Papers
1
Total Citations
9
H-Index
1
About
Pengfei Sun is a researcher whose work lies at the intersection of robotics, control systems, and deep learning. His primary research focuses on inverse dynamics modeling for robotic manipulators—a critical challenge for achieving precise computed-torque control. Sun’s most notable contribution is the development of a hierarchical recurrent network based on a modified Simple Recurrent Unit (SRU-HM), which introduces nested memory structures to capture complex temporal dependencies in robotic motion. This innovative approach, detailed in his 2019 paper, has garnered 9 citations and represents a significant step toward more accurate and efficient robot control. Beyond this core work, Sun’s research explores how recurrent architectures can bridge the gap between theoretical control algorithms and real-world robotic applications. His contributions are particularly relevant for students and researchers interested in combining recurrent neural networks with physical system modeling, offering a practical framework for improving manipulator performance. With a growing citation footprint, Sun continues to advance the field of intelligent robotics, demonstrating how deep learning can enhance the fidelity and responsiveness of automated systems.
Research Focus
Key Achievements
Top Papers
- 1