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

doi:10.1007/978-3-030-64919-7_3

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 volume › Conference contribution › Scientific › peer-review

8 Citations (Scopus)

51 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 language	English
Title of host publication	Active Inference
Subtitle of host publication	Proceedings of the First International Workshop, IWAI 2020, Co-located with ECML/PKDD 2020
Editors	Tim Verbelen, Pablo Lanillos, Christopher L. Buckley, Cedric De Boom
Place of Publication	Cham, Switzerland
Publisher	Springer
Pages	20-27
ISBN (Electronic)	978-3-030-64919-7
ISBN (Print)	978-3-030-64918-0
DOIs	https://doi.org/10.1007/978-3-030-64919-7_3
Publication status	Published - 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 - Ghent, Belgium Duration: 14 Sept 2020 → 14 Sept 2020

Publication series

Name	Communications in Computer and Information Science
Volume	1326
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	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
Country/Territory	Belgium
City	Ghent
Period	14/09/20 → 14/09/20

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

Access to Document

10.1007/978-3-030-64919-7_3

Pezzato2020_Chapter_ActiveInferenceForFaultToleranFinal published version, 492 KB

Cite this

Pezzato, C., Baioumy, M., Corbato, C. H., Hawes, N., Wisse, M., & Ferrari, R. (2020). Active inference for fault tolerant control of robot manipulators with sensory faults. In T. Verbelen, P. Lanillos, C. L. Buckley, & C. De Boom (Eds.), Active Inference: Proceedings of the First International Workshop, IWAI 2020, Co-located with ECML/PKDD 2020 (pp. 20-27). (Communications in Computer and Information Science; Vol. 1326). Springer. https://doi.org/10.1007/978-3-030-64919-7_3

Pezzato, Corrado ; Baioumy, Mohamed ; Corbato, Carlos Hernández et al. / Active inference for fault tolerant control of robot manipulators with sensory faults. Active Inference: Proceedings of the First International Workshop, IWAI 2020, Co-located with ECML/PKDD 2020. editor / Tim Verbelen ; Pablo Lanillos ; Christopher L. Buckley ; Cedric De Boom. Cham, Switzerland : Springer, 2020. pp. 20-27 (Communications in Computer and Information Science).

@inproceedings{f823b363b4704758b04d2220087db228,

title = "Active inference for fault tolerant control of robot manipulators with sensory faults",

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.",

keywords = "Active inference, Fault recovery, Fault-tolerant control, Free-energy, Robot manipulator",

author = "Corrado Pezzato and Mohamed Baioumy and Corbato, {Carlos Hern{\'a}ndez} and Nick Hawes and Martijn Wisse and Riccardo Ferrari",

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.; 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 ; Conference date: 14-09-2020 Through 14-09-2020",

year = "2020",

doi = "10.1007/978-3-030-64919-7_3",

language = "English",

isbn = "978-3-030-64918-0",

series = "Communications in Computer and Information Science",

publisher = "Springer",

pages = "20--27",

editor = "Tim Verbelen and Pablo Lanillos and Buckley, {Christopher L.} and {De Boom}, Cedric",

booktitle = "Active Inference",

}

Pezzato, C, Baioumy, M, Corbato, CH, Hawes, N, Wisse, M & Ferrari, R 2020, Active inference for fault tolerant control of robot manipulators with sensory faults. in T Verbelen, P Lanillos, CL Buckley & C De Boom (eds), Active Inference: Proceedings of the First International Workshop, IWAI 2020, Co-located with ECML/PKDD 2020. Communications in Computer and Information Science, vol. 1326, Springer, Cham, Switzerland, pp. 20-27, 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, Ghent, Belgium, 14/09/20. https://doi.org/10.1007/978-3-030-64919-7_3

Active inference for fault tolerant control of robot manipulators with sensory faults. / Pezzato, Corrado; Baioumy, Mohamed; Corbato, Carlos Hernández et al.
Active Inference: Proceedings of the First International Workshop, IWAI 2020, Co-located with ECML/PKDD 2020. ed. / Tim Verbelen; Pablo Lanillos; Christopher L. Buckley; Cedric De Boom. Cham, Switzerland: Springer, 2020. p. 20-27 (Communications in Computer and Information Science; Vol. 1326).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Active inference for fault tolerant control of robot manipulators with sensory faults

AU - Pezzato, Corrado

AU - Baioumy, Mohamed

AU - Corbato, Carlos Hernández

AU - Hawes, Nick

AU - Wisse, Martijn

AU - Ferrari, Riccardo

N1 - 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.

PY - 2020

Y1 - 2020

N2 - 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.

AB - 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.

KW - Active inference

KW - Fault recovery

KW - Fault-tolerant control

KW - Free-energy

KW - Robot manipulator

UR - http://www.scopus.com/inward/record.url?scp=85098249275&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-64919-7_3

DO - 10.1007/978-3-030-64919-7_3

M3 - Conference contribution

AN - SCOPUS:85098249275

SN - 978-3-030-64918-0

T3 - Communications in Computer and Information Science

SP - 20

EP - 27

BT - Active Inference

A2 - Verbelen, Tim

A2 - Lanillos, Pablo

A2 - Buckley, Christopher L.

A2 - De Boom, Cedric

PB - Springer

CY - Cham, Switzerland

T2 - 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

Y2 - 14 September 2020 through 14 September 2020

ER -

Pezzato C, Baioumy M, Corbato CH, Hawes N, Wisse M , Ferrari R. Active inference for fault tolerant control of robot manipulators with sensory faults. In Verbelen T, Lanillos P, Buckley CL, De Boom C, editors, Active Inference: Proceedings of the First International Workshop, IWAI 2020, Co-located with ECML/PKDD 2020. Cham, Switzerland: Springer. 2020. p. 20-27. (Communications in Computer and Information Science). doi: 10.1007/978-3-030-64919-7_3

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

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this