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.
|Title of host publication||Proceedings of the European Control Conference (ECC 2021)|
|Publication status||Published - 2021|
|Event||2021 European Control Conference (ECC) - Virtual , Netherlands|
Duration: 29 Jun 2021 → 2 Jul 2021
|Conference||2021 European Control Conference (ECC)|
|Period||29/06/21 → 2/07/21|
Bibliographical noteGreen 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.
- Fault-tolerant control
- fault recovery
- active inference
- free-energy principle
- robot manipulator