From MIT Technology Review · · 1m
AI robot learns from therapists to help stroke patients
A new robotic system trained on real therapists uses AI to provide personalized physical rehabilitation, aiming to extend care as therapist shortages grow.
In brief
A new robotic system trained on real therapists uses AI to provide personalized physical rehabilitation, aiming to extend care as therapist shortages grow. Researchers at Purdue and MIT developed a robotic therapy system using generative AI to learn from human therapists and assist stroke patients with rehabilitation…
Stroke patients face therapy shortage
Strokes leave five million people with long-term impairments each year, but a growing shortage of physical therapists makes it hard for them to get the care they need.
Robot learns from real therapists
Johannes Lachner at Purdue University and Noah Geiger developed a robotic system using generative AI and real-time force feedback to learn from human therapists and provide personalized assistance during rehabilitation exercises.
“not to replace therapists, but to extend their reach”
Clinical trials and future applications
Initial robotic experiments have demonstrated feasibility. The next phase aims to develop therapist-specific models and evaluate them in a long-term clinical study with patients who previously received manual therapy.
The big picture
Researchers at Purdue and MIT developed a robotic therapy system using generative AI to learn from human therapists and assist stroke patients with rehabilitation exercises.
