Alessandra Bernardini
Papers
3
Total Citations
26
H-Index
3
About
Alessandra Bernardini is a leading researcher at the intersection of robotics, human-machine interaction, and biosignal processing. Her work focuses on developing intuitive, non-invasive control strategies for robotic hands and collaborative robots using surface electromyography (sEMG) signals. Bernardini’s major contributions include pioneering novel regression frameworks that combine deep neural networks with non-negative matrix factorization to enable self-supervised and minimally supervised control of robotic grasping. Her 2022 paper on soft-DTW neural networks for sEMG-based grasping control (13 citations) and her 2023 work on self-supervised regression (10 citations) have established foundational methods for reducing the labeling burden in human-in-the-loop systems. Most recently, her 2024 study on neuromuscular interfacing for kinesthetic programming by demonstration (3 citations) advances teleoperated robot teaching by integrating wearable sensors into collaborative robotics workflows. Bernardini’s research directly addresses the critical challenge of making robotic control more natural and accessible, with clear applications in prosthetics, industrial automation, and assistive technology. Her work is essential reading for anyone interested in sEMG-based control, human-robot collaboration, and the future of intuitive robotic interfaces.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3