Mengyue Lu
Papers
3
Total Citations
9
H-Index
2
About
Mengyue Lu is at the forefront of humanoid and bipedal robot locomotion, specializing in adaptive control strategies that enable stable, disturbance-resistant walking. Her research bridges model-based dynamics and learning-based control to tackle one of robotics’ most persistent challenges: achieving natural, straight-legged gait under real-world perturbations. In her most-cited work, she introduces an adaptive feedback compensation control method that allows bipedal robots to maintain balance during continuous external disturbances, a critical step toward practical deployment. Her 2024 paper on Conditional Adversarial Motion Priors further advances the field by combining a novel retargeting method with adversarial learning, enabling more versatile and human-like motion control for humanoid robots. Most recently, Lu has developed a COM trajectory planning framework grounded in CP-ZMP-COM dynamics, which integrates center-of-mass, zero-moment point, and capture point dynamics to improve both sagittal and coronal plane stability. With early citations already accruing—including 4 and 3 citations on her 2024 works—her contributions are gaining rapid recognition. Lu’s work is essential reading for researchers pursuing robust, adaptive locomotion in legged robots.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3