Todd Frush
Papers
5
Total Citations
43
H-Index
3
About
Todd Frush is a researcher at the forefront of integrating machine learning with bioelectrical signal processing to advance robotic assistive technologies. His primary research areas include electromyography (EMG)-based control systems, upper-limb exoskeletons, and robotic-assisted orthopedic surgery. Frush’s major contributions lie in developing real-time, volitional control systems for bionic assistive robots, addressing the challenge of processing multiple EMG channels amidst noise and biological variability. His most cited work, "Volitional control of upper-limb exoskeleton empowered by EMG sensors and machine learning computing" (2023, 23 citations), demonstrates how machine learning can enable more intuitive and responsive motion control. He has also pioneered a fixed-bandwidth frequency-domain embedded system for robotic hand control (2022, 10 citations) and validated real-time, multi-channel shoulder EMG processing using artificial neural networks (2021, 5 citations). Beyond rehabilitation robotics, Frush has contributed to orthopedic outcomes research, comparing robotic-assisted versus manual total knee and patellofemoral arthroplasty using registry data. His work bridges the gap between offline EMG analysis and practical, online control systems, positioning him as a key innovator in human-machine interaction and rehabilitative engineering.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5