Zhehua Mao

The London College, University of Technology Sydney

Papers

Total Citations

H-Index

About

Zhehua Mao is a pioneering researcher at the intersection of robotic perception and surgical automation, whose work bridges fundamental advances in simultaneous localization and mapping (SLAM) with cutting-edge applications in medical robotics. His landmark theoretical contribution, "Feature-Based SLAM: Why Simultaneous Localisation and Mapping?" (2021), proved a foundational result: when feature observation errors have isotropic covariance, robot poses and feature positions obtained during Gauss-Newton iterations in SLAM optimization exhibit a critical structural property. This insight has shaped modern understanding of SLAM convergence and efficiency. More recently, Mao has translated these principles into surgical practice. In his 2024 study on automated surgical skill assessment during endoscopic pituitary surgery, he developed real-time instrument tracking on high-fidelity bench-top phantoms, demonstrating how machine learning can replace subjective, labor-intensive evaluation with objective, data-driven metrics. This work directly addresses a pressing clinical need—improving surgical training and patient outcomes through automated assessment. With both papers accumulating citations, Mao's dual impact in theoretical robotics and translational surgical technology positions him as a unique voice in the growing field of intelligent surgical systems, where mathematical rigor meets real-world clinical impact.