Zhaozheng Yin
Stony Brook University, NY·Computer Science
Walking with a leg prosthesis is hard work. People with lower limb amputation often walk unevenly, use more energy and strain their lower backs.
- Fields
Computer Science
Biomedical Engineering
Engineering
- Topics
prosthetics
lower limb amputation
prosthetic robot
- Grants
- 1 known grant, through Jun 2027
What they work on
- Develop motion capture from wearable inertial measurement unit (IMU) sensors alone to reconstruct and predict daily-life gait, using knowledge distillation from a multi-sensor teacher network to a simpler student network.
- Design a lightweight, energy-efficient, semi-active prosthesis combining pneumatic and hydraulic components that users can tune for different walking environments.
- Build a reinforcement-learning control algorithm that syncs user and prosthesis, using a mixed-criticality design from real-time systems to keep the robot safe and stable.
More about the research
Today's robotic prostheses either respond too slowly and inaccurately or work only in a lab. A key gap is that they get no feedback from what the user sees ahead, such as stairs or slopes. The rest of the body must compensate, raising the risk of falls and joint damage. This collaborative project aims to build a prosthetic robot that uses the user's visual information to rebuild this missing feedback and adjust its control ahead of time across daily walking conditions.
Why it matters
People with lower limb amputation could benefit from prostheses that anticipate terrain. This may reduce falls, back strain and joint damage while making walking less tiring. Wearable gait monitoring outside the lab could help clinicians assess users and prescribe and tune prostheses more effectively.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Zhishan Guo
North Carolina State University, NC·Engineering
Develop a gait capture method using only wearable inertial motion unit (IMU) sensors, using knowledge distillation so a multi-sensor teacher network trains a simpler IMU-only student network to predict walking in daily life.
Tonya Stone
Mississippi State University, MS·Engineering
Design an elastic spring for an ankle foot prosthesis using machine learning-based optimization to determine the curvatures and contours that maximize energy return during walking.
Sunghoon Lee
University of Massachusetts, MA·Biomedical Engineering
Develop a Body Channel Identification (BCID) sensing platform, with batteryless object tags read by a wrist-worn device through the body during touch, that records object identity, contact timing, grip pressure and wrist motion.
The school
Stony Brook University: 32 labs on PI Pages, $319M a year on research, 289 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.