Groundbreaking reseacher in the field of AI, Prosthesis Design & Biomedical Engineering.
Jon Sensinger, PhD
Jon makes it easier for people with amputations to control their prostheses.
Dr. Jonathon Sensinger is a professor of electrical and computer engineering at the University of New Brunswick in Fredericton and director of the university’s Institute of Biomedical Engineering (IBME). Since 1965, the institute has been producing leading research and real-world solutions for patients. It’s known as one of three international leaders in prothesis control.
An innovator in the field of biomedical engineering, Dr. Sensinger was recruited to UNB in 2013 from the USA’s top rehabilitation hospital, the Shirley Ryan Ability Lab where he was director of the Prosthesis Design and Control Lab.
Dr. Sensinger holds a doctorate Biomedical/Medical Engineering from Northwestern University and a Bachelor of Science in Bioengineering and Biomedical Engineering from the University of Illinois Chicago. He is also co-founder of Coapt LLC, the first company to commercialize artificial intelligence algorithms in prosthetic arms.
His research into the use of bionic limbs equipped with artificial intelligence that responds to touch makes the use of a prosthesis more intuitive for people with amputations.
Research projects with impact:
Using AI to attain human-like function in bionic limbs
Bionic prostheses have restorative potential. However, the complex interplay between intuitive motor control, proprioception, and touch that represents the hallmark of human upper limb function has not been revealed.
Here, we show that the neurorobotic fusion of touch, grip kinesthesia, and intuitive motor control promotes levels of behavioral performance that are stratified toward able-bodied function and away from standard-of-care prosthetic users.
‘Teaching’ bionic limbs to respond to
unexpected behaviours improves performance
Pattern recognition is a useful tool for deciphering movement intent from myoelectric signals. Recognition paradigms must adapt with the user to be clinically viable over time.
Supervised adaptation can achieve high accuracy since the intended class is known, but at the cost of repeated cumbersome training sessions.
Unsupervised adaptation attempts to achieve high accuracy without knowledge of the intended class, thus achieving adaptation that is not cumbersome to the user, but at the cost of reduced accuracy. All supervised adaptation paradigms reduced error over time by at least 26%.