Papers
7
Total Citations
75
H-Index
5
About
Zida Zhao is a rising researcher at the intersection of mechanical reliability and intelligent control, with key contributions in fault diagnosis of harmonic reducers and humanoid robot locomotion. His work on flexible thin-walled elliptical bearings in harmonic reducers—a critical component in robotics and aerospace—has garnered 20 citations, establishing a foundation for dynamics modeling and fault diagnosis in complex mechanical systems. Zhao pioneered the SCG-GFFE method, a self-constructed graph fault feature extractor using graph auto-encoders for unlabeled vibration signals, earning 16 citations for its novel approach to data-scarce environments. He further advanced the field with the MCVAE-GAN framework, addressing fault signal scarcity and diversity challenges. In humanoid robotics, Zhao’s investigation into leveraging large language models for comprehensive locomotion control—cited 14 times—offers a transformative alternative to resource-intensive reinforcement learning by eliminating manual reward design. His fusion of dynamics control with reinforcement learning achieved precise gait and high robustness, while his design of continuous jumping gaits pushed the boundaries of motion function. With over 75 total citations across his 2023-2024 publications, Zhao’s work bridges mechanical engineering and AI, promising impactful advances in reliable automation and autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7