Max Robotics — Global Service Robot Directory + US Certification

About

Gihwon Kwon is a researcher at the forefront of safe artificial intelligence, specializing in the intersection of reinforcement learning (RL) and formal verification. His primary research focuses on ensuring that AI systems, particularly those used in safety-critical domains like autonomous driving and robotics, operate reliably under strict safety constraints. Kwon’s major contribution lies in pioneering the application of quantitative model checking—a formal method typically used for hardware and software verification—to analyze and guarantee safety in RL policies. His 2024 paper, "Applying Quantitative Model Checking to Analyze Safety in Reinforcement Learning" (4 citations), is a foundational work that shifts the focus from purely reward-maximizing policies to those that satisfy non-functional safety requirements. Building on this, his 2025 study (2 citations) introduces an innovative framework that combines KMeans++ clustering with probabilistic model checking to optimize state space exploration and verify safety in deep RL systems. Earlier in his career, Kwon explored multi-robot collaboration through simulation (2012, 2 citations). While his citation counts are modest, his work is highly impactful for researchers tackling the critical challenge of AI safety.