Zhenhuan Wang
Papers
4
Total Citations
23
H-Index
3
About
Zhenhuan Wang’s research lies at the intersection of robotic manipulation, nonlinear control systems, and intelligent autonomy. His work fundamentally advances how robots handle uncertainty and redundancy in real-time operations. Wang’s most influential contribution is the **Feedback-Added Pseudoinverse-Type Balanced Minimization (FPBM) scheme** for redundant robot manipulators, which elegantly combines minimum acceleration norm and weighted minimum velocity norm solutions to achieve smoother, more stable kinematic control. This paper has garnered **11 citations**, establishing a foundation for subsequent work in robotic trajectory tracking. Building on this, Wang developed a **reinforcement learning-based compound controller** (5 citations) that merges traditional model-based control with deep RL, significantly improving tracking accuracy for manipulators facing unknown dynamics. His recent work on **predefined-time consensus tracking** for nonlinear multiagent systems (5 citations) introduces active disturbance rejection and self-triggered communication, a breakthrough for distributed robotic teams operating under communication constraints. Wang has also addressed practical SLAM failures with an **immediate pose recovery method** for untracked frames (2 citations), ensuring robust visual navigation in challenging environments. Through these contributions, Wang is shaping the next generation of adaptive, resilient robotic systems capable of operating reliably in unstructured, uncertain worlds.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4