Papers
2
Total Citations
9
H-Index
2
About
Feng Han is an emerging robotics and autonomous systems researcher whose work sits at the intersection of motion planning, control theory, and machine learning. His research focuses primarily on mobile robot control and robotic arm path planning, areas that are central to advancing practical autonomous systems. Han's most notable contribution is his 2019 work on applying deep reinforcement learning to the motion control of non-holonomic constrained mobile robots — a technically challenging problem given the inherent movement restrictions of such systems. By constructing a kinematic model to support deep reinforcement learning memory architectures, he proposed a point stabilization control law that bridges classical robotics theory with modern AI-driven approaches. This paper has garnered 7 citations, reflecting meaningful early recognition within the robotics community. His more recent 2025 research addresses computational efficiency in robotic arm path planning, introducing a two-stage optimization of the widely-used RRT* algorithm to reduce convergence time and computational overhead in dynamic environments — a practical concern for real-world deployment. While Han's citation profile suggests he is at an early career stage, his consistent focus on solving concrete control and planning challenges positions him as a researcher contributing thoughtful, applied solutions to fundamental problems in intelligent robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2