Title
Active inference for fault tolerant control of robot manipulators with sensory faults
Author
Pezzato, C. (TU Delft Robot Dynamics) 
Baioumy, Mohamed (University of Oxford)
Hernández, Carlos (TU Delft Robot Dynamics)
Hawes, Nick (University of Oxford)
Wisse, M. (TU Delft Robot Dynamics)
Ferrari, Riccardo M.G. (TU Delft Team Jan-Willem van Wingerden)
Contributor
Verbelen, Tim (editor)
Lanillos, Pablo (editor)
Buckley, Christopher L. (editor)
De Boom, Cedric (editor)
Date
2020
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.
Subject
Active inference
Fault recovery
Fault-tolerant control
Free-energy
Robot manipulator
To reference this document use:
http://resolver.tudelft.nl/uuid:f823b363-b470-4758-b04d-2220087db228
DOI
https://doi.org/10.1007/978-3-030-64919-7_3
Publisher
Springer, Cham, Switzerland
Embargo date
2021-06-18
ISBN
978-3-030-64918-0
Source
Active Inference: Proceedings of the First International Workshop, IWAI 2020, Co-located with ECML/PKDD 2020
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, Ghent, Belgium
Series
Communications in Computer and Information Science, 1865-0929, 1326
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.
Part of collection
Institutional Repository
Document type
conference paper
Rights
© 2020 C. Pezzato, Mohamed Baioumy, Carlos Hernández, Nick Hawes, M. Wisse, Riccardo M.G. Ferrari