Yaping Fu
Papers
2
Total Citations
44
H-Index
2
About
Yaping Fu is a leading researcher in autonomous navigation and simultaneous localization and mapping (SLAM), with a particular focus on dynamic and unstructured environments. Fu’s most impactful work centers on fusing deep learning with traditional SLAM frameworks to achieve robust, dense point cloud mapping in real-world settings. In a landmark 2024 study, Fu introduced a method that integrates an improved YOLOv8 object detector with ORB-SLAM3, enabling the system to filter out moving objects—such as pedestrians and vehicles—that would otherwise corrupt the map. This approach achieves high-precision dense point cloud reconstruction while maintaining real-time performance, addressing a critical bottleneck in SLAM for autonomous driving and robotics. The work has already garnered over 40 citations, reflecting its immediate relevance and influence. Fu’s contributions are pivotal for advancing perception systems that operate reliably in cluttered, dynamic scenes, bridging the gap between classical geometric SLAM and modern deep learning. By tackling the challenge of dynamic environments head-on, Fu is helping to pave the way for safer, more capable autonomous systems in applications ranging from service robots to self-driving cars.
Research Focus
Key Achievements
Top Papers
- 1
- 2