Professor Arash Arami uses machine learning and system identification techniques to uncover the neural control of human movements and to design optimal controllers and AI for assistive robotic systems such as exoskeletons.
Using the identified neuromechanics, control theory and the recent findings in the field of human motor control and movement neuroscience, Professor Arami and the researchers in his lab design assistive controllers for robotic systems that will assist human subjects in a collaborative manner.
Machine learning techniques are widely used in their robotic system control approaches to provide intention decoding and adaptation to the needs of each subject. They also benefit from wearable systems and in-field movement analysis to evaluate the effect of their assistive and rehabilitation robotic systems.
See Professor Arami's faculty profile for more details about his work outside of the RoboHub.