Liping Wu

Shenyang University of Technology, Iowa State University

Papers

Total Citations

H-Index

About

Liping Wu is a researcher specializing in robotic manipulation, with a focus on combining perception and learning for complex assembly tasks. Her work bridges tactile and visual sensing to enhance robot dexterity, particularly in precision operations like peg-in-hole assembly. In her most-cited paper (2021, 6 citations), she developed a deep reinforcement learning framework that integrates tactile feedback—sensitive to contact forces—with visual perception, which excels at detecting positional changes. This alignment method significantly improves assembly accuracy and adaptability. Earlier, Wu explored interactive robot learning in her 2010 work (5 citations), where she designed an active learning strategy enabling robots to efficiently master doorbell button pressing through exploratory behaviors. Though her citation counts are modest, her contributions are foundational in advancing sensor fusion and autonomous skill acquisition for industrial robotics. Wu’s research demonstrates a practical, hands-on approach to teaching robots fine motor skills, making her work valuable for students and engineers interested in reinforcement learning, perception integration, and real-world robotic applications.