The system is described in a study published June 19 in Science Robotics and conducted by researchers from Carnegie Mellon University in Pittsburgh and the University of Minnesota in Minneapolis. They used novel sensing and machine learning techniques to train the interface to decode neural signals.
In the study, a group of able-bodied participants were enlisted to test the interface. With sensors attached to a helmet-like device on their heads, the system translated their brain signals to control the robotic arm, which was used to continuously track and follow a computer cursor on a screen, to great success.
According to the researchers, the technology could eventually be used to help patients with paralysis and movement disorders complete everyday tasks. “There have been major advances in mind-controlled robotic devices using brain implants,” said Bin He, PhD, head of Carnegie Mellon’s biomedical engineering department. “But noninvasive is the ultimate goal. Advances in neural decoding and the practical utility of noninvasive robotic arm control will have major implications on the eventual development of noninvasive neurorobotics.”
More articles about AI:
FDA clears tool for radiologists to accept, reject, interact with AI imaging data
Updated White House AI policy prioritizes public-private collaboration
Philips updates AI-enabled cardiac ultrasound platform to make it faster, easier to use
