Shihang Yu

Papers

Total Citations

H-Index

About

Shihang Yu is a researcher in computational intelligence and robotics, specializing in neural dynamics for real-time optimization and control. His work centers on zeroing neural networks (ZNN), a class of recurrent neural networks designed for solving time-varying problems with high precision. Yu’s major contribution lies in developing novel ZNN models that handle bound-constrained and underdetermined nonlinear systems—challenges critical for autonomous systems operating under physical limits. His most cited paper, "Zeroing neural network for bound-constrained time-varying nonlinear equation solving and its application to mobile robot manipulators" (2021, 19 citations), demonstrates how these networks enable mobile manipulators to achieve accurate, real-time motion control despite joint constraints. A follow-up study on discrete-time ZNN for underdetermined systems (2021, 8 citations) further advances the field by providing efficient, discrete-time solutions suitable for digital implementation. Yu’s work bridges theoretical neural dynamics and practical robotics, offering robust tools for trajectory planning and obstacle avoidance. His achievements highlight the potential of ZNN in enhancing the autonomy and safety of robotic systems, making his research highly relevant for students and engineers in control theory, optimization, and robotics.