Abstract
As next generation robotics and automation move toward high stakes environments ranging from autonomous navigation to assistive healthcare, the reliance on conventional manual programming and physical control interfaces presents a significant barrier to real-time efficiency. This session explores the paradigm of The Invisible Interface, where interaction is driven by the decoding of internal human intent through Brain-Computer Interfaces (BCI) and Electrooculography (EOG).

Drawing on extensive research in EEG signal processing, automated artifact removal, and the development of BCI-driven wheelchair and UAV navigation, this discussion examines how advanced machine learning algorithms (such as SVM, CNNs, and deep learning) can transform raw physiological signals into actionable commands. By integrating multi-scale feature extraction and intelligent signal classification, we conducted EOG based controlled wheel chair and objective identification of pain due to uterine contraction during the first stage of labour using continuous EEG signals and SVM. This eventually can create a “transparent” loop between the user’s neural intent and potential application on natural user interface. We proposing that the ultimate interface is one that is not seen or touched, but felt moving toward an era where intelligent system function as an intuitive extension of the human motor and cognitive system.