A Survey of Robot Learning from Demonstration - Robotics Institute Carnegie Mellon University

A Survey of Robot Learning from Demonstration

Brenna Argall, Sonia Chernova, Manuela Veloso, and Brett Browning
Journal Article, Robotics and Autonomous Systems, Vol. 57, No. 5, pp. 469 - 483, May, 2009

Abstract

Wepresent a comprehensive survey of robot Learning from Demonstration (LfD), a technique that develops policies from example state to action mappings. We introduce the LfD design choices in terms of demonstrator, problem space, policy derivation and performance, and contribute the foundations for a structure in which to categorize LfD research. Specifically, we analyze and categorize the multiple ways in which examples are gathered, ranging from teleoperation to imitation, as well as the various techniques for policy derivation, including matching functions, dynamics models and plans. To conclude we discuss LfD limitations and related promising areas for future research.

BibTeX

@article{Argall-2009-17073,
author = {Brenna Argall and Sonia Chernova and Manuela Veloso and Brett Browning},
title = {A Survey of Robot Learning from Demonstration},
journal = {Robotics and Autonomous Systems},
year = {2009},
month = {May},
volume = {57},
number = {5},
pages = {469 - 483},
keywords = {Learning from demonstration, Robotics, Machine learning, Autonomous systems},
}