Papers
24
Total Citations
339
H-Index
11
About
Valerio Modugno is a robotics researcher whose work spans humanoid robot control, teleoperation, learning-based control, and surgical robotics. He has made significant contributions to the field of whole-body motion control for redundant and humanoid robots, most notably through his pioneering work on real-time motion retargeting from humans to humanoids, which has garnered 74 citations and laid important groundwork for intuitive human-robot teleoperation. Building on this, his multimode teleoperation framework for the iCub robot (40 citations) demonstrates practical applications in hazardous environments such as search-and-rescue and industrial settings. A recurring theme in Modugno's research is the automation of complex controller tuning through machine learning. His series of papers on learning soft task priorities for redundant and humanoid robots — collectively accumulating over 80 citations — addresses the longstanding challenge of automatically deriving task priorities and control gains, reducing reliance on expert knowledge. He has also made notable contributions to surgical robotics, applying Bayesian Neural Networks and Model Predictive Control to tendon-driven systems to ensure precision and safety under uncertainty. More recently, his work on navigation among movable obstacles reflects a broadening interest in autonomous mobile manipulation, further demonstrating the versatility and impact of his research portfolio.
Research Focus
Key Achievements
Top Papers
- 1Robust Real-Time Whole-Body Motion Retargeting from Human to Humanoid74 citations · 2018
- 2
- 3Learning soft task priorities for control of redundant robots34 citations · 2016
- 4
- 5
- 6
- 7Learning Robust Task Priorities and Gains for Control of Redundant Robots17 citations · 2020
- 8Learning Robust Task Priorities of QP-Based Whole-Body Torque-Controllers12 citations · 2018
- 9
- 10