Soft robotic wearable could transform stroke and ALS recovery

For many people living with neurodegenerative diseases or recovering from stroke, daily routines can become exhausting challenges. Simple actions like brushing teeth, raising a fork, or combing hair demand strength and coordination that weak muscles can no longer provide. The loss of such movements chips away at independence.

Yet scientists and engineers are finding new ways to restore that independence through technology. A team of researchers has developed a soft, wearable robotic device that adapts to an individual’s unique movement patterns, making everyday actions less of a struggle. The system doesn’t just offer mechanical support—it learns, adjusts, and personalizes assistance so that it feels like a natural extension of the body.

At the heart of this breakthrough is a carefully engineered mix of robotics, sensors, and machine learning. And for those who have lost mobility, it could mean the difference between relying on others and regaining a measure of self-sufficiency.

When Kate Nycz was diagnosed with ALS in 2018, she was only 33. Over time, she lost much of her arm strength, which made eating, writing, and other daily motions frustrating and tiring. Now 39, she has tested several versions of the soft robotic device, offering feedback to improve its design.

“My arm can get to maybe 90 degrees, but then it fatigues and falls,” Nycz explained. “To eat or do a repetitive motion with my right hand, which was my dominant hand, is difficult. I’ve mainly become left-handed.” For people like her, the robot represents not just a tool, but hope. “I’m big on technology and devices to help improve quality of life for people living with ALS … I feel like this robot could help with that goal,” she said.

Developed by engineers at the John A. Paulson School of Engineering and Applied Sciences, in collaboration with physicians at Massachusetts General Hospital and Harvard Medical School, the device uses a soft vest fitted with sensors and a balloon-like support under the arm. The balloon inflates or deflates to help lift or lower a weakened limb.

Earlier versions could provide lifting force but sometimes resisted when a person tried to bring the arm back down. That meant some users needed more residual strength than they had to counter the robot’s push. To address this, the team introduced two complementary models.

The first is a machine learning system that decodes a person’s motion intentions by analyzing sensor data from motion and pressure changes. The second is a physics-based model that estimates the minimum pressure needed to support the arm without over-assisting. When combined, these models allow the robot to recognize subtle movement attempts and adjust its help in real time.

Graduate student James Arnold, co-first author of the study, explained: “Some people didn’t have enough residual strength to overcome any kind of mistake the robot was making.” With the new software, the robot responds more naturally, easing the effort needed for actions like eating or drinking.

The team tested the system with nine volunteers, including five recovering from stroke and four living with ALS. The results, published in Nature Communications, were striking. The controller recognized shoulder movement with 94.2% accuracy from minimal changes in angle. Users needed nearly one-third less effort to lower their arms compared to earlier models.

Not only did force demands drop, but movement quality improved. Range of motion increased in shoulders, elbows, and wrists, while trunk compensation—leaning or twisting to make up for weak arms—was cut by as much as 25%. Even the efficiency of hand movements improved by more than 50%, meaning motions were smoother and closer to natural patterns.

Stroke specialist Dr. David Lin, co-author of the study, has worked with the engineering team for more than six years. He emphasized that the design process involved both clinical and patient perspectives from the beginning. ALS researcher Dr. Sabrina Paganoni agreed, adding: “This collaborative approach allowed us to work together on the very initial prototypes and study design.”

For Nycz, who provided long-term feedback, the partnership has been rewarding. “They’ve done a great job incorporating and including the person,” she said. “They’re not sitting in the lab just playing with the robot. I felt like they were really engaged with me. I didn’t feel like a lab rat or a cog in a wheel.”

The need for personalization is critical. No two people move in exactly the same way, especially those with neurological impairments. ALS gradually robs people of motor control, while stroke survivors often work toward regaining lost movement. That means the same robot must adapt to different goals—long-term support for one group, rehabilitation for another.

Dr. Paganoni explained: “For people living with ALS, the most important considerations include comfort, ease of use, and the ability of the device to adapt to their specific needs and movement patterns. Personalization is crucial to enhance their functional independence and quality of life.”

By tailoring assistance through machine learning, the robot provides nuanced help for both populations. For stroke patients, it supports the gradual return of muscle activity. For those with ALS, it eases daily fatigue and extends the ability to perform tasks for as long as possible.

To evaluate how well the robot helped, researchers borrowed techniques from the entertainment industry. Using motion capture systems similar to those that create lifelike animations in movies, they tracked joint movement during daily activities.

Co-first author and postdoctoral fellow Prabhat Pathak explained: “What we did here was look at simulated activities of daily living, using a highly accurate motion capture system. We looked at how each and every joint movement changed, and if they were able to do the tasks more efficiently.” That detailed view confirmed what participants reported: smoother motions, less reliance on body compensation, and a closer return to natural activity.

While the device is still being tested, the long-term vision is broad. It could eventually serve anyone with upper limb impairments, from older adults with age-related weakness to those recovering from injuries. The adaptability makes it promising for both clinical therapy settings and home use.

As research continues, the collaboration between engineers, physicians, and patients remains central. The technology is not about replacing movement but about restoring independence, dignity, and quality of life. For Nycz, and for many others, that hope is reason enough to keep going.

Like these kind of feel good stories? Get The Brighter Side of News' newsletter.