This project aims to create an intuitive communication channel between humans and robots that uses naturally occurring brain signals - to allow robots to adapt to humans rather than the other way around.

Seamless communication between humans and robots is a critical condition for successful human-robot interaction; not only for safety purposes but to properly convey information, coordinate activities, and minimize the cost of collaborative actions. In these human-robot scenarios, humans are required to act as critics and communicate the decisions via an input device (i.e. keyboard, mouse), which alienates them (albeit briefly) from the real goal of the task. Our research focuses on using specific brain signals that respond to success or failure events in order to inform the other agents of such outcomes so that these can adapt their strategies and, in the long term, learn the optimal behavior.

Check out our YouTube videos here and here, and see the DRL website page for more information (including the paper PDF).

 

Project members include Andres F. Salazar-Gomez, Joseph DelPreto, Stephanie Gil, Frank H. Guenther, and Daniela Rus.