Zelin Shi

Papers

Total Citations

H-Index

About

Zelin Shi is a robotics researcher focused on advancing autonomous manipulation in unstructured and industrial environments. Their work centers on two key areas: monocular vision-based grasping for mobile manipulators and deep learning-driven instance segmentation for low-texture objects. Shi’s 2021 paper on monocular vision grasping proposed a novel approach enabling mobile manipulators to recognize and localize objects without expensive 3D sensors, directly addressing a critical challenge in flexible automation. This work has garnered 4 citations, reflecting its relevance to the growing field of service and industrial robotics. In a second highly cited paper, Shi tackled the difficult problem of instance segmentation for low-texture industrial parts, where traditional RGB-based deep learning methods often fail. By developing a technique less reliant on color information, this research (2 citations) advances robot grasping in cluttered, scattered environments. Shi’s contributions are notable for bridging the gap between computer vision and practical robotics, offering solutions that enhance the adaptability and efficiency of autonomous systems in real-world settings—a vital step toward more capable and cost-effective industrial automation.