Shu‐Mei Guo

Papers

Total Citations

H-Index

About

Shu-Mei Guo is a researcher at the forefront of intelligent robotics, specializing in visual-guided robotic manipulation and deep learning. Her work addresses a critical bottleneck in industrial automation: enabling robot arms to perceive and grasp objects with high precision and speed. Guo’s major contributions center on developing advanced computer vision architectures for robotic control. Her most-cited paper, “Visual-Guided Robot Arm Using Multi-Task Faster R-CNN” (2019, 6 citations), introduces a multi-task deep neural network that simultaneously detects and localizes objects, significantly improving real-time performance. She further advanced the field with “Embedded-Based Object Matching and Robot Arm Control” (2019, 4 citations), which demonstrates a complete embedded system using an Nvidia Jetson TX2 for efficient, on-device template matching and control. Notably, Guo also explores self-supervised learning in “Visual-Guided Robot Arm Using Self-Supervised Deep Convolutional Neural Networks” (2019, 3 citations), tackling the challenge of costly labeled datasets by enabling robots to learn from unlabeled data—a key step toward scalable, autonomous systems. Her work bridges cutting-edge AI with practical embedded solutions, making her a rising voice in the integration of deep learning and robotics.