A virtual demonstrator environment for robot imitation learning

Di Wei Huang, Garrett Katz, Joshua Langsfeld, Rodolphe Gentili, James Reggia

Research output: Chapter in Book/Entry/PoemConference contribution

14 Scopus citations

Abstract

To support studies in robot imitation learning, this paper presents a software platform, SMILE (Simulator for Maryland Imitation Learning Environment), specifically targeting tasks in which exact human motions are not critical. We hypothesize that in this class of tasks, object behaviors are far more important than human behaviors, and thus one can significantly reduce complexity by not processing human motions at all. As such, SMILE simulates a virtual environment where a human demonstrator can manipulate objects using GUI controls without body parts being visible to a robot in the same environment. Imitation learning is therefore based on the behaviors of manipulated objects only. A simple Matlab interface for programming a simulated robot is also provided in SMILE, along with an XML interface for initializing objects in the virtual environment. SMILE lowers the barriers for studying robot imitation learning by (1) simplifying learning by making the human demonstrator be a virtual presence and (2) eliminating the immediate need to purchase special equipment for motion capturing.

Original languageEnglish (US)
Title of host publication2015 IEEE International Conference on Technologies for Practical Robot Applications, TePRA 2015
PublisherIEEE Computer Society
ISBN (Electronic)9781479987573, 9781479987573
DOIs
StatePublished - Aug 24 2015
Externally publishedYes
EventIEEE International Conference on Technologies for Practical Robot Applications, TePRA 2015 - Woburn, United States
Duration: May 11 2015May 12 2015

Publication series

NameIEEE Conference on Technologies for Practical Robot Applications, TePRA
Volume2015-August
ISSN (Print)2325-0526
ISSN (Electronic)2325-0534

Other

OtherIEEE International Conference on Technologies for Practical Robot Applications, TePRA 2015
Country/TerritoryUnited States
CityWoburn
Period5/11/155/12/15

Keywords

  • Graphical user interfaces
  • Joints
  • MATLAB
  • Robot kinematics
  • Robot sensing systems
  • XML

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'A virtual demonstrator environment for robot imitation learning'. Together they form a unique fingerprint.

Cite this