Chenrui Wu

Papers

Total Citations

H-Index

About

Chenrui Wu’s research lies at the intersection of robotics, computer vision, and industrial automation, with a focus on enabling precise manipulation of challenging objects. His major contributions address the limitations of visual servoing and pose estimation for textureless and low-texture parts—a critical bottleneck in manufacturing. In his highly cited 2018 work, “Moment-Based 2.5-D Visual Servoing for Textureless Planar Part Grasping” (47 citations), Wu systematically analyzes the practical shortcomings of conventional moment-based methods, which rely on high-order image moments prone to instability, and proposes a robust framework that enhances reliability for industrial grasping tasks. Building on this, his 2017 paper, “A Circular Feature-Based Pose Measurement Method for Metal Part Grasping” (21 citations), tackles the common yet difficult problem of grasping circular metal components like bearings and flanges. By moving beyond point-feature approaches that fail on low-texture, repetitive surfaces, Wu introduces a novel pose measurement method that leverages circular features for accurate 3D localization. His work has direct implications for smart manufacturing, offering scalable solutions for automated assembly lines. With a growing citation impact, Wu is recognized for bridging theoretical vision algorithms with real-world industrial constraints.