EValueAction: a proposal for policy evaluation in simulation to support interactive imitation learning

Fiorella Sibona*, Jelle Luijkx, Bas Van Der Heijden, Laura Ferranti, Marina Indri

*Corresponding author for this work

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

Abstract

The up-and-coming concept of Industry 5.0 fore-sees human-centric flexible production lines, where collaborative robots support human workforce. In order to allow a seamless collaboration between intelligent robots and human workers, designing solutions for non-expert users is crucial. Learning from demonstration emerged as the enabling approach to address such a problem. However, more focus should be put on finding safe solutions which optimize the cost associated with the demonstrations collection process. This paper introduces a preliminary outline of a system, namely EValueAction (EVA), designed to assist the human in the process of collecting interactive demonstrations taking advantage of simulation to safely avoid failures. A policy is pre-trained with human-demonstrations and, where needed, new informative data are interactively gathered and aggregated to iteratively improve the initial policy. A trial case study further reinforces the relevance of the work by demonstrating the crucial role of informative demonstrations for generalization.

Original languageEnglish
Title of host publicationProceedings of the IEEE 21st International Conference on Industrial Informatics, INDIN 2023
EditorsHelene Dorksen, Stefano Scanzio, Jurgen Jasperneite
PublisherIEEE
Number of pages6
ISBN (Electronic)978-1-6654-9313-0
DOIs
Publication statusPublished - 2023
Event21st IEEE International Conference on Industrial Informatics, INDIN 2023 - Lemgo, Germany
Duration: 17 Jul 202320 Jul 2023

Conference

Conference21st IEEE International Conference on Industrial Informatics, INDIN 2023
Country/TerritoryGermany
CityLemgo
Period17/07/2320/07/23

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

  • Human-centered manufacturing
  • Interactive imitation learning
  • Learning from Demonstration
  • Simulation

Fingerprint

Dive into the research topics of 'EValueAction: a proposal for policy evaluation in simulation to support interactive imitation learning'. Together they form a unique fingerprint.

Cite this