Feng-Chieh Ku

Hello! I am Feng-Chieh Ku, a robotics researcher passionate about developing intelligent robotic systems that can bridge the gap between simulation and the real world. My research interests lie at the intersection of robot learning, imitation learning, sim-to-real transfer, digital twins, and autonomous robotic manipulation.

Currently, I am working on scalable robotic manipulation systems using NVIDIA Isaac Sim / Isaac Lab and real robotic platforms such as UR manipulators. My work focuses on leveraging simulation, vision-based policy learning, and real-world deployment to enable robots to perform precise manipulation tasks in complex environments. I am particularly interested in imitation learning, behavior cloning, diffusion-based policies, residual learning, and human-in-the-loop approaches for improving robustness and adaptability in real-world robotic systems.

More broadly, I am motivated by the challenge of building robots that can learn efficiently from both simulated and real-world data, generalize across visual and physical variations, and operate reliably outside controlled laboratory settings. Through my research, I aim to develop practical learning-based robotic systems that can support future applications in automation, healthcare, and assistive robotics.