Xilai Chen

Guangxi University of Science and Technology

Papers

Total Citations

H-Index

About

Xilai Chen is a researcher advancing the frontiers of autonomous navigation through robust visual SLAM (Simultaneous Localization and Mapping) systems. His primary research focuses on developing algorithms that enable robots to accurately perceive and map dynamic, real-world environments—a critical challenge for applications from service robotics to autonomous driving. Chen’s most notable contribution is the YDD-SLAM system, an innovative framework that fuses YOLOv5 object detection with depth information to dramatically improve positioning accuracy and real-time performance in highly dynamic scenes. By intelligently filtering out moving objects, his work addresses a fundamental limitation of traditional VSLAM algorithms, which often fail when dynamic elements dominate the visual field. With 15 citations on his leading paper, Chen’s research is gaining traction among engineers tackling real-world deployment of autonomous systems. His achievements demonstrate a keen ability to bridge deep learning and classical robotics, offering practical solutions that balance computational efficiency with robust perception. For students and researchers in robotics and computer vision, Chen’s work provides a compelling blueprint for building SLAM systems that truly work outside the lab.