[Mike Rosenstein]


Robot learning with predictions of operator intent
M.T. Rosenstein, A.H. Fagg, and R.A. Grupen. Robot learning with predictions of operator intent. In Papers from the 2004 AAAI Fall Symposium on The Intersection of Cognitive Science and Robotics: From Interfaces to Intelligence, pp. 107-108, 2004.
Abstract: 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.
Download: pdf (127KB)
See also:
  Remote supervisory control of a humanoid robot
  User intentions funneled through a human-robot interface
  Supervised actor-critic reinforcement learning

updated 13-Dec-2005
mtr@cs.umass.edu