Yuanyuan Shao

Papers

Total Citations

216

H-Index

About

Yuanyuan Shao is a leading researcher in agricultural robotics and computer vision, whose work is transforming how machines perceive and interact with fruit crops. Her primary research areas include deep learning-based semantic segmentation, object detection, and machine vision for automated harvesting systems. Shao's most impactful contribution is her pioneering work on litchi branch detection using the DeepLabV3+ model, which achieved 162 citations by solving a critical challenge: enabling picking robots to accurately segment small, easily damaged branches for precise cutting. She further advanced field detection with an improved YOLOv3 model (17 citations), addressing illumination, occlusion, and complex backgrounds that plague real-world harvesting. Earlier, she explored multi-class fruit recognition using SVM (32 citations), laying groundwork for versatile, cost-effective picking robots. Shao also contributed to robotics kinematics with a reverse-driving trajectory planning method for joint robots (5 citations). Her cumulative work—spanning semantic segmentation, real-time detection, and trajectory optimization—has directly enhanced the reliability and adaptability of agricultural robots, making her a key figure in precision agriculture and intelligent harvesting systems.