Yoonsu Jang

About

Yoonsu Jang is a researcher at the intersection of reinforcement learning, robotics, and control systems, with a particular focus on bridging the simulation-to-reality (sim-to-real) gap for autonomous aerial vehicles. His most notable contribution is the development of a transformer-based dynamics model that enables quadrotor control policies learned in simulation to transfer effectively to real-world platforms, even when experimental data is scarce. This work addresses a critical bottleneck in deploying learning-based controllers on physical robots, where data collection is often expensive or time-consuming. While his citation count is still growing, Jang’s research is positioned at the forefront of leveraging modern deep learning architectures—specifically transformers—for model-based reinforcement learning in robotics. His approach demonstrates how limited real-world data can be used to fine-tune sim-to-real transfer, making his work particularly relevant for students and researchers interested in sample-efficient robot learning. Jang’s contributions are paving the way for more robust and data-efficient autonomous systems, especially in agile flight control scenarios.

Research Focus

Key Achievements

Top Papers

1. 1
   Transformer-based dynamics model for sim-to-real reinforcement learning control of a quadrotor with limited experimental data

   1 citations · 2025

Key Collaborators

Contact & Links