Keaton L. Scherpereel

Keaton L. Scherpereel

Auto-generated profile, based on publicly available information

Keaton L. Scherpereel

George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 November 2024 in Nature
Verified
Journal Article
Closed access
PDF file
DMDean D. Molinaro
Dean D. Molinaro
KSKeaton L. Scherpereel
Keaton L. Scherpereel
ESEthan B. Schonhaut
Ethan B. Schonhaut
GEGeorgios Evangelopoulos
Georgios Evangelopoulos
MSMax K. Shepherd
Max K. Shepherd
AYAaron J. Young
Aaron J. Young

21 December 2023 in Scientific Data
Verified
Journal Article
Open access
PDF file
KSKeaton Scherpereel
Keaton Scherpereel
DMDean Molinaro
Dean Molinaro
OIOmer Inan
Omer Inan
MSMax Shepherd
Max Shepherd
AYAaron Young
Aaron Young
Tasks of daily living are often sporadic, highly variable, and asymmetric. Analyzing these real-world non-cyclic activities is integral for expanding the applicability of exoskeletons, protheses, wearable sensing, and activity classification to real life, and could provide new insights into human biomechanics. Yet, currently available biomechanics datasets focus on either highly consistent, continuous, and symmetric activities, such as walking and running, or only a single specific non-cyclic task. To capture a more holistic picture of lower limb movements in everyday life, we collected data from 12 participants performing 20 non-cyclic activities (e.g. sit-to-stand, jumping, squatting, lunging, cutting) as well as 11 cyclic activities (e.g. walking, running) while kinematics (motion capture and IMUs), kinetics (force plates), and electromyography (EMG) were collected. This dataset provides normative biomechanics for a highly diverse range of activities and common tasks from a consistent set of participants and sensors.

9 October 2020 in Annals of Biomedical Engineering
Verified
Journal Article
Closed access
PDF file
KSKeaton L. Scherpereel
Keaton L. Scherpereel
NBNicholas B. Bolus
Nicholas B. Bolus
HJHyeon Ki Jeong
Hyeon Ki Jeong
OIOmer T. Inan
Omer T. Inan
AYAaron J. Young
Aaron J. Young

15 April 2024 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
KSKeaton L. Scherpereel
Keaton L. Scherpereel
DMDean D. Molinaro
Dean D. Molinaro
MSMax K. Shepherd
Max K. Shepherd
OIOmer Inan
Omer Inan
AYAaron J. Young
Aaron J. Young
Objective: Real-time measurement of biological joint moment could enhance clinical assessments and generalize exoskeleton control. Accessing joint moments outside clinical and laboratory settings requires harnessing non-invasive wearable sensor data for indirect estimation. Previous approaches have been primarily validated during cyclic tasks, such as walking, but these methods are likely limited when translating to non-cyclic tasks where the mapping from kinematics to moments is not unique. Methods: We trained deep learning models to estimate hip and knee joint moments from kinematic sensors, electromyography (EMG), and simulated pressure insoles from a dataset including 10 cyclic and 18 non-cyclic activities. We assessed estimation error on combinations of sensor modalities during both activity types. Results: Compared to the kinematics-only baseline, adding EMG reduced RMSE by 16.9% at the hip and 30.4% at the knee (p < 0.05) and adding insoles reduced RMSE by 21.7% at the hip and 33.9% at the knee (p < 0.05). Adding both modalities reduced RMSE by 32.5% at the hip and 41.2% at the knee (p < 0.05) which was significantly higher than either modality individually (p < 0.05). All sensor additions improved model performance on non-cyclic tasks more than cyclic tasks (p < 0.05). Conclusion: These results demonstrate that adding kinetic sensor information through EMG or insoles improves joint moment estimation both individually and jointly. These additional modalities are most important during non-cyclic tasks, tasks that reflect the variable and sporadic nature of the real-world. Significance: Improved joint moment estimation and task generalization is pivotal to developing wearable robotic systems capable of enhancing mobility in everyday life.

1 January 2026 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
ESEthan B. Schonhaut
Ethan B. Schonhaut
KSKeaton L. Scherpereel
Keaton L. Scherpereel
AYAaron J. Young
Aaron J. Young
Objective: Accurate, non-invasive methods for estimating joint and muscle physiological states have the potential to greatly enhance control of wearable devices during real-world ambulation. Traditional modeling approaches and current estimation methods used to predict muscle dynamics often rely on complex equipment or computationally intensive simulations and have difficulty estimating across a broad spectrum of tasks or subjects. Methods: Our approach used deep learning (DL) models trained on kinematic inputs to estimate internal physiological states at the knee, including moment, power, velocity, and force. We assessed each model's performance against ground truth labels from both a commonly used, standard OpenSim musculoskeletal model without EMG (static optimization) and an EMG-informed method (CEINMS), across 28 different cyclic and noncyclic tasks. Results: EMG provided no benefit for joint moment/power estimation (e.g., biological moment), but was critical for estimating muscle states. Models trained with EMG-informed labels but without EMG as an input to the DL system significantly outperformed models trained without EMG (e.g., 33.7% improvement for muscle moment estimation) (p < 0.05). Models that included EMG-informed labels and EMG as a model input demonstrated even higher performance (49.7% improvement for muscle moment estimation) (p < 0.05), but require the availability of EMG during model deployment, which may be impractical. Conclusion/Significance: While EMG information is not necessary for estimating joint level states, there is a clear benefit during muscle level state estimation. Our results demonstrate excellent tracking of these states with EMG included only during training, highlighting the practicality of real-time deployment of this approach.

19 November 2025 in Science Robotics
Verified
Journal Article
Closed access
KSKeaton L. Scherpereel
Keaton L. Scherpereel
MGMatthew C Gombolay
Matthew C Gombolay
MSMax K. Shepherd
Max K. Shepherd
CCCarlos A. Carrasquillo
Carlos A. Carrasquillo
OIOmer Inan
Omer Inan
AYAaron J. Young
Aaron J. Young
Data-driven methods have transformed our ability to assess and respond to human movement with wearable robots, promising real-world rehabilitation and augmentation benefits. However, the proliferation of data-driven methods, with the associated demand for increased personalization and performance, requires vast quantities of high-quality, device-specific data. Procuring these data is often intractable because of resource and personnel costs. We propose a framework that overcomes data scarcity by leveraging simulated sensors from biomechanical models to form a stepping-stone domain through which easily accessible data can be translated into data-limited domains. We developed and optimized a deep domain adaptation network that replaces costly, device-specific, labeled data with open-source datasets and unlabeled exoskeleton data. Using our network, we trained a hip and knee joint moment estimator with performance comparable to a best-case model trained with a complete, device-specific dataset [incurring only an 11 to 20%, 0.019 to 0.028 newton-meters per kilogram (Nm/kg) increase in error for a semisupervised model and 20 to 44%, 0.033 to 0.062 Nm/kg for an unsupervised model]. Our network significantly outperformed counterpart networks without domain adaptation (which incurred errors of 36 to 45% semisupervised and 50 to 60% unsupervised). Deploying our models in the real-time control loop of a hip/knee exoskeleton ( N = 8) demonstrated estimator performance similar to offline results while augmenting user performance based on those estimated moments (9.5 to 14.6% metabolic cost reductions compared with no exoskeleton). Our framework enables researchers to train real-time deployable deep learning, task-agnostic models with limited or no access to labeled, device-specific data.