Meiqin Pan

Shanghai International Studies University

Papers

Total Citations

H-Index

About

Meiqin Pan’s research lies at the intersection of robotics, formal modeling, and automated learning, with a particular focus on Petri net theory. Her most cited work, “A Method for Learning a Petri Net Model Based on Region Theory” (2020), addresses a critical challenge in robotics: how to derive accurate, analyzable models from limited real-world interactions. By applying region theory—a technique traditionally used in Petri net synthesis—Pan developed a method that can infer a complete system model from sparse robot trial data, effectively bridging the gap between empirical learning and formal verification. This contribution is especially valuable for controlling and analyzing autonomous systems where exhaustive training data is unavailable. Though early in her career, Pan’s work has already garnered attention (5 citations), signaling its relevance to researchers in robotics and discrete event systems. Her approach offers a principled way to supplement incomplete observations, making it a promising tool for safer, more reliable robot deployment. Pan’s research continues to push toward integrating learning algorithms with formal methods, a key direction for next-generation intelligent systems.