Papers
3
Total Citations
33
H-Index
2
About
Xiaotong Kong is an emerging researcher specializing in visual Simultaneous Localization and Mapping (SLAM), with a particular focus on enabling robust robot perception under challenging environmental conditions. Their work addresses one of the most persistent limitations in autonomous systems: the degradation of localization and mapping performance in difficult lighting scenarios, from low-light environments to high-contrast or unpredictable illumination. Kong's most notable contribution, "Light-SLAM," introduces a deep learning-based visual SLAM framework leveraging LightGlue for feature matching, achieving significantly improved robustness in adverse lighting conditions that confound traditional handcrafted feature methods. This work has rapidly garnered 19 citations since its 2025 publication, signaling strong community interest. Complementing this, the "BVT-SLAM" system (2023, 12 citations) demonstrates creative sensor fusion by combining binocular visible and thermal cameras to maintain reliable SLAM performance in low-light environments where conventional cameras fail entirely. Together, these contributions reflect Kong's broader mission of making autonomous robots and intelligent transportation systems more resilient to real-world perceptual challenges. Their research is increasingly relevant as autonomous driving and robotics demand reliable all-condition navigation, positioning Kong as a promising voice in next-generation SLAM development.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3