Papers
4
Total Citations
39
H-Index
3
About
Naifeng He is a leading researcher in mobile robotics, specializing in autonomous navigation, trajectory control, and adaptive locomotion. His work addresses fundamental challenges in enabling robots to operate intelligently in complex, unstructured environments. He’s best known for developing a dynamic path planning algorithm that overcomes the classic pitfalls of the artificial potential field method—gravity imbalance, local minima, and oscillation—a contribution that has garnered 27 citations and become a reference point for subsequent improvements in the field. He further advanced trajectory tracking with a novel self-adaptive double Q-backstepping approach, integrating reinforcement learning to ensure high precision for inspection tasks, even under demanding conditions. His recent research pushes the frontier of learning-based autonomy, enabling robots to navigate unmapped spaces using only low-precision sensors. Most notably, He has introduced a residual policy optimization framework with trust region constraints for wheel-legged robots, achieving stable and agile locomotion across abrupt terrain transitions. This work, published in 2025, promises to unlock new capabilities for hybrid robots in real-world deployment, cementing He’s reputation as a pioneer in practical, learning-driven robotics.
Research Focus
Key Achievements
Top Papers
- 1Dynamic path planning of mobile robot based on artificial potential field27 citations · 2020
- 2
- 3Learning Autonomous Navigation in Unmapped and Unknown Environments5 citations · 2024
- 4