Xudong Zhu

Papers

Total Citations

H-Index

About

Xudong Zhu’s research bridges the gap between classical robotics and modern computer vision, with a focus on visual servoing and object detection. His foundational work on optimal control laws for robotic visual tracking, published in 2005, introduced a delta-operator-based approach for real-time 3-D object tracking using a camera-in-hand configuration. This work addressed the challenge of controlling robots to track objects moving at unknown velocities, establishing mathematical models for direct visual feedback. Nearly two decades later, Zhu advanced this line of inquiry by incorporating deep learning, developing a multi-scale feature fusion network with attention mechanisms for crowded road object detection in 2024. This work, which has already garnered 13 citations, demonstrates his ability to evolve from classical control theory to modern AI-driven perception. Zhu’s contributions are notable for their sustained relevance, spanning from foundational control laws to cutting-edge detection systems. His research offers valuable insights for students and researchers working at the intersection of robotics, control systems, and computer vision, particularly those interested in real-time visual tracking and autonomous navigation in complex environments.