Neurotechnology for prosthetic legs enables natural movement control

Researchers have decoded leg movement signals directly from peripheral nerves in amputees, paving the way for prosthetic legs with more natural control and sensory feedback.

A research team led by Chalmers University of Technology has demonstrated a new approach to prosthetic leg control by directly reading signals from the nervous system. Published in Nature Communications, the study shows how implantable neurotechnology combined with AI can interpret intended movements in people with above-knee amputations.

Current prosthetic technologies often rely on residual muscle activity or automated mechanical systems. However, this limits control in cases of major amputations where muscles are no longer available.

The new approach focuses on peripheral nerve signals, which remain active even after limb loss. As Giacomo Valle, assistant professor at Chalmers, explains: "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. This means you can find all the information needed within those nerves. The major challenge is extracting that information and understanding the neural code behind it – and that’s been the focus of our work."

The researchers used ultrathin, flexible neural implants placed in the tibial branch of the sciatic nerve. These implants enabled high-resolution recording of nerve activity, which had previously been difficult due to weak signal strength. Unlike earlier studies that focused on upper limbs, this research specifically targets above-knee amputations, addressing a major unmet need in prosthetic development.

To interpret the recorded signals, the team applied an AI method based on spiking neural networks (SNNs). These models process time-based electrical impulses, closely resembling biological neural communication.

Elisa Donati, professor at the University of Zurich and ETH Zürich, states: "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. This is an important step towards low-power, fully implantable systems for more natural control of prosthetic limbs."

In tests with two participants, the system successfully decoded intended leg movements, including movements of the knee, ankle, and even toes.

"With this approach, we were able to map specific nerve signals to specific movements and predict, with high accuracy, which movements the participants were attempting," says Valle. The researchers highlight that even subtle signals, such as the intention to wiggle toes, could be detected.

A key advantage of the technology is its bidirectional functionality. The same implant can be used not only to read motor signals but also to deliver sensory feedback.

"The system is bidirectional," explains Valle. "Once electrodes are implanted inside the nerve, they can be used to communicate bidirectionally with the nervous system. So, for the first time, a single neurotechnology can provide both natural neural control and sensory feedback in the same implantable device."

The study represents a proof of concept for next-generation neuroprosthetics. The next step is to integrate the system into a fully functional prosthetic leg and evaluate its performance in real-world conditions.

MEDICA-tradefair.com; Source: Chalmers University of Technology