Controllers for Functional Electrical Stimulation (FES) are still not able to restore natural movements in the paretic arm. In this work, Reinforcement Learning (RL) is used for the first time to control a hybrid upper limb robotic system for stroke rehabilitation in a real environment. The feasibility of the FES controller is tested on one healthy subject during elbow flex-extension in the horizontal plane. Results showed an absolute position error <1.2° for a maximum range of motion of 50°.
An upper limb Functional Electrical Stimulation controller based on Reinforcement Learning: A feasibility case study.
D. Di Febbo;E. Ambrosini;M. Pirotta;M. Restelli;A. Pedrocchi;S. Ferrante
2018-01-01
Abstract
Controllers for Functional Electrical Stimulation (FES) are still not able to restore natural movements in the paretic arm. In this work, Reinforcement Learning (RL) is used for the first time to control a hybrid upper limb robotic system for stroke rehabilitation in a real environment. The feasibility of the FES controller is tested on one healthy subject during elbow flex-extension in the horizontal plane. Results showed an absolute position error <1.2° for a maximum range of motion of 50°.File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
document_diFebbo_GNB18.pdf
accesso aperto
Descrizione: Articolo principale
Dimensione
230.38 kB
Formato
Adobe PDF
|
230.38 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
