StrokeNCT05536739
Adaptive Hip Exoskeleton for Stroke Gait Enhancement
A study testing Hip exoskeleton and Baseline in people with Stroke, run by Georgia Institute of Technology at 1 site in United States.
Trial summary
This work will focus on new algorithms for robotic exoskeletons and testing these in human subject tests. Individuals who have previously had a stroke will walk while wearing a robotic exoskeleton on a specialized treadmill as well as during other movement tasks (e.g. over ground, stairs, ramps). Read more about this study
- Who is it for?
- Ages 18 to 85 years
- Conditions the study is for
- Stroke
- What is being tested?
- Hip exoskeleton and Baseline
- Type of treatment
- Medical device
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 12 participants
- Where
- 1 siteUnited States
- Study dates
- 21 May 2025to 29 Aug 2025
- Phase
- Interventional
- Are there results?
- Yes, posted in the registrySummary in the doctors' view
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 to 85 years
- All sexes
- No healthy volunteers
- Adult, Older adult
Who may be able to join
- Between 18-85 years of age
- Had a stroke at least 6 months prior to study involvement
- Are community dwelling, which means the participant does not live in an assisted living facility
- Are able to provide informed consent to participate in the study activities
- Can safely participate in the study activities (per self-report)
- Must have a Functional Ambulation Category (FAC) score of 3 or above, which means the participant can walk without the assistance of another person
Who cannot join
- Require a walker to walk independently
- Have a shuffling gait pattern overground
- Have a Functional Ambulation Category (FAC) score of 2 or lower, which means the participant requires the assistance of another person in order to walk
- Have a significant secondary deficit beyond stroke (e.g. amputation, legal blindness or other severe impairment or condition) that in the opinion of the Principal Investigator (PI), would likely affect the study outcome or confound the results
- For exoskeleton-only studies, the exoskeleton device does not fit appropriately or safely, as determined by the research team during the fitting assessment.
Trial locations and contacts
1 site in 1 country.
United States1 site
Exoskeleton and Prosthetic Intelligent Controls Lab
Atlanta, Georgia, 30332
About this study
Official title: Adaptive Hip Exoskeleton for Stroke Survivors With Gait Impairment
This work will focus on new algorithms for robotic exoskeletons and testing these in human subject tests. Individuals who have previously had a stroke will walk while wearing a robotic exoskeleton on a specialized treadmill as well as during other movement tasks (e.g. over ground, stairs, ramps). The study will compare the performance of the advanced algorithm with not using the device to determine the clinical benefit.
Read the detailed description
The focus of this work is a proposed novel artificial intelligence (AI) system to self-adapt control policy in powered exoskeletons to aid deployment systems that personalize to individual patient gait. Individuals post stroke have a broad range of mobility challenges including asymmetric gait, substantially decreased SSWS, and reduced stability, and therefore have greatly impaired overall mobility independence in the community. The investigators expect the proposed novel controller, capable of personalization to such variable and asymmetric gait patterns, will have significant benefits towards increasing community independence and mobility for patients post stroke. Patients post stroke will be fit with a hip exoskeleton (in a powered and/or unpowered state) and proceed to walk on a treadmill or perform various movement tasks. The same tasks will be performed by the patients without wearing the hip exoskeleton to serve as a baseline. The investigators expect improved outcomes in the powered hip exoskeleton compared to the unpowered hip exoskeleton and baseline conditions.
- Conditions
- Stroke
- Being tested
- Hip exoskeleton, Baseline
- Keywords
- Stroke
- Medical subject headings
- Stroke
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Hip exoskeletonDevice
The intervention is an experimental robotic hip exoskeleton in a powered state providing assistance to the user that has been previously developed by the team. It is used to improve walking gait performance.
BaselineOther
The intervention will serve as a baseline where participants will be asked to perform the tasks without wearing a hip exoskeleton.
| Study group | Role | What they receive |
|---|---|---|
| Hip Exoskeleton for Stroke Gait Assistance | Experimental | This study will be conducted on a sample population of stroke subjects (single arm). Subjects will be tested with the hip exoskeleton and baseline. Receives: Device: Hip exoskeleton; Other: Baseline |
What is being measured
The primary outcome is the main question the study is designed to answer.
