Learning task-parameterized dynamic movement primitives using mixture of GMMs

Affan Pervez, Dongheui Lee

Research output: Contribution to journalArticlepeer-review

57 Scopus citations

Abstract

Task-parameterized skill learning aims at adaptive motion encoding to new situations. While existing approaches for task-parameterized skill learning have demonstrated good adaptation within the demonstrated region, the extrapolation problem of task-parameterized skills has not been investigated enough. In this work, with the aim of good adaptation not only within the demonstrated region but also outside of the region, we propose to combine a generative model with a dynamic movement primitive by formulating learning as a density estimation problem. Moreover, for efficient learning from relatively few demonstrations, we propose to augment training data with additional incomplete data. The proposed method is tested and compared with existing works in simulations and real robot experiments. Experimental results verified its generalization in the extrapolation region.

Original languageEnglish
Pages (from-to)61-78
Number of pages18
JournalIntelligent Service Robotics
Volume11
Issue number1
DOIs
StatePublished - 1 Jan 2018
Externally publishedYes

Keywords

  • Dynamic movement primitives
  • Programming by demonstration
  • Task-parameterized movement

Fingerprint

Dive into the research topics of 'Learning task-parameterized dynamic movement primitives using mixture of GMMs'. Together they form a unique fingerprint.

Cite this