Daxuan Yan
Papers
2
Total Citations
10
H-Index
2
About
Daxuan Yan is making impactful strides at the intersection of neural network theory and robotic control. His primary research focuses on developing advanced recurrent neural networks for solving time-varying optimization problems, with a particular emphasis on quadratic programming and sparse representation techniques. Yan’s most notable contribution is the introduction of a novel error-based adaptive feedback zeroing neural network (EAF-ZNN), which dynamically adjusts its parameters to solve time-varying quadratic programming problems with unprecedented efficiency. This work, published in 2024, has already garnered 8 citations, signaling its rapid adoption in the field. Building on this foundation, Yan has extended his research to dual-arm robotic systems, proposing an \(L_0\)-norm-based sparse projection neural network that promotes joint-angle sparsity under physical constraints. This 2025 paper, with 2 early citations, addresses critical challenges in cooperative robot motion by reducing computational demands while maintaining performance under real-world constraints. Yan’s work is particularly significant for its practical implications in robotics and optimization, offering elegant mathematical solutions to complex, time-sensitive problems. His innovative approach to adaptive gain mechanisms and sparsification techniques positions him as a rising voice in computational intelligence and control systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2