Loading [MathJax]/extensions/MathMenu.js
Robust Robot Learning from Demonstration and Skill Repair Using Conceptual Constraints | IEEE Conference Publication | IEEE Xplore

Robust Robot Learning from Demonstration and Skill Repair Using Conceptual Constraints


Abstract:

Learning from demonstration (LfD) has enabled robots to rapidly gain new skills and capabilities by leveraging examples provided by novice human operators. While effectiv...Show More

Abstract:

Learning from demonstration (LfD) has enabled robots to rapidly gain new skills and capabilities by leveraging examples provided by novice human operators. While effective, this training mechanism presents the potential for sub-optimal demonstrations to negatively impact performance due to unintentional operator error. In this work we introduce Concept Constrained Learning from Demonstration (CC-LfD), a novel algorithm for robust skill learning and skill repair that incorporates annotations of conceptually-grounded constraints (in the form of planning predicates) during live demonstrations into the LfD process. Through our evaluation, we show that CC-LfD can be used to quickly repair skills with as little as a single annotated demonstration without the need to identify and remove low-quality demonstrations. We also provide evidence for potential applications to transfer learning, whereby constraints can be used to adapt demonstrations from a related task to achieve proficiency with few new demonstrations required.
Date of Conference: 01-05 October 2018
Date Added to IEEE Xplore: 06 January 2019
ISBN Information:

ISSN Information:

Conference Location: Madrid, Spain

References

References is not available for this document.