Papers
2
Total Citations
7
H-Index
2
About
Pu Han’s research centers on intelligent control systems for robotic manipulators, with a focus on trajectory tracking and dynamic decoupling. His major contributions lie in developing hybrid control strategies that integrate artificial neural networks (ANNs) with fuzzy logic and PID controllers to address the challenges of unknown or uncertain robot dynamics. In his 2004 work, Han proposed a novel scheme combining an improved backpropagation neural network as a feed-forward controller with a fuzzy feedback controller, enabling precise torque approximation and robust trajectory tracking. This paper has garnered 4 citations, reflecting its foundational role in adaptive robotic control. His 2005 study further advanced the field by introducing an ANN-based α-th order inverse system method to decouple robotic manipulators, paired with PID control for enhanced stability and accuracy. With 3 citations, this work demonstrates his ability to merge nonlinear inversion techniques with neural networks for practical decoupling. Han’s research is notable for its practical applicability in real-world robotics, offering computationally efficient solutions that bypass the need for explicit dynamic models. His achievements underscore a career dedicated to bridging theoretical control methods with tangible robotic performance.
Research Focus
Key Achievements
Top Papers
- 1
- 2