Xueyuan She
Papers
1
Total Citations
25
H-Index
1
About
Xueyuan She is a researcher working at the intersection of robotics, dynamical systems, and machine learning, with a particular focus on hybrid modeling approaches that bridge physics-based and data-driven methodologies. Her most recognized contribution is HybridNet, introduced in 2018, a pioneering framework that integrates model-based and data-driven learning to predict the spatiotemporal evolution of complex dynamical systems. This work addresses a critical challenge in autonomous robotics: enabling reliable system predictions even when complete knowledge of underlying dynamics is unavailable. By combining the interpretability of physics-informed models with the flexibility of deep learning, HybridNet represents a meaningful step toward more robust and generalizable autonomous systems. The paper has garnered 25 citations, reflecting its relevance to researchers tackling real-world control and prediction problems in robotics and beyond. She's work speaks to a broader movement in the field toward hybrid intelligence — systems that do not rely solely on data or solely on hand-crafted models, but thoughtfully leverage both. Her contributions are particularly valuable for students and practitioners exploring the frontier of physics-informed machine learning and intelligent autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1