no code implementations • 15 May 2023 • Thomas Beckers, Tom Z. Jiahao, George J. Pappas
Switching physical systems are ubiquitous in modern control applications, for instance, locomotion behavior of robots and animals, power converters with switches and diodes.
no code implementations • 3 Apr 2023 • Sandeep Manjanna, Tom Z. Jiahao, M. Ani Hsieh
Our algorithm makes use of the predictions from a learned prediction model to plan a path for an autonomous vehicle to adaptively and efficiently survey the region of interest.
1 code implementation • 19 Jul 2022 • Tom Z. Jiahao, Kong Yao Chee, M. Ani Hsieh
To improve the adaptiveness of the model and the controller, we propose an online dynamics learning framework that continually improves the accuracy of the dynamic model during deployment.
no code implementations • 10 Sep 2021 • Kong Yao Chee, Tom Z. Jiahao, M. Ani Hsieh
Using a quadrotor, we benchmark our hybrid model against a state-of-the-art Gaussian Process (GP) model and show that the hybrid model provides more accurate predictions of the quadrotor dynamics and is able to generalize beyond the training data.
no code implementations • CVPR 2022 • Yifan Wu, Tom Z. Jiahao, Jiancong Wang, Paul A. Yushkevich, M. Ani Hsieh, James C. Gee
Deformable image registration (DIR), aiming to find spatial correspondence between images, is one of the most critical problems in the domain of medical image analysis.
1 code implementation • 7 Oct 2020 • Tom Z. Jiahao, M. Ani Hsieh, Eric Forgoston
For the Lorenz system, different types of domain knowledge are incorporated to demonstrate the strength of knowledge embedding in data-driven system identification.