NOIR: Neural Signal Operated Intelligent Robots for Everyday Activities
This work addresses the problem of human-robot interaction for general users by replacing traditional methods with direct neural communication, though it appears incremental as it builds on existing brain-robot interfaces and robot learning algorithms.
The authors tackled the problem of enabling humans to command robots for everyday activities using brain signals, achieving success in 20 challenging household tasks such as cooking and cleaning.
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 demonstrates success in an expansive array of 20 challenging, everyday household activities, including cooking, cleaning, personal care, and entertainment. The effectiveness of the system is improved by its synergistic integration of robot learning algorithms, allowing for NOIR to adapt to individual users and predict their intentions. Our work enhances the way humans interact with robots, replacing traditional channels of interaction with direct, neural communication. Project website: https://noir-corl.github.io/.