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

Conference Paper (2020)
Author(s)

Corrado Pezzato (TU Delft - Mechanical Engineering)

Mohamed Baioumy (University of Oxford)

Carlos Hernández Corbato (TU Delft - Mechanical Engineering)

Nick Hawes (University of Oxford)

Martijn Wisse (TU Delft - Mechanical Engineering)

Riccardo Ferrari (TU Delft - Mechanical Engineering)

Research Group
Robust Robot Systems
DOI related publication
https://doi.org/10.1007/978-3-030-64919-7_3 Final published version
More Info
expand_more
Publication Year
2020
Language
English
Research Group
Robust Robot Systems
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.
Pages (from-to)
20-27
Publisher
Springer
ISBN (print)
978-3-030-64918-0
ISBN (electronic)
978-3-030-64919-7
Event
1st 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 (2020-09-14 - 2020-09-14), Ghent, Belgium
Page Views
593
Collections
Institutional Repository
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

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.

Files

Pezzato2020_Chapter_ActiveInfe... (pdf)
(pdf | 0.603 Mb)
- Embargo expired in 18-06-2021
License info not available