Shaoping Xiao
Papers
2
Total Citations
8
H-Index
2
About
Shaoping Xiao is a researcher specializing in autonomous systems, motion planning, and formal methods for robotics, with a particular focus on the intersection of reinforcement learning and formal verification. Their work addresses one of the most challenging problems in modern robotics: synthesizing reliable control strategies under real-world uncertainty, where both robot motion and environmental properties are inherently probabilistic. Xiao's most notable contributions center on developing model-free reinforcement learning frameworks that incorporate temporal logic constraints, enabling robots to satisfy complex, mission-critical specifications even in unpredictable environments. By leveraging probabilistic labeled Markov decision processes (PL-MDPs) and limit-deterministic generalized Büchi automata, their research bridges the gap between expressive formal specification languages and practical, scalable learning algorithms. A distinctive feature of this work is the treatment of temporal logic constraints as "soft," allowing for flexible satisfaction that accounts for real-world imperfections rather than imposing rigid, potentially infeasible requirements. Although Xiao's publication record in this area is still growing — with key papers accumulating citations since 2021 — the technical depth and novelty of this research positions it as a meaningful contribution to safe and verifiable autonomous systems. Students exploring robot motion planning under uncertainty or formal methods in AI will find Xiao's work both rigorous and practically motivated.
Research Focus
Key Achievements
Top Papers
- 1
- 2