Zhebin Yu

Papers

Total Citations

H-Index

About

Zhebin Yu is a leading researcher in human-machine interaction and neural-driven robotics, with a primary focus on decoding motor intent from surface electromyography (sEMG) signals. His work centers on developing advanced deep learning architectures for continuous, proportional control of robotic hands and prosthetics, bridging the gap between biological signals and dexterous artificial movement. Yu’s most impactful contribution is his 2022 paper on a CNN-Attention network for estimating finger kinematics from sEMG, which has garnered 58 citations and represents a significant step toward simultaneous and proportional control in both industrial and rehabilitation settings. He further refined this approach with his Attention-MLP model, demonstrating robust joint angle estimation for six distinct grasp types. By integrating attention mechanisms with convolutional and multilayer perceptron networks, Yu has improved the precision and responsiveness of myoelectric control systems, directly benefiting assistive robotics and prosthetic technology. His work is widely cited by researchers in neural engineering and rehabilitation robotics, and he continues to push the boundaries of how human motor intent can be translated into fluid, intuitive machine movement.