[Federal Register Volume 91, Number 30 (Friday, February 13, 2026)]
[Notices]
[Pages 6864-6865]
From the Federal Register Online via the Government Publishing Office [www.gpo.gov]
[FR Doc No: 2026-02906]


-----------------------------------------------------------------------

DEPARTMENT OF HEALTH AND HUMAN SERVICES

National Institutes of Health


Government Owned Inventions Available for License: Gait 
Assistance Systems and Methods of Control Thereof

AGENCY: National Institutes of Health, HHS.

ACTION: Notice.

-----------------------------------------------------------------------

SUMMARY: The Clinical Center (CC), an institute/center of the National 
Institutes of Health (NIH), Department of Health and Human Services 
(HHS), is giving notice of the license opportunity for the invention 
listed below, which is owned by an agency of the U.S. Government and is 
available to achieve expeditious commercialization of results of 
federally-funded research and development.

FOR FURTHER INFORMATION CONTACT: Inquiries related to this license 
opportunity should be directed to: Tedd Fenn, J.D., M.S., Technology 
Transfer Manager, NCI, Technology Transfer Center, Email: 
[email protected] or Phone: 240-276-6833.

SUPPLEMENTARY INFORMATION: Human movement disorders such as those 
arising from cerebral palsy cause diminished coordination, impaired 
motor control, and often long-term abnormal walking patterns in 
children and adults. There is a need for more effective interventions 
which can preserve and/or augment mobility and strength on a continuous 
basis for those with such movement disorders, especially in pediatrics. 
Robotic exoskeleton devices and powered orthoses are specifically 
designed for treatment of gait pathologies but better methods of 
controlling such devices/systems to better personalize and adapt them 
to a patient and provide assistive torque, are needed.
    Researchers at the National Institutes of Health Clinical Center 
have developed an adaptive, machine-learning-based method and 
associated computing system for generating personalized assistive 
torque in powered gait assistance systems (e.g., exoskeletons and 
orthotic devices). The method employs a multilayer perceptron (MLP) 
trained on sensor data collected from multiple individuals using 
powered gait assistance systems, including data that may be pre-
processed through attention mechanisms and recurrent neural networks. 
Once trained, the model processes real-time sensor inputs from a new 
user to generate predicted torque values tailored to that individual's 
gait dynamics, or alternatively, to generate a predicted gait cycle for 
the user in which a specific torque profile is applied. These predicted 
torque values are applied directly to a motor in the powered gait 
assistance system, enabling adaptive assistive torque between 
mechanical arms or joints. The approach allows rapid personalization 
without extensive manual tuning or user-specific recalibration. The

[[Page 6865]]

technology uses sensor data and a trained neural network to predict and 
apply individualized torque profiles, enabling more natural, efficient, 
and responsive gait assistance across users with varying biomechanics.
    This Notice is in accordance with 35 U.S.C. 209 and 37 CFR part 404 
and the intellectual property rights have been assigned to the 
Government of the United States of America.
    NIH Reference Number: E-121-2013.
    Product Type: Powered gait assistance systems for robotic orthotic 
devices, powered orthoses, and exoskeleton devices and methods of 
control.
    Therapeutic Area(s): Gait assistance systems.
    Potential Commercial Applications:
     Lower-limb exoskeletons for mobility assistance.
     Rehabilitation robotics for neurological or orthopedic 
conditions.
     Assistive devices for aging or mobility-impaired 
populations.
     Wearable robotic devices for load-bearing assistance in 
military or industrial applications.
    Competitive Advantages:
     Personalized assistance without lengthy calibration.
     Improved gait naturalness and user comfort.
     Scalable across users and device platforms.
     Compatible with real-time sensor data streams.
    Patent Status: A PCT application was filed on September 20, 2024.
    Development Stage: Prototype.
    Collaboration Opportunity: Researchers at the CC seek licensees for 
powered gait assistance systems and associated computing environments 
and methods of control in certain fields of use.

    Dated: February 10, 2026.
Richard U. Rodriguez,
Associate Director, Technology Transfer Center, National Cancer 
Institute.
[FR Doc. 2026-02906 Filed 2-12-26; 8:45 am]
BILLING CODE 4140-01-P