Tommaso Castiglione Ferrari

Papers

Total Citations

H-Index

About

Tommaso Castiglione Ferrari is a robotics researcher advancing the frontier of data-driven control and planning for aerial systems. His work centers on learning-based dynamics modeling for quadrotors, with a particular focus on overcoming the limitations of short-horizon predictions that constrain traditional approaches. In his highly cited 2024 paper, "Learning Long-Horizon Predictions for Quadrotor Dynamics," Ferrari introduces a novel framework that extends predictive accuracy over extended time horizons, enabling more reliable and high-performance planning for agile flight. This contribution addresses a critical bottleneck in autonomous drone navigation, where precise long-term state estimation is essential for tasks like aggressive maneuvering and obstacle avoidance. Though early in his career, Ferrari’s research has already garnered attention for its practical impact on real-world robotic systems. His work bridges the gap between theoretical learning methods and deployable control solutions, positioning him as a rising voice in the intersection of machine learning and robotics. For students and researchers, Ferrari’s approach exemplifies how targeted innovations in dynamics modeling can unlock new capabilities in autonomous flight.