Brain-Computer Interface-Based Humanoid Control: A Review

Abstract

A Brain-Computer Interface (BCI) acts as a communication mechanism using brain signals to control external devices. The generation of such signals is sometimes independent of the nervous system, such as in Passive BCI. This is majorly beneficial for those who have severe motor disabilities. Traditional BCI systems have been dependent only on brain signals recorded using Electroencephalography (EEG) and have used a rule-based translation algorithm to generate control commands. However, the recent use of multi-sensor data fusion and machine learning-based translation algorithms has improved the accuracy of such systems. This paper discusses various BCI applications such as tele-presence, grasping of objects, navigation, etc. that use multi-sensor fusion and machine learning to control a humanoid robot to perform a desired task. The paper also includes a review of the methods and system design used in the discussed applications.

Living Things Are Not (20th Century) Machines: Updating Mechanism Metaphors in Light of the Modern Science of Machine Behavior

“…And even if one holds out for some essential ingredient that, in principle, technology cannot copy, there is the issue of hybridization. Biological brains readily incorporate novel sensory-motor (Bach-y-Rita, 1967;Sampaio et al, 2001;Ptito et al, 2005;Froese et al, 2012;Chamola et al, 2020) and information-processing (Clark and Chalmers, 1998) functions provided by embedded electronic interfaces or machine-learning components that provide smart, closed-loop reward neurotransmitter levels (Bozorgzadeh et al, 2016) or electrical activity which can modulate cognition. Even if "true" preferences, motivations, goal-directedness, symbol grounding, and understanding are somehow only possible in biological media, we now know that hybrid functional systems can be constructed that are part living tissue and part (perhaps smart) electronics (Reger et al, 2000;DeMarse and Dockendorf, 2005;Hamann et al, 2015;von Mammen et al, 2016;Ando and Kanzaki, 2020), presumably conferring all of those features onto the system.…”

Toward EEG-Based BCI Applications for Industry 4.0: Challenges and Possible Applications

“…P300 is a positive event-related potential that is apparent whenever the user has noticed an unexpected or a rare visual or auditory event (e.g., Walter et al, 1964;Donchin and Smith, 1970). Although associated to a fast training, this technique remains very sensitive to surrounding noise and motor artifacts (e.g., Chamola et al, 2020), preventing its use in a noisy or multitasking context. In addition, a single command requires the user to focus their attention on several consecutive events, including nonrelevant (non-rare) and relevant (rare and unexpected) ones, which necessarily decreases the system's speed (e.g., Lotte et al, 2015) while being costly in terms of attentional processes (fatigability).…”

Mind the gap: State-of-the-art technologies and applications for EEG-based brain–computer interfaces

“… 75 To circumvent this limitation, hybrid systems that combine inputs from multiple types of sensors have been developed. 76,77 These hybrid systems have been shown to provide higher ITRs, lower false positive rates, and enhanced man-machine adaptability, when compared to conventional single-mode BCIs. 78 Finally, apart from considerations related to hardware and software components, one critical aspect of eBCI design corresponds to the selection of a system paradigm.…”