Policy adaptation with tactile feedback

Brenna D. Argall, Eric L. Sauser, Aude G. Billard

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Behavior adaptation with execution experience is a practical feature for any policy learning system. Our work provides performance feedback to a robot learner in the form of tactile corrections from a human teacher, for the purpose of policy refinement as well as policy reuse. Multiple variants of our general approach have been validated on the iCub robot, as building blocks towards a high-DoF humanoid system that integrates tactile sensing on the hands and arms into complex behaviors and sophisticated learning routines.

Original languageEnglish (US)
Title of host publicationHRI 2011 - Proceedings of the 6th ACM/IEEE International Conference on Human-Robot Interaction
Pages107-108
Number of pages2
DOIs
StatePublished - Apr 1 2011
Event6th ACM/IEEE International Conference on Human-Robot Interaction, HRI 2011 - Lausanne, Switzerland
Duration: Mar 6 2011Mar 9 2011

Publication series

NameHRI 2011 - Proceedings of the 6th ACM/IEEE International Conference on Human-Robot Interaction

Other

Other6th ACM/IEEE International Conference on Human-Robot Interaction, HRI 2011
CountrySwitzerland
CityLausanne
Period3/6/113/9/11

Keywords

  • Demonstration learning
  • Humanoid robots
  • Tactile feedback

ASJC Scopus subject areas

  • Human-Computer Interaction

Fingerprint Dive into the research topics of 'Policy adaptation with tactile feedback'. Together they form a unique fingerprint.

Cite this