Alessandro Chiuso

Papers

Total Citations

H-Index

About

Alessandro Chiuso is a researcher whose work sits at the intersection of machine learning, robotics, and system identification. His research focuses on developing intelligent algorithms for modeling robot dynamics, with particular emphasis on inverse dynamics — a critical challenge in enabling robots to move accurately and efficiently in real-world environments. Among his notable contributions, Chiuso has pioneered semi-parametric approaches to robot learning that elegantly bridge classical physics-based modeling and modern data-driven techniques. His 2016 paper on online semi-parametric learning for inverse dynamics cleverly combines rigid body dynamics equations with kernel-based non-parametric methods, offering robots the ability to learn and adapt in real time. Building on this foundation, his 2019 work established a unified framework for online inverse dynamics modeling, accommodating a broad spectrum of model classes — from purely parametric to fully data-driven — while introducing derivative-free optimization strategies that enhance practical applicability. Though his citation counts are still growing, reflecting relatively recent contributions to the field, Chiuso's integrative methodology represents a meaningful step forward in making robot learning more flexible, physically grounded, and computationally tractable — qualities increasingly essential as robotics pushes into more complex, unstructured environments.