An asynchronous wheelchair control by hybrid EEG–EOG brain–computer interface

Abstract

Wheelchair control requires multiple degrees of freedom and fast intention detection, which makes electroencephalography (EEG)-based wheelchair control a big challenge. In our previous study, we have achieved direction (turning left and right) and speed (acceleration and deceleration) control of a wheelchair using a hybrid brain-computer interface (BCI) combining motor imagery and P300 potentials. In this paper, we proposed hybrid EEG-EOG BCI, which combines motor imagery, P300 potentials, and eye blinking to implement forward, backward, and stop control of a wheelchair. By performing relevant activities, users (e.g., those with amyotrophic lateral sclerosis and locked-in syndrome) can navigate the wheelchair with seven steering behaviors. Experimental results on four healthy subjects not only demonstrate the efficiency and robustness of our brain-controlled wheelchair system but also indicate that all the four subjects could control the wheelchair spontaneously and efficiently without any other assistance (e.g., an automatic navigation system).

Review of real brain-controlled wheelchairs

“…Furthermore, the characteristics of the signal P300 was extracted through CSP in the proposal of Wang et al (52) while in the BCW of Puanhvuan and Wongsawat (40) a magnitude summing method was presented. However, there was one proposal which used the raw signal, the BCW of (38).…”

“…Percentage of hits (37) Qualitative evaluation (38) Time required (40) Success rate, time required and transfer rate (commands per minute) (42) Task success, path length, time, used commands, collisions and obstacle clearance (minimum and average distance to the obstacles) (45) Time optimality rate (51) Success rate and error rate (specified in false positives and false negatives) (52) Task success, path length, time required, path length optimality ratio and time optimality ratio (56) Task success, path length, time required, path length optimality ratio and time optimality ratio, collisions, mean velocity, workload, learnability, confidence and difficulty signal (28,46,57). Other papers used methods such as learning vector quantization in mu and beta bands (43), the logarithmic value in the bands of interest (34,35), the common spatial patterns (CSP) (44,59) …”

“…Nine BCWs assisted with muscle signal publications were found: seven were based on an ERD/ERS signal (36)(37)(38)42,45,51,56), one on P300 signal (40) and one was hybrid of ERD/ERS and P300 signals (52). There was no muscledassisted BCW based on an SSVEP signal.…”

“…Six BCWs used a low-level operation (37,38,45,51,52,56), two high-level (36,42) and one shared control, in which the user could select the type of management by blinking, depending on their needs (40). There was a clear trend to use low-level navigation in muscle-assisted systems, a fact that may be related to the use of an ERD/ERS signal in most of these systems.…”

“…The most used metric was the success rate, followed by the time required to complete the path. Only two studies included optimized metrics, in terms of time or distance employed to complete the path (45,52). The article with a more complete assessment of muscled-assisted BCWs was published by Wang et al (52), and was based on some of the metrics used by Iturrate et al (29).…”