Guangxin Xing
Papers
1
Total Citations
5
H-Index
1
About
Guangxin Xing is a researcher focused on advancing visual simultaneous localization and mapping (SLAM) systems, a critical technology for autonomous robotics and augmented reality. His primary work addresses the challenging problem of loop closure detection—the ability of a robot to recognize previously visited locations, which is essential for correcting drift in long-term navigation. Xing’s most cited paper, "Loop Closure Detection in RGB-D SLAM by Utilizing Siamese ConvNet Features" (2021), introduces a deep learning approach that leverages Siamese convolutional neural networks to extract robust visual features from RGB-D data. This method significantly improves the accuracy and reliability of loop closure detection, directly enhancing the performance of SLAM systems in complex environments. With 5 citations, this work has already drawn attention from researchers in robotics and computer vision, highlighting its relevance to ongoing efforts in autonomous navigation. Xing’s contributions are particularly notable for integrating modern deep learning techniques with classical SLAM frameworks, offering a practical solution to a long-standing problem. His research continues to push the boundaries of how machines perceive and map their surroundings, making him a promising voice in the field of intelligent robotics.
Research Focus
Key Achievements
Top Papers
- 1