Max Robotics — Global Service Robot Directory + US Certification

About

Qing Song’s research focuses on the intersection of neural network control, robotics, and intelligent systems, with a particular emphasis on enhancing the robustness and adaptability of autonomous machines. His major contributions lie in developing advanced control algorithms for biped and mobile robots, including a robust recurrent neural network (RNN) controller that improved biped robot stability and a discrete-time MIMO RNN training algorithm designed for fault-tolerant control in robotic systems. Song also addressed complex 3D path planning challenges by proposing an improved RRT algorithm for mobile robots navigating rugged terrain. His most-cited work, “Robust Recurrent Neural Network Control of Biped Robot” (2007), has garnered 25 citations, while his 2010 paper on robust RNN training for fault-tolerant control has 19 citations, reflecting the practical relevance of his methods. Notably, his 1999 paper on neural network-based iterative learning control for robot trajectory tracking introduced a dead-zone weight-tuning algorithm with theoretical convergence guarantees, laying groundwork for repeatable precision tasks. Song’s research continues to influence the development of resilient, learning-enabled robotic systems.