Xinjie Feng

Guangxi University of Science and Technology, Beihang University

Papers

Total Citations

H-Index

About

Xinjie Feng is a robotics researcher whose work focuses on the intersection of autonomous navigation, perception, and control in dynamic environments. Their key research areas include visual simultaneous localization and mapping (VSLAM), deep learning for object detection, and safety-critical model predictive control (NMPC) for mobile robots. Feng’s most notable contribution is the development of YDD-SLAM, a novel VSLAM system that fuses YOLOv5 with depth information to achieve robust positioning and real-time performance in highly dynamic indoor scenes—a persistent challenge in the field. This work has already garnered 15 citations since its 2023 publication, reflecting its timely impact on improving robot autonomy. More recently, Feng has advanced safety-critical control by proposing an NMPC framework for car-like robots with limited detection range, enabling safe target tracking in obstacle-filled environments through the use of temporary artificial references. This forward-looking research addresses the practical constraints of real-world robotic systems. Feng’s contributions are shaping the next generation of resilient, perception-driven robots capable of operating reliably in unpredictable, human-centered spaces.