Developing a Motor Imagery-Based Real-Time Asynchronous Hybrid BCI Controller for a Lower-Limb Exoskeleton

Abstract

This study aimed to develop an intuitive gait-related motor imagery (MI)-based hybrid brain-computer interface (BCI) controller for a lower-limb exoskeleton and investigate the feasibility of the controller under a practical scenario including stand-up, gait-forward, and sit-down. A filter bank common spatial pattern (FBCSP) and mutual information-based best individual feature (MIBIF) selection were used in the study to decode MI electroencephalogram (EEG) signals and extract a feature matrix as an input to the support vector machine (SVM) classifier. A successive eye-blink switch was sequentially combined with the EEG decoder in operating the lower-limb exoskeleton. Ten subjects demonstrated more than 80% accuracy in both offline (training) and online. All subjects successfully completed a gait task by wearing the lower-limb exoskeleton through the developed real-time BCI controller. The BCI controller achieved a time ratio of 1.45 compared with a manual smartwatch controller. The developed system can potentially be benefit people with neurological disorders who may have difficulties operating manual control.

A Hybrid Brain–Computer Interface for Real-Life Meal-Assist Robot Control

“…There have been numerous prior research studies aiming at the development of highly accurate asynchronous BCI [ 31 , 32 ]. Therefore, several recent studies on real-life BCI [ 5 , 13 ], including the current study, used eye-blink as an activation mechanism. (4) The proposed system used EMG for real-life purposes to detect chewing a morsel, on which the system determined the end of the user’s a single meal cycle.…”

“…In particular, their self-esteem decreases if they cannot even perform basic activities such as walking and eating, which consequently increases their helplessness. Recently, robots have been actively developed for applications in healthcare [ 3 ], such as home-assist robots [ 4 ], exoskeleton robots [ 5 ], and meal-assist robots [ 6 ]. These robots have progressed from being directly controlled to completely automatic applications.…”

“…Thus, many researchers have conducted studies based on human–computer interactions (HCIs) [ 8 , 9 ]. There are various studies on healthcare robots based on augmented/virtual reality (AR/VR) [ 9 ], voice [ 7 ], and electroencephalograms (EEG) [ 5 , 6 ].…”

“…Non-invasive brain–computer interfaces (BCIs) are HCI methods based on non-invasive measurements such as EEG [ 10 , 11 ]. Several scholars have studied the daily-life application of non-invasive BCIs: assist robots [ 5 , 12 ], smart home [ 13 , 14 , 15 ], emotion detectors [ 16 ], and wheelchairs [ 17 ]. In particular, BCI-based assist robots are expected to be in practical application for the disabled and elderly population.…”

“…In particular, BCI-based assist robots are expected to be in practical application for the disabled and elderly population. Typically, the methods used for transferring human intentions include motor imagery (MI), event-related potential (ERP), and steady-state evoked potential (SSVEP) [ 5 , 13 , 15 ]. Research based on MI is advantageous for intuitively controlling the devices.…”