Denna sida har översatts automatiskt och översättningens korrekthet kan inte garanteras. Vänligen se engelsk version för en källtext.

AI-Driven Hip Exoskeleton Control for Diverse Users and Walking Tasks

10 november 2026 uppdaterad av: Inseung Kang, Carnegie Mellon University

AI-Driven Hip Exoskeleton Control Framework That Rapidly Generalizes to a Broad Range of Users and Real-World Locomotor Tasks

The goal of this clinical trial is to evaluate the feasibility of a prototype artificial intelligence (AI)-based controller for a lightweight hip exoskeleton across a broad range of users, including healthy younger adults (18-39 years) and older adults (65 years and older). The main questions it aims to answer are:

  • Can the AI-based controller accurately estimate gait phase in real time across younger and older adults?
  • How does hip exoskeleton assistance change walking energy cost, mechanics, and muscle activity?

Researchers will compare walking with powered hip exoskeleton assistance to walking without the exoskeleton and walking while wearing the exoskeleton with no assistance (zero torque).

Participants will:

  • Complete a short screening and frailty assessment
  • Walk on a treadmill under different conditions with and without the hip exoskeleton during 2 to 5 lab visits
  • Wear motion capture markers, muscle activity (EMG) sensors, and a mask that measures breathing to estimate energy use

Studieöversikt

Status

Rekrytering

Detaljerad beskrivning

This study is funded by the National Institute of Biomedical Imaging and Bioengineering (R21EB037268) and conducted at the University of Texas at Austin in collaboration with Carnegie Mellon University. The CMU Hip Exoskeleton is a research prototype with powered hip joints for flexion and extension (peak torque 18 Nm, total weight 3.5 kg). Its controller uses joint angle and user-state estimates to command assistive torque, limited to less than 0.2 Nm/kg (at most about 30% of typical biological hip moments during walking), so it supplements rather than overrides the user's own muscle effort.

During each visit, participants walk on a force-instrumented treadmill at 1.25 m/s with safety harness and handrails. Researchers record whole-body motion capture, ground reaction forces, inertial measurement unit data, lower-limb electromyography, and metabolic energy expenditure via open-circuit indirect calorimetry. Walking conditions include no exoskeleton, exoskeleton worn with zero torque, and powered exoskeleton assistance. Outcomes will be compared across conditions and between younger and older adults using repeated-measures statistical analysis.

Studietyp

Interventionell

Inskrivning (Beräknad)

16

Fas

  • Inte tillämpbar

Kontakter och platser

Det här avsnittet innehåller kontaktuppgifter för dem som genomför studien och information om var denna studie genomförs.

Studiekontakt

Studieorter

Deltagandekriterier

Forskare letar efter personer som passar en viss beskrivning, så kallade behörighetskriterier. Några exempel på dessa kriterier är en persons allmänna hälsotillstånd eller tidigare behandlingar.

Urvalskriterier

Åldrar som är berättigade till studier

18 år och äldre (Vuxen, Äldre vuxen)

Tar emot friska volontärer

Ja

Kön som är behöriga för studier

Allt

Beskrivning

Inclusion Criteria:

  • Age 18 to 39 years (younger adult group) or 65 years and older (older adult group)
  • Willing and able to provide informed consent
  • Able to walk independently without assistance
  • No known cardiovascular, metabolic, or renal disease, and no signs or symptoms suggestive of such disease
  • Cleared for light- to moderate-intensity exercise without the need for medical clearance under American College of Sports Medicine (ACSM) preparticipation screening guidelines

Exclusion Criteria:

  • Age 40 to 64 years
  • Leg surgery within the past 5 years
  • Orthopedic disability that could impair movement or limit participation in the exercise protocol
  • Neurologic disorder that may affect neuromuscular function or gait (e.g., stroke, Parkinson's disease, peripheral neuropathy, traumatic brain injury)
  • Known metabolic or cardiovascular disease (hypertension alone is not exclusionary), or requiring medical clearance under ACSM guidelines without having obtained it
  • Metal implants in the lower extremities, cardiac pacemaker, or other implanted electronic device
  • Pregnancy
  • History of seizure disorder or fainting (syncope)

Studieplan

Det här avsnittet ger detaljer om studieplanen, inklusive hur studien är utformad och vad studien mäter.

Hur är studien utformad?

Designdetaljer

  • Primärt syfte: Enhetens genomförbarhet
  • Tilldelning: N/A
  • Interventionsmodell: Enskild gruppuppgift
  • Maskning: Ingen (Open Label)

Vapen och interventioner

Deltagargrupp / Arm
Intervention / Behandling
Experimentell: Hip Exoskeleton Walking

Healthy younger adults (18-39 years) and older adults (65+ years) walk on an instrumented treadmill under multiple conditions across 2-5 lab visits: no exoskeleton, wearing the CMU Hip Exoskeleton with zero torque, and with powered assistance from the AI-driven hip exoskeleton controller (assistance limited to <0.2 Nm/kg). The primary objective is to evaluate real-time gait phase estimation accuracy of the prototype controller across users; metabolic cost, biomechanics, and muscle activity are recorded as secondary measures.

