A Smart Exoskeleton Glove Helps People With Hand Paralysis Grasp Everyday Objects
Key Takeaways:
- Researchers in Munich have built a soft, air-powered glove that helps people with hand paralysis grasp everyday objects again.
- Electrical signals from the forearm muscles, read by machine learning, predict a person’s intention to grasp with up to 97% reliability.
- A man living with ALS used the glove to hold a fork for the first time in four years.
A soft exoskeleton driven by air and intention
A soft, pneumatic glove developed at the Technical University of Munich (TUM) is giving people with hand paralysis a way to grasp objects once more. The device was created by researchers at the TUM Chair of Cognitive Systems, who use electrical signals from the forearm muscles to reliably predict the moment a person intends to reach for something. Its designers believe it could one day support people whose hands have been paralysed as a result of accidents or neurological disorders. The research is published in the journal Nature Machine Intelligence.
The team calls the device a “soft-hand exoskeleton”. At its heart is a fabric glove, developed by the researchers, with air cushions fitted to its outer surface. Those cushions are inflated through a total of 13 tubes, each one providing targeted support for the specific hand movements needed to hold a plate or grasp a glass, fork or spoon. Because the cushions can be inflated independently, every finger can be bent and straightened on its own, and the wrist can be rotated too, so that an object can be held securely in the hand.
Reading the intention to grasp
The clever part is knowing when the wearer actually wants to grasp something. To work this out, the researchers measure muscle activity in the forearm. Sensors placed on the forearm capture the faint electrical signals produced by the muscles, and machine learning then analyses those signals to determine the intended movement.
Keeping hold of an object once it has been picked up is a separate challenge. “To prevent objects from being dropped accidentally, we use additional motion sensors to detect transport movements and keep the exoskeleton’s grip securely closed throughout the movement,” says researcher Nicolas Berberich.
Devices like the soft-hand exoskeleton reflect a wider movement of artificial intelligence into everyday clinical care, and professional bodies have increasingly urged healthcare professionals to build the judgement needed to use such tools safely and effectively – the focus of the CPD-accredited digital health training now offered by providers including the College of Contemporary Health.
A soft-hand exoskeleton that anyone can afford
For the team, the appeal of the glove lies as much in its simplicity as in its sophistication. “Our solution is intelligent in two ways,” explains Dr John Nassour. “On the one hand, we’ve developed a highly reliable method of predicting grasping movements by inferring intentions from signals with 97% reliability. On the other hand, with our glove, we’ve developed hardware that optimally supports the intended movements.”
There is a practical advantage on top of that. Dr Nassour sewed the glove himself, and the fabric it requires costs very little. It may not look high-tech at first glance, but it can be used by many people living with paralysis. “We’ve found a solution that anyone can afford but still works very well,” says Prof. Gordon Cheng, director of the Institute for Cognitive Systems.
Central to the project was close collaboration with a man living with amyotrophic lateral sclerosis (ALS).
Working with a person living with ALS
People with ALS gradually lose control of their movements. This happens because the nerve cells responsible for contracting skeletal muscle become damaged and continue to degenerate over time.
By the start of the project, the participant already had very little control over his hands, but he could still move the first joint of his thumb. The researchers built their approach around the strongest signals his thumb muscles could still produce. To record this electromyogram, they attached a sensor to his forearm that picks up the strong signals from the flexor pollicis longus muscle as soon as it moves. Those signals, in turn, trigger the inflation of the glove’s air cushions.
Picking up a fork for the first time in four years
Even though the signals were very weak, the system correctly recognised the participant’s intention in 9 out of 10 cases. With the glove’s support, he was able to reach for objects, hold a fork for the first time in four years, and pick up small cubes and drop them into a container.
A video game played its own part in that progress. The participant had to make a character jump using only the movement of his thumb joint, a simple exercise that helped sharpen the system’s response. The researchers found that just five minutes of this practice was enough to greatly improve his ability to grasp objects. “This patient has shown us that our soft-hand exoskeleton can support him despite one of the most severe neurological disorders,” says Prof. Cheng.
Adapting the glove for more people
The team is now looking beyond ALS. “We are now adapting the concept for other patients, such as stroke survivors,” the researcher adds. A central finding of the current study is that people with severe impairments can more effectively regain the ability to grasp objects with the help of the glove.
That potential is echoed by clinicians working alongside the researchers. Neurologist Prof. Tobias Wächter, from the partner institution Klinik Passauer Wolf, is convinced of what the specialised glove could offer. “In principle, this glove can help people with flaccid paralysis, including, for example, people who have sustained peripheral nerve damage following motorcycle or bicycle accidents, or patients with polyneuropathy,” says Prof. Wächter.
CCH insight
As AI-assisted and digital health tools move from the research lab into everyday practice, the ability to evaluate them safely and confidently is fast becoming a core clinical skill. The College of Contemporary Health’s CPD-accredited short course AI Essentials for Primary Care (3.5 CPD hours) helps nurses, pharmacists, physician associates and the wider team assess new tools, work within clinical governance, and use them responsibly in patient care – no technical background required.
Explore AI Essentials for Primary Care →
Read More