Jaeyoun Choi

Mr. Jaeyoun Choi


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
24 July 2024 in Science Robotics
Verified
Journal Article
Closed access
JKJae In Kim
Jae In Kim
JCJaeyoun Choi
Jaeyoun Choi
JKJunhyung Kim
Junhyung Kim
JSJunkyung Song
Junkyung Song
JPJaebum Park
Jaebum Park
YPYong-Lae Park
Yong-Lae Park
Lumbar spine injuries resulting from heavy or repetitive lifting remain a prevalent concern in workplaces. Back-support devices have been developed to mitigate these injuries by aiding workers during lifting tasks. However, existing devices often fall short in providing multidimensional force assistance for asymmetric lifting, an essential feature for practical workplace use. In addition, validation of device safety across the entire human spine has been lacking. This paper introduces the Bilateral Back Extensor Exosuit (BBEX), a robotic back-support device designed to address both functionality and safety concerns. The design of the BBEX draws inspiration from the anatomical characteristics of the human spine and back extensor muscles. Using a multi–degree-of-freedom architecture and serially connected linear actuators, the device’s components are strategically arranged to closely mimic the biomechanics of the human spine and back extensor muscles. To establish the efficacy and safety of the BBEX, a series of experiments with human participants was conducted. Eleven healthy male participants engaged in symmetric and asymmetric lifting tasks while wearing the BBEX. The results confirm the ability of the BBEX to provide effective multidimensional force assistance. Moreover, comprehensive safety validation was achieved through analyses of muscle fatigue in the upper and the lower erector spinae muscles, as well as mechanical loading on spinal joints during both lifting scenarios. By seamlessly integrating functionality inspired by human biomechanics with a focus on safety, this study offers a promising solution to address the persistent challenge of preventing lumbar spine injuries in demanding work environments.

1 September 2026 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
JCJaeyoun Choi
Jaeyoun Choi
OSOswin So
Oswin So
SZSongyuan Zhang
Songyuan Zhang
CTCooper Taylor
Cooper Taylor
CFChuchu Fan
Chuchu Fan

8 June 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
LLLaurin Ludmann
Laurin Ludmann
JCJaeyoun Choi
Jaeyoun Choi
JNJens Neubeck
Jens Neubeck
AWAndreas Wagner
Andreas Wagner
CFChuchu Fan
Chuchu Fan
This paper introduces Hybrid Physics-Augmented Neural Network (HyPA-Net), a hybrid modeling framework that integrates physics-based linear time-invariant models with artificial neural networks (ANNs) to address dynamic system modeling when only partial physical knowledge is available. The approach leverages the interpretability and robustness of established physical models while using ANNs — such as Long Short-Term Memory architectures—to capture unknown or nonlinear system behaviors. The methodology normalizes state and input variables for compatibility with ANN training, and expands traditional recursive state-space equations for efficient backpropagation over sequences. Vehicle dynamics, specifically using a rear wheel steering test case, validate the proposed framework. Various HyPA-Net configurations are benchmarked against pure physics-based and pure data-driven models, demonstrating improved prediction accuracy and model flexibility. The experimental results confirm that hybrid models yield superior performance over strict physical approaches and can implicitly learn submodel dynamics within a unified, yet modular architecture, opening avenues for applications in domains where partial physics-based knowledge is available but insufficient on its own.

27 July 2026 in Vehicles
Verified
Journal Article
Open access
PDF file
LLLaurin Ludmann
Laurin Ludmann
JCJaeyoun Choi
Jaeyoun Choi
JNJens Neubeck
Jens Neubeck
AWAndreas Wagner
Andreas Wagner
CFChuchu Fan
Chuchu Fan
This paper introduces Hybrid Physics-Augmented Neural Network (HyPA-Net), a hybrid modeling framework that integrates physics-based linear time-invariant models with artificial neural networks (ANNs) to address dynamic system modeling when only partial physical knowledge is available. The approach leverages the interpretability and robustness of established physical models while using ANNs—such as long short-term memory architectures—to capture unknown or nonlinear system behaviors. The methodology normalizes state and input variables for compatibility with ANN training and expands traditional recursive state-space equations for efficient backpropagation over sequences. Vehicle dynamics, specifically using a rear-wheel steering test case, validate the proposed framework. Various HyPA-Net configurations are benchmarked against pure physics-based and pure data-driven models, demonstrating improved prediction accuracy and model flexibility. The experimental results in this application confirm that hybrid models yield superior performance over strict physical approaches and can implicitly approximate submodel dynamics within a unified, yet modular, architecture, opening avenues for applications in domains where partial physics-based knowledge is available but insufficient on its own.

5 October 2021 in Smart Materials and Structures
Verified
Journal Article
Closed access
PDF file
JKJunghan Kwon
Junghan Kwon
MPMyungsun Park
Myungsun Park
JCJaeyoun Choi
Jaeyoun Choi
YPYong-Lae Park
Yong-Lae Park
Self-folding is a promising concept in the fields of smart materials and robotics, which allows self-assembly and multi-functionality. Although there have been approaches to realize self-folding mechanisms using different techniques, and their practical applications are not sufficiently investigated. Here, we propose untethered, self-folding polymer structures with embedded air chambers, which easily transform two-dimensional flat shapes into preprogrammed three-dimensional (3D) shapes when heat energy is transferred into the structures resulting in thermal expansion of the air chambers. This mechanism is particularly useful for casting materials that require shape and phase changes simultaneously if the proposed structures are used as molds. As a practical application, we present pop-up cookie molds that can bake 3D-shaped cookies from flat cookie dough. Analytical modelings based on the ideal gas law, the principle of minimum potential energy, and the lumped capacitance method for heat transfer are established and experimentally validated using prototypes. These provide a prediction of the structure’s bending curvature during the baking process. Furthermore, other target shapes, including bending, twisting, and their combinations, are also achieved by configuring various chamber designs. Finally, practical prototypes with more complex shapes are proposed, and their performances are demonstrated.

9 February 2026 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
MVMatti Vahs
Matti Vahs
JCJaeyoun Choi
Jaeyoun Choi
NSNiklas Schmid
Niklas Schmid
JTJana Tumova
Jana Tumova
CFChuchu Fan
Chuchu Fan
Robots deployed in dynamic environments must remain safe even when key physical parameters are uncertain or change over time. We propose Parameter-Robust Model Predictive Path Integral (PRMPPI) control, a framework that integrates online parameter learning with probabilistic safety constraints. PRMPPI maintains a particle-based belief over parameters via Stein Variational Gradient Descent, evaluates safety constraints using Conformal Prediction, and optimizes both a nominal performance-driven and a safety-focused backup trajectory in parallel. This yields a controller that is cautious at first, improves performance as parameters are learned, and ensures safety throughout. Simulation and hardware experiments demonstrate higher success rates, lower tracking error, and more accurate parameter estimates than baselines.