Ziqi Chai

Papers

Total Citations

H-Index

About

Ziqi Chai is a researcher focused on advancing robotic perception for industrial automation, specializing in 6D object pose estimation—a critical technology enabling robots to accurately recognize and manipulate objects in manufacturing environments. His work addresses the challenge of balancing speed and precision when estimating the full six degrees of freedom (position and orientation) of industrial parts, particularly texture-less objects that are difficult for traditional methods. Chai’s most cited paper, “Multi-pyramid-based hierarchical template matching for 6D pose estimation in industrial grasping task” (2023, 6 citations), introduces a hierarchical approach that reduces runtime while maintaining accuracy, making it practical for real-time industrial applications. His earlier contributions, including “A new method for fast detection and pose estimation of texture-less industrial parts” (2018, 4 citations) and “A Fast Global Method Combined with Local Features for 6D Object Pose Estimation” (2019, 4 citations), further demonstrate his systematic effort to combine global and local features for robust pose estimation. Though his citation counts are modest, Chai’s work directly addresses a pressing industrial need: enabling robots to handle diverse, untextured parts efficiently. His research is particularly valuable for students and engineers seeking practical solutions for vision-guided robotics in smart manufacturing.