Learning and Composing Primitive Skills for Dual-Arm Manipulation

Èric Pairet, Paola Ardón, Michael Mistry, Yvan Petillot

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

1 Citation (Scopus)
18 Downloads (Pure)

Abstract

In an attempt to confer robots with complex manipulation capabilities, dual-arm anthropomorphic systems have become an important research topic in the robotics community. Most approaches in the literature rely upon a great understanding of the dynamics underlying the system’s behaviour and yet offer limited autonomous generalisation capabilities. To address these limitations, this work proposes a modelisation for dual-arm manipulators based on dynamic movement primitives laying in two orthogonal spaces. The modularity and learning capabilities of this model are leveraged to formulate a novel end-to-end learning-based framework which (i) learns a library of primitive skills from human demonstrations, and (ii) composes such knowledge simultaneously and sequentially to confront novel scenarios. The feasibility of the proposal is evaluated by teaching the iCub humanoid the basic skills to succeed on simulated dual-arm pick-and-place tasks. The results suggest the learning and generalisation capabilities of the proposed framework extend to autonomously conduct undemonstrated dual-arm manipulation tasks.

Original languageEnglish
Title of host publicationTowards Autonomous Robotic Systems
Subtitle of host publicationTAROS 2019
EditorsKaspar Althoefer, Jelizaveta Konstantinova, Ketao Zhang
PublisherSpringer
Pages65-77
Number of pages13
ISBN (Print)9783030238063
DOIs
Publication statusE-pub ahead of print - 28 Jun 2019
Event20th Towards Autonomous Robotic Systems Conference 2019 - London, United Kingdom
Duration: 3 Jul 20195 Jul 2019

Publication series

NameLecture Notes in Computer Science
Volume11649
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference20th Towards Autonomous Robotic Systems Conference 2019
Abbreviated titleTAROS 2019
CountryUnited Kingdom
CityLondon
Period3/07/195/07/19

Keywords

  • Autonomous agents
  • Dual arm manipulation
  • Humanoid robots
  • Learning from demonstration
  • Model learning for control

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Fingerprint Dive into the research topics of 'Learning and Composing Primitive Skills for Dual-Arm Manipulation'. Together they form a unique fingerprint.

  • Cite this

    Pairet, È., Ardón, P., Mistry, M., & Petillot, Y. (2019). Learning and Composing Primitive Skills for Dual-Arm Manipulation. In K. Althoefer, J. Konstantinova, & K. Zhang (Eds.), Towards Autonomous Robotic Systems: TAROS 2019 (pp. 65-77). (Lecture Notes in Computer Science; Vol. 11649). Springer. https://doi.org/10.1007/978-3-030-23807-0_6