Robot Learning with Predictions of Operator Intent

Michael T. Rosenstein, Andrew H. Fagg, and Roderic A. Grupen

The goal of this paper is to sketch a scenario for robot learning with remote operation by a person. We are particularly interested in situations where a user interface provides not only feedback about robot performance but also predictions of operator intent. We describe several benefits and challenges of this learning paradigm.

This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.