Shaofei Li
Papers
2
Total Citations
69
H-Index
2
About
Shaofei Li is a robotics and computer vision researcher whose work focuses on the challenging problem of 6D pose estimation for industrial objects in robotic manipulation scenarios. Operating at the intersection of deep learning, point cloud processing, and automated manufacturing, Li has made significant contributions to enabling robots to accurately identify and grasp objects in complex, real-world environments. Li's most impactful work addresses one of the field's most persistent difficulties: accurately estimating the pose of textureless and low-textured industrial objects in cluttered, occluded scenes where traditional color-based approaches fall short. By leveraging instance segmentation combined with 3D point cloud data, Li's 2023 paper on bin-picking has already garnered 66 citations, demonstrating rapid uptake within the robotics community. This work provides practical solutions directly applicable to automated manufacturing and warehouse systems. Building on this foundation, Li's earlier 2022 research explored deep learning frameworks specifically tailored for pose prediction of textureless objects, further cementing a focused and coherent research agenda. Li's contributions are particularly valuable as industries worldwide accelerate automation efforts, making robust robotic grasping an increasingly critical capability. For students and researchers working in industrial robotics, computer vision, or human-robot interaction, Li's publications offer both methodological rigor and strong real-world applicability.
Research Focus
Key Achievements
Top Papers
- 1
- 2