Temporal Convolutional Network (TCN) Model Performance (Joint Moment Accuracy)
This outcome represents the error with which the deep learning model embedded into our hip exoskeleton's microprocessor predicts hip joint moments in stroke patients. Specifically, the coefficient of determination (R²) is computed between the predicted hip joint moments and the ground truth measurements. Ground truth measurements are obtained from a laboratory-grade force plate system and inverse dynamics calculations. For these measures, higher R² values (closer to 1.0) indicate better correlation between predicted and actual hip joint moments. This metric provides a comprehensive assessment of the exoskeleton's ability to accurately estimate hip joint moments in stroke patients during tasks, with improved outcomes representing better assistive capabilities for the user.
Measured: 5 Days
Metabolic Cost for Level Ground Walking
Metabolic energy expenditure will be quantified using an indirect calorimetry system (Parvo Medics, UT) that measures oxygen consumption (VO₂) and carbon dioxide production (VCO₂) during experimental tasks. Measurements will be collected from each participant during a 5-minute baseline standing period followed by level ground walking trials under three conditions: without the exoskeleton, with the exoskeleton in a powered state, and with the exoskeleton in an unpowered state. Metabolic cost will be calculated from respiratory gas exchange data using standard equations for energy expenditure.
Measured: 5 days
Biological Joint Work - Level Walking
Mechanical work performed by the lower limb joints during level walking will be quantified through biomechanical analysis of motion capture data. Joint moments and angular velocities will be derived through inverse dynamics and kinematics, respectively. Joint power, calculated as the product of joint moment and angular velocity, will be integrated with respect to time using trapezoidal integration to determine mechanical work. Positive work will be calculated by integrating positive joint powers, providing comprehensive quantification of joint energy generation at each joint during level walking.
Measured: 5 days
Biological Joint Work - Incline Walking
Mechanical work performed by the lower limb joints will be quantified during incline walking through biomechanical analysis of motion capture data. Joint moments and angular velocities will be derived through inverse dynamics and kinematics, respectively. Joint power, calculated as the product of joint moment and angular velocity, will be integrated with respect to time using trapezoidal integration to determine mechanical work. Positive work will be calculated by integrating positive joint powers, providing comprehensive quantification of joint energy generation at each joint during the incline walking.
Measured: 5 days
Biological Joint Work - Stair Ascent
Mechanical work performed by the lower limb joints will be quantified during stair ascent through biomechanical analysis of motion capture data. Joint moments and angular velocities will be derived through inverse dynamics and kinematics, respectively. Joint power, calculated as the product of joint moment and angular velocity, will be integrated with respect to time using trapezoidal integration to determine mechanical work. Positive work will be calculated by integrating positive joint powers, providing comprehensive quantification of joint energy generation at each joint during the stair ascent task.
Measured: 5 days
Biological Joint Work - Sit to Stand
Mechanical work performed by the lower limb joints will be quantified during sit to stand through biomechanical analysis of motion capture data. Joint moments and angular velocities will be derived through inverse dynamics and kinematics, respectively. Joint power, calculated as the product of joint moment and angular velocity, will be integrated with respect to time using trapezoidal integration to determine mechanical work. Positive work will be calculated by integrating positive joint powers, providing comprehensive quantification of joint energy generation at each joint during the sit to stand task.
Measured: 5 days
Biological Joint Work - go and Grab
Mechanical work performed by the lower limb joints will be quantified during a go and grab task through biomechanical analysis of motion capture data. In the go and grab task, participants take several steps, lean forward, and pick up a weighted object from a low surface just above ground level. Joint moments and angular velocities will be derived through inverse dynamics and kinematics, respectively. Joint power, calculated as the product of joint moment and angular velocity, will be integrated with respect to time using trapezoidal integration to determine mechanical work. Positive work will be calculated by integrating positive joint powers, providing comprehensive quantification of joint energy generation at each joint during the go and grab task.
Measured: 5 days
Secondary outcomes (6)
10 Meter Walk Test (Self-selected)
This will be measured as the participant walks a distance of 10 meters across a gait mat at their self-selected (or comfortable) walking speed. This measure will be recorded in seconds with lower values indicating faster speed and higher values indicating slower speeds. Self-selected walking speed is highly correlated with functional ability and dependence.
