A survey of robot learning from demonstration

Brenna D. Argall*, Sonia Chernova, Manuela Veloso, Brett Browning

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

1661 Scopus citations

Abstract

We present 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.

Original languageEnglish (US)
Pages (from-to)469-483
Number of pages15
JournalRobotics and Autonomous Systems
Volume57
Issue number5
DOIs
StatePublished - May 31 2009

Keywords

  • Autonomous systems
  • Learning from demonstration
  • Machine learning
  • Robotics

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Mathematics(all)
  • Computer Science Applications

Fingerprint Dive into the research topics of 'A survey of robot learning from demonstration'. Together they form a unique fingerprint.

Cite this