Papers
31
Total Citations
788
H-Index
15
About
Andong Liu is a prolific researcher specializing in autonomous robotics, control systems, and machine learning-based approaches for robotic applications. His work spans mobile robot formation control, state estimation, visual servoing, and human-robot collaboration, establishing him as a significant contributor to modern robotics and control engineering. Liu's most influential contributions include his development of extended state observer-based distributed model predictive control (DMPC) for multi-robot formation with disturbance rejection (106 citations), and innovative multirate moving horizon estimation techniques for mobile robots integrating heterogeneous sensors (84 citations). His exploration of deep reinforcement learning for visual servoing with visibility constraints (68 citations) and his comprehensive survey of learning-based robotic visual servoing systems (68 citations) demonstrate his leadership at the intersection of classical control theory and modern AI. More recently, Liu has advanced variable impedance control for robotic manipulators, addressing the precision-compliance tradeoff in contact-rich tasks (62 citations), and pioneered hierarchical frameworks for human-robot collaboration using reinforcement learning (36 citations). His research on stable demonstration learning through flexible neural energy functions further highlights his commitment to safe, reliable autonomous systems. Collectively, his body of work, accumulating hundreds of citations, reflects deep expertise in bridging theoretical control with intelligent, real-world robotic applications.
Research Focus
Key Achievements
Top Papers
- 1
- 2Moving Horizon Estimation for Mobile Robots With Multirate Sampling84 citations · 2016
- 3
- 4A survey Of learning-Based control of robotic visual servoing systems68 citations · 2021
- 5
- 6
- 7
- 8
- 9
- 10An Optimal Variable Impedance Control With Consideration of the Stability29 citations · 2022