Papers
8
Total Citations
955
H-Index
6
About
Shengli Xie is a leading figure in neural information processing and intelligent robotic control, whose work bridges the gap between theoretical learning algorithms and real-world autonomous systems. His research centers on developing robust control frameworks for complex robotic platforms, particularly addressing the critical challenges of unknown actuator dynamics, sensor nonlinearities, and system uncertainties. Xie’s highly influential 2015 work on saturated Nussbaum functions introduced a novel approach to eliminate control shock in robotic systems, a contribution that has garnered 154 citations and remains foundational for safe actuator control. His coordinated motion/force control strategies for multiarm robots, published in 2016, tackled the pervasive issue of sensor deadzone nonlinearity, enabling more reliable manipulation of objects under uncertainty. More recently, Xie has pioneered Lyapunov-based reinforcement learning and imitation learning frameworks for trajectory planning in mobile robots and wheeled vehicles, directly addressing data efficiency, safety, and convergence in autonomous navigation. With his 2017 work on neural information processing accumulating over 695 citations, Xie’s research continues to shape the future of intelligent, learning-driven robotic systems.
Research Focus
Key Achievements
Top Papers
- 1Neural Information Processing695 citations · 2017
- 2
- 3Neural Information Processing35 citations · 2017
- 4
- 5Neural Information Processing17 citations · 2017
- 6Neural Information Processing13 citations · 2017
- 7
- 8