Research agenda

Research vision, methodological priorities, and current themes

My research sits at the intersection of computational modeling, intelligent systems, and scientific rigor. I am interested in methods that are not only accurate, but also credible, interpretable, and useful in real scientific and engineering settings.

Research statement

Connecting physical structure with computational intelligence

I work on problems where simulation, data, and intelligent decision systems must interact in a principled way. This includes research in numerical simulation, machine learning, deep learning, scientific machine learning, robotics, and control. Across these areas, I am especially interested in methods that preserve structure, improve reliability, and remain meaningful for real applications.

This perspective is useful for scientific forecasting, engineering analysis, robot control, and hybrid computational systems, where purely empirical methods may be insufficient on their own.

Method pillars
  • Simulation-aware and physics-aware machine learning
  • Robotics experiments grounded in sensing and control
  • Deep learning for structured scientific and engineering data
  • Control-theoretic thinking for trustworthy intelligent behavior
Core themes

Major research areas

These themes are presented as a coherent research program rather than disconnected topics.

Current research questions

Questions that motivate the work

These questions can be adapted over time as your projects, publications, and dissertation direction evolve.

Question 01

How can scientific structure improve machine learning performance and trust?

This includes physics-informed losses, hybrid models, domain-aware features, and evaluation strategies that go beyond purely black-box prediction.

Question 02

How can robotics systems combine learning with reliable control?

The goal is to connect sensing, embedded implementation, and control strategies with intelligent adaptation that remains stable and useful.

Question 03

How can simulation outputs support more effective intelligent systems?

Simulation data can act as structure, supervision, prior knowledge, or benchmarking evidence for learning and analysis pipelines.

Question 04

How can research be communicated clearly across audiences?

Strong academic work should also be documented through clear writing, reproducible code, teaching materials, and technical outreach.

Research workflow

How projects move from idea to output

My preferred workflow begins with a domain question, moves through modeling and implementation, and ends with evidence-based evaluation, publication-quality outputs, and communication materials that help others understand and reuse the work.

Typical stages
  1. Problem framing through scientific, engineering, or system-level questions.
  2. Model design using simulation, learning, control, or hybrid methods.
  3. Implementation with code, experiments, visualization, and documentation.
  4. Evaluation through comparisons, ablations, interpretation, and technical writing.