Active inference for fault tolerant control of robot manipulators with sensory faults

Corrado Pezzato*, Mohamed Baioumy, Carlos Hernández Corbato, Nick Hawes, Martijn Wisse, Riccardo Ferrari

*Corresponding author for this work

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

3 Citations (Scopus)
16 Downloads (Pure)

Abstract

We present a fault tolerant control scheme for robot manipulators based on active inference. The proposed solution makes use of the sensory prediction errors in the free-energy to simplify the residuals and thresholds generation for fault detection and isolation and does not require additional controllers for fault recovery. Results validating the benefits in a simulated 2DOF manipulator are presented and the limitations of the current approach are highlighted.

Original languageEnglish
Title of host publicationActive Inference
Subtitle of host publicationProceedings of the First International Workshop, IWAI 2020, Co-located with ECML/PKDD 2020
EditorsTim Verbelen, Pablo Lanillos, Christopher L. Buckley, Cedric De Boom
Place of PublicationCham, Switzerland
PublisherSpringer
Pages20-27
ISBN (Electronic)978-3-030-64919-7
ISBN (Print)978-3-030-64918-0
DOIs
Publication statusPublished - 2020
Event1st International Workshop on Active Inference, IWAI 2020 held in conjunction with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML-PKDD 2020 - Ghent, Belgium
Duration: 14 Sep 202014 Sep 2020

Publication series

NameCommunications in Computer and Information Science
Volume1326
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference1st International Workshop on Active Inference, IWAI 2020 held in conjunction with the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, ECML-PKDD 2020
Country/TerritoryBelgium
CityGhent
Period14/09/2014/09/20

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

  • Active inference
  • Fault recovery
  • Fault-tolerant control
  • Free-energy
  • Robot manipulator

Fingerprint

Dive into the research topics of 'Active inference for fault tolerant control of robot manipulators with sensory faults'. Together they form a unique fingerprint.

Cite this