Papers
2
Total Citations
13
H-Index
2
About
Hu Zhu’s research focuses on enabling mobile robots to navigate and map dynamic, real-world environments with high reliability. His core contributions lie at the intersection of visual SLAM (Simultaneous Localization and Mapping) and robust 3D perception, addressing the critical failure of traditional SLAM systems when faced with moving objects. Zhu’s most cited work, “Fusing Panoptic Segmentation and Geometry Information for Robust Visual SLAM in Dynamic Environments” (2022, 10 citations), pioneers a hybrid approach that combines semantic panoptic segmentation with geometric cues to accurately identify and exclude dynamic entities, significantly improving localization accuracy in cluttered scenes. His earlier work, “Robust Method for Static 3D Point Cloud Map Building using Multi-View Images with Multi-Resolution” (2021, 3 citations), tackles the persistent problem of “ghost tracks” in long-term mapping by developing a multi-resolution strategy that filters dynamic artifacts, ensuring clean, static 3D maps for autonomous missions. These contributions are vital for applications ranging from warehouse logistics to service robotics, where environments are inherently unpredictable. Zhu’s work is notable for its practical, learning-based solutions that bridge the gap between theoretical SLAM and real-world deployment, making him a key figure in advancing robust, long-term autonomy for mobile robots.
Research Focus
Key Achievements
Top Papers
- 1
- 2