Jiongyan Yu

Papers

Total Citations

H-Index

About

Jiongyan Yu is a researcher at the forefront of robotic perception and manipulation, specializing in the intersection of computer vision and deep learning for autonomous systems. Their primary research areas include point cloud processing, instance segmentation, and robot grasping, with a particular focus on leveraging RGB-D sensors to help machines understand and interact with their environments. Yu’s major contributions lie in developing deep learning methods that enable robots to accurately segment and interpret 3D point cloud data—a critical step for tasks like object recognition and pose estimation. Notably, their 2021 work on instance segmentation of point clouds captured by RGB-D sensors (21 citations) demonstrates how high-quality segmentation directly impacts the performance of subsequent robotic algorithms. In their equally influential study on simulation and deep learning for robot grasping (11 citations), Yu introduced PointSimGr, a novel deep learning approach that simplifies training data generation while accurately estimating target poses for robotic manipulation. This work bridges the gap between simulation and real-world application, offering practical solutions for deploying intelligent grasping systems. With a growing citation impact, Yu’s research continues to shape how robots perceive and interact with their surroundings, making significant strides toward more autonomous and capable robotic systems.