Papers
45
Total Citations
806
H-Index
16
About
Yufeng Yue is a robotics and autonomous systems researcher whose work spans multi-robot coordination, collaborative mapping, and intelligent perception. His research tackles some of the most demanding challenges in autonomous systems, including how groups of robots can navigate, communicate, and build shared understanding of complex, unstructured environments. Yue's most-cited contribution (103 citations) introduced a vision-based flexible leader–follower formation control framework for nonholonomic mobile robots, advancing beyond the rigid formation paradigms that dominated prior literature. This foundational work complements his prolific output on collaborative semantic mapping, where he has developed hierarchical probabilistic fusion frameworks enabling multiple robots to merge 3D occupancy maps and semantic information in real or near-real time — work that has collectively accumulated hundreds of citations. His research on sensor fusion extends to heterogeneous platforms, including a notable two-step LiDAR-to-thermal-camera calibration method enabling sparse 3D sensors to operate reliably in challenging conditions. More recently, Yue has embraced open-vocabulary scene representations, with his OpenGraph framework leveraging Vision-Language Models to construct hierarchical 3D graphs for large-scale outdoor environments — signaling a forward-looking trajectory toward human-robot interaction. Across his body of work, Yue has established himself as a leading voice in multi-robot perception, mapping, and coordination research.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8A Hierarchical Framework for Collaborative Probabilistic Semantic Mapping31 citations · 2020
- 9
- 10