Active Robot Learning for Temporal Task Models

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

6 Citations (Scopus)
171 Downloads (Pure)

Abstract

With the goal of having robots learn new skills after deployment, we propose an active learning framework for modelling user preferences about task execution. The proposed approach interactively gathers information by asking questions expressed in natural language. We study the validity and the learning performance of the proposed approach and two of its variants compared to a passive learning strategy. We further investigate the human-robot-interaction nature of the framework conducting a usability study with 18 subjects. The results show that active strategies are applicable for learning preferences in temporal tasks from non-expert users. Furthermore, the results provide insights in the interaction design of active learning robots.
Original languageEnglish
Title of host publicationProceedings of the 2018 ACM/IEEE International Conference on Human-Robot Interaction, HRI'18
PublisherACM
Pages123-131
Number of pages9
VolumePart F135041
ISBN (Electronic)978-1-4503-4953-6
DOIs
Publication statusPublished - 2018
MoE publication typeA4 Article in a conference publication
EventACM/IEEE International Conference on Human-Robot Interaction - Chicago, United States
Duration: 5 Mar 20188 Mar 2018
Conference number: 13
http://humanrobotinteraction.org/2018/

Publication series

NameACM/IEEE International Conference on Human-Robot Interaction
PublisherACM
ISSN (Print)2167-2121
ISSN (Electronic)2167-2148

Conference

ConferenceACM/IEEE International Conference on Human-Robot Interaction
Abbreviated titleHRI
CountryUnited States
CityChicago
Period05/03/201808/03/2018
Internet address

Keywords

  • Interactive machine learning
  • human-robot interaction

Fingerprint Dive into the research topics of 'Active Robot Learning for Temporal Task Models'. Together they form a unique fingerprint.

  • Projects

    Robots and the Future of Welfare Services

    Kyrki, V., Heikura, T., Forsman, P., Harmo, P., Racca, M., Verdoja, F., Brander, T., Lundell, J. & Pieters, R.

    01/05/201528/02/2018

    Project: Academy of Finland: Strategic research funding

    Cite this

    Racca, M., & Kyrki, V. (2018). Active Robot Learning for Temporal Task Models. In Proceedings of the 2018 ACM/IEEE International Conference on Human-Robot Interaction, HRI'18 (Vol. Part F135041, pp. 123-131). (ACM/IEEE International Conference on Human-Robot Interaction). ACM. https://doi.org/10.1145/3171221.3171241