Mohammad Fereydounian
Papers
1
Total Citations
3
H-Index
1
About
Mohammad Fereydounian is a researcher at the intersection of control theory, optimization, and safe machine learning. His work addresses a critical challenge in autonomous systems: how to make decisions when both the objectives and safety constraints are uncertain or unknown. In his highly cited 2020 paper, "Safe Learning under Uncertain Objectives and Constraints," Fereydounian tackles non-convex optimization problems with safety-critical constraints that cannot be fully identified beforehand—a scenario common in robotics, manufacturing, and medical procedures. This foundational contribution has garnered 3 citations and established a framework for ensuring safety during learning, even in partially unknown environments. His research is particularly impactful for real-world applications where failures are costly, such as autonomous navigation and surgical robotics. By bridging rigorous mathematical theory with practical safety guarantees, Fereydounian is shaping how next-generation intelligent systems learn and adapt without compromising safety. His work continues to influence researchers developing trustworthy AI for high-stakes domains.
Research Focus
Key Achievements
Top Papers
- 1Safe Learning under Uncertain Objectives and Constraints3 citations · 2020