Controlling a Robotic Arm with Brain
Two research groups at EPFL (École polytechnique fédérale de Lausanne) supervised by Prof. Aude G. Billard, and Prof. José del R. Millán developed a machine learning (ML) algorithm that can learn from the patient’s thoughts and enables to control a robot’s movements based on electrical signals from the brain.
This research has potential applications to help tetraplegic patients who are unable to speak or perform any movement to independently perform activities of daily living (ADL).
- Patients move the robot with their thoughts, and no auditory or tactile feedback is needed.
- The electroencephalogram (EEG) scans of the patient’s brain are conducted with electrodes on a head cap.
- Inverse reinforcement learning is deployed to correct the errors.