Jingkun Yan

Lanzhou University, Chongqing Institute of Green and Intelligent Technology

Papers

Total Citations

291

H-Index

About

Dr. Jingkun Yan is a leading researcher in robotics and computational mathematics, specializing in recurrent neural networks (RNNs) and their applications to robotic control and signal processing. His most impactful work addresses the challenging time-variant generalized Sylvester equation (TVGSE), a complex mathematical formulation rarely studied before. In his seminal 2020 paper (174 citations), Dr. Yan developed an RNN-based approach to solve TVGSEs, demonstrating direct applications in robot control and acoustic source localization—providing a powerful new tool for real-time computation in dynamic environments. He further advanced the field by pioneering RNN-based receding horizon control for redundant robot manipulators (2021, 61 citations), enabling precise trajectory tracking without requiring full system models. Most recently, his 2024 work on data-driven model predictive control (56 citations) tackles the critical challenge of controlling redundant manipulators when their mathematical models are completely unknown, a common real-world limitation. Dr. Yan’s contributions bridge theoretical mathematics and practical robotics, offering robust, model-free solutions that enhance the autonomy and adaptability of robotic systems in uncertain environments.