Papers
6
Total Citations
68
H-Index
4
About
Yuping Wu is a leading researcher in robotic environmental perception, with a primary focus on terrain classification and autonomous navigation for wheeled mobile robots. Their work addresses the critical challenge of enabling robots to identify and adapt to non-geometric hazards—such as uneven, soft, or slippery terrains—that threaten traversing efficiency and safety in field environments. Wu’s most-cited paper (27 citations) introduces a Feature-Temporal Semi-Supervised Extreme Learning Machine, pioneering a method that reduces human supervision by leveraging smoothness assumptions in feature space. A second highly influential work (22 citations) develops a Laplacian Support Vector Machine for vibration-based terrain classification, advancing robot autonomy in hazard detection. Wu has also innovated in sensor fusion, proposing a nonmagnetic inertial-visual heading determination system (9 citations) that replaces magnetic compasses for indoor navigation. More recently, their research on unsupervised domain adaptation and broad feature alignment (2021–2022) tackles the critical problem of performance degradation when robots move from controlled experimental settings to dynamic, real-world environments. Through these contributions, Wu is helping to build more resilient, perceptive autonomous systems capable of operating reliably beyond the laboratory.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6