Learning from demonstrations with partially observable task parameters

Tohid Alizadeh, Sylvain Calinon, Darwin G. Caldwell

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

37 Citations (Scopus)

Abstract

Robot learning from demonstrations requires the robot to learn and adapt movements to new situations, often characterized by position and orientation of objects or landmarks in the robot's environment. In the task-parameterized Gaussian mixture model framework, the movements are considered to be modulated with respect to a set of candidate frames of reference (coordinate systems) attached to a set of objects in the robot workspace. Following a similar approach, this paper addresses the problem of having missing candidate frames during the demonstrations and reproductions, which can happen in various situations such as visual occlusion, sensor unavailability, or tasks with a variable number of descriptive features. We study this problem with a dust sweeping task in which the robot requires to consider a variable amount of dust areas to clean for each reproduction trial.

Original languageEnglish
Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages3309-3314
Number of pages6
ISBN (Electronic)9781479936854, 9781479936854
DOIs
Publication statusPublished - Sept 22 2014
Externally publishedYes
Event2014 IEEE International Conference on Robotics and Automation, ICRA 2014 - Hong Kong, China
Duration: May 31 2014Jun 7 2014

Publication series

NameProceedings - IEEE International Conference on Robotics and Automation
ISSN (Print)1050-4729

Other

Other2014 IEEE International Conference on Robotics and Automation, ICRA 2014
Country/TerritoryChina
CityHong Kong
Period5/31/146/7/14

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Learning from demonstrations with partially observable task parameters'. Together they form a unique fingerprint.

Cite this