Meiyu Hu

Papers

Total Citations

H-Index

About

Meiyu Hu’s research lies at the intersection of mobile robotics, autonomous navigation, and environmental perception, with a particular focus on advancing Simultaneous Localization and Mapping (SLAM) systems. Her work addresses critical challenges in enabling robots to operate effectively in complex, unknown environments—especially for rescue and disaster response applications. In her 2015 study on three-dimensional mapping, Hu pioneered the integration of SIFT and RANSAC algorithms to enhance mobile robot mapping accuracy, laying groundwork for robust spatial reconstruction. She further advanced the field with her 2017 paper on loop closure detection for visual SLAM, where she applied deep learning techniques to solve a persistent problem: maintaining map consistency and navigation precision over long trajectories. This work directly addresses how closed-loop detection impacts SLAM stability—a key bottleneck in autonomous systems. Though her most-cited papers each hold 6 citations, their influence is notable for tackling foundational SLAM problems that continue to drive robotics research. Hu’s contributions are particularly significant for students and engineers developing real-world autonomous systems, as her methods bridge classical computer vision with modern deep learning approaches to make robots more reliable in unstructured environments.