Fun Ye

Papers

Total Citations

H-Index

About

Fun Ye is a researcher whose work lies at the intersection of autonomous robotics and computer vision, with a particular focus on humanoid robot soccer. Her key research areas include self-localization, object recognition, and efficient neural network architectures for real-time robotic perception. In her most cited works, both from 2009, Ye developed an efficient neural network approach for self-localization that enables humanoid robots to determine their position within dynamic, unpredictable environments—a critical capability for autonomous agents. She also designed a robust object recognition system tailored for humanoid robot vision, allowing robots to identify and track objects despite the challenges of real-time processing and environmental variability. These contributions, each garnering 7 citations, have provided foundational methods for enhancing the autonomy and perceptual accuracy of humanoid robots in competitive settings like robot soccer. Ye’s work is notable for its focus on practical, computationally efficient solutions that bridge the gap between theoretical machine learning and real-world robotic applications, making her research valuable for students and engineers working on autonomous systems and intelligent robotics.