Detecting intention to grasp during reaching movements from EEG

Abstract

Abstract-Brain-computer interfaces (BCI) have been shown to be a promising tool in rehabilitation and assistive scenarios. Within these contexts, brain signals can be decoded and used as commands for a robotic device, allowing to translate user's intentions into motor actions in order to support the user's impaired neuro-muscular system. Recently, it has been suggested that slow cortical potentials (SCPs), negative deflections in the electroencephalographic (EEG) signals peaking around one second before the initiation of movements, might be of interest because they offer an accurate time resolution for the provided feedback. Many state-of-the-art studies exploiting SCPs have focused on decoding intention of movements related to walking and arm reaching, but up to now few studies have focused on decoding the intention to grasp, which is of fundamental importance in upper-limb tasks. In this work, we present a technique that exploits EEG to decode grasping correlates during reaching movements. Results obtained with four subjects show the existence of SCPs prior to the execution of grasping movements and how they can be used to classify, with accuracy rates greater than 70% across all subjects, the intention to grasp. Using a sliding window approach, we have also demonstrated how this intention can be decoded on average around 400 ms before the grasp movements for two out of four subjects, and after the onset of grasp itself for the two other subjects.

Analyzing and Decoding Natural Reach-and-Grasp Actions Using Gel, Water and Dry EEG Systems

“…No significant differences in performance between recording systems could be found anymore. Unfortunately, a direct comparison to other reach-and-grasp studies such as ( Agashe et al, 2015 ; Randazzo et al, 2015 ; Iturrate et al, 2018 ) is difficult due significant differences in experimental setup and paradigm and hence cannot be made in a serious manner.…”

“…Recent investigations have shown that brain patterns of singular upper limb movements can be identified and decoded from EEGs’ low frequency time domain (LFTD) signals. These so called movement-related cortical potentials (MRCPs) ( Shibasaki et al, 1980 ) have been shown to hold discriminable information of upper limb movements ( Ofner et al, 2017 ), different grasps ( Agashe et al, 2015 ; Jochumsen et al, 2016 ), different reach-and-grasp actions ( Randazzo et al, 2015 ; Iturrate et al, 2018 ; Schwarz et al, 2018 , 2019 ) and can even be decoded online ( Ofner et al, 2019 ; Schwarz et al, 2020 ).…”

mano: A Wearable Hand Exoskeleton for Activities of Daily Living and Neurorehabilitation

“…By showing that subject-dependent classifiers were able to uncover discriminable patterns between pure passive motions and exoskeleton-assisted motor imagery, this work started to tackle several open questions regarding continuous control exploiting only EEG signals. As an alternative, we have recently shown that other neural correlates could be used for the control of similar systems [34], [35].…”

Interfaz cerebro-computador multimodal para procesos de neurorrehabilitación de miembros superiores en pacientes con lesiones de médula espinal: una revisión

“…Implementar una BCI multimodal que pueda decodificar la intención de movimiento antes que este se produzca es clave para brindar esa sensación de comando natural del dispositivo de asistencia del miembro superior. Muchos trabajos han sido publicados en la literatura científica alrededor de esta problemática [35,[57][58][59][60][61][62][63][64], sin embargo este tipo de BCI actualmente requieren de largos periodos de entrenamiento para lograr un nivel aceptable de naturalidad al comandar el dispositivo de asistencia del miembro superior, esto hace que en la mayoría de los casos pierdan el interés en el uso de este tipo de interfaces, este fenómeno inclusive ocurre en sujetos sanos.…”