Xianzhi Li

Chinese University of Hong Kong, Jiamusi University, Huazhong University of Science and Technology

Papers

Total Citations

H-Index

About

Xianzhi Li is a leading researcher in robotic perception and manipulation, with a primary focus on bridging the sim-to-real gap for industrial automation. His core contributions lie in developing deep-learning frameworks that enable robots to accurately recognize and localize objects in cluttered, real-world environments without requiring extensive manual annotation. His most influential work, the S2R-Pick framework (2022, 52 citations), provides a generic and robust solution for industrial robotic bin picking, tackling the unique challenges of texture-less and reflective industrial parts. Building on this, Li introduced the Self-Ensembling Sim-to-Real (SESR) approach for instance segmentation in auto-store bin picking, further reducing the need for costly labeled data. His earlier work on intelligent greenhouse management robots demonstrates a broader interest in applying robotics to practical, high-efficiency agriculture. With a citation count exceeding 60, Li’s research is directly shaping the future of automated manufacturing and logistics, offering scalable, cost-effective solutions that move beyond the limitations of everyday object recognition.