Papers
3
Total Citations
38
H-Index
3
About
Amr Alanwar is a researcher at the forefront of safe autonomy, specializing in reinforcement learning, reachability analysis, and data-driven control for robotic systems. His work addresses one of the most pressing challenges in modern robotics: ensuring safety guarantees in uncertain, real-world environments where accurate system models are often unavailable. Alanwar's most influential contribution, "Safe Reinforcement Learning Using Black-Box Reachability Analysis" (2022, 28 citations), tackles the critical gap between the impressive performance of deep reinforcement learning and its lack of formal safety guarantees. By integrating black-box reachability analysis, his framework enables robots to navigate complex environments without requiring explicit knowledge of system dynamics — a significant step toward deployable autonomous systems. Complementing this work, his research on data-driven reachability analysis enhanced by temporal logic side information offers elegant solutions to over-conservative safety constraints, making autonomous planning more practically viable. His work on data-driven predictive control further bridges theoretical safety frameworks with real-world RL applications. Collectively, Alanwar's research builds a rigorous foundation for trustworthy autonomous systems, making him a notable emerging voice in safety-critical robotics and control theory.
Research Focus
Key Achievements
Top Papers
- 1Safe Reinforcement Learning Using Black-Box Reachability Analysis28 citations · 2022
- 2
- 3Safe Reinforcement Learning using Data-Driven Predictive Control4 citations · 2022