MIT has created an inflatable prosthetic hand

It’s lighter, cheaper, and as capable as traditional advanced prosthetics.

Advanced prosthetics have opened up a world of new, powerful, smart, and beautiful devices for people with amputated limbs. 

They use AI to help optimize their performance when walking over different types of terrain; they can be controlled utilizing nerve signals — these are called neuroprosthetics — and send signals back to the brain in turn. 

All of this comes at a cost, however — literally. Advanced prostheses can be expensive, running into the tens of thousands of dollars, and are made from heavy materials, from metal and electric motors, which can make them tip the scales at over a pound.

To try and bring the advancements made in prosthetic tech to more people, researchers at MIT and Shanghai Jiao Tong University have created a soft, inexpensive robotic hand that provides many of the same capabilities as other prosthetics but at a fraction of the weight and price.

Advanced prostheses can be expensive, running into the tens of thousands of dollars, and can tip the scales at over a pound

“This is not a product yet, but the performance is already similar or superior to existing neuroprosthetics, which we’re excited about,” Xuanhe Zhao, MIT researcher and engineering professor, said

Marvel-ous inspiration: The researcher’s prosthetic, published in Nature Biomedical Engineering, looks — and works — a lot like Baymax, the inflatable, elastic, and adorable robot hero from Big Hero 6.

Fibers, segmented like finger bones, are arranged around a 3D-printed “palm,” all wrapped in a soft, stretchy material. 

How it works: The fingers work a bit like balloons; instead of being moved by motors, they are flexed using a system of pumps and valves to adjust how much air pressure is in them. he system can be worn on the user’s hip, so the prosthetic only weighs half a pound, about half as much as other prostheses. MIT postdoc Shaoting Lin created a computer model to match air pressures to finger positions. Using these models, the researchers can get the prosthetic to do some common grasps, including a balled fist, cupping your palm, and pinching fingers together. 

“We now have four grasp types. There can be more,” Zhao said. 

To control those grasps, the inflatable hand uses sensors that detect signals from the residual limb. Those signals are then read by an algorithm, which matches them up with the grasps and tells the controller what to do. 

So if someone is thinking of, say, pinching their fingers together, the signals those thoughts generated in their residual limb would be detected, decoded, and fed back to the controller, causing the hand to pinch. 

The inflatable hand provides many of the same capabilities as other prosthetics but at a fraction of the weight and price.

Those signals don’t just go one way, however; the researchers also wanted their soft prosthetic to be able to give users tactile information. Pressure sensors at the end of each fingertip deliver a signal to specific places on the residual limb, letting users know where on the hand is being pressed.

Most neuroprosthetics on the market lack this feature, MIT notes.

Putting the hand to the test: For their proof of concept test, the researchers had two volunteers perform a range of tasks like turning book pages, picking up delicate objects, and writing with both the soft-Baymax-like prosthetic and a traditional one.  

The inflatable hand worked as well or better than the traditional prosthetic, according to the researchers. 

It worked especially well for one volunteer, who took to the hand quick enough to deploy it in everyday actions, including shaking hands, handling a laptop, and petting a cat. When they blindfolded this volunteer, they found that he could tell which finger on the prosthetic was being touched, and even “feel” and discern the size of various bottles. 

“There’s huge potential to make this soft prosthetic very low cost, for low-income families who have suffered from amputation.”

Xuanhe Zhao

“The team sees these experiments as a promising sign that amputees can regain a form of sensation and real-time control with the inflatable hand,” MIT’s statement said. 

The next steps: According to Zhao, the next steps include figuring out better decoders to translate those electrical signals into instructions, making the pump system worn on the waist smaller, and packing in more sensors. 

“There’s huge potential to make this soft prosthetic very low cost, for low-income families who have suffered from amputation,” Zhao said.

We’d love to hear from you! If you have a comment about this article or if you have a tip for a future Freethink story, please email us at [email protected].

Related
OpenAI’s GPT-4 outperforms doctors in another new study
OpenAI’s most powerful AI model, GPT-4, outperformed junior doctors in deciding how to treat patients with eye problems.
AI can help predict whether a patient will respond to specific tuberculosis treatments
Instead of a one-size-fits-all treatment approach, AI could help personalize treatments for each patient to provide the best outcomes.
In a future with brain-computer interfaces like Elon Musk’s Neuralink, we may need to rethink freedom of thought
In a future with more “mind reading,” thanks to computer-brain interfaces, we may need to rethink freedom of thought.
Personalized cancer vaccines are having a moment
Personalized cancer vaccines were a recurring theme at the annual meeting of the American Association for Cancer Research in 2024.
When an antibiotic fails: MIT scientists are using AI to target “sleeper” bacteria
Most antibiotics target metabolically active bacteria, but AI can help efficiently screen compounds that are lethal to dormant microbes.
Up Next
keyhole surgery
Subscribe to Freethink for more great stories