Maddalena Zuccotto
Papers
1
Total Citations
3
H-Index
1
About
Maddalena Zuccotto is a robotics researcher whose work focuses on improving autonomous decision-making under uncertainty, particularly for mobile robots navigating complex environments. Her key contributions lie at the intersection of partially observable Markov decision processes (POMDPs) and machine learning, where she has developed novel frameworks to enhance planning performance. In her most cited work, "Learning State-Variable Relationships in POMCP: A Framework for Mobile Robots" (2022), Zuccotto addresses a critical challenge in Partially Observable Monte Carlo Planning (POMCP) by learning relationships between state variables and representing this knowledge using Markov Random Fields. This approach enables more efficient and accurate planning in partially observable settings, a fundamental problem in robotics. While her citation count is still growing, her work represents an important step toward more intelligent and adaptive robot behavior. Zuccotto's research is particularly relevant for applications in autonomous navigation, where robots must make decisions with incomplete sensor information, and her framework offers a promising path for integrating structural learning into existing planning algorithms.
Research Focus
Key Achievements
Top Papers
- 1