Valentino Fossi
Papers
3
Total Citations
171
H-Index
3
About
Valentino Fossi is a leading researcher in advanced control systems for robotics, with a primary focus on discrete-time sliding mode control (DSMC) and intelligent adaptive algorithms. His most influential work, "Discrete time sliding mode control of robotic manipulators: Development and experimental validation" (2012), has garnered 103 citations, establishing a foundational framework for robust manipulator control in discrete-time environments. Fossi’s major contributions lie in integrating neural networks—specifically Minimal Resource Allocating Networks and Radial Basis Function networks—with DSMC to autonomously learn and compensate for system uncertainties. His 2012 paper on this topic (61 citations) introduces an online learning algorithm that dynamically grows and prunes network nodes, enabling real-time adaptation without prior system knowledge. Additionally, his 2011 work pioneers the use of autoregressive models identified via Kalman Filters for predictive uncertainty compensation, validated through experimental trials. Fossi’s research bridges theoretical rigor with practical validation, offering scalable solutions for high-precision robotic tasks. His work is essential reading for engineers and researchers developing robust, adaptive controllers for autonomous systems, demonstrating how machine learning can enhance traditional sliding mode techniques.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3