Yujiao Lu
Papers
2
Total Citations
11
H-Index
2
About
Yujiao Lu’s research lies at the intersection of robotics, machine learning, and autonomous navigation, with a central focus on enabling legged robots to intelligently perceive and adapt to off-road environments. Her major contributions center on developing real-time terrain recognition systems that allow quadruped robots to classify ground surfaces—such as grass, gravel, or soil—using advanced feature extraction and classification algorithms. In her most cited work (2017, 6 citations), Lu pioneered the application of extreme learning machines combined with wavelet features, achieving high classification accuracy while meeting the stringent real-time demands of legged locomotion. She extended this framework in 2018 (5 citations) by integrating both wavelet and texture features, further improving recognition robustness in unstructured outdoor settings. These contributions directly address a critical bottleneck in field robotics: the trade-off between computational efficiency and classification precision. By demonstrating that extreme learning theory can outperform traditional training methods in dynamic terrain scenarios, Lu has provided a practical foundation for autonomous mobility in agriculture, search-and-rescue, and planetary exploration. Her work is particularly notable for bridging theoretical machine learning advances with real-world robotic deployment, making her a key voice in the growing field of terrain-adaptive locomotion.
Research Focus
Key Achievements
Top Papers
- 1
- 2