Monroe D. Kennedy III, PhD

Byadivnich

Assistant Professor 
Mechanical Engineering (courtesy Computer Science)

https://profiles.stanford.edu/monroe-kennedy

Monroe Kennedy III is an Assistant Professor of Mechanical Engineering, with a courtesy appointment in Computer Science. He received his Ph.D. in Mechanical Engineering and Applied Mechanics and a Masters in Robotics from the University of Pennsylvania where he was a recipient of both the NSF and GEM graduate research fellowships. His area of expertise is in robotics, specifically the development of theoretical and experimental approaches to perform control and estimation for robotic systems, particularly robotic manipulation and human-robot collaborative tasks. He applies expertise in dynamical systems analysis, control theory (classical, non-linear and robust control), state estimation and prediction, motion planning, vision for robotic autonomy, and machine learning.

He is the Director of the Assistive Robotics and Manipulation Lab (ARMLab), which specializes in development of intelligent robotic systems, including robotic assistants, connected devices, and intelligent wearables,  that can improve everyday life by anticipating and acting on the needs of human counterparts. Dr. Kennedy recently received an NSF CAREER award to develop soft robotic fingertips for dexterous task performance. In the community, he is a National Director for Black in Robotics, which aims to increase engagement of underrepresented minorities in robotics.

SAGE Project: Development of a Fall Prevention System for Older Adults Utilizing Wearable Sensors for Human Gait and Path Prediction

Falls are the leading cause of fatal and non-fatal injuries in older adults (ages 65+). Injuries due to falling result in 2.8 million emergency visits annually, and 25% of falls result in very serious injuries (such as fractures or traumatic brain injury). This project aims to develop a wearable device that can alert the wearer to the risk of falling and potentially prevent falls. When worn on the torso, the “smartbelt” will be able to measure the wearer’s odometry, gait, stability, and walking path trajectory. The ultimate goal is to be able to provide vibrotactile feedback alert to the wearer to warn of poor stability and risk of injury. As a first step, the team has developed a platform capable of sensing the surrounding environment and predicting the expected path, walking rate, and torso sway of the person. In the next steps, this prediction will be improved to allow for multiple path hypotheses, and the predicted torso sway will be used to inform the user of potential fall risk.