Research
Our research group studies questions at the intersection of AI, neuroscience, and engineering. We build brain-machine interfaces to help paralyzed people move again, and we use AI to model and understand how populations of neurons carry out computations in the brain.
Projects
Non-invasive BMIs
We build non-invasive brain-machine interfaces (BMIs) to help people with paralysis move. We record and decode EEG in real-time with state-of-the-art AI to control robotic arms and computer cursors.
Video: A paralyzed participant controls a robotic arm with neural signals recorded through a headcap. Full video + description here.
Shared autonomy
We design algorithms for AI copilots to assist humans with tasks.
Video: A participant is unable to play Lunar Lander well (left) but with IDA, an AI copilot, he plays the game at a high level (right).
EMG interfaces
We build EMG interfaces to non-invasively perform tasks.
Video: Non-invasive EMG control of Pacman and Mario Kart.
