Maegan Tucker
Short Biography
Maegan Tucker is an Assistant Professor at the Georgia Institute of Technology, with a joint appointment in both the School of Electrical and Computer Engineering, as well as the George W. Woodruff School of Mechanical Engineering. She received her Ph.D. in Mechanical Engineering from the California Institute of Technology (Caltech) in May of 2023. Her research aims to develop and unify techniques from both nonlinear control theory and machine learning to systematically achieve dynamic yet comfortable robotic-assisted locomotion. Her awards and recognitions include the 2023 Centennial Prize for Best Thesis in Mechanical and Civil Engineering from Caltech, the 2022 Simoudis Discovery Prize from Caltech, and two “Best Paper” awards (Best Conference Paper and Best Paper in Human Robot Interaction) for the IEEE International Conference on Robotics and Automation (ICRA) in 2020. Aside from her research, Maegan is deeply passionate about furthering DEI efforts within the robotics community.
Abstract
Whole-body control applied to human robotic assistance (via lower-limb exoskeletons or prostheses) creates additional challenges due to the close interaction with the human user. Specifically, one of the primary challenges when considering robotic assistive devices is that the system must be able to generalize robustly across a diverse set of human models, yet also be customized to individual users to maximize potential clinical benefits. My work approaches the challenges of generalization and customization by developing systematic methods for improving locomotive robustness via hybrid system theory and enabling fast user-customization via preference-based learning. In this talk, I will briefly overview these methods, as well as introduce remaining open problems in the field of whole-body control for human assistance.