GoKawiilPurdue and MIT researchers build AI robot that learns stroke rehab from therapists
Johannes Lachner, now an assistant professor at Purdue, and former MIT visiting student Noah Geiger developed a robotic system that combines generative AI with real-time force feedback to learn from human physical therapists. The system then applies this learned behavior to assist stroke patients with exercises such as reaching, raising their arms, and practicing daily living tasks, adjusting the level of help it provides.
GoKawiil's interpretation of the reporting above, not reported fact.
With roughly 5 million stroke survivors facing long-term impairment each year and a shortage of physical therapists, tools that can replicate therapist techniques could widen access to rehabilitation care. Lachner frames the system as a complement rather than a substitute for therapists, suggesting it could let clinicians oversee more patients rather than eliminate their role, though how this plays out in clinical settings remains to be seen.
- Robotic system uses generative AI and force feedback to mimic therapist guidance during rehab exercises
- Developed by Johannes Lachner (Purdue) and Noah Geiger (formerly at MIT)
- Aimed at easing therapist shortages by extending, not replacing, human care
Source: technologyreview.com — Anne Wilson, 2026-10-20
Published there as: “Robotic therapy for stroke patients”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.