DMP and GMR based teaching by demonstration for a KUKA LBR robot

Alexander Hewitt, Chenguang Yang, Yong Li, Rongxin Cui

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

13 Scopus citations

Abstract

This paper investigates the problem of Teaching by Demonstration (TbD) on a KUKA lightweight robot (LBR). Motions are recorded by a human operator, and then the data is used to model a nonlinear system, i.e., the dynamic motor primitive (DMP). In order to learn from multiple demonstrations, Gaussian Mixture Models (GMM) are employed rather than using conventional Gaussian process for the evaluation of the non-linear term of the DMP. Then the Gaussian mixture regression (GMR) algorithm is applied to generate a synthesized trajectory with smaller position errors in 3D space. The proposed approach is tested and demonstrated by performing two tasks with KUKA iiwa robot.

Original languageEnglish
Title of host publicationICAC 2017 - 2017 23rd IEEE International Conference on Automation and Computing
Subtitle of host publicationAddressing Global Challenges through Automation and Computing
EditorsJie Zhang
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9780701702618
DOIs
StatePublished - 23 Oct 2017
Event23rd IEEE International Conference on Automation and Computing, ICAC 2017 - Huddersfield, United Kingdom
Duration: 7 Sep 20178 Sep 2017

Publication series

NameICAC 2017 - 2017 23rd IEEE International Conference on Automation and Computing: Addressing Global Challenges through Automation and Computing

Conference

Conference23rd IEEE International Conference on Automation and Computing, ICAC 2017
Country/TerritoryUnited Kingdom
CityHuddersfield
Period7/09/178/09/17

Keywords

  • Dynamic motor primitive
  • Gaussian mixture model
  • Gaussian mixture regression
  • KUKA
  • Teaching by demonstration

Fingerprint

Dive into the research topics of 'DMP and GMR based teaching by demonstration for a KUKA LBR robot'. Together they form a unique fingerprint.

Cite this