Enabling Human Mobility Through Personalized Robotic Control
Assistive robotic technologies-like protheses, exoskeletons, and semi-autonomous powered wheelchairs-have the potential to meaningfully transform human mobility. Yet, despite great strides in the development of wearable assistive robots over the last several decades, people are not widely using these systems in their daily lives. Fundamentally, we do not yet know how to apply robotic assistance to the human body in order to promote meaningful clinical improvements or achieve targeted physiological goals. To this end, my work is focused on the design and experimental evaluation of personalized, adaptive control strategies for assistive robotic devices. In this seminar, I will present work that advances our understanding of how to provide robotic assistance to users outside the laboratory environment. I will discuss how data-driven modeling and wearable sensors can be used to estimate important physiological metrics (e.g., metabolic cost) outside the lab. Such measurements are necessary for adaptive control strategies to respond to real-time changes in the user's physiology. As an example of a personalized control system, I will demonstrate that exoskeleton users can quickly and precisely identify features of robotic assistance that they prefer, and highlight characteristics of user preference that make the design of personalized control systems both compelling and challenging. While many assistive robots support users during walking, I will also share insights into how these methods may be applied to wheeled mobility technologies, specifically for children with disabilities. Together, this work supports my future research goal of designing personalized, adaptive control strategies for wearable assistive robots in order to enable people to meet their goals and achieve full participation in their daily lives.