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

Conference paper (2021)

Authors

Mohamed Baioumy University of Oxford
C. Pezzato Robot Dynamics - Mechanical, Maritime and Materials Engineering
Riccardo M.G. Ferrari Team Riccardo Ferrari - Mechanical, Maritime and Materials Engineering
Carlos Hernández Robot Dynamics - Mechanical, Maritime and Materials Engineering
Nick Hawes University of Oxford
Research Group
Robot Dynamics (Mechanical, Maritime and Materials Engineering) (TU Delft)
Copyright: © 2021 Mohamed Baioumy, C. Pezzato, Riccardo M.G. Ferrari, Carlos Hernández, Nick Hawes
DOI: https://doi.org/10.23919/ECC54610.2021.9654913
More Info
expand_more

Published Date

2021

Language

English

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.

Faculty

Mechanical, Maritime and Materials Engineering

Department

Cognitive Robotics

Research Group

Robot Dynamics

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