# A Hybrid Neural-Machine Interface for Volitional Control of a Powered Lower Limb Prosthesis

> **NIH NIH K00** · UNIVERSITY OF PENNSYLVANIA · 2022 · $72,598

## Abstract

Project Summary
 The goal of the proposed work is to develop a robust hybrid neural-machine interface (NMI),
combining brain and muscle signals, to improve overall control of a lower limb prosthetic device during
activities of daily living. Limb amputation affects over 600,000 individuals annually in the US, and is a major
cause of physical disability that causes activities of daily living to become difficult or impossible for the amputee.
The limitations of current lower-limb prostheses are associated with limited volitional control, reduced mobility,
and chronic gait abnormalities, which have been linked to exhaustion from increased energy expenditure,
increased risk of falling, and degenerative bone and joint disorders in both the intact and amputated limb. In this
study, EMG signals from both residual and intact lower limbs and EEG signals from the cortex are leveraged to
decode transitions to and from various modes of locomotion modes in able-bodied individuals and transfemoral
amputees, and to provide a global understanding of movement at the cortical, muscular, and kinematic level in
amputees. Specifically, time and frequency domain features are leveraged to create a prediction algorithm
capable of identifying upcoming terrain transitions in advance. In lower limb amputees, this hybrid NMI paradigm
translates to volitional control of a powered lower-limb prosthesis, which allows for seamless transitions between
various movement conditions. The high-level of control is expected to result in significant increases in level of
activity and overall improvements in gait. Previous studies have demonstrated the feasibility of EEG or EMG
based NMIs for orthotic and prosthetic devices; however, no study to date has integrated EEG and EMG in a
NMI for powered lower limb prostheses. This study is motivated by the need to explore advanced neural control
sources for intuitive control of artificial limbs.
 This project aligns directly with the Mission & Goals of the NIH, the Brain Initiative, and NIH’s Blueprint
Program by expanding fundamental knowledge of neuroscience, human, health and wellness; by utilizing an
innovative research strategy; and ultimately returning the knowledge to the public through the development of a
highly advanced medical technology. Furthermore, the technology developed through this work has implications
beyond the amputee population in the treatment of many neurological conditions and injuries, such as in
neurorehabilitation after stroke. The innovation of this project lies in the novel approach of using multimodal
neural signals and movement synergies as a framework for interpreting movement of the lower limb. The
scientific impact is realized by a greater understanding of the neural correlates of movement after lower-limb
amputation. The direct clinical significance for the patient can be measured directly through improved gait
performance and walking confidence, leading to increased mobility and a reduced risk of falling, e...

## Key facts

- **NIH application ID:** 10492006
- **Project number:** 5K00NS105210-05
- **Recipient organization:** UNIVERSITY OF PENNSYLVANIA
- **Principal Investigator:** Justin Alexander Brantley
- **Activity code:** K00 (R01, R21, SBIR, etc.)
- **Funding institute:** NIH
- **Fiscal year:** 2022
- **Award amount:** $72,598
- **Award type:** 5
- **Project period:** 2017-09-28 → 2023-02-28

## Primary source

NIH RePORTER: https://reporter.nih.gov/project-details/10492006

## Citation

> US National Institutes of Health, RePORTER application 10492006, A Hybrid Neural-Machine Interface for Volitional Control of a Powered Lower Limb Prosthesis (5K00NS105210-05). Retrieved via AI Analytics 2026-05-25 from https://api.ai-analytics.org/grant/nih/10492006. Licensed CC0.

---

*[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*