Reduced balance is a critical challenge for individuals with disabilities, most notably in affecting their ability to walk. Advances in wearable devices, robotic exoskeletons, or prostheses have opened great potential to assist those individuals. However, one central challenge remains: how to control these sophisticated devices, while also taking into account human responses. For, humans often respond unintuitively when assisted. Dr. Kim has been working on developing human-in-the-loop control using a combination of theoretical and experimental methods to solve this problem.
Dr. Kim developed the first balance-assistance controller that successfully reduced balance-related efforts of steady-state walking in a wearable device. This result was achieved by modulating ankle push-off work at each step in an ankle-foot prosthesis emulator, while directly including a subject’s balance state in a control strategy. This control idea was initially developed from her theoretical study using a numerical model of amputee walking.
To maximize assistance benefit, she developed a systematic, efficient individualization method, human-in the-loop online optimization, for a textile-based soft robotic exoskeleton. Her approach used the physiological signal expressed during a human subject’s effort (metabolic cost) to optimize the control parameters of the wearable device. By utilizing Bayesian optimization – sample-efficient, noise-tolerant, and global optimization methods – she has demonstrated that an optimal parameter can be found within 30 minutes, with a great reduction in metabolic cost. In this seminar, she will discuss the challenges and opportunities offered by the human-in-the-loop assistance controller and online optimization method she has developed. One exciting future direction will be to design controllers that take into account non-steady-state dynamics to improve mobility and comfort. The methodology, designing and experimentally evaluating computational approaches, also holds promise for designing even more effective assistance methods.
When: Friday, September 27, 1-2:00pm
Where: CDM Theater 708
Who: Dr. Myunghee Kim, Assistant Professor, Department of Mechanical and Industrial Engineering, UIC
Now the colloquium talks are live-streamed and available on YouTube!
Speaker bio: Myunghee Kim joined as an assistant professor at UIC Department of Mechanical and Industrial Engineering. Myunghee Kim’s primary research focus is the development of assistive robotic devices for improving mobility and quality of life through integrative approaches of numerical dynamic models, machine learning techniques, experimental testbeds, and controlled human-subject experiments. She received her M.S. degrees from Korea Advanced Institute of Science (KAIST) and Technology and Massachusetts Institute of Technology (MIT), a Ph.D. degree from Carnegie Mellon University and held a post-doctoral appointment at Harvard University. She was a control engineer in humanoid robotics at Samsung. She received Best Paper Award in the Medical Devices category at International Conference on Robotics and Automation (ICRA) 2015. Recently, her group work on a data-driven model estimation method resulted in the Best Poster Award at the US-Korea Conference (UKC) 2019.