Papers
15
Total Citations
632
H-Index
13
About
Zhengtai Xie is a robotics and control systems researcher whose work centers on the kinematic control and motion planning of redundant robot manipulators. His most significant contributions lie in developing advanced neural network-based schemes and data-driven approaches that address longstanding challenges in robotic redundancy resolution, repetitive motion generation, and motion-force control. Xie's most cited work — a 2019 paper with 137 citations — introduced a generalized repetitive motion planning (RMP) framework aided by dynamic neural networks and nonconvex bound constraints, unifying previously disparate control schemes under a coherent theoretical structure. Building on this, his orthogonal projection-based recurrent neural network approach (121 citations) resolved a fundamental theoretical flaw in existing repetitive motion generation schemes, eliminating persistent position errors. His data-driven research direction is particularly noteworthy, enabling precise robot control even when structural or kinematic parameters are unknown — a practically vital capability for real-world deployments subject to mechanical modification or uncertainty. More recently, Xie has extended his expertise to fuzzy neural controllers, obstacle avoidance, mobile robotic arms, and bi-criteria optimization for motion-force control, reflecting a broadening research vision. With over 560 cumulative citations across a decade of focused output, Xie has established himself as a meaningful contributor to intelligent and adaptive robotic control.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10