Measured: 5 days
The Timed up and go (TUG)
This will be measured as the time it takes a participant to rise from a chair, walk three meters at a self-selected pace, turn, walk back to the chair and sit down. The total time taken will be measured in seconds with longer times indicating poorer physical performance. This test assesses functional mobility and dynamic balance.
Measured: 5 days
6 Minute Walk Test
This is a measurement of endurance and functional ability that assesses the participants ability to walk a distance over a time period of 6 minutes. It is measured in distance with greater distances indicating improved levels of endurance and functional ability.
Measured: 5 days
Modified Stroke Impact Scale
The Modified Stroke Impact Scale (SIS) is a self-report questionnaire that evaluates disability and health-related quality of life after stroke. Each item is rated in a 5-point Likert scale in terms of the difficulty the patient has experienced in completing each item. Scores are transformed to a 0-100 scale, with 0 indicating the poorest perceived health status and 100 indicating the best, across domains of disability and health-related quality of life. Higher scores are indicative of improved quality of life.
Measured: 5 days
Modified Activities-specific Balance Confidence
The modified activities specific balance confidence is a self-report measure of balance confidence in performing various activities without losing balance or experiencing a sense of unsteadiness. Confidence is rated for various activities on a scale from 0% to 100% for each activity, with 0% indicative of no confidence and 100% indicative of complete confidence. Scores reflect balance confidence with higher scores indicative of improved balance confidence.
Measured: 5 days
Fast Self-selected Walking Speed
This will be measured as the participant walks on a treadmill at their fastest and safest walking speed. This measure will be recorded in meters/seconds with higher values indicating faster speed and lower values indicating slower speeds.
Measured: 5 days
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted13 Sep 2022
- Study start21 May 2025
- Primary completion29 Aug 2025
- Study completion29 Aug 2025
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Posted resultsParticipant flow, outcome measures and adverse events reported by the sponsor.
- Other trials for StrokeStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Basic science
- Allocation
- Not applicable
- Intervention model
- Single group
- Model description
- The model used is a repeated measures single arm study
- Masking
- None (open label)
- Enrolment
- 12 participants (actual)
Sponsor and investigators
- Lead sponsor
- Georgia Institute of Technology
- Sponsor type
- University, hospital or other
- Collaborators
- Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD)
- Responsible party
- Sponsor
- Investigators
- Aaron Young, Ph.D., Principal investigator, Georgia Institute of Technology
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT05536739
- Sponsor's protocol ID
- H18182
- Other IDs
- R03HD097740, DP2HD111709
- Status last verified
- May 2026
- First submitted
- 8 Sep 2022
- Last updated
- 1 Jul 2026
- Results posted
- Yes, on ClinicalTrials.gov
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- Yes
- Individual data sharing
- No
Study at a glance
From the registry record, last updated by the sponsor on 1 Jul 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Adaptive Hip Exoskeleton for Stroke Survivors With Gait Impairment
- ClinicalTrials.gov ID
- NCT05536739
- Acronym / sponsor ID
- H18182
- Conditions
- Stroke
- Keywords
- Stroke
- Study type
- Interventional
- Recruitment status
- Completed
- Enrolment
- 12 participants (actual)
- Lead sponsor
- Georgia Institute of TechnologyUniversity, hospital or other
- Collaborators
- Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD)
- Study start
- 21 May 2025 (actual)
- Primary completion
- 29 Aug 2025 (actual)
- Study completion
- 29 Aug 2025 (actual)
- First posted
- 13 Sep 2022 (actual)
- Results
- Posted 1 Jul 2026
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
This work will focus on new algorithms for robotic exoskeletons and testing these in human subject tests. Individuals who have previously had a stroke will walk while wearing a robotic exoskeleton on a specialized treadmill as well as during other movement tasks (e.g. over ground, stairs, ramps). The study will compare the performance of the advanced algorithm with not using the device to determine the clinical benefit.
Detailed description
The focus of this work is a proposed novel artificial intelligence (AI) system to self-adapt control policy in powered exoskeletons to aid deployment systems that personalize to individual patient gait. Individuals post stroke have a broad range of mobility challenges including asymmetric gait, substantially decreased SSWS, and reduced stability, and therefore have greatly impaired overall mobility independence in the community. The investigators expect the proposed novel controller, capable of personalization to such variable and asymmetric gait patterns, will have significant benefits towards increasing community independence and mobility for patients post stroke. Patients post stroke will be fit with a hip exoskeleton (in a powered and/or unpowered state) and proceed to walk on a treadmill or perform various movement tasks. The same tasks will be performed by the patients without wearing the hip exoskeleton to serve as a baseline. The investigators expect improved outcomes in the powered hip exoskeleton compared to the unpowered hip exoskeleton and baseline conditions.
