Zhaobing Liu
Papers
10
Total Citations
194
H-Index
7
About
Zhaobing Liu is an emerging researcher whose work spans the intersection of robotics, intelligent control systems, and agricultural automation. His scholarship is anchored in three principal domains: soft robotics control, neural network-based manipulator modeling, and vision-driven harvesting automation — areas where he has rapidly established a compelling body of work. Liu's most influential contributions include a widely cited review on artificial neural network-based modeling and control of robotic manipulators (2023, 63 citations) and a complementary survey on vision-based target recognition for harvesting robots (2023, 47 citations), together offering the field a comprehensive theoretical foundation. His pioneering work on soft pneumatic actuators introduces sophisticated fuzzy cascade and Koopman-based modeling strategies to address the persistent challenge of hysteresis nonlinearity — a problem that fundamentally limits soft robot precision (2022, 31 citations). Particularly noteworthy is Liu's development of the Koopman operator framework applied to soft robotics, enabling data-driven, model-free optimal control without requiring explicit system identification. His YOLOv5s-BC method further demonstrates his versatility, delivering real-time apple detection improvements meaningful for precision agriculture. With a growing citation profile and multiple high-impact publications across 2023–2025, Liu represents an exciting voice bridging theoretical control design and applied robotic intelligence.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4YOLOv5s-BC: an improved YOLOv5s-based method for real-time apple detection18 citations · 2024
- 5
- 6
- 7A Data-driven Koopman Modeling Framework With Application to Soft Robots7 citations · 2025
- 8
- 9
- 10