BME Seminar: AI Computing and Machine learning framework for Human-robot Interaction and wearable robotics: Tr


3:00 pm
Add to Outlook/iCal
Add to Google Calendar


Communicore Room C1-17
1249 Center Dr.
Gainesville, FL 32610


Shuzhen Luo, Ph.D.
Postdoctoral research associate
Department of BIomedical engineering
UNC Chapel Hill & NC State University

Shuzhen Luo is a postdoctoral research associate in the Department of Biomedical Engineering at UNC Chapel Hill and NC State University. She earned her Ph.D. degree in control science and engineering at Nankai University in China in 2018. Since 2018, she has worked as a research associate at Rutgers University and then as a postdoctoral fellow at New Jersey Institute of Technology, UNC Chapel Hill and NC State University.

As an AI researcher in healthcare and rehabilitation engineering, her research interests lie in the area of bio-inspired wearable assistive robotics, large-scale AI computation, deep reinforcement learning-based digital clone for human-robot interaction, biomechanics, and musculoskeletal modeling. Her current research is rooted in the translation of AI-powered wearable robots to healthcare (treatment and medicine for people with musculoskeletal disorders). She has published 20 journal articles and holds one patent on learning-enabled intelligent exoskeletons. She envisions developing AI computing-based predictive neuromechanical simulation or machine learning-based digital motor clones, which will be used to provide optimal and customized treatments to people with musculoskeletal disorders. Her work is geared towards empowering engineering solutions that augment human mobility for people with disabilities in community settings.

Talk title: AI Computing and Machine learning framework for Human-robot Interaction and wearable robotics: Translational Medicine and treatment


Wearable robots have the potential to improve human mobility for people with disabilities. However, the development of robot control strategies for community activities is still limited by the need for hours-long human testing and specialized laboratory equipment. They lack the ability to adapt to varying individual needs, which is imperative when assisting older adults who commonly suffer from heterogeneous impairments. In our work, we aim to enable a paradigm shift of AI-powered assistive robots from lab-bounded rehabilitation machines to ubiquitous personal wearable devices for functional movement augmentation in community settings. We created a data-driven and physics-informed approach that leverages deep reinforcement learning in concert with a musculoskeletal model to automatically learn a robot controller entirely in simulation. Moreover, we proposed a domain randomization method in simulation to account for the variability of human gait biomechanics. The immediate deployment of the controller on a microcontroller of a portable hip exoskeleton significantly reduced the significant energy expenditure for the able-bodied subjects during walking, running, and stair climbing, respectively compared with no-exoskeleton conditions. We also evaluated our method through detailed human subject experiments involving individuals with varying impairments, such as osteoarthritis, cerebral palsy, and stroke. These experiments revealed the potential benefits of our robot in improving functional mobility in these subject populations. Our work is the first investigation of using AI and reinforcement learning in wearable robots for real-world assistance of human mobility for people with disabilities.


Hosted by

Dr. Ana Porras