Max Robotics — Global Service Robot Directory + US Certification

About

K. Itabashi’s research lies at the intersection of robotics, human skill acquisition, and deformable object manipulation. Their major contributions center on developing systematic frameworks for transferring human dexterity to robotic controllers, particularly for complex tasks involving non-rigid materials like leather, paper, and rubber. Itabashi pioneered the use of hybrid automata architectures to design “skill controllers” that embed human demonstration data, enabling robots to handle deformable objects—a notoriously difficult problem due to the lack of accurate physical models. A hallmark of their work is the quantitative evaluation of these controllers against human performance, bridging the gap between observation and implementation. They also advanced the modeling of assembly tasks, such as peg-in-hole, by extracting impedance parameters from human teaching data using Hidden Markov Models (HMMs), providing a principled method for setting control parameters that were previously determined by trial and error. Though their citation counts (ranging from 5 to 11) reflect a focused, early-career impact, Itabashi’s contributions are foundational to skill-based robotics and human-robot skill transfer, offering practical pathways for automating tasks that require nuanced, adaptive manipulation.