Novel learning from demonstration approach for repetitive teleoperation tasks

Affan Pervez, Arslan Ali, Jee Hwan Ryu, Dongheui Lee

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

43 Scopus citations

Abstract

While teleoperation provides a possibility for a robot to operate at extreme conditions instead of a human, teleoperating a robot still demands a heavy mental workload from a human operator. Learning from demonstrations can reduce the human operator's burden by learning repetitive teleoperation tasks. However, one of challenging issues is that demonstrations via teleoperation are less consistent compared to other modalities of human demonstrations. In order to solve this problem, we propose a learning scheme based on Dynamic Movement Primitives (DMPs) which can handle less consistent, asynchronized and incomplete demonstrations. In particular we proposed a new Expectation Maximization (EM) algorithm which can synchronize and encode demonstrations with temporal and spatial variances, different initial and final conditions and partial executions. The proposed algorithm is tested and validated with three different experiments of a peg-in-hole task conducted on 3-Degree of freedom (DOF) masterslave teleoperation system.

Original languageEnglish
Title of host publication2017 IEEE World Haptics Conference, WHC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages60-65
Number of pages6
ISBN (Electronic)9781509014255
DOIs
StatePublished - 21 Jul 2017
Externally publishedYes
Event7th IEEE World Haptics Conference, WHC 2017 - Munich, Germany
Duration: 6 Jun 20179 Jun 2017

Publication series

Name2017 IEEE World Haptics Conference, WHC 2017

Conference

Conference7th IEEE World Haptics Conference, WHC 2017
Country/TerritoryGermany
CityMunich
Period6/06/179/06/17

Fingerprint

Dive into the research topics of 'Novel learning from demonstration approach for repetitive teleoperation tasks'. Together they form a unique fingerprint.

Cite this