NOIR: Neural Signal Operated Intelligent Robots for Everyday Activities

Sharon Lee, Ruohan Zhang, Minjune Hwang, Ayano Hiranaka, Chen Wang, Wensi Ai, Jin Jie Ryan Tan, Shreya Gupta, Yilun Hao, Gabrael Levine, Ruohan Gao, Anthony Norcia, Li Fei-Fei, Jiajun Wu

Keywords: Brain-Robot Interface; Human-Robot Interaction

TL;DR: We present a general-purpose, intelligent brain-robot interface system that enables humans to command robots to perform everyday activities through brain signals.

Abstract:

We present Neural Signal Operated Intelligent Robots (NOIR), a
general-purpose, intelligent brain-robot interface system that enables humans to
command robots to perform everyday activities through brain signals. Through
this interface, humans communicate their intended objects of interest and actions
to the robots using electroencephalography (EEG). Our novel system demon-
strates success in an expansive array of 20 challenging, everyday household ac-
tivities, including cooking, cleaning, personal care, and entertainment. The effec-
tiveness of the system is improved by its synergistic integration of robot learning
algorithms, allowing for NOIR to adapt to individual users and predict their inten-
tions. Our work enhances the way humans interact with robots, replacing tradi-
tional channels of interaction with direct, neural communication

Submission Number: 5