Search NASA⌕ Search

Engineering topics

Yoo, Shinjae

Publications and source records attributed to Yoo, Shinjae.

8 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

MCP agents in PanDA

Explore the source record for details and available documents.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

A Real2Sim Digital Twin Pipeline for Photorealistic Robot Simulation: Evaluating VLA Policy Deployment on a Bimanual Mobile Robot

Digital twins that are automatically constructed from robot sensor data offer a promising pathway for scalable Real2Sim and Sim2Real transfer. However, it remains an open question whether photorealistic reconstruction alone is sufficient to support reliable deployment of vision-language-action (VLA) policies. We present a generative-AI-assisted Real2Sim pipeline that generates simulation-ready digital twins from real-world RGB observations with minimal manual intervention. The pipeline uses prompted segmentation to isolate scene components and a generative 3D model to directly produce simulation assets, eliminating the need for traditional multi-view reconstruction or manual 3D modeling.\r\nTo evaluate simulation fidelity, we deploy and compare policies from two VLA models in both the real robot and the reconstructed\r\nsimulation under identical tasks and initial conditions. We compare joint-level action trajectories and analyze how divergence evolves over time in closed-loop execution. Although the reconstructed environments are visually accurate, we observe increasing trajectory divergence during closedloop operation. These results indicate that photorealistic reconstruction alone is insufficient to preserve closed-loop control behavior\r\nin VLA policies, particularly in contact-rich manipulation settings where small perceptual errors compound over time.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

A Two-Stage Quantum Reinforcement Learning Method for Multi-Objective Transmission Switching

Multi-objective transmission switching (MO-TS) problems involve the strategic reconfiguration of network topology to simultaneously optimize multiple objectives. As the system scale increases, finding feasible solutions becomes increasingly challenging due to the problem's nonlinearity and high computational complexity. To address these challenges, this paper proposes a two-stage quantum reinforcement learning method that leverages potential quantum advantages for MO-TS. In the first stage, candidate switching lines are identified using a graph-theoretical approach to reduce the problem's dimensionality. The second stage introduces a quantum-classical reinforcement learning framework, where a learnable measurement-based CNN-ResVQC architecture is developed to effectively reduce the input dimension for quantum processing, mitigate vanishing gradients, and enhance trainability while improving the quantum circuit's flexibility in modeling complex decision policies for MO-TS. Numerical studies on IEEE 14-bus, 57-bus, and 118-bus systems demonstrate that the proposed algorithm achieves superior training stability and faster convergence with approximately 1% of the network parameters required by classical algorithms, highlighting its effectiveness, efficiency, and scalability. Furthermore, the practicality is validated through its stable convergence under three common quantum noise channels.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2025

FM4NPP: A Scaling Foundation Model for Nuclear and Particle Physics

Large language models have revolutionized artificial intelligence by enabling large, generalizable models trained through self-supervision. This paradigm has inspired the development of scientific foundation models (FMs). However, applying this capability to experimental particle physics is challenging due to the sparse, spatially distributed nature of detector data, which differs dramatically from natural language. This work addresses if an FM for particle physics can scale and generalize across diverse tasks. We introduce a new dataset with more than 11 million particle collision events and a suite of downstream tasks and labeled data for evaluation. We propose a novel self-supervised training method for detector data and demonstrate its neural scalability with models that feature up to 188 million parameters. With frozen weights and task-specific adapters, this FM consistently outperforms baseline models across all downstream tasks. The performance also exhibits robust data-efficient adaptation. Further analysis reveals that the representations extracted by the FM are task-agnostic but can be specialized via a single linear mapping for different downstream tasks.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
DOE OSTI2024

Use of physics to improve solar forecast: Part III, impacts of different cloud types

Cloud-type impacts present a great challenge to solar forecasting due to diverse and complex cloud-radiation interactions. This third part of our paper sequence seeks to address this challenge by quantifying the forecast accuracies under eight cloud types: cumulus (Cu), stratified clouds (St), altocumulus (Ac), altostratus (As), cirrostratus/anvil (Cr), cirrus (Ci), congestus (Co), deep convective clouds (Dc) across four physics-informed persistence models reported in Part I. To generalize the cloud impacts, the eight cloud types are further grouped into three cloud categories based on their common features: weak convective clouds, stratiform clouds, and strong convective clouds. Here, the decade-long (2001 ~ 2014) collocated measurements of irradiances and cloud types at the U.S. Department of Energy (DOE) Atmospheric Radiation Measurement (ARM) Program South Great Plain (SGP) Central Facility site are used for model evaluation. Results reveal a clear performance hierarchy for global horizontal irradiance (GHI) and direct normal irradiance (DNI): best for weak convective clouds and cirrus, intermediate for stratiform clouds, and worst for strong convective clouds. Performance for diffuse horizontal irradiance (DHI) is less influenced by cloud types. Cloud albedo dominates all three irradiances for Dc, while both cloud albedo and cloud fraction are influential for other cloud types. A 12 %~33 % improvement in accuracy at 6-hour lead time compared to the benchmark smart model confirms the effectiveness of incorporating physics into the models for various cloud types; further improvements are expected by directly integrating cloud type information into forecasting models by modifying the physical formulation of cloud-radiation interaction, and/or using more advanced machine learning models.

14 SOLAR ENERGY↗