018-03-17

n/a:
Download fulltextPDF
External link:
Download fulltextURL
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)