Fault-tolerant Control of Robot Manipulators with Sensory Faults using Unbiased Active Inference

Conference Paper (2021)
Author(s)

Mohamed Mohamed Ashraf Mohamdy Baioumy (University of Oxford)

C. Pezzato (TU Delft - Robot Dynamics)

R. Ferrari (TU Delft - Team Riccardo Ferrari)

Carlos Hernandez Hernández (TU Delft - Robot Dynamics)

Nick Hawes (University of Oxford)

Research Group
Robot Dynamics
Copyright
© 2021 Mohamed Baioumy, C. Pezzato, Riccardo M.G. Ferrari, Carlos Hernández, Nick Hawes
DOI related publication
https://doi.org/10.23919/ECC54610.2021.9654913
More Info
expand_more
Publication Year
2021
Language
English
Copyright
© 2021 Mohamed Baioumy, C. Pezzato, Riccardo M.G. Ferrari, Carlos Hernández, Nick Hawes
Research Group
Robot Dynamics
Pages (from-to)
1119-1125
ISBN (print)
978-1-6654-7945-5
ISBN (electronic)
978-9-4638-4236-5
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

This work presents a novel fault-tolerant control scheme based on active inference. Specifically, a new formulation of active inference which, unlike previous solutions, provides unbiased state estimation and simplifies the definition of probabilistically robust thresholds for fault-tolerant control of robotic systems using the free-energy. The proposed solution makes use of the sensory prediction errors in the free-energy for the generation of residuals and thresholds for fault detection and isolation of sensory faults, and it does not require additional controllers for fault recovery. Results validating the benefits in a simulated 2-DOF manipulator are presented, and future directions to improve the current fault recovery approach are discussed.

Files

Fault_tolerant_Control_of_Robo... (pdf)
(pdf | 1.2 Mb)
- Embargo expired in 03-07-2022
License info not available