A lightweight (3.5 kg) research hip exoskeleton developed at Carnegie Mellon University with powered hip flexion/extension joints, a backpack-mounted computer and battery, and thigh and waist interfaces secured with straps. An AI-driven controller estimates the user's gait state from joint angle and wearable sensor data and commands assistive hip torque in real time, limited to <0.2 Nm/kg (peak device torque 18 Nm). Participants walk on a treadmill with powered assistance, with the device worn at zero torque, and without the device. The device was determined by the UT Austin IRB to be a non-significant risk device.

Andra namn:
  • CMU Hip Exoskeleton

Vad mäter studien?

Primära resultatmått

Resultatmått
Åtgärdsbeskrivning
Tidsram
Gait Phase Estimation Error of the AI-Driven Hip Exoskeleton Controller
Tidsram: Day 1

Root-mean-square error (RMSE) between the controller's real-time gait phase estimate and ground-truth gait phase derived from force-instrumented treadmill data during powered hip exoskeleton walking, reported as percent of the gait cycle (%). Used to evaluate feasibility of the prototype controller across younger and older adult users.

Day 1

Sekundära resultatmått

Resultatmått
Åtgärdsbeskrivning
Tidsram
Net Metabolic Power During Powered Hip Exoskeleton Walking
Tidsram: Day 1

Net metabolic power (W/kg), measured by open-circuit indirect calorimetry with resting value subtracted, during treadmill walking at 1.25 m/s with powered hip exoskeleton assistance.

Day 1
Peak Hip Joint Moment During Powered Hip Exoskeleton Walking
Tidsram: Day 1

Peak biological hip extension moment (Nm/kg), computed from motion capture and force-instrumented treadmill data, during treadmill walking with powered hip exoskeleton assistance.

Day 1
Lower-Limb Muscle Activity During Powered Hip Exoskeleton Walking
Tidsram: Day 1

Average electromyography (EMG) amplitude normalized to maximum voluntary contraction (%MVC), averaged across eight recorded lower-limb muscles, during treadmill walking with powered hip exoskeleton assistance.

Day 1

Samarbetspartners och utredare

Det är här du hittar personer och organisationer som är involverade i denna studie.

Utredare

  • Huvudutredare: Inseung Kang, PhD, Carnegie Mellon University

Studieavstämningsdatum

Dessa datum spårar framstegen för inlämningar av studieposter och sammanfattande resultat till ClinicalTrials.gov. Studieposter och rapporterade resultat granskas av National Library of Medicine (NLM) för att säkerställa att de uppfyller specifika kvalitetskontrollstandarder innan de publiceras på den offentliga webbplatsen.

Studera stora datum

Studiestart (Faktisk)

6 augusti 2026

Primärt slutförande (Beräknad)

31 augusti 2027

Avslutad studie (Beräknad)

31 januari 2028

Studieregistreringsdatum

Först inskickad

3 november 2026

Först inskickad som uppfyllde QC-kriterierna

10 november 2026

Första postat (Faktisk)

16 november 2026

Uppdateringar av studier

Senaste uppdatering publicerad (Faktisk)

16 november 2026

Senaste inskickade uppdateringen som uppfyllde QC-kriterierna

10 november 2026

Senast verifierad

1 november 2026

Mer information

Termer relaterade till denna studie

Andra studie-ID-nummer

  • STUDY2026_00000477
  • R21EB037268 (U.S.S. NIH-anslag/kontrakt)

Plan för individuella deltagardata (IPD)

Planerar du att dela individuella deltagardata (IPD)?

JA

IPD-planbeskrivning

De-identified individual participant data underlying published results will be shared, including biomechanics (motion capture, ground reaction forces), electromyography, metabolic, and exoskeleton sensor/controller data, along with participant characteristics (age group, sex, height, mass). Identifiable information, including video recordings, will not be shared.

Tidsram för IPD-delning

Data will be made available no later than the time of associated publication or the end of the award period, whichever comes first, and will remain available for at least 5 years.

Kriterier för IPD Sharing Access

De-identified data and supporting information will be deposited in a public data repository and made openly available to researchers without restriction, subject to the repository's terms of use.

IPD-delning som stöder informationstyp

  • STUDY_PROTOCOL
  • ANALYTIC_CODE

Läkemedels- och apparatinformation, studiedokument

Studerar en amerikansk FDA-reglerad läkemedelsprodukt

Nej

Studerar en amerikansk FDA-reglerad produktprodukt

Ja

produkt tillverkad i och exporterad från U.S.A.

Nej

Denna information hämtades direkt från webbplatsen clinicaltrials.gov utan några ändringar. Om du har några önskemål om att ändra, ta bort eller uppdatera dina studieuppgifter, vänligen kontakta register@clinicaltrials.gov. Så snart en ändring har implementerats på clinicaltrials.gov, kommer denna att uppdateras automatiskt även på vår webbplats .

Prenumerera