Xiaotao Huang
Papers
1
Total Citations
9
H-Index
1
About
Xiaotao Huang is a researcher working at the intersection of computer vision, robotics, and autonomous systems, with a focused expertise in Visual Simultaneous Localization and Mapping (V-SLAM). His work addresses one of the most pressing challenges in intelligent robotics: enabling reliable navigation and localization in highly dynamic, real-world environments. His most recognized contribution, "ADM-SLAM" (2024), introduces a sophisticated framework that combines adaptive feature point extraction, the DeepLabv3Pro semantic segmentation architecture, and multi-view geometry to achieve accurate and fast SLAM performance even when dynamic objects populate the scene — a scenario that routinely defeats conventional approaches. By integrating deep learning-based scene understanding with geometric reasoning, Huang's methodology represents a meaningful step forward in making autonomous systems more robust and deployable outside controlled settings. Already accumulating 9 citations shortly after publication, this work signals growing community interest in his approach. For students and researchers navigating the rapidly evolving landscape of autonomous navigation, Huang's research offers practical, technically rigorous solutions to the enduring problem of dynamic environment perception in intelligent robotic systems.
Research Focus
Key Achievements
Top Papers
- 1