Max Robotics — Global Service Robot Directory + US Certification

About

Kazuki Fujimoto is a leading researcher in robot learning and control, specializing in imitation learning for precise object manipulation. His work uniquely integrates force and position information through bilateral control, enabling robots to perform complex contact motions that require force adjustment. Fujimoto’s most-cited paper, “Imitation Learning for Object Manipulation Based on Position/Force Information Using Bilateral Control” (2018, 51 citations), addresses a critical challenge: separating acting and reaction forces during manipulation. By introducing bilateral control, his method allows robots to learn from human demonstrations with high fidelity, achieving precise force-sensitive tasks. His subsequent work on variable speed contact motion (2022, 14 citations) extends this approach to operate up to control bandwidth, enhancing adaptability in real-world environments. Fujimoto also explores time-series motion generation (2019, 12 citations), considering long short-term motion patterns for human-robot interaction. With over 89 total citations, his contributions are foundational for end-to-end learning in robotics, reducing manual algorithm design while improving task success rates. His research is pivotal for advancing autonomous robots that can safely and effectively collaborate with humans in daily life.