Can Li

Papers

Total Citations

H-Index

About

Can Li is a robotics researcher whose work bridges computer vision and intelligent manipulation, with a focus on precision assembly tasks. His key contributions lie in developing vision-guided methods for robotic peg-in-hole and shaft-in-hole assembly, a critical challenge in automated manufacturing. In his most cited work, "A Coarse-to-Fine Method for Estimating the Axis Pose Based on 3D Point Clouds in Robotic Cylindrical Shaft-in-Hole Assembly" (2021, 23 citations), Li introduces a novel approach that combines 3D point cloud processing with admittance control. By replacing traditional, time-consuming force-sensing methods with efficient 3D vision, his coarse-to-fine pose estimation framework significantly improves both speed and accuracy in robotic assembly. This work demonstrates his ability to integrate perception and control for real-world industrial applications. Li’s research is particularly valuable for advancing flexible automation, where robots must adapt to varying part geometries and tolerances. His contributions continue to influence the development of more intelligent, vision-driven robotic systems for complex assembly operations.