Na Wu

Papers

Total Citations

H-Index

About

Na Wu’s research lies at the intersection of cognitive robotics, imitation learning, and human-robot interaction, with a focus on enabling robots to acquire both motor skills and semantic knowledge through natural interaction. In her most cited work, “Robots Learn Writing” (2012, 12 citations), Wu introduced a novel method for robots to learn writing motions by mapping high-dimensional joint angle data into simplified 2D trajectories using a modified ISOMAP algorithm. This approach allowed robots to simultaneously learn the physical movements and the associated semantic meaning of written characters. Building on this, Wu proposed a broader learning framework in her 2015 paper (5 citations), where robots learn behaviors through imitation and spoken interaction with humans. Here, she developed a modified codebook method for object segmentation and recognition, enabling robots to extract task-relevant semantic information from speech commands. Though her citation counts are modest, Wu’s work is notable for its early integration of motor learning with symbolic understanding—a foundational challenge in cognitive robotics. Her contributions offer a practical pathway toward more intuitive, interactive robot training, making her research a valuable reference for those exploring embodied learning and human-robot collaboration.