Learning motion and impedance behaviors from human demonstrations

Matteo Saveriano, Dongheui Lee

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

10 Scopus citations

Abstract

Human-robot skill transfer has been deeply investigated from a kinematic point of view, generating various approaches to increase the robot knowledge in a simple and compact way. Nevertheless, social robotics applications require a close and active interaction with humans in a safe and natural manner. Torque controlled robots, with their variable impedance capabilities, seem a viable option toward a safe and profitable human-robot interaction. In this paper, an approach is proposed to simultaneously learn motion and impedance behaviors from tasks demonstrations. Kinematic aspects of the task are represented in a statistical way, while the variability along the demonstrations is used to define a variable impedance behavior. The effectiveness of our approach is validated with simulations on real and synthetic data.

Original languageEnglish
Title of host publication2014 11th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages368-373
Number of pages6
ISBN (Electronic)9781479953325
DOIs
StatePublished - 2014
Externally publishedYes
Event2014 11th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2014 - Kuala Lumpur, Malaysia
Duration: 12 Nov 201415 Nov 2014

Publication series

Name2014 11th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2014

Conference

Conference2014 11th International Conference on Ubiquitous Robots and Ambient Intelligence, URAI 2014
Country/TerritoryMalaysia
CityKuala Lumpur
Period12/11/1415/11/14

Keywords

  • Learning from Demonstrations
  • state-dependent behavior
  • variable impedance control

Fingerprint

Dive into the research topics of 'Learning motion and impedance behaviors from human demonstrations'. Together they form a unique fingerprint.

Cite this