Neil F. Lugovoy
Papers
1
Total Citations
85
H-Index
1
About
Neil F. Lugovoy is a leading researcher at the intersection of safety-critical autonomous systems and machine learning. His work is primarily focused on bridging the gap between formal safety guarantees from robust optimal control and the scalability of modern reinforcement learning (RL). His most influential contribution, the 2019 paper "Bridging Hamilton-Jacobi Safety Analysis and Reinforcement Learning" (85 citations), pioneered a framework that integrates Hamilton-Jacobi reachability analysis—a rigorous method for certifying constraint satisfaction—into RL training. This allows autonomous systems to learn complex behaviors while maintaining provable safety bounds, a critical step for deploying robots in human environments. Beyond this foundational work, Lugovoy has advanced techniques for real-time safety verification and safe exploration in high-dimensional systems. His research is widely recognized for enabling practical, certifiably safe autonomy, with his papers serving as essential references for engineers and researchers developing trustworthy AI and robotic systems.
Research Focus
Key Achievements
Top Papers
- 1Bridging Hamilton-Jacobi Safety Analysis and Reinforcement Learning85 citations · 2019