Papers
4
Total Citations
79
H-Index
3
About
Marco Forgione is a leading researcher in robotic control and automation, with a focus on intelligent, adaptive systems that reduce human intervention. His key research areas include robot control parameter auto-tuning, predictive visual servoing, and meta-learning for robot dynamics. Forgione’s major contributions center on developing automated tuning methodologies for industrial manipulators, enabling them to self-regulate under varying operational conditions—a critical step toward true autonomy. His most cited work, "Robot control parameters auto-tuning in trajectory tracking applications" (2020, 61 citations), introduces a two-stage framework that optimizes controller gains without time-consuming manual calibration, significantly enhancing efficiency in manufacturing. Expanding on this, his "Two-Stage Robot Controller Auto-Tuning Methodology" (2020, 9 citations) and "Fast predictive visual servoing" (2023, 7 citations) further advance real-time predictive control, balancing computational speed with precision. Most recently, his 2024 paper "RoboMorph: In-Context Meta-Learning for Robot Dynamics Modeling" (2 citations) explores Transformer-based architectures for physical applications, signaling a shift toward data-driven, adaptive models. Forgione’s work bridges classical control theory and modern machine learning, offering practical solutions for next-generation autonomous robotics.
Research Focus
Key Achievements
Top Papers
- 1Robot control parameters auto-tuning in trajectory tracking applications61 citations · 2020
- 2
- 3Fast predictive visual servoing: A reference governor-based approach7 citations · 2023
- 4RoboMorph: In-Context Meta-Learning for Robot Dynamics Modeling2 citations · 2024