Zhuliang Yu
Papers
5
Total Citations
577
H-Index
5
About
Zhuliang Yu is a researcher whose work sits at the intersection of neural computing, optimization, and robotics, with particular expertise in recurrent neural networks and intelligent control systems for robotic manipulators. His most influential contributions center on the development of novel neural network architectures designed to solve complex, time-sensitive mathematical problems in real-world robotic applications. Yu's landmark achievement is the creation of the Varying-Parameter Convergent-Differential Neural Network (VP-CDNN), introduced in two highly cited 2018 studies (accumulating 187 and 124 citations respectively), which addresses time-varying convex quadratic programming problems and joint-angular-drift challenges in redundant robot manipulators. These works marked a significant advance over fixed-parameter neural network approaches by enabling adaptive, faster convergence in dynamic environments. His 2017 paper comparing recurrent neural networks and numerical solvers for repetitive motion planning (185 citations) further demonstrated his systematic, comparative approach to solving joint-drift problems. Additional contributions include tricriteria optimization frameworks for dual-robot coordination and visual tracking systems for robotic vision. Collectively, Yu's research has meaningfully advanced the theoretical and practical foundations of intelligent robotic motion planning, earning him a strong citation record and recognition within the computational intelligence and robotics communities.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5