Francesco Trotti
Papers
1
Total Citations
2
H-Index
1
About
Francesco Trotti is a rising researcher at the forefront of safe autonomous navigation, whose work bridges the critical gap between reinforcement learning and formal safety guarantees. His primary research areas include control barrier functions (CBFs), neural network verification, and hierarchical control frameworks for robotics. In his most-cited work, "Designing Control Barrier Function via Probabilistic Enumeration for Safe Reinforcement Learning Navigation" (2025), Trotti introduces an innovative hierarchical control framework that leverages neural network verification to design CBFs and policy corrections. This approach enables autonomous systems to navigate dynamic, uncertain environments while maintaining rigorous safety constraints—a fundamental challenge in deploying robots beyond controlled settings. Though early in his career with 2 citations to date, Trotti's contribution addresses a pressing need in the field: ensuring that learning-based navigation policies can be formally verified for safety without sacrificing performance. His work represents an important step toward trustworthy autonomy, offering a principled methodology that could influence future safety-critical applications in autonomous driving, warehouse robotics, and drone navigation. As the demand for verifiably safe AI systems grows, Trotti's research positions him at the intersection of control theory and machine learning, promising impactful advances in how robots learn to operate safely in the real world.
Research Focus
Key Achievements
Top Papers
- 1