Study design
- Primary purpose
- Basic science
- Allocation
- Not applicable
- Intervention model
- Single group
- Masking
- None (open label)
- Number of arms
- 1
- Model description
- The model used is a repeated measures single arm study
| Arm | Type | Receives |
|---|---|---|
| Hip Exoskeleton for Stroke Gait Assistance | Experimental | Device: Hip exoskeleton, Other: BaselineThis study will be conducted on a sample population of stroke subjects (single arm). Subjects will be tested with the hip exoskeleton and baseline. |
Who may qualify
- Ages
- 18 to 85 years
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (6 listed)
- Between 18-85 years of age
- Had a stroke at least 6 months prior to study involvement
- Are community dwelling, which means the participant does not live in an assisted living facility
- Are able to provide informed consent to participate in the study activities
- Can safely participate in the study activities (per self-report)
Key exclusion criteria (5 listed)
- Require a walker to walk independently
- Have a shuffling gait pattern overground
- Have a Functional Ambulation Category (FAC) score of 2 or lower, which means the participant requires the assistance of another person in order to walk
- Have a significant secondary deficit beyond stroke (e.g. amputation, legal blindness or other severe impairment or condition) that in the opinion of the Principal Investigator (PI), would likely affect the study outcome or confound the results
- For exoskeleton-only studies, the exoskeleton device does not fit appropriately or safely, as determined by the research team during the fitting assessment.
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| Hip exoskeletonThe intervention is an experimental robotic hip exoskeleton in a powered state providing assistance to the user that has been previously developed by the team. It is used to improve walking gait performance. | Device | Hip Exoskeleton for Stroke Gait Assistance |
| BaselineThe intervention will serve as a baseline where participants will be asked to perform the tasks without wearing a hip exoskeleton. | Other | Hip Exoskeleton for Stroke Gait Assistance |
Primary outcome
Temporal Convolutional Network (TCN) Model Performance (Joint Moment Accuracy)
Time frame: 5 Days
This outcome represents the error with which the deep learning model embedded into our hip exoskeleton's microprocessor predicts hip joint moments in stroke patients. Specifically, the coefficient of determination (R²) is computed between the predicted hip joint moments and the ground truth measurements. Ground truth measurements are obtained from a laboratory-grade force plate system and inverse dynamics calculations. For these measures, higher R² values (closer to 1.0) indicate better correlation between predicted and actual hip joint moments. This metric provides a comprehensive assessment of the exoskeleton's ability to accurately estimate hip joint moments in stroke patients during tasks, with improved outcomes representing better assistive capabilities for the user.
Metabolic Cost for Level Ground Walking
Time frame: 5 days
Metabolic energy expenditure will be quantified using an indirect calorimetry system (Parvo Medics, UT) that measures oxygen consumption (VO₂) and carbon dioxide production (VCO₂) during experimental tasks. Measurements will be collected from each participant during a 5-minute baseline standing period followed by level ground walking trials under three conditions: without the exoskeleton, with the exoskeleton in a powered state, and with the exoskeleton in an unpowered state. Metabolic cost will be calculated from respiratory gas exchange data using standard equations for energy expenditure.
Biological Joint Work - Level Walking
Time frame: 5 days
Mechanical work performed by the lower limb joints during level walking will be quantified through biomechanical analysis of motion capture data. Joint moments and angular velocities will be derived through inverse dynamics and kinematics, respectively. Joint power, calculated as the product of joint moment and angular velocity, will be integrated with respect to time using trapezoidal integration to determine mechanical work. Positive work will be calculated by integrating positive joint powers, providing comprehensive quantification of joint energy generation at each joint during level walking.
