Ezequiel Castellano
Papers
2
Total Citations
26
H-Index
2
About
Ezequiel Castellano is a leading researcher at the intersection of autonomous systems and trustworthy artificial intelligence. His work primarily focuses on ensuring the safe and reliable deployment of machine learning agents in complex, real-world environments. Castellano’s major contribution is the development of a runtime monitoring framework that enforces critical invariants on reinforcement learning agents, allowing them to explore and learn effectively without prior environmental knowledge—a foundational step toward verifiable AI safety. This seminal work has garnered 16 citations and is widely referenced in the safe RL community. More recently, he has advanced the field of multi-robot logistics, proposing an incremental search-based allocation algorithm for autonomous goods delivery. This 2023 study, with 10 citations, addresses the critical challenge of coordinating multiple stakeholders in dynamic delivery systems, promising reduced traffic congestion and operational costs. Castellano’s research bridges the gap between theoretical AI safety and practical robotic deployment, making him a key figure in the development of dependable autonomous systems for smart cities and industrial automation.
Research Focus
Key Achievements
Top Papers
- 1
- 2Incremental Search-Based Allocation of Autonomous Robots for Goods Delivery10 citations · 2023