Max Robotics — Global Service Robot Directory + US Certification

About

F. Fujiwara is a pioneering researcher in the field of robotic manipulation, with a particular focus on enabling robots to handle complex, deformable objects such as leather, paper, and rubber. His foundational work addresses one of robotics’ most significant challenges: designing controllers for tasks where physical modeling is nearly impossible. Fujiwara’s major contribution lies in the development of “skill controllers” that extract and embed human expertise into robotic systems. By leveraging hybrid automata architectures and impedance control, he created frameworks that allow robots to learn from human demonstrations, particularly in precision tasks like peg-in-hole assembly. His research introduced innovative methods for quantitatively evaluating these skill controllers by comparing them directly with human performance, and he pioneered the use of Hidden Markov Models (HMMs) to model impedance parameters from teaching data. Fujiwara also explored human-robot cooperation in virtual environments, enabling real-time skill transfer between operators and semi-autonomous slave robots. Though his most-cited works (2002–2004) have accumulated modest citation counts (5–11), their influence is significant in the niche domain of deformable object manipulation and skill-based robotic control, establishing foundational techniques that continue to inform research in learning from demonstration and human-robot collaboration.