Guanrong Tang

Guangdong Institute of Intelligent Manufacturing

Papers

Total Citations

H-Index

About

Guanrong Tang is a researcher whose work lies at the intersection of robotic control, nonlinear dynamics, and neural network computation. His primary contributions focus on enhancing the intelligence and robustness of redundant manipulators—robotic arms with more degrees of freedom than necessary. In his highly cited 2020 paper, "Bi-criteria Acceleration Level Obstacle Avoidance of Redundant Manipulator" (12 citations), Tang developed a novel kinematic control scheme that abstracts both the manipulator and obstacles as mathematical geometries, enabling real-time, collision-free motion planning at the acceleration level. This work provides a dual-criteria optimization framework that balances task execution with safety. Tang further advanced the field by addressing computational challenges in control systems. His paper "An Integration-Enhanced Noise-Resistant RNN Model with Superior Performance Illustrated via Time-Varying Sylvester Equation Solving" (5 citations) introduces a recurrent neural network (RNN) model that is inherently resistant to noise, a critical improvement over existing solvers for the Sylvester equation—a fundamental tool in inverse-kinematic control. By integrating enhanced noise resistance, Tang’s RNN model demonstrates superior stability and accuracy, making it highly applicable to real-world robotic systems operating in uncertain environments. His work is recognized for bridging theoretical advances in neural computation with practical robotic applications, earning him a growing reputation in the field of intelligent control systems.