Model selection for incremental learning of generalizable movement primitives

Murtaza Hazara, Ville Kyrki

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

6 Citations (Scopus)
202 Downloads (Pure)

Abstract

Although motor primitives (MPs) have been studied extensively, much less attention has been devoted to studying their generalization to new situations. To cope with varying conditions, a MP's policy encoding must support generalization over task parameters to avoid learning separate primitives for each condition. Local and linear parameterized models have been proposed to interpolate over task parameters to provide limited generalization. In this paper, we present a global parametric motion primitive which allows generalization beyond local or linear models. Primitives are modelled using a linear basis function model with global non-linear basis functions. Using the global parametric model, we developed an online incremental learning framework for constructing a database of MPs from a single human demonstration. Above all, we propose a model selection method that can choose an optimal model complexity even with few training samples, which makes it suitable for online incremental learning. Experiments with a ball-in-a-cup task with varying string lengths demonstrate that the global parametric approach can successfully extract underlying regularities in a database of MPs leading to enhanced generalization capability of the parametric MPs and increased speed (convergence rate) of learning. Furthermore, it significantly excels over locally weighted regression both in terms of inter- and extrapolation.

Original languageEnglish
Title of host publicationProceedings of the 2017 18th International Conference on Advanced Robotics, ICAR 2017
PublisherIEEE
Pages359-366
Number of pages8
ISBN (Electronic)9781538631577
DOIs
Publication statusPublished - 30 Aug 2017
MoE publication typeA4 Article in a conference publication
EventInternational Conference on Advanced Robotics - Hong Kong, China
Duration: 10 Jul 201712 Jul 2017
Conference number: 18

Conference

ConferenceInternational Conference on Advanced Robotics
Abbreviated titleICAR
CountryChina
CityHong Kong
Period10/07/201712/07/2017

Keywords

  • Generalizable parametric movement primitives
  • Incremental learning
  • Learning from demonstration
  • Model selection

Fingerprint Dive into the research topics of 'Model selection for incremental learning of generalizable movement primitives'. Together they form a unique fingerprint.

Cite this