Loris Roveda
Dalle Molle Institute for Artificial Intelligence Research, National Research Council, University of Applied Sciences and Arts of Southern Switzerland, Università della Svizzera italiana, Politecnico di Milano, Institute of Intelligent Industrial Systems and Technologies for Advanced Manufacturing, University of Salerno, Stanford University, Tecnologie Avanzate (Italy)
Papers
83
Total Citations
1,939
H-Index
24
About
Loris Roveda is a prominent robotics researcher whose work sits at the intersection of human-robot collaboration, adaptive control, and machine learning for robotic systems. His research has fundamentally advanced how robots interact with humans and uncertain environments, spanning industrial manipulation, assistive technologies, and rehabilitation robotics. Roveda's most influential contributions center on intelligent impedance control — developing frameworks that allow robots to dynamically adjust their compliance and force behavior during physical interaction. His 2020 paper on model-based reinforcement learning for variable impedance control (192 citations) established a landmark approach for adaptive human-robot collaboration, while earlier foundational work on force-tracking impedance control (123 citations) addressed critical challenges in delicate interaction tasks such as polishing fragile materials. His iterative learning and Bayesian optimization methods further demonstrated how robots can reliably learn and refine industrial assembly tasks under real-world uncertainty. Beyond industrial robotics, Roveda has made meaningful contributions to rehabilitation engineering, with his review of patient-cooperative exoskeleton control strategies (104 citations) becoming a key reference in the field. His consistent application of reinforcement learning and model predictive control across diverse robotic domains reflects a unifying vision: intelligent, safe, and human-aware robots. With over 900 cumulative citations across his top works, Roveda stands as a leading voice in modern interactive robotics research.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9Robot control parameters auto-tuning in trajectory tracking applications61 citations · 2020
- 10