Caltech Young Investigators Lecture

Tuesday, April 25, 2023
11:00am to 12:00pm
Add to Cal
Gates-Thomas 135
Exoskeleton-Based Training For Novel Motor Skill Acquisition
Keya Ghonasgi, Ph.D. candidate, University of Texas, Austin,


Humans are highly adaptable and can learn to interact with their environment. Technology for human use capitalizes on this ability through interfaces like touch screens and controllers. However, human motor behavior is difficult to quantify and predict which limits the effectiveness of physical human-robot interactions (HRI). For example, upper-body exoskeleton robots for rehabilitation have only shown comparable or lower training effects than traditional physical therapy, despite their promising sensing and actuation capabilities. My research interprets HRI through the lens of neuroscience and translates the findings into intelligent engineering solutions. In this talk, I discuss human learning in a robotic exoskeleton environment. I start by exploring methods to quantify human learning during robot interactions. I then motivate novel exoskeleton interaction modes based on observed task-specific expert behaviors. Finally, I present a curriculum-based approach for adaptive motor training protocol design. This work has several potential applications including motor re-training for rehabilitation, athletic, and surgical skill training.


Keya Ghonasgi is a Ph.D. candidate in the Mechanical Engineering department at the University of Texas at Austin. Her research at Prof. Ashish D. Deshpande's ReNeu Robotics lab focuses on human-exoskeleton interaction for rehabilitation and motor training. Keya received her M.S. in Mechanical Engineering with a focus in Robotics from Columbia University in 2018 and her B.Tech. in Mechanical Engineering and M.S. in Mathematics from the Birla Institute of Technology and Science – Pilani, Goa campus in 2016. In 2022, she was awarded the university continuing graduate fellowship by the University of Texas at Austin, and recognized as a Rising Star in Mechanical Engineering. Her research interest lies at the intersection of neuroscience, engineering, and artificial intelligence and she aims to realize the potential of human-robot interaction in improving human quality of life.

This lecture is part of the Young Investigators Lecture Series sponsored by the Caltech Division of Engineering & Applied Science.

For more information, please contact Stacie Takase by email at [email protected].