General Information
Details
My group focuses on four broad research areas to advance autonomy for both virtual characters and real-world robots. We explore how human motion data can inform the control of robots with various morphologies. We also investigate sim-to-real algorithms to effectively transfer the learned control policies to physical robotic platforms. Third, we develop visuomotor controllers that enable autonomous navigation, manipulation, and task execution using onboard sensors. Finally, we pursue broader societal impact by investigating real-world applications, including robotic guide dogs and assistive robots in hospitals.
I believe effective learning stems from active teacher-student interaction. Based on this philosophy, I have taught: CS4496/7496 Computer Animation, CS 3451 Computer Graphics, CS 4801/8801 Programming Interview Preparation, and CS 8803 Deep Reinforcement Learning. CS 4496/7496 Computer Animation is a course for learning the principles behind modern kinematic- and physics-based animation techniques. CS 8803 Deep Reinforcement Learning, where I taught state-of-the-art deep RL algorithms.
* H. Jung, Z. Gu, Y. Zhao, H. -W. Park and S. Ha, "PPF: Pre-Training and Preservative Fine-Tuning of Humanoid Locomotion via Model-Assumption-Based Regularization," in IEEE Robotics and Automation Letters, vol. 10, no. 11, pp. 11466-11473, Nov. 2025, doi: 10.1109/LRA.2025.3608637.
* Rho, S., Garg, K., Byrd, M. & Ha, S.. (2025). Unsupervised Skill Discovery as Exploration for Learning Agile Locomotion. <i>Proceedings of The 9th Conference on Robot Learning</i>, in <i>Proceedings of Machine Learning Research</i> 305:2678-2694 Available from https://proceedings.mlr.press/v305/rho25a.html.
* N. Yokoyama, S. Ha, D. Batra, J. Wang and B. Bucher, "VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation," 2024 IEEE International Conference on Robotics and Automation (ICRA), Yokohama, Japan, 2024, pp. 42-48, doi: 10.1109/ICRA57147.2024.10610712.