Biological Joint Work - Incline Walking
Time frame: 5 days
Mechanical work performed by the lower limb joints will be quantified during incline walking through biomechanical analysis of motion capture data. Joint moments and angular velocities will be derived through inverse dynamics and kinematics, respectively. Joint power, calculated as the product of joint moment and angular velocity, will be integrated with respect to time using trapezoidal integration to determine mechanical work. Positive work will be calculated by integrating positive joint powers, providing comprehensive quantification of joint energy generation at each joint during the incline walking.
Biological Joint Work - Stair Ascent
Time frame: 5 days
Mechanical work performed by the lower limb joints will be quantified during stair ascent through biomechanical analysis of motion capture data. Joint moments and angular velocities will be derived through inverse dynamics and kinematics, respectively. Joint power, calculated as the product of joint moment and angular velocity, will be integrated with respect to time using trapezoidal integration to determine mechanical work. Positive work will be calculated by integrating positive joint powers, providing comprehensive quantification of joint energy generation at each joint during the stair ascent task.
Biological Joint Work - Sit to Stand
Time frame: 5 days
Mechanical work performed by the lower limb joints will be quantified during sit to stand through biomechanical analysis of motion capture data. Joint moments and angular velocities will be derived through inverse dynamics and kinematics, respectively. Joint power, calculated as the product of joint moment and angular velocity, will be integrated with respect to time using trapezoidal integration to determine mechanical work. Positive work will be calculated by integrating positive joint powers, providing comprehensive quantification of joint energy generation at each joint during the sit to stand task.
Biological Joint Work - go and Grab
Time frame: 5 days
Mechanical work performed by the lower limb joints will be quantified during a go and grab task through biomechanical analysis of motion capture data. In the go and grab task, participants take several steps, lean forward, and pick up a weighted object from a low surface just above ground level. Joint moments and angular velocities will be derived through inverse dynamics and kinematics, respectively. Joint power, calculated as the product of joint moment and angular velocity, will be integrated with respect to time using trapezoidal integration to determine mechanical work. Positive work will be calculated by integrating positive joint powers, providing comprehensive quantification of joint energy generation at each joint during the go and grab task.
6 secondary outcomes
10 Meter Walk Test (Self-selected)
Time frame: 5 days
The Timed up and go (TUG)
Time frame: 5 days
6 Minute Walk Test
Time frame: 5 days
Modified Stroke Impact Scale
Time frame: 5 days
Modified Activities-specific Balance Confidence
Time frame: 5 days
Fast Self-selected Walking Speed
Time frame: 5 days
Results and safety
Loading the posted results from ClinicalTrials.gov…
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 1 Jul 2026.
- Posted resultsParticipant flow, baseline, all outcome measures and adverse events.
- Individual participant dataSharing planned: No
Related trials for Stroke
Recruiting
Connectomic Alterations Following Acute Ischemic Stroke in the MCA Territory
Ischemic Stroke
RecruitingObservational study
Clevidipine for the Antihypertensive Treatment of Acute Intracerebral Hemorrhage
Intracerebral Hemorrhage, Stroke
Active, not recruitingPhase 4
A Study Testing How Well the Drug Extract of Ginkgo Biloba Leaves Tablets Works for People With Memory or Thinking Problems After a Stroke When Added to Standard Treatment
Ischemic Stroke Hospitalized, Impairment, Cognitive
Not yet recruitingPhase 4
Anti-inflammatory and Anti-thrombotic Therapy With colcHicine and Low Dose Rivaroxaban for Major Adverse Cardiovascular Events Reduction in Ischemic Stroke
Ischemic Stroke
RecruitingObservational study
CoMind Early Feasibility Study
Intracranial Pressure, Intracranial Pressure Changes
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part. This study is not recruiting at the moment.
Aaron Young, Ph.D. principal investigator
Georgia Institute of Technology
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing Hip exoskeleton and Baseline in people with Stroke, run by Georgia Institute of Technology at 1 site in United States.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 6 inclusion and 5 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: finished, as of the sponsor's last update on 1 Jul 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in United States. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
Yes. Results are posted in the registry (first posted 1 Jul 2026). A summary is in the For doctors view, and the full results are on ClinicalTrials.gov.
How can a doctor refer a patient or contact the research team?
The record lists no contact. The official record names the sponsor, who can be asked directly. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Temporal Convolutional Network (TCN) Model Performance (Joint Moment Accuracy) (time frame: 5 Days). The study lists 7 primary outcomes in all. It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 1 Jul 2026.