For the first time, scientists have successfully decoded detailed leg movements from the existing nerves of individuals with above-knee amputations, thanks to new prosthetic leg technology developed by researchers at Chalmers University of Technology.
Using implantable neurotechnology and an AI method that interprets the nervous system’s own “language,” the team has been able to read signals linked to small movements, such as the intent to wiggle toes. This new capability represents a major step forward in developing prostheses that move and feel more like natural limbs.
While prosthetics have long been helpful, they have also presented challenges in everyday use. These new developments could significantly improve users’ functional independence. In the past, arm and hand prostheses relied on remaining muscles that still responded to brain signals. However, this approach is limited in cases of major amputation, where those muscles may no longer be present. For leg prostheses, control has typically been mechanical, using sensors to automatically adjust walking patterns without direct user input.
Published in Nature Communications, the researchers examined how residual nerve signals could be used to enable more intuitive control of prosthetic legs.
“When you tell your body to move, signals travel through the nerves to the muscles which carry out the action—even if the limb is no longer there,” explained Giacomo Valle, assistant professor at Chalmers and senior author of the study. “The major challenge is extracting that information and understanding the neural code behind it—and that’s been the focus of our work.”
However, capturing neural signals is not easy. Previous research has focused on upper-limb prosthetics, while lower-limb amputations are more common than expected.
“If an implant can be connected directly to the remaining nerves, instead of through residual muscles, you can use exactly the same natural signals used to move your limbs. It greatly increases the potential to create prostheses with natural control, sensory feedback, and unprecedented resolution,” adds Valle.
The Chalmers team overcame this by combining a flexible, ultrathin neural implant with an AI algorithm based on Spiking Neural Networks (SNNs). Unlike earlier forms of AI, SNNs process electrical impulses—also known as “spikes”—used by biological neurons, making them particularly effective for interpreting nerve activity.
The system was tested on two individuals with above-knee amputations. Researchers implanted four extremely thin wires into a key nerve responsible for leg movement and sensation.
Even though their leg was no longer present, attempts to move it still generated neural signals. The system was able to interpret those signals with unprecedented precision, identifying the intended movements more accurately than previous methods.
“This is the first study to demonstrate that signals recorded directly from peripheral nerves can be used to accurately interpret intended leg movements in amputees,” Valle said. The technology was capable of distinguishing specific movements of the knees, ankles, and even toes.
“Our study shows that decoding peripheral nerve activity works best when it respects the language of the nervous system,” said Elisa Donati, professor at the University of Zurich and ETH Zürich and senior author of the study. “Peripheral nerves communicate through discrete electrical impulses–or spikes–and spiking neural networks are therefore naturally suited to processing this type of signal.”
“By aligning our computational models more closely with biology, we can extract movement intent efficiently, using compact models and relatively limited data,” Donati added. “This is an important step towards low-power, fully implantable systems for more natural control of prosthetic limbs.”
While the study stands as a proof of concept, the goal is ultimately to integrate these new findings into a functional prosthetic leg.
Chrissy Newton is a PR professional and the founder of VOCAB Communications. She currently appears on The Discovery Channel and Max and hosts the Rebelliously Curious podcast, which can be found on YouTube and on all audio podcast streaming platforms. Follow her on X: @ChrissyNewton, Instagram: @BeingChrissyNewton, and chrissynewton.com. To contact Chrissy with a story, please email chrissy @ thedebrief.org.