Ryan Pollard

Mr. Ryan Pollard

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
3 June 2024 in IEEE Transactions on Medical Robotics and Bionics
Verified
Journal Article
Closed access
RPRyan Pollard
Ryan Pollard
DHDavid Hollinger
David Hollinger
INIván E. Nail-Ulloa
Iván E. Nail-Ulloa
MZMichael E. Zabala
Michael E. Zabala
Elevated runtimes of machine learning algorithms and neural networks make their inclusion in near-future joint angle estimation difficult. The purpose of this study was to develop simple, analytical models that prioritize historical joint kinematics when estimating near-future joint angles. Five kinematically-informed and extrapolation-based methods were developed for joint angle estimation at three near-future estimation horizons: tpred = 50 ms, 75 ms, and 100 ms. The estimation error and required runtimes of each prediction algorithm were evaluated on the sagittal-plane ankle angles of 24 individual subjects who performed three level-ground walking trials. Results showed that the kinematically-informed models had significantly faster estimation runtimes than Random Forest (RF) machine learning models trained and tested on identical datasets (kinematic models: trun < 0.62 ms, RF models: trun > 8.19 ms for all estimation horizons). The RF models exhibited significantly lower prediction errors than the kinematic models for estimation horizons of tpred = 75 ms and 100 ms, but no significance was found between the top-performing kinematic model and RF models for a tpred = 50 ms. These results indicate that a kinematically-informed approach to joint angle estimation can serve as a simple alternative to complex machine learning models for very near-future applications (tpred ≤ 50 ms) while serving as a comparison baseline for more distant estimation horizons (tpred ≥ 75 ms).

31 August 2024 in Sensors
Verified
Journal Article
Open access
PDF file
RPRyan Pollard
Ryan Pollard
SBSarah M. Bass
Sarah M. Bass
MSMark Schall
Mark Schall
MZMichael Zabala
Michael Zabala
A common challenge for exoskeleton control is discerning operator intent to provide seamless actuation of the device with the operator. One way to accomplish this is with joint angle estimation algorithms and multiple sensors on the human–machine system. However, the question remains of what can be accomplished with just one sensor. The objective of this study was to deploy a modular testing approach to test the performance of two joint angle estimation models—a kinematic extrapolation algorithm and a Random Forest machine learning algorithm—when each was informed solely with kinematic gait data from a single potentiometer on an ankle exoskeleton mock-up. This study demonstrates (i) the feasibility of implementing a modular approach to exoskeleton mock-up evaluation to promote continuity between testing configurations and (ii) that a Random Forest algorithm yielded lower realized errors of estimated joint angles and a decreased actuation time than the kinematic model when deployed on the physical device.

26 August 2025 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
JBJacquelyn R. Brokamp
Jacquelyn R. Brokamp
RPRyan Pollard
Ryan Pollard
INIvan Nail-Ulloa
Ivan Nail-Ulloa
MZMichael E. Zabala
Michael E. Zabala
Additive manufacturing enables the rapid production and customization of ankle-foot orthoses (AFOs), offering substantial advantages over traditional fabrication methods. Understanding the mechanical properties of these devices, particularly stiffness and deflection during ambulation, is essential for their effective deployment as it may inform future benchtop performance tests, such as fatigue life analysis. However, previous studies seemingly disregard the combined effects of the passive and active ankle joint contributions to stiffness during ambulation, limiting the predictive accuracy of the mechanical performance tests. Accordingly, this study investigates how the AFO-ankle complex quasi-stiffness (the combined stiffness of the AFO and the ankle joint) and participant-specific anthropometric measures (height and body mass) influence AFO deflection throughout the gait cycle. Nine healthy, unimpaired participants were fitted unilaterally with custom-fit AFOs fabricated using XO-Armor® 3D-scanning and 3D-printing technology. Gait analyses were conducted under AFO and no-AFO conditions, focusing on three subphases of stance: controlled plantarflexion (CPF), controlled dorsiflexion (CDF), and powered plantarflexion (PPF). The results revealed significant positive correlations between anthropometric measures and both AFO-ankle complex quasi-stiffness throughout stance phase and peak AFO deflection in dorsiflexion (θDF,max). Additionally, AFO-ankle complex quasi-stiffness during CDF (KAFO,CDF) exhibited an inverse relationship with θDF,max. No significant relationships were identified between maximum deflection in plantarflexion (θPF,max) and either anthropometric measures or AFO-ankle complex quasi-stiffness during CPF (KAFO,CDF). The findings of this study suggest that height, weight, and KAFO,CDF should be considered when developing standardized protocols for custom-fit AFOs to enhance the predictive accuracy of benchtop testing, particularly when estimating θDF,max.

9 December 2024 in Sensors
Verified
Journal Article
Open access
PDF file
DHDavid Hollinger
David Hollinger
RPRyan Pollard
Ryan Pollard
MSMark Schall
Mark Schall
HCHoward Chen
Howard Chen
MZMichael Zabala
Michael Zabala
Recent applications of wearable inertial measurement units (IMUs) for predicting human movement have often entailed estimating action-level (e.g., walking, running, jumping) and joint-level (e.g., ankle plantarflexion angle) motion. Although action-level or joint-level information is frequently the focus of movement intent prediction, contextual information is necessary for a more thorough approach to intent recognition. Therefore, a combination of action-level and joint-level information may offer a more comprehensive approach to predicting movement intent. In this study, we devised a novel hierarchical-based method combining action-level classification and subsequent joint-level regression to predict joint angles 100 ms into the future. K-nearest neighbors (KNN), bidirectional long short-term memory (BiLSTM), and temporal convolutional network (TCN) models were employed for action-level classification, and a random forest model trained on action-specific IMU data was used for joint-level prediction. A joint-level action-generic model trained on multiple actions (e.g., backward walking, kneeling down, kneeling up, running, and walking) was also used for predicting the joint angle. Compared with a hierarchical-based approach, the action-generic model had lower prediction error for backward walking, kneeling down, and kneeling up. Although the TCN and BiLSTM classifiers achieved classification accuracies of 89.87% and 89.30%, respectively, they did not surpass the performance of the action-generic random forest model when used in combination with an action-specific random forest model. This may have been because the action-generic approach was trained on more data from multiple actions. This study demonstrates the advantage of leveraging large, disparate data sources over a hierarchical-based approach for joint-level prediction. Moreover, it demonstrates the efficacy of an IMU-driven, task-agnostic model in predicting future joint angles across multiple actions.

1 November 2025 in IEEE Transactions on Medical Robotics and Bionics
Verified
Journal Article
Closed access
RPRyan Pollard
Ryan Pollard
JBJacquelyn R. Brokamp
Jacquelyn R. Brokamp
INIvan Nail-Ulloa
Ivan Nail-Ulloa
MZMichael Zabala
Michael Zabala

31 July 2026 in Journal of Biomechanics
Verified
Journal Article
Closed access
JBJacquelyn R. Brokamp
Jacquelyn R. Brokamp
RPRyan Pollard
Ryan Pollard
INIván E. Nail-Ulloa
Iván E. Nail-Ulloa
JLJacob S. Larson
Jacob S. Larson
MZMichael Zabala
Michael Zabala