Liying Zou

Papers

Total Citations

H-Index

About

Liying Zou is a robotics researcher whose work centers on advancing visual servoing systems—a critical technology enabling robots to use visual feedback for precise manipulation. Her primary research areas include binocular stereo vision, uncalibrated visual servoing, and the integration of neural networks with Kalman filtering for robotic control. Zou’s major contributions address fundamental challenges in eye-in-hand robot systems, particularly the estimation of the image Jacobian matrix without requiring depth information or extensive calibration. Her 2008 paper, “A New Binocular Stereo Visual Servoing Model,” with 11 citations, introduced a control-theoretic formulation that eliminates depth measurement, simplifying real-time implementation. Building on this, her 2016 work, “Singular Value Decomposition Aided Cubature Kalman Filter with Neural Network in Uncalibrated Binocular Stereo Visual Servoing System,” with 3 citations, proposed a novel hybrid method combining SVD, Cubature Kalman filtering, and neural networks for robust Jacobian estimation in uncalibrated systems. Though her citation counts are modest, Zou’s work represents a focused, technically rigorous contribution to the niche of binocular visual servoing, offering practical solutions for industrial robot guidance where calibration is difficult or impossible.