Alex Serban
Papers
2
Total Citations
66
H-Index
2
About
Alex Serban’s research lies at the intersection of safe artificial intelligence and autonomous systems, with a focus on reinforcement learning and software architecture for self-driving vehicles. His most influential work, “Safe Reinforcement Learning Using Probabilistic Shields” (2020, 52 citations), introduces a novel method for constructing safety shields that ensure reliable decision-making under uncertainty using Markov decision processes. This contribution is critical for deploying RL in high-stakes environments where failures are unacceptable. In parallel, Serban addresses the engineering challenges of autonomy through “A Standard Driven Software Architecture for Fully Autonomous Vehicles” (2020, 14 citations), proposing a structured framework to manage the immense software complexity required for self-driving cars. By advocating for standardization, his work helps bridge the gap between experimental algorithms and production-ready systems. With a growing citation record, Serban’s research is shaping how we build trustworthy, scalable AI—offering practical tools for safety verification and robust system design that resonate with both academic researchers and industry practitioners.
Research Focus
Key Achievements
Top Papers
- 1Safe Reinforcement Learning Using Probabilistic Shields52 citations · 2020
- 2A Standard Driven Software Architecture for Fully Autonomous Vehicles14 citations · 2020