My research lies at intersection of deep learning, dynamical systems, and robotics. I think about ways for combining deep learning with first-principles models, which are known for their extrapolation powers. But how should we combine the two? What benefits would we get? And what are the potential drawbacks? I aim to answer these questions by proposing novel deep learning techniques, which are validated on both simulated and physical robotic platforms.
Y. Wu, T. Z. Jiahao, J. Wang, P. A. Yushkevich, M. A. Hsieh, and J. C. Gee, "NODEO: A Neural Ordinary Differential Equation Based Optimization Framework for Deformable Image Registration," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
K. Y. Chee, T. Z. Jiahao, and M. A. Hsieh, “Knode-mpc: A knowledge-based data-driven predictive control framework for aerial robots,” IEEE Robotics and Automation Letters (RA-L), vol. 7, no. 2, pp. 2819–2826, 2022.
T. Z. Jiahao, L. Pan, and M. A. Hsieh, "Learning to swarm with knowledge-based neural ordinary differential equations," IEEE International Conference on Robotics and Automation (ICRA), 2022.
T. Z. Jiahao, M. A. Hsieh, and E. Forgoston, “Knowledge-based learning of nonlinear dynamics and chaos,” Chaos: An Interdisciplinary Journal of Nonlinear Science, vol. 31, no. 11,p. 111101, 2021.
T. Nathans-Kelly, R. Evans, L. Klein, and J. Zhang, "We WOVE, we designed, we conquered: Assessing engineering self-efficacy in a Mechanical Engineering Communication Initiative—Instructor and student perspectives," 2017 IEEE International Professional Communication Conference (ProComm), 2017, pp. 1-8, doi: 10.1109/IPCC.2017.8013963.
I occasionally write posts about my research and other topics on Medium: