Yanwen Zhang

Anhui Agricultural University, South China University of Technology

Papers

Total Citations

H-Index

About

Yanwen Zhang is a researcher at the forefront of intelligent robotics and agricultural automation, whose work bridges adaptive control theory and deep learning for real-world perception. Her most impactful contribution, the 2024 paper "MLP-based multimodal tomato detection in complex scenarios," has already garnered 31 citations, demonstrating its immediate relevance to precision agriculture. In this work, she systematically analyzes feature fusion architectures, showing that a carefully designed multi-layer perceptron (MLP) can outperform more complex convolutional networks for fruit detection in challenging field conditions—a practical insight for deploying lightweight models on resource-constrained agricultural robots. Earlier, Zhang developed a dynamic learning method for adaptive neural control of uncertain n-link robots, achieving guaranteed full-state tracking precision (2017, 4 citations). This theoretical contribution ensures that robotic manipulators can learn from experience while maintaining strict performance bounds on both joint angles and velocities, a critical requirement for safe human-robot interaction. By combining rigorous control theory with applied computer vision, Zhang’s work exemplifies how foundational robotics research can directly enable autonomous systems in agriculture, where reliability and efficiency are paramount. Her trajectory points toward increasingly integrated perception-and-control solutions for complex, unstructured environments.