Dongsheng Guo
Papers
11
Total Citations
80
H-Index
5
About
Dongsheng Guo is an emerging robotics and computational intelligence researcher whose work centers on neural network-based optimization, kinematic control, and motion planning for robotic systems. His most significant contributions lie in advancing zeroing neural network (ZNN) frameworks for solving time-dependent optimization problems, particularly equality-constrained quadratic programs — a class of problems fundamental to real-time robot control. His 2024 paper on harmonic noise rejection ZNN has already garnered 20 citations, reflecting rapid recognition within the field, while his work on discrete-time ZNN with quintic error modes demonstrates a sophisticated push toward more robust and accurate computational solutions. Guo's research extends prominently into redundant robot manipulator control, addressing repetitive motion planning, obstacle avoidance, and joint-limit constraints through elegant quadratic programming formulations. He has also tackled dual-arm cooperative control, mobile robot manipulators at the acceleration level, and underwater robot hovering — showcasing impressive breadth. His recent contributions to visual-inertial SLAM further demonstrate range across perception and localization domains. With multiple highly cited papers published within a single year and growing cross-disciplinary reach, Guo represents a productive young voice in intelligent robotics, whose optimization-driven approaches are shaping practical solutions for next-generation robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10