Mattia Zorzi
Papers
2
Total Citations
6
H-Index
2
About
Mattia Zorzi is a researcher whose work sits at the intersection of robotics, machine learning, and control theory, with a particular focus on inverse dynamics modeling. His major contributions lie in developing advanced algorithms that enable robots to learn and adapt their motion models in real time, a critical capability for autonomous systems operating in dynamic environments. Zorzi’s 2016 paper on "Online semi-parametric learning for inverse dynamics modeling" (4 citations) introduced a novel hybrid approach that combines the physical accuracy of parametric rigid body dynamics with the flexibility of non-parametric kernel methods, allowing robots to compensate for unmodeled effects. He further advanced the field with his 2019 work on "Derivative-Free Online Learning of Inverse Dynamics Models" (2 citations), which unified various model classes—including purely data-driven and semiparametric models—into a common framework, eliminating the need for computationally expensive derivative calculations. While his citation counts are modest, Zorzi’s work is notable for its practical focus on real-time, online learning, addressing fundamental challenges in adaptive robotics. His contributions are particularly valuable for researchers and students interested in bridging model-based and data-driven approaches for robot control.
Research Focus
Key Achievements
Top Papers
- 1Online semi-parametric learning for inverse dynamics modeling4 citations · 2016
- 2Derivative-Free Online Learning of Inverse Dynamics Models2 citations · 2019