kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Imitating by Generating: Deep Generative Models for Imitation of Interactive Tasks
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL. Intelligent Robotics Research Group, Aalto University, Espoo, Finland.ORCID iD: 0000-0001-6738-9872
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL. Department of Computer Engineering, Alanya Alaaddin Keykubat University, Antalya, Turkey.
KTH, School of Electrical Engineering and Computer Science (EECS), Intelligent systems, Robotics, Perception and Learning, RPL.ORCID iD: 0000-0003-0579-3372
Show others and affiliations
2020 (English)In: Frontiers in Robotics and AI, E-ISSN 2296-9144, Vol. 7, article id 47Article in journal (Refereed) Published
Abstract [en]

To coordinate actions with an interaction partner requires a constant exchange of sensorimotor signals. Humans acquire these skills in infancy and early childhood mostly by imitation learning and active engagement with a skilled partner. They require the ability to predict and adapt to one's partner during an interaction. In this work we want to explore these ideas in a human-robot interaction setting in which a robot is required to learn interactive tasks from a combination of observational and kinesthetic learning. To this end, we propose a deep learning framework consisting of a number of components for (1) human and robot motion embedding, (2) motion prediction of the human partner, and (3) generation of robot joint trajectories matching the human motion. As long-term motion prediction methods often suffer from the problem of regression to the mean, our technical contribution here is a novel probabilistic latent variable model which does not predict in joint space but in latent space. To test the proposed method, we collect human-human interaction data and human-robot interaction data of four interactive tasks “hand-shake,” “hand-wave,” “parachute fist-bump,” and “rocket fist-bump.” We demonstrate experimentally the importance of predictive and adaptive components as well as low-level abstractions to successfully learn to imitate human behavior in interactive social tasks.

Place, publisher, year, edition, pages
Frontiers Media SA , 2020. Vol. 7, article id 47
Keywords [en]
deep learning, generative models, human-robot interaction, imitation learning, sensorimotor coordination, variational autoencoders
National Category
Robotics
Identifiers
URN: urn:nbn:se:kth:diva-277188DOI: 10.3389/frobt.2020.00047ISI: 000531230100001PubMedID: 33501215Scopus ID: 2-s2.0-85084053889OAI: oai:DiVA.org:kth-277188DiVA, id: diva2:1454071
Note

QC 20200714

Available from: 2020-07-14 Created: 2020-07-14 Last updated: 2022-06-26Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records

Bütepage, JudithGhadirzadeh, AliÖztimur Karadag, ÖzgeBjörkman, MårtenKragic, Danica

Search in DiVA

By author/editor
Bütepage, JudithGhadirzadeh, AliÖztimur Karadag, ÖzgeBjörkman, MårtenKragic, Danica
By organisation
Robotics, Perception and Learning, RPL
In the same journal
Frontiers in Robotics and AI
Robotics

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